diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/__pycache__/swap.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/__pycache__/swap.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4fe353d639c5bcbb35461d6c4ced7cac98c30907 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/__pycache__/swap.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/betweenness.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/betweenness.py new file mode 100644 index 0000000000000000000000000000000000000000..b4b1f3963b00e451258b9838723b71a2d9f799fe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/betweenness.py @@ -0,0 +1,435 @@ +"""Betweenness centrality measures.""" +from collections import deque +from heapq import heappop, heappush +from itertools import count + +import networkx as nx +from networkx.algorithms.shortest_paths.weighted import _weight_function +from networkx.utils import py_random_state +from networkx.utils.decorators import not_implemented_for + +__all__ = ["betweenness_centrality", "edge_betweenness_centrality"] + + +@py_random_state(5) +@nx._dispatch(edge_attrs="weight") +def betweenness_centrality( + G, k=None, normalized=True, weight=None, endpoints=False, seed=None +): + r"""Compute the shortest-path betweenness centrality for nodes. + + Betweenness centrality of a node $v$ is the sum of the + fraction of all-pairs shortest paths that pass through $v$ + + .. math:: + + c_B(v) =\sum_{s,t \in V} \frac{\sigma(s, t|v)}{\sigma(s, t)} + + where $V$ is the set of nodes, $\sigma(s, t)$ is the number of + shortest $(s, t)$-paths, and $\sigma(s, t|v)$ is the number of + those paths passing through some node $v$ other than $s, t$. + If $s = t$, $\sigma(s, t) = 1$, and if $v \in {s, t}$, + $\sigma(s, t|v) = 0$ [2]_. + + Parameters + ---------- + G : graph + A NetworkX graph. + + k : int, optional (default=None) + If k is not None use k node samples to estimate betweenness. + The value of k <= n where n is the number of nodes in the graph. + Higher values give better approximation. + + normalized : bool, optional + If True the betweenness values are normalized by `2/((n-1)(n-2))` + for graphs, and `1/((n-1)(n-2))` for directed graphs where `n` + is the number of nodes in G. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + Weights are used to calculate weighted shortest paths, so they are + interpreted as distances. + + endpoints : bool, optional + If True include the endpoints in the shortest path counts. + + seed : integer, random_state, or None (default) + Indicator of random number generation state. + See :ref:`Randomness`. + Note that this is only used if k is not None. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with betweenness centrality as the value. + + See Also + -------- + edge_betweenness_centrality + load_centrality + + Notes + ----- + The algorithm is from Ulrik Brandes [1]_. + See [4]_ for the original first published version and [2]_ for details on + algorithms for variations and related metrics. + + For approximate betweenness calculations set k=#samples to use + k nodes ("pivots") to estimate the betweenness values. For an estimate + of the number of pivots needed see [3]_. + + For weighted graphs the edge weights must be greater than zero. + Zero edge weights can produce an infinite number of equal length + paths between pairs of nodes. + + The total number of paths between source and target is counted + differently for directed and undirected graphs. Directed paths + are easy to count. Undirected paths are tricky: should a path + from "u" to "v" count as 1 undirected path or as 2 directed paths? + + For betweenness_centrality we report the number of undirected + paths when G is undirected. + + For betweenness_centrality_subset the reporting is different. + If the source and target subsets are the same, then we want + to count undirected paths. But if the source and target subsets + differ -- for example, if sources is {0} and targets is {1}, + then we are only counting the paths in one direction. They are + undirected paths but we are counting them in a directed way. + To count them as undirected paths, each should count as half a path. + + This algorithm is not guaranteed to be correct if edge weights + are floating point numbers. As a workaround you can use integer + numbers by multiplying the relevant edge attributes by a convenient + constant factor (eg 100) and converting to integers. + + References + ---------- + .. [1] Ulrik Brandes: + A Faster Algorithm for Betweenness Centrality. + Journal of Mathematical Sociology 25(2):163-177, 2001. + https://doi.org/10.1080/0022250X.2001.9990249 + .. [2] Ulrik Brandes: + On Variants of Shortest-Path Betweenness + Centrality and their Generic Computation. + Social Networks 30(2):136-145, 2008. + https://doi.org/10.1016/j.socnet.2007.11.001 + .. [3] Ulrik Brandes and Christian Pich: + Centrality Estimation in Large Networks. + International Journal of Bifurcation and Chaos 17(7):2303-2318, 2007. + https://dx.doi.org/10.1142/S0218127407018403 + .. [4] Linton C. Freeman: + A set of measures of centrality based on betweenness. + Sociometry 40: 35–41, 1977 + https://doi.org/10.2307/3033543 + """ + betweenness = dict.fromkeys(G, 0.0) # b[v]=0 for v in G + if k is None: + nodes = G + else: + nodes = seed.sample(list(G.nodes()), k) + for s in nodes: + # single source shortest paths + if weight is None: # use BFS + S, P, sigma, _ = _single_source_shortest_path_basic(G, s) + else: # use Dijkstra's algorithm + S, P, sigma, _ = _single_source_dijkstra_path_basic(G, s, weight) + # accumulation + if endpoints: + betweenness, _ = _accumulate_endpoints(betweenness, S, P, sigma, s) + else: + betweenness, _ = _accumulate_basic(betweenness, S, P, sigma, s) + # rescaling + betweenness = _rescale( + betweenness, + len(G), + normalized=normalized, + directed=G.is_directed(), + k=k, + endpoints=endpoints, + ) + return betweenness + + +@py_random_state(4) +@nx._dispatch(edge_attrs="weight") +def edge_betweenness_centrality(G, k=None, normalized=True, weight=None, seed=None): + r"""Compute betweenness centrality for edges. + + Betweenness centrality of an edge $e$ is the sum of the + fraction of all-pairs shortest paths that pass through $e$ + + .. math:: + + c_B(e) =\sum_{s,t \in V} \frac{\sigma(s, t|e)}{\sigma(s, t)} + + where $V$ is the set of nodes, $\sigma(s, t)$ is the number of + shortest $(s, t)$-paths, and $\sigma(s, t|e)$ is the number of + those paths passing through edge $e$ [2]_. + + Parameters + ---------- + G : graph + A NetworkX graph. + + k : int, optional (default=None) + If k is not None use k node samples to estimate betweenness. + The value of k <= n where n is the number of nodes in the graph. + Higher values give better approximation. + + normalized : bool, optional + If True the betweenness values are normalized by $2/(n(n-1))$ + for graphs, and $1/(n(n-1))$ for directed graphs where $n$ + is the number of nodes in G. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + Weights are used to calculate weighted shortest paths, so they are + interpreted as distances. + + seed : integer, random_state, or None (default) + Indicator of random number generation state. + See :ref:`Randomness`. + Note that this is only used if k is not None. + + Returns + ------- + edges : dictionary + Dictionary of edges with betweenness centrality as the value. + + See Also + -------- + betweenness_centrality + edge_load + + Notes + ----- + The algorithm is from Ulrik Brandes [1]_. + + For weighted graphs the edge weights must be greater than zero. + Zero edge weights can produce an infinite number of equal length + paths between pairs of nodes. + + References + ---------- + .. [1] A Faster Algorithm for Betweenness Centrality. Ulrik Brandes, + Journal of Mathematical Sociology 25(2):163-177, 2001. + https://doi.org/10.1080/0022250X.2001.9990249 + .. [2] Ulrik Brandes: On Variants of Shortest-Path Betweenness + Centrality and their Generic Computation. + Social Networks 30(2):136-145, 2008. + https://doi.org/10.1016/j.socnet.2007.11.001 + """ + betweenness = dict.fromkeys(G, 0.0) # b[v]=0 for v in G + # b[e]=0 for e in G.edges() + betweenness.update(dict.fromkeys(G.edges(), 0.0)) + if k is None: + nodes = G + else: + nodes = seed.sample(list(G.nodes()), k) + for s in nodes: + # single source shortest paths + if weight is None: # use BFS + S, P, sigma, _ = _single_source_shortest_path_basic(G, s) + else: # use Dijkstra's algorithm + S, P, sigma, _ = _single_source_dijkstra_path_basic(G, s, weight) + # accumulation + betweenness = _accumulate_edges(betweenness, S, P, sigma, s) + # rescaling + for n in G: # remove nodes to only return edges + del betweenness[n] + betweenness = _rescale_e( + betweenness, len(G), normalized=normalized, directed=G.is_directed() + ) + if G.is_multigraph(): + betweenness = _add_edge_keys(G, betweenness, weight=weight) + return betweenness + + +# helpers for betweenness centrality + + +def _single_source_shortest_path_basic(G, s): + S = [] + P = {} + for v in G: + P[v] = [] + sigma = dict.fromkeys(G, 0.0) # sigma[v]=0 for v in G + D = {} + sigma[s] = 1.0 + D[s] = 0 + Q = deque([s]) + while Q: # use BFS to find shortest paths + v = Q.popleft() + S.append(v) + Dv = D[v] + sigmav = sigma[v] + for w in G[v]: + if w not in D: + Q.append(w) + D[w] = Dv + 1 + if D[w] == Dv + 1: # this is a shortest path, count paths + sigma[w] += sigmav + P[w].append(v) # predecessors + return S, P, sigma, D + + +def _single_source_dijkstra_path_basic(G, s, weight): + weight = _weight_function(G, weight) + # modified from Eppstein + S = [] + P = {} + for v in G: + P[v] = [] + sigma = dict.fromkeys(G, 0.0) # sigma[v]=0 for v in G + D = {} + sigma[s] = 1.0 + push = heappush + pop = heappop + seen = {s: 0} + c = count() + Q = [] # use Q as heap with (distance,node id) tuples + push(Q, (0, next(c), s, s)) + while Q: + (dist, _, pred, v) = pop(Q) + if v in D: + continue # already searched this node. + sigma[v] += sigma[pred] # count paths + S.append(v) + D[v] = dist + for w, edgedata in G[v].items(): + vw_dist = dist + weight(v, w, edgedata) + if w not in D and (w not in seen or vw_dist < seen[w]): + seen[w] = vw_dist + push(Q, (vw_dist, next(c), v, w)) + sigma[w] = 0.0 + P[w] = [v] + elif vw_dist == seen[w]: # handle equal paths + sigma[w] += sigma[v] + P[w].append(v) + return S, P, sigma, D + + +def _accumulate_basic(betweenness, S, P, sigma, s): + delta = dict.fromkeys(S, 0) + while S: + w = S.pop() + coeff = (1 + delta[w]) / sigma[w] + for v in P[w]: + delta[v] += sigma[v] * coeff + if w != s: + betweenness[w] += delta[w] + return betweenness, delta + + +def _accumulate_endpoints(betweenness, S, P, sigma, s): + betweenness[s] += len(S) - 1 + delta = dict.fromkeys(S, 0) + while S: + w = S.pop() + coeff = (1 + delta[w]) / sigma[w] + for v in P[w]: + delta[v] += sigma[v] * coeff + if w != s: + betweenness[w] += delta[w] + 1 + return betweenness, delta + + +def _accumulate_edges(betweenness, S, P, sigma, s): + delta = dict.fromkeys(S, 0) + while S: + w = S.pop() + coeff = (1 + delta[w]) / sigma[w] + for v in P[w]: + c = sigma[v] * coeff + if (v, w) not in betweenness: + betweenness[(w, v)] += c + else: + betweenness[(v, w)] += c + delta[v] += c + if w != s: + betweenness[w] += delta[w] + return betweenness + + +def _rescale(betweenness, n, normalized, directed=False, k=None, endpoints=False): + if normalized: + if endpoints: + if n < 2: + scale = None # no normalization + else: + # Scale factor should include endpoint nodes + scale = 1 / (n * (n - 1)) + elif n <= 2: + scale = None # no normalization b=0 for all nodes + else: + scale = 1 / ((n - 1) * (n - 2)) + else: # rescale by 2 for undirected graphs + if not directed: + scale = 0.5 + else: + scale = None + if scale is not None: + if k is not None: + scale = scale * n / k + for v in betweenness: + betweenness[v] *= scale + return betweenness + + +def _rescale_e(betweenness, n, normalized, directed=False, k=None): + if normalized: + if n <= 1: + scale = None # no normalization b=0 for all nodes + else: + scale = 1 / (n * (n - 1)) + else: # rescale by 2 for undirected graphs + if not directed: + scale = 0.5 + else: + scale = None + if scale is not None: + if k is not None: + scale = scale * n / k + for v in betweenness: + betweenness[v] *= scale + return betweenness + + +@not_implemented_for("graph") +def _add_edge_keys(G, betweenness, weight=None): + r"""Adds the corrected betweenness centrality (BC) values for multigraphs. + + Parameters + ---------- + G : NetworkX graph. + + betweenness : dictionary + Dictionary mapping adjacent node tuples to betweenness centrality values. + + weight : string or function + See `_weight_function` for details. Defaults to `None`. + + Returns + ------- + edges : dictionary + The parameter `betweenness` including edges with keys and their + betweenness centrality values. + + The BC value is divided among edges of equal weight. + """ + _weight = _weight_function(G, weight) + + edge_bc = dict.fromkeys(G.edges, 0.0) + for u, v in betweenness: + d = G[u][v] + wt = _weight(u, v, d) + keys = [k for k in d if _weight(u, v, {k: d[k]}) == wt] + bc = betweenness[(u, v)] / len(keys) + for k in keys: + edge_bc[(u, v, k)] = bc + + return edge_bc diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/closeness.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/closeness.py new file mode 100644 index 0000000000000000000000000000000000000000..6a95ac14ef848c8d146dee8ceba01d3b2de5eeee --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/closeness.py @@ -0,0 +1,281 @@ +""" +Closeness centrality measures. +""" +import functools + +import networkx as nx +from networkx.exception import NetworkXError +from networkx.utils.decorators import not_implemented_for + +__all__ = ["closeness_centrality", "incremental_closeness_centrality"] + + +@nx._dispatch(edge_attrs="distance") +def closeness_centrality(G, u=None, distance=None, wf_improved=True): + r"""Compute closeness centrality for nodes. + + Closeness centrality [1]_ of a node `u` is the reciprocal of the + average shortest path distance to `u` over all `n-1` reachable nodes. + + .. math:: + + C(u) = \frac{n - 1}{\sum_{v=1}^{n-1} d(v, u)}, + + where `d(v, u)` is the shortest-path distance between `v` and `u`, + and `n-1` is the number of nodes reachable from `u`. Notice that the + closeness distance function computes the incoming distance to `u` + for directed graphs. To use outward distance, act on `G.reverse()`. + + Notice that higher values of closeness indicate higher centrality. + + Wasserman and Faust propose an improved formula for graphs with + more than one connected component. The result is "a ratio of the + fraction of actors in the group who are reachable, to the average + distance" from the reachable actors [2]_. You might think this + scale factor is inverted but it is not. As is, nodes from small + components receive a smaller closeness value. Letting `N` denote + the number of nodes in the graph, + + .. math:: + + C_{WF}(u) = \frac{n-1}{N-1} \frac{n - 1}{\sum_{v=1}^{n-1} d(v, u)}, + + Parameters + ---------- + G : graph + A NetworkX graph + + u : node, optional + Return only the value for node u + + distance : edge attribute key, optional (default=None) + Use the specified edge attribute as the edge distance in shortest + path calculations. If `None` (the default) all edges have a distance of 1. + Absent edge attributes are assigned a distance of 1. Note that no check + is performed to ensure that edges have the provided attribute. + + wf_improved : bool, optional (default=True) + If True, scale by the fraction of nodes reachable. This gives the + Wasserman and Faust improved formula. For single component graphs + it is the same as the original formula. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with closeness centrality as the value. + + Examples + -------- + >>> G = nx.Graph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)]) + >>> nx.closeness_centrality(G) + {0: 1.0, 1: 1.0, 2: 0.75, 3: 0.75} + + See Also + -------- + betweenness_centrality, load_centrality, eigenvector_centrality, + degree_centrality, incremental_closeness_centrality + + Notes + ----- + The closeness centrality is normalized to `(n-1)/(|G|-1)` where + `n` is the number of nodes in the connected part of graph + containing the node. If the graph is not completely connected, + this algorithm computes the closeness centrality for each + connected part separately scaled by that parts size. + + If the 'distance' keyword is set to an edge attribute key then the + shortest-path length will be computed using Dijkstra's algorithm with + that edge attribute as the edge weight. + + The closeness centrality uses *inward* distance to a node, not outward. + If you want to use outword distances apply the function to `G.reverse()` + + In NetworkX 2.2 and earlier a bug caused Dijkstra's algorithm to use the + outward distance rather than the inward distance. If you use a 'distance' + keyword and a DiGraph, your results will change between v2.2 and v2.3. + + References + ---------- + .. [1] Linton C. Freeman: Centrality in networks: I. + Conceptual clarification. Social Networks 1:215-239, 1979. + https://doi.org/10.1016/0378-8733(78)90021-7 + .. [2] pg. 201 of Wasserman, S. and Faust, K., + Social Network Analysis: Methods and Applications, 1994, + Cambridge University Press. + """ + if G.is_directed(): + G = G.reverse() # create a reversed graph view + + if distance is not None: + # use Dijkstra's algorithm with specified attribute as edge weight + path_length = functools.partial( + nx.single_source_dijkstra_path_length, weight=distance + ) + else: + path_length = nx.single_source_shortest_path_length + + if u is None: + nodes = G.nodes + else: + nodes = [u] + closeness_dict = {} + for n in nodes: + sp = path_length(G, n) + totsp = sum(sp.values()) + len_G = len(G) + _closeness_centrality = 0.0 + if totsp > 0.0 and len_G > 1: + _closeness_centrality = (len(sp) - 1.0) / totsp + # normalize to number of nodes-1 in connected part + if wf_improved: + s = (len(sp) - 1.0) / (len_G - 1) + _closeness_centrality *= s + closeness_dict[n] = _closeness_centrality + if u is not None: + return closeness_dict[u] + return closeness_dict + + +@not_implemented_for("directed") +@nx._dispatch +def incremental_closeness_centrality( + G, edge, prev_cc=None, insertion=True, wf_improved=True +): + r"""Incremental closeness centrality for nodes. + + Compute closeness centrality for nodes using level-based work filtering + as described in Incremental Algorithms for Closeness Centrality by Sariyuce et al. + + Level-based work filtering detects unnecessary updates to the closeness + centrality and filters them out. + + --- + From "Incremental Algorithms for Closeness Centrality": + + Theorem 1: Let :math:`G = (V, E)` be a graph and u and v be two vertices in V + such that there is no edge (u, v) in E. Let :math:`G' = (V, E \cup uv)` + Then :math:`cc[s] = cc'[s]` if and only if :math:`\left|dG(s, u) - dG(s, v)\right| \leq 1`. + + Where :math:`dG(u, v)` denotes the length of the shortest path between + two vertices u, v in a graph G, cc[s] is the closeness centrality for a + vertex s in V, and cc'[s] is the closeness centrality for a + vertex s in V, with the (u, v) edge added. + --- + + We use Theorem 1 to filter out updates when adding or removing an edge. + When adding an edge (u, v), we compute the shortest path lengths from all + other nodes to u and to v before the node is added. When removing an edge, + we compute the shortest path lengths after the edge is removed. Then we + apply Theorem 1 to use previously computed closeness centrality for nodes + where :math:`\left|dG(s, u) - dG(s, v)\right| \leq 1`. This works only for + undirected, unweighted graphs; the distance argument is not supported. + + Closeness centrality [1]_ of a node `u` is the reciprocal of the + sum of the shortest path distances from `u` to all `n-1` other nodes. + Since the sum of distances depends on the number of nodes in the + graph, closeness is normalized by the sum of minimum possible + distances `n-1`. + + .. math:: + + C(u) = \frac{n - 1}{\sum_{v=1}^{n-1} d(v, u)}, + + where `d(v, u)` is the shortest-path distance between `v` and `u`, + and `n` is the number of nodes in the graph. + + Notice that higher values of closeness indicate higher centrality. + + Parameters + ---------- + G : graph + A NetworkX graph + + edge : tuple + The modified edge (u, v) in the graph. + + prev_cc : dictionary + The previous closeness centrality for all nodes in the graph. + + insertion : bool, optional + If True (default) the edge was inserted, otherwise it was deleted from the graph. + + wf_improved : bool, optional (default=True) + If True, scale by the fraction of nodes reachable. This gives the + Wasserman and Faust improved formula. For single component graphs + it is the same as the original formula. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with closeness centrality as the value. + + See Also + -------- + betweenness_centrality, load_centrality, eigenvector_centrality, + degree_centrality, closeness_centrality + + Notes + ----- + The closeness centrality is normalized to `(n-1)/(|G|-1)` where + `n` is the number of nodes in the connected part of graph + containing the node. If the graph is not completely connected, + this algorithm computes the closeness centrality for each + connected part separately. + + References + ---------- + .. [1] Freeman, L.C., 1979. Centrality in networks: I. + Conceptual clarification. Social Networks 1, 215--239. + https://doi.org/10.1016/0378-8733(78)90021-7 + .. [2] Sariyuce, A.E. ; Kaya, K. ; Saule, E. ; Catalyiirek, U.V. Incremental + Algorithms for Closeness Centrality. 2013 IEEE International Conference on Big Data + http://sariyuce.com/papers/bigdata13.pdf + """ + if prev_cc is not None and set(prev_cc.keys()) != set(G.nodes()): + raise NetworkXError("prev_cc and G do not have the same nodes") + + # Unpack edge + (u, v) = edge + path_length = nx.single_source_shortest_path_length + + if insertion: + # For edge insertion, we want shortest paths before the edge is inserted + du = path_length(G, u) + dv = path_length(G, v) + + G.add_edge(u, v) + else: + G.remove_edge(u, v) + + # For edge removal, we want shortest paths after the edge is removed + du = path_length(G, u) + dv = path_length(G, v) + + if prev_cc is None: + return nx.closeness_centrality(G) + + nodes = G.nodes() + closeness_dict = {} + for n in nodes: + if n in du and n in dv and abs(du[n] - dv[n]) <= 1: + closeness_dict[n] = prev_cc[n] + else: + sp = path_length(G, n) + totsp = sum(sp.values()) + len_G = len(G) + _closeness_centrality = 0.0 + if totsp > 0.0 and len_G > 1: + _closeness_centrality = (len(sp) - 1.0) / totsp + # normalize to number of nodes-1 in connected part + if wf_improved: + s = (len(sp) - 1.0) / (len_G - 1) + _closeness_centrality *= s + closeness_dict[n] = _closeness_centrality + + # Leave the graph as we found it + if insertion: + G.remove_edge(u, v) + else: + G.add_edge(u, v) + + return closeness_dict diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/current_flow_betweenness_subset.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/current_flow_betweenness_subset.py new file mode 100644 index 0000000000000000000000000000000000000000..debfca27f55d84d7e40eff227ccdb6e5dd236c6c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/current_flow_betweenness_subset.py @@ -0,0 +1,226 @@ +"""Current-flow betweenness centrality measures for subsets of nodes.""" +import networkx as nx +from networkx.algorithms.centrality.flow_matrix import flow_matrix_row +from networkx.utils import not_implemented_for, reverse_cuthill_mckee_ordering + +__all__ = [ + "current_flow_betweenness_centrality_subset", + "edge_current_flow_betweenness_centrality_subset", +] + + +@not_implemented_for("directed") +@nx._dispatch(edge_attrs="weight") +def current_flow_betweenness_centrality_subset( + G, sources, targets, normalized=True, weight=None, dtype=float, solver="lu" +): + r"""Compute current-flow betweenness centrality for subsets of nodes. + + Current-flow betweenness centrality uses an electrical current + model for information spreading in contrast to betweenness + centrality which uses shortest paths. + + Current-flow betweenness centrality is also known as + random-walk betweenness centrality [2]_. + + Parameters + ---------- + G : graph + A NetworkX graph + + sources: list of nodes + Nodes to use as sources for current + + targets: list of nodes + Nodes to use as sinks for current + + normalized : bool, optional (default=True) + If True the betweenness values are normalized by b=b/(n-1)(n-2) where + n is the number of nodes in G. + + weight : string or None, optional (default=None) + Key for edge data used as the edge weight. + If None, then use 1 as each edge weight. + The weight reflects the capacity or the strength of the + edge. + + dtype: data type (float) + Default data type for internal matrices. + Set to np.float32 for lower memory consumption. + + solver: string (default='lu') + Type of linear solver to use for computing the flow matrix. + Options are "full" (uses most memory), "lu" (recommended), and + "cg" (uses least memory). + + Returns + ------- + nodes : dictionary + Dictionary of nodes with betweenness centrality as the value. + + See Also + -------- + approximate_current_flow_betweenness_centrality + betweenness_centrality + edge_betweenness_centrality + edge_current_flow_betweenness_centrality + + Notes + ----- + Current-flow betweenness can be computed in $O(I(n-1)+mn \log n)$ + time [1]_, where $I(n-1)$ is the time needed to compute the + inverse Laplacian. For a full matrix this is $O(n^3)$ but using + sparse methods you can achieve $O(nm{\sqrt k})$ where $k$ is the + Laplacian matrix condition number. + + The space required is $O(nw)$ where $w$ is the width of the sparse + Laplacian matrix. Worse case is $w=n$ for $O(n^2)$. + + If the edges have a 'weight' attribute they will be used as + weights in this algorithm. Unspecified weights are set to 1. + + References + ---------- + .. [1] Centrality Measures Based on Current Flow. + Ulrik Brandes and Daniel Fleischer, + Proc. 22nd Symp. Theoretical Aspects of Computer Science (STACS '05). + LNCS 3404, pp. 533-544. Springer-Verlag, 2005. + https://doi.org/10.1007/978-3-540-31856-9_44 + + .. [2] A measure of betweenness centrality based on random walks, + M. E. J. Newman, Social Networks 27, 39-54 (2005). + """ + import numpy as np + + from networkx.utils import reverse_cuthill_mckee_ordering + + if not nx.is_connected(G): + raise nx.NetworkXError("Graph not connected.") + n = G.number_of_nodes() + ordering = list(reverse_cuthill_mckee_ordering(G)) + # make a copy with integer labels according to rcm ordering + # this could be done without a copy if we really wanted to + mapping = dict(zip(ordering, range(n))) + H = nx.relabel_nodes(G, mapping) + betweenness = dict.fromkeys(H, 0.0) # b[v]=0 for v in H + for row, (s, t) in flow_matrix_row(H, weight=weight, dtype=dtype, solver=solver): + for ss in sources: + i = mapping[ss] + for tt in targets: + j = mapping[tt] + betweenness[s] += 0.5 * np.abs(row[i] - row[j]) + betweenness[t] += 0.5 * np.abs(row[i] - row[j]) + if normalized: + nb = (n - 1.0) * (n - 2.0) # normalization factor + else: + nb = 2.0 + for v in H: + betweenness[v] = betweenness[v] / nb + 1.0 / (2 - n) + return {ordering[k]: v for k, v in betweenness.items()} + + +@not_implemented_for("directed") +@nx._dispatch(edge_attrs="weight") +def edge_current_flow_betweenness_centrality_subset( + G, sources, targets, normalized=True, weight=None, dtype=float, solver="lu" +): + r"""Compute current-flow betweenness centrality for edges using subsets + of nodes. + + Current-flow betweenness centrality uses an electrical current + model for information spreading in contrast to betweenness + centrality which uses shortest paths. + + Current-flow betweenness centrality is also known as + random-walk betweenness centrality [2]_. + + Parameters + ---------- + G : graph + A NetworkX graph + + sources: list of nodes + Nodes to use as sources for current + + targets: list of nodes + Nodes to use as sinks for current + + normalized : bool, optional (default=True) + If True the betweenness values are normalized by b=b/(n-1)(n-2) where + n is the number of nodes in G. + + weight : string or None, optional (default=None) + Key for edge data used as the edge weight. + If None, then use 1 as each edge weight. + The weight reflects the capacity or the strength of the + edge. + + dtype: data type (float) + Default data type for internal matrices. + Set to np.float32 for lower memory consumption. + + solver: string (default='lu') + Type of linear solver to use for computing the flow matrix. + Options are "full" (uses most memory), "lu" (recommended), and + "cg" (uses least memory). + + Returns + ------- + nodes : dict + Dictionary of edge tuples with betweenness centrality as the value. + + See Also + -------- + betweenness_centrality + edge_betweenness_centrality + current_flow_betweenness_centrality + + Notes + ----- + Current-flow betweenness can be computed in $O(I(n-1)+mn \log n)$ + time [1]_, where $I(n-1)$ is the time needed to compute the + inverse Laplacian. For a full matrix this is $O(n^3)$ but using + sparse methods you can achieve $O(nm{\sqrt k})$ where $k$ is the + Laplacian matrix condition number. + + The space required is $O(nw)$ where $w$ is the width of the sparse + Laplacian matrix. Worse case is $w=n$ for $O(n^2)$. + + If the edges have a 'weight' attribute they will be used as + weights in this algorithm. Unspecified weights are set to 1. + + References + ---------- + .. [1] Centrality Measures Based on Current Flow. + Ulrik Brandes and Daniel Fleischer, + Proc. 22nd Symp. Theoretical Aspects of Computer Science (STACS '05). + LNCS 3404, pp. 533-544. Springer-Verlag, 2005. + https://doi.org/10.1007/978-3-540-31856-9_44 + + .. [2] A measure of betweenness centrality based on random walks, + M. E. J. Newman, Social Networks 27, 39-54 (2005). + """ + import numpy as np + + if not nx.is_connected(G): + raise nx.NetworkXError("Graph not connected.") + n = G.number_of_nodes() + ordering = list(reverse_cuthill_mckee_ordering(G)) + # make a copy with integer labels according to rcm ordering + # this could be done without a copy if we really wanted to + mapping = dict(zip(ordering, range(n))) + H = nx.relabel_nodes(G, mapping) + edges = (tuple(sorted((u, v))) for u, v in H.edges()) + betweenness = dict.fromkeys(edges, 0.0) + if normalized: + nb = (n - 1.0) * (n - 2.0) # normalization factor + else: + nb = 2.0 + for row, (e) in flow_matrix_row(H, weight=weight, dtype=dtype, solver=solver): + for ss in sources: + i = mapping[ss] + for tt in targets: + j = mapping[tt] + betweenness[e] += 0.5 * np.abs(row[i] - row[j]) + betweenness[e] /= nb + return {(ordering[s], ordering[t]): v for (s, t), v in betweenness.items()} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/current_flow_closeness.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/current_flow_closeness.py new file mode 100644 index 0000000000000000000000000000000000000000..daefbae902ba7f513f3f7b979c4b4918053eaf9a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/current_flow_closeness.py @@ -0,0 +1,97 @@ +"""Current-flow closeness centrality measures.""" +import networkx as nx +from networkx.algorithms.centrality.flow_matrix import ( + CGInverseLaplacian, + FullInverseLaplacian, + SuperLUInverseLaplacian, +) +from networkx.utils import not_implemented_for, reverse_cuthill_mckee_ordering + +__all__ = ["current_flow_closeness_centrality", "information_centrality"] + + +@not_implemented_for("directed") +@nx._dispatch(edge_attrs="weight") +def current_flow_closeness_centrality(G, weight=None, dtype=float, solver="lu"): + """Compute current-flow closeness centrality for nodes. + + Current-flow closeness centrality is variant of closeness + centrality based on effective resistance between nodes in + a network. This metric is also known as information centrality. + + Parameters + ---------- + G : graph + A NetworkX graph. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + The weight reflects the capacity or the strength of the + edge. + + dtype: data type (default=float) + Default data type for internal matrices. + Set to np.float32 for lower memory consumption. + + solver: string (default='lu') + Type of linear solver to use for computing the flow matrix. + Options are "full" (uses most memory), "lu" (recommended), and + "cg" (uses least memory). + + Returns + ------- + nodes : dictionary + Dictionary of nodes with current flow closeness centrality as the value. + + See Also + -------- + closeness_centrality + + Notes + ----- + The algorithm is from Brandes [1]_. + + See also [2]_ for the original definition of information centrality. + + References + ---------- + .. [1] Ulrik Brandes and Daniel Fleischer, + Centrality Measures Based on Current Flow. + Proc. 22nd Symp. Theoretical Aspects of Computer Science (STACS '05). + LNCS 3404, pp. 533-544. Springer-Verlag, 2005. + https://doi.org/10.1007/978-3-540-31856-9_44 + + .. [2] Karen Stephenson and Marvin Zelen: + Rethinking centrality: Methods and examples. + Social Networks 11(1):1-37, 1989. + https://doi.org/10.1016/0378-8733(89)90016-6 + """ + if not nx.is_connected(G): + raise nx.NetworkXError("Graph not connected.") + solvername = { + "full": FullInverseLaplacian, + "lu": SuperLUInverseLaplacian, + "cg": CGInverseLaplacian, + } + n = G.number_of_nodes() + ordering = list(reverse_cuthill_mckee_ordering(G)) + # make a copy with integer labels according to rcm ordering + # this could be done without a copy if we really wanted to + H = nx.relabel_nodes(G, dict(zip(ordering, range(n)))) + betweenness = dict.fromkeys(H, 0.0) # b[v]=0 for v in H + n = H.number_of_nodes() + L = nx.laplacian_matrix(H, nodelist=range(n), weight=weight).asformat("csc") + L = L.astype(dtype) + C2 = solvername[solver](L, width=1, dtype=dtype) # initialize solver + for v in H: + col = C2.get_row(v) + for w in H: + betweenness[v] += col[v] - 2 * col[w] + betweenness[w] += col[v] + for v in H: + betweenness[v] = 1 / (betweenness[v]) + return {ordering[k]: v for k, v in betweenness.items()} + + +information_centrality = current_flow_closeness_centrality diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/degree_alg.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/degree_alg.py new file mode 100644 index 0000000000000000000000000000000000000000..2631730dbc0d63e1c907a0accc3170af00c50dfa --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/degree_alg.py @@ -0,0 +1,149 @@ +"""Degree centrality measures.""" +import networkx as nx +from networkx.utils.decorators import not_implemented_for + +__all__ = ["degree_centrality", "in_degree_centrality", "out_degree_centrality"] + + +@nx._dispatch +def degree_centrality(G): + """Compute the degree centrality for nodes. + + The degree centrality for a node v is the fraction of nodes it + is connected to. + + Parameters + ---------- + G : graph + A networkx graph + + Returns + ------- + nodes : dictionary + Dictionary of nodes with degree centrality as the value. + + Examples + -------- + >>> G = nx.Graph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)]) + >>> nx.degree_centrality(G) + {0: 1.0, 1: 1.0, 2: 0.6666666666666666, 3: 0.6666666666666666} + + See Also + -------- + betweenness_centrality, load_centrality, eigenvector_centrality + + Notes + ----- + The degree centrality values are normalized by dividing by the maximum + possible degree in a simple graph n-1 where n is the number of nodes in G. + + For multigraphs or graphs with self loops the maximum degree might + be higher than n-1 and values of degree centrality greater than 1 + are possible. + """ + if len(G) <= 1: + return {n: 1 for n in G} + + s = 1.0 / (len(G) - 1.0) + centrality = {n: d * s for n, d in G.degree()} + return centrality + + +@not_implemented_for("undirected") +@nx._dispatch +def in_degree_centrality(G): + """Compute the in-degree centrality for nodes. + + The in-degree centrality for a node v is the fraction of nodes its + incoming edges are connected to. + + Parameters + ---------- + G : graph + A NetworkX graph + + Returns + ------- + nodes : dictionary + Dictionary of nodes with in-degree centrality as values. + + Raises + ------ + NetworkXNotImplemented + If G is undirected. + + Examples + -------- + >>> G = nx.DiGraph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)]) + >>> nx.in_degree_centrality(G) + {0: 0.0, 1: 0.3333333333333333, 2: 0.6666666666666666, 3: 0.6666666666666666} + + See Also + -------- + degree_centrality, out_degree_centrality + + Notes + ----- + The degree centrality values are normalized by dividing by the maximum + possible degree in a simple graph n-1 where n is the number of nodes in G. + + For multigraphs or graphs with self loops the maximum degree might + be higher than n-1 and values of degree centrality greater than 1 + are possible. + """ + if len(G) <= 1: + return {n: 1 for n in G} + + s = 1.0 / (len(G) - 1.0) + centrality = {n: d * s for n, d in G.in_degree()} + return centrality + + +@not_implemented_for("undirected") +@nx._dispatch +def out_degree_centrality(G): + """Compute the out-degree centrality for nodes. + + The out-degree centrality for a node v is the fraction of nodes its + outgoing edges are connected to. + + Parameters + ---------- + G : graph + A NetworkX graph + + Returns + ------- + nodes : dictionary + Dictionary of nodes with out-degree centrality as values. + + Raises + ------ + NetworkXNotImplemented + If G is undirected. + + Examples + -------- + >>> G = nx.DiGraph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)]) + >>> nx.out_degree_centrality(G) + {0: 1.0, 1: 0.6666666666666666, 2: 0.0, 3: 0.0} + + See Also + -------- + degree_centrality, in_degree_centrality + + Notes + ----- + The degree centrality values are normalized by dividing by the maximum + possible degree in a simple graph n-1 where n is the number of nodes in G. + + For multigraphs or graphs with self loops the maximum degree might + be higher than n-1 and values of degree centrality greater than 1 + are possible. + """ + if len(G) <= 1: + return {n: 1 for n in G} + + s = 1.0 / (len(G) - 1.0) + centrality = {n: d * s for n, d in G.out_degree()} + return centrality diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/dispersion.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/dispersion.py new file mode 100644 index 0000000000000000000000000000000000000000..a551c387d88b0c69f4763678b5cc88567455d98b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/dispersion.py @@ -0,0 +1,107 @@ +from itertools import combinations + +import networkx as nx + +__all__ = ["dispersion"] + + +@nx._dispatch +def dispersion(G, u=None, v=None, normalized=True, alpha=1.0, b=0.0, c=0.0): + r"""Calculate dispersion between `u` and `v` in `G`. + + A link between two actors (`u` and `v`) has a high dispersion when their + mutual ties (`s` and `t`) are not well connected with each other. + + Parameters + ---------- + G : graph + A NetworkX graph. + u : node, optional + The source for the dispersion score (e.g. ego node of the network). + v : node, optional + The target of the dispersion score if specified. + normalized : bool + If True (default) normalize by the embeddedness of the nodes (u and v). + alpha, b, c : float + Parameters for the normalization procedure. When `normalized` is True, + the dispersion value is normalized by:: + + result = ((dispersion + b) ** alpha) / (embeddedness + c) + + as long as the denominator is nonzero. + + Returns + ------- + nodes : dictionary + If u (v) is specified, returns a dictionary of nodes with dispersion + score for all "target" ("source") nodes. If neither u nor v is + specified, returns a dictionary of dictionaries for all nodes 'u' in the + graph with a dispersion score for each node 'v'. + + Notes + ----- + This implementation follows Lars Backstrom and Jon Kleinberg [1]_. Typical + usage would be to run dispersion on the ego network $G_u$ if $u$ were + specified. Running :func:`dispersion` with neither $u$ nor $v$ specified + can take some time to complete. + + References + ---------- + .. [1] Romantic Partnerships and the Dispersion of Social Ties: + A Network Analysis of Relationship Status on Facebook. + Lars Backstrom, Jon Kleinberg. + https://arxiv.org/pdf/1310.6753v1.pdf + + """ + + def _dispersion(G_u, u, v): + """dispersion for all nodes 'v' in a ego network G_u of node 'u'""" + u_nbrs = set(G_u[u]) + ST = {n for n in G_u[v] if n in u_nbrs} + set_uv = {u, v} + # all possible ties of connections that u and b share + possib = combinations(ST, 2) + total = 0 + for s, t in possib: + # neighbors of s that are in G_u, not including u and v + nbrs_s = u_nbrs.intersection(G_u[s]) - set_uv + # s and t are not directly connected + if t not in nbrs_s: + # s and t do not share a connection + if nbrs_s.isdisjoint(G_u[t]): + # tick for disp(u, v) + total += 1 + # neighbors that u and v share + embeddedness = len(ST) + + dispersion_val = total + if normalized: + dispersion_val = (total + b) ** alpha + if embeddedness + c != 0: + dispersion_val /= embeddedness + c + + return dispersion_val + + if u is None: + # v and u are not specified + if v is None: + results = {n: {} for n in G} + for u in G: + for v in G[u]: + results[u][v] = _dispersion(G, u, v) + # u is not specified, but v is + else: + results = dict.fromkeys(G[v], {}) + for u in G[v]: + results[u] = _dispersion(G, v, u) + else: + # u is specified with no target v + if v is None: + results = dict.fromkeys(G[u], {}) + for v in G[u]: + results[v] = _dispersion(G, u, v) + # both u and v are specified + else: + results = _dispersion(G, u, v) + + return results diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/eigenvector.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/eigenvector.py new file mode 100644 index 0000000000000000000000000000000000000000..267e7b5102734d0d28f310ad019325d483c931cb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/eigenvector.py @@ -0,0 +1,341 @@ +"""Functions for computing eigenvector centrality.""" +import math + +import networkx as nx +from networkx.utils import not_implemented_for + +__all__ = ["eigenvector_centrality", "eigenvector_centrality_numpy"] + + +@not_implemented_for("multigraph") +@nx._dispatch(edge_attrs="weight") +def eigenvector_centrality(G, max_iter=100, tol=1.0e-6, nstart=None, weight=None): + r"""Compute the eigenvector centrality for the graph G. + + Eigenvector centrality computes the centrality for a node by adding + the centrality of its predecessors. The centrality for node $i$ is the + $i$-th element of a left eigenvector associated with the eigenvalue $\lambda$ + of maximum modulus that is positive. Such an eigenvector $x$ is + defined up to a multiplicative constant by the equation + + .. math:: + + \lambda x^T = x^T A, + + where $A$ is the adjacency matrix of the graph G. By definition of + row-column product, the equation above is equivalent to + + .. math:: + + \lambda x_i = \sum_{j\to i}x_j. + + That is, adding the eigenvector centralities of the predecessors of + $i$ one obtains the eigenvector centrality of $i$ multiplied by + $\lambda$. In the case of undirected graphs, $x$ also solves the familiar + right-eigenvector equation $Ax = \lambda x$. + + By virtue of the Perron–Frobenius theorem [1]_, if G is strongly + connected there is a unique eigenvector $x$, and all its entries + are strictly positive. + + If G is not strongly connected there might be several left + eigenvectors associated with $\lambda$, and some of their elements + might be zero. + + Parameters + ---------- + G : graph + A networkx graph. + + max_iter : integer, optional (default=100) + Maximum number of power iterations. + + tol : float, optional (default=1.0e-6) + Error tolerance (in Euclidean norm) used to check convergence in + power iteration. + + nstart : dictionary, optional (default=None) + Starting value of power iteration for each node. Must have a nonzero + projection on the desired eigenvector for the power method to converge. + If None, this implementation uses an all-ones vector, which is a safe + choice. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. Otherwise holds the + name of the edge attribute used as weight. In this measure the + weight is interpreted as the connection strength. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with eigenvector centrality as the value. The + associated vector has unit Euclidean norm and the values are + nonegative. + + Examples + -------- + >>> G = nx.path_graph(4) + >>> centrality = nx.eigenvector_centrality(G) + >>> sorted((v, f"{c:0.2f}") for v, c in centrality.items()) + [(0, '0.37'), (1, '0.60'), (2, '0.60'), (3, '0.37')] + + Raises + ------ + NetworkXPointlessConcept + If the graph G is the null graph. + + NetworkXError + If each value in `nstart` is zero. + + PowerIterationFailedConvergence + If the algorithm fails to converge to the specified tolerance + within the specified number of iterations of the power iteration + method. + + See Also + -------- + eigenvector_centrality_numpy + :func:`~networkx.algorithms.link_analysis.pagerank_alg.pagerank` + :func:`~networkx.algorithms.link_analysis.hits_alg.hits` + + Notes + ----- + Eigenvector centrality was introduced by Landau [2]_ for chess + tournaments. It was later rediscovered by Wei [3]_ and then + popularized by Kendall [4]_ in the context of sport ranking. Berge + introduced a general definition for graphs based on social connections + [5]_. Bonacich [6]_ reintroduced again eigenvector centrality and made + it popular in link analysis. + + This function computes the left dominant eigenvector, which corresponds + to adding the centrality of predecessors: this is the usual approach. + To add the centrality of successors first reverse the graph with + ``G.reverse()``. + + The implementation uses power iteration [7]_ to compute a dominant + eigenvector starting from the provided vector `nstart`. Convergence is + guaranteed as long as `nstart` has a nonzero projection on a dominant + eigenvector, which certainly happens using the default value. + + The method stops when the change in the computed vector between two + iterations is smaller than an error tolerance of ``G.number_of_nodes() + * tol`` or after ``max_iter`` iterations, but in the second case it + raises an exception. + + This implementation uses $(A + I)$ rather than the adjacency matrix + $A$ because the change preserves eigenvectors, but it shifts the + spectrum, thus guaranteeing convergence even for networks with + negative eigenvalues of maximum modulus. + + References + ---------- + .. [1] Abraham Berman and Robert J. Plemmons. + "Nonnegative Matrices in the Mathematical Sciences." + Classics in Applied Mathematics. SIAM, 1994. + + .. [2] Edmund Landau. + "Zur relativen Wertbemessung der Turnierresultate." + Deutsches Wochenschach, 11:366–369, 1895. + + .. [3] Teh-Hsing Wei. + "The Algebraic Foundations of Ranking Theory." + PhD thesis, University of Cambridge, 1952. + + .. [4] Maurice G. Kendall. + "Further contributions to the theory of paired comparisons." + Biometrics, 11(1):43–62, 1955. + https://www.jstor.org/stable/3001479 + + .. [5] Claude Berge + "Théorie des graphes et ses applications." + Dunod, Paris, France, 1958. + + .. [6] Phillip Bonacich. + "Technique for analyzing overlapping memberships." + Sociological Methodology, 4:176–185, 1972. + https://www.jstor.org/stable/270732 + + .. [7] Power iteration:: https://en.wikipedia.org/wiki/Power_iteration + + """ + if len(G) == 0: + raise nx.NetworkXPointlessConcept( + "cannot compute centrality for the null graph" + ) + # If no initial vector is provided, start with the all-ones vector. + if nstart is None: + nstart = {v: 1 for v in G} + if all(v == 0 for v in nstart.values()): + raise nx.NetworkXError("initial vector cannot have all zero values") + # Normalize the initial vector so that each entry is in [0, 1]. This is + # guaranteed to never have a divide-by-zero error by the previous line. + nstart_sum = sum(nstart.values()) + x = {k: v / nstart_sum for k, v in nstart.items()} + nnodes = G.number_of_nodes() + # make up to max_iter iterations + for _ in range(max_iter): + xlast = x + x = xlast.copy() # Start with xlast times I to iterate with (A+I) + # do the multiplication y^T = x^T A (left eigenvector) + for n in x: + for nbr in G[n]: + w = G[n][nbr].get(weight, 1) if weight else 1 + x[nbr] += xlast[n] * w + # Normalize the vector. The normalization denominator `norm` + # should never be zero by the Perron--Frobenius + # theorem. However, in case it is due to numerical error, we + # assume the norm to be one instead. + norm = math.hypot(*x.values()) or 1 + x = {k: v / norm for k, v in x.items()} + # Check for convergence (in the L_1 norm). + if sum(abs(x[n] - xlast[n]) for n in x) < nnodes * tol: + return x + raise nx.PowerIterationFailedConvergence(max_iter) + + +@nx._dispatch(edge_attrs="weight") +def eigenvector_centrality_numpy(G, weight=None, max_iter=50, tol=0): + r"""Compute the eigenvector centrality for the graph G. + + Eigenvector centrality computes the centrality for a node by adding + the centrality of its predecessors. The centrality for node $i$ is the + $i$-th element of a left eigenvector associated with the eigenvalue $\lambda$ + of maximum modulus that is positive. Such an eigenvector $x$ is + defined up to a multiplicative constant by the equation + + .. math:: + + \lambda x^T = x^T A, + + where $A$ is the adjacency matrix of the graph G. By definition of + row-column product, the equation above is equivalent to + + .. math:: + + \lambda x_i = \sum_{j\to i}x_j. + + That is, adding the eigenvector centralities of the predecessors of + $i$ one obtains the eigenvector centrality of $i$ multiplied by + $\lambda$. In the case of undirected graphs, $x$ also solves the familiar + right-eigenvector equation $Ax = \lambda x$. + + By virtue of the Perron–Frobenius theorem [1]_, if G is strongly + connected there is a unique eigenvector $x$, and all its entries + are strictly positive. + + If G is not strongly connected there might be several left + eigenvectors associated with $\lambda$, and some of their elements + might be zero. + + Parameters + ---------- + G : graph + A networkx graph. + + max_iter : integer, optional (default=50) + Maximum number of Arnoldi update iterations allowed. + + tol : float, optional (default=0) + Relative accuracy for eigenvalues (stopping criterion). + The default value of 0 implies machine precision. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. Otherwise holds the + name of the edge attribute used as weight. In this measure the + weight is interpreted as the connection strength. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with eigenvector centrality as the value. The + associated vector has unit Euclidean norm and the values are + nonegative. + + Examples + -------- + >>> G = nx.path_graph(4) + >>> centrality = nx.eigenvector_centrality_numpy(G) + >>> print([f"{node} {centrality[node]:0.2f}" for node in centrality]) + ['0 0.37', '1 0.60', '2 0.60', '3 0.37'] + + Raises + ------ + NetworkXPointlessConcept + If the graph G is the null graph. + + ArpackNoConvergence + When the requested convergence is not obtained. The currently + converged eigenvalues and eigenvectors can be found as + eigenvalues and eigenvectors attributes of the exception object. + + See Also + -------- + :func:`scipy.sparse.linalg.eigs` + eigenvector_centrality + :func:`~networkx.algorithms.link_analysis.pagerank_alg.pagerank` + :func:`~networkx.algorithms.link_analysis.hits_alg.hits` + + Notes + ----- + Eigenvector centrality was introduced by Landau [2]_ for chess + tournaments. It was later rediscovered by Wei [3]_ and then + popularized by Kendall [4]_ in the context of sport ranking. Berge + introduced a general definition for graphs based on social connections + [5]_. Bonacich [6]_ reintroduced again eigenvector centrality and made + it popular in link analysis. + + This function computes the left dominant eigenvector, which corresponds + to adding the centrality of predecessors: this is the usual approach. + To add the centrality of successors first reverse the graph with + ``G.reverse()``. + + This implementation uses the + :func:`SciPy sparse eigenvalue solver` (ARPACK) + to find the largest eigenvalue/eigenvector pair using Arnoldi iterations + [7]_. + + References + ---------- + .. [1] Abraham Berman and Robert J. Plemmons. + "Nonnegative Matrices in the Mathematical Sciences." + Classics in Applied Mathematics. SIAM, 1994. + + .. [2] Edmund Landau. + "Zur relativen Wertbemessung der Turnierresultate." + Deutsches Wochenschach, 11:366–369, 1895. + + .. [3] Teh-Hsing Wei. + "The Algebraic Foundations of Ranking Theory." + PhD thesis, University of Cambridge, 1952. + + .. [4] Maurice G. Kendall. + "Further contributions to the theory of paired comparisons." + Biometrics, 11(1):43–62, 1955. + https://www.jstor.org/stable/3001479 + + .. [5] Claude Berge + "Théorie des graphes et ses applications." + Dunod, Paris, France, 1958. + + .. [6] Phillip Bonacich. + "Technique for analyzing overlapping memberships." + Sociological Methodology, 4:176–185, 1972. + https://www.jstor.org/stable/270732 + + .. [7] Arnoldi iteration:: https://en.wikipedia.org/wiki/Arnoldi_iteration + + """ + import numpy as np + import scipy as sp + + if len(G) == 0: + raise nx.NetworkXPointlessConcept( + "cannot compute centrality for the null graph" + ) + M = nx.to_scipy_sparse_array(G, nodelist=list(G), weight=weight, dtype=float) + _, eigenvector = sp.sparse.linalg.eigs( + M.T, k=1, which="LR", maxiter=max_iter, tol=tol + ) + largest = eigenvector.flatten().real + norm = np.sign(largest.sum()) * sp.linalg.norm(largest) + return dict(zip(G, largest / norm)) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/flow_matrix.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/flow_matrix.py new file mode 100644 index 0000000000000000000000000000000000000000..e9cd7e26016e1be01c8d096b0404a33144799eb6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/flow_matrix.py @@ -0,0 +1,130 @@ +# Helpers for current-flow betweenness and current-flow closeness +# Lazy computations for inverse Laplacian and flow-matrix rows. +import networkx as nx + + +@nx._dispatch(edge_attrs="weight") +def flow_matrix_row(G, weight=None, dtype=float, solver="lu"): + # Generate a row of the current-flow matrix + import numpy as np + + solvername = { + "full": FullInverseLaplacian, + "lu": SuperLUInverseLaplacian, + "cg": CGInverseLaplacian, + } + n = G.number_of_nodes() + L = nx.laplacian_matrix(G, nodelist=range(n), weight=weight).asformat("csc") + L = L.astype(dtype) + C = solvername[solver](L, dtype=dtype) # initialize solver + w = C.w # w is the Laplacian matrix width + # row-by-row flow matrix + for u, v in sorted(sorted((u, v)) for u, v in G.edges()): + B = np.zeros(w, dtype=dtype) + c = G[u][v].get(weight, 1.0) + B[u % w] = c + B[v % w] = -c + # get only the rows needed in the inverse laplacian + # and multiply to get the flow matrix row + row = B @ C.get_rows(u, v) + yield row, (u, v) + + +# Class to compute the inverse laplacian only for specified rows +# Allows computation of the current-flow matrix without storing entire +# inverse laplacian matrix +class InverseLaplacian: + def __init__(self, L, width=None, dtype=None): + global np + import numpy as np + + (n, n) = L.shape + self.dtype = dtype + self.n = n + if width is None: + self.w = self.width(L) + else: + self.w = width + self.C = np.zeros((self.w, n), dtype=dtype) + self.L1 = L[1:, 1:] + self.init_solver(L) + + def init_solver(self, L): + pass + + def solve(self, r): + raise nx.NetworkXError("Implement solver") + + def solve_inverse(self, r): + raise nx.NetworkXError("Implement solver") + + def get_rows(self, r1, r2): + for r in range(r1, r2 + 1): + self.C[r % self.w, 1:] = self.solve_inverse(r) + return self.C + + def get_row(self, r): + self.C[r % self.w, 1:] = self.solve_inverse(r) + return self.C[r % self.w] + + def width(self, L): + m = 0 + for i, row in enumerate(L): + w = 0 + x, y = np.nonzero(row) + if len(y) > 0: + v = y - i + w = v.max() - v.min() + 1 + m = max(w, m) + return m + + +class FullInverseLaplacian(InverseLaplacian): + def init_solver(self, L): + self.IL = np.zeros(L.shape, dtype=self.dtype) + self.IL[1:, 1:] = np.linalg.inv(self.L1.todense()) + + def solve(self, rhs): + s = np.zeros(rhs.shape, dtype=self.dtype) + s = self.IL @ rhs + return s + + def solve_inverse(self, r): + return self.IL[r, 1:] + + +class SuperLUInverseLaplacian(InverseLaplacian): + def init_solver(self, L): + import scipy as sp + + self.lusolve = sp.sparse.linalg.factorized(self.L1.tocsc()) + + def solve_inverse(self, r): + rhs = np.zeros(self.n, dtype=self.dtype) + rhs[r] = 1 + return self.lusolve(rhs[1:]) + + def solve(self, rhs): + s = np.zeros(rhs.shape, dtype=self.dtype) + s[1:] = self.lusolve(rhs[1:]) + return s + + +class CGInverseLaplacian(InverseLaplacian): + def init_solver(self, L): + global sp + import scipy as sp + + ilu = sp.sparse.linalg.spilu(self.L1.tocsc()) + n = self.n - 1 + self.M = sp.sparse.linalg.LinearOperator(shape=(n, n), matvec=ilu.solve) + + def solve(self, rhs): + s = np.zeros(rhs.shape, dtype=self.dtype) + s[1:] = sp.sparse.linalg.cg(self.L1, rhs[1:], M=self.M, atol=0)[0] + return s + + def solve_inverse(self, r): + rhs = np.zeros(self.n, self.dtype) + rhs[r] = 1 + return sp.sparse.linalg.cg(self.L1, rhs[1:], M=self.M, atol=0)[0] diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/group.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/group.py new file mode 100644 index 0000000000000000000000000000000000000000..8207a71a5ae3bd0acfe0d90370ec10304d8a8c67 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/group.py @@ -0,0 +1,785 @@ +"""Group centrality measures.""" +from copy import deepcopy + +import networkx as nx +from networkx.algorithms.centrality.betweenness import ( + _accumulate_endpoints, + _single_source_dijkstra_path_basic, + _single_source_shortest_path_basic, +) +from networkx.utils.decorators import not_implemented_for + +__all__ = [ + "group_betweenness_centrality", + "group_closeness_centrality", + "group_degree_centrality", + "group_in_degree_centrality", + "group_out_degree_centrality", + "prominent_group", +] + + +@nx._dispatch(edge_attrs="weight") +def group_betweenness_centrality(G, C, normalized=True, weight=None, endpoints=False): + r"""Compute the group betweenness centrality for a group of nodes. + + Group betweenness centrality of a group of nodes $C$ is the sum of the + fraction of all-pairs shortest paths that pass through any vertex in $C$ + + .. math:: + + c_B(v) =\sum_{s,t \in V} \frac{\sigma(s, t|v)}{\sigma(s, t)} + + where $V$ is the set of nodes, $\sigma(s, t)$ is the number of + shortest $(s, t)$-paths, and $\sigma(s, t|C)$ is the number of + those paths passing through some node in group $C$. Note that + $(s, t)$ are not members of the group ($V-C$ is the set of nodes + in $V$ that are not in $C$). + + Parameters + ---------- + G : graph + A NetworkX graph. + + C : list or set or list of lists or list of sets + A group or a list of groups containing nodes which belong to G, for which group betweenness + centrality is to be calculated. + + normalized : bool, optional (default=True) + If True, group betweenness is normalized by `1/((|V|-|C|)(|V|-|C|-1))` + where `|V|` is the number of nodes in G and `|C|` is the number of nodes in C. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + The weight of an edge is treated as the length or distance between the two sides. + + endpoints : bool, optional (default=False) + If True include the endpoints in the shortest path counts. + + Raises + ------ + NodeNotFound + If node(s) in C are not present in G. + + Returns + ------- + betweenness : list of floats or float + If C is a single group then return a float. If C is a list with + several groups then return a list of group betweenness centralities. + + See Also + -------- + betweenness_centrality + + Notes + ----- + Group betweenness centrality is described in [1]_ and its importance discussed in [3]_. + The initial implementation of the algorithm is mentioned in [2]_. This function uses + an improved algorithm presented in [4]_. + + The number of nodes in the group must be a maximum of n - 2 where `n` + is the total number of nodes in the graph. + + For weighted graphs the edge weights must be greater than zero. + Zero edge weights can produce an infinite number of equal length + paths between pairs of nodes. + + The total number of paths between source and target is counted + differently for directed and undirected graphs. Directed paths + between "u" and "v" are counted as two possible paths (one each + direction) while undirected paths between "u" and "v" are counted + as one path. Said another way, the sum in the expression above is + over all ``s != t`` for directed graphs and for ``s < t`` for undirected graphs. + + + References + ---------- + .. [1] M G Everett and S P Borgatti: + The Centrality of Groups and Classes. + Journal of Mathematical Sociology. 23(3): 181-201. 1999. + http://www.analytictech.com/borgatti/group_centrality.htm + .. [2] Ulrik Brandes: + On Variants of Shortest-Path Betweenness + Centrality and their Generic Computation. + Social Networks 30(2):136-145, 2008. + http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.72.9610&rep=rep1&type=pdf + .. [3] Sourav Medya et. al.: + Group Centrality Maximization via Network Design. + SIAM International Conference on Data Mining, SDM 2018, 126–134. + https://sites.cs.ucsb.edu/~arlei/pubs/sdm18.pdf + .. [4] Rami Puzis, Yuval Elovici, and Shlomi Dolev. + "Fast algorithm for successive computation of group betweenness centrality." + https://journals.aps.org/pre/pdf/10.1103/PhysRevE.76.056709 + + """ + GBC = [] # initialize betweenness + list_of_groups = True + # check weather C contains one or many groups + if any(el in G for el in C): + C = [C] + list_of_groups = False + set_v = {node for group in C for node in group} + if set_v - G.nodes: # element(s) of C not in G + raise nx.NodeNotFound(f"The node(s) {set_v - G.nodes} are in C but not in G.") + + # pre-processing + PB, sigma, D = _group_preprocessing(G, set_v, weight) + + # the algorithm for each group + for group in C: + group = set(group) # set of nodes in group + # initialize the matrices of the sigma and the PB + GBC_group = 0 + sigma_m = deepcopy(sigma) + PB_m = deepcopy(PB) + sigma_m_v = deepcopy(sigma_m) + PB_m_v = deepcopy(PB_m) + for v in group: + GBC_group += PB_m[v][v] + for x in group: + for y in group: + dxvy = 0 + dxyv = 0 + dvxy = 0 + if not ( + sigma_m[x][y] == 0 or sigma_m[x][v] == 0 or sigma_m[v][y] == 0 + ): + if D[x][v] == D[x][y] + D[y][v]: + dxyv = sigma_m[x][y] * sigma_m[y][v] / sigma_m[x][v] + if D[x][y] == D[x][v] + D[v][y]: + dxvy = sigma_m[x][v] * sigma_m[v][y] / sigma_m[x][y] + if D[v][y] == D[v][x] + D[x][y]: + dvxy = sigma_m[v][x] * sigma[x][y] / sigma[v][y] + sigma_m_v[x][y] = sigma_m[x][y] * (1 - dxvy) + PB_m_v[x][y] = PB_m[x][y] - PB_m[x][y] * dxvy + if y != v: + PB_m_v[x][y] -= PB_m[x][v] * dxyv + if x != v: + PB_m_v[x][y] -= PB_m[v][y] * dvxy + sigma_m, sigma_m_v = sigma_m_v, sigma_m + PB_m, PB_m_v = PB_m_v, PB_m + + # endpoints + v, c = len(G), len(group) + if not endpoints: + scale = 0 + # if the graph is connected then subtract the endpoints from + # the count for all the nodes in the graph. else count how many + # nodes are connected to the group's nodes and subtract that. + if nx.is_directed(G): + if nx.is_strongly_connected(G): + scale = c * (2 * v - c - 1) + elif nx.is_connected(G): + scale = c * (2 * v - c - 1) + if scale == 0: + for group_node1 in group: + for node in D[group_node1]: + if node != group_node1: + if node in group: + scale += 1 + else: + scale += 2 + GBC_group -= scale + + # normalized + if normalized: + scale = 1 / ((v - c) * (v - c - 1)) + GBC_group *= scale + + # If undirected than count only the undirected edges + elif not G.is_directed(): + GBC_group /= 2 + + GBC.append(GBC_group) + if list_of_groups: + return GBC + return GBC[0] + + +def _group_preprocessing(G, set_v, weight): + sigma = {} + delta = {} + D = {} + betweenness = dict.fromkeys(G, 0) + for s in G: + if weight is None: # use BFS + S, P, sigma[s], D[s] = _single_source_shortest_path_basic(G, s) + else: # use Dijkstra's algorithm + S, P, sigma[s], D[s] = _single_source_dijkstra_path_basic(G, s, weight) + betweenness, delta[s] = _accumulate_endpoints(betweenness, S, P, sigma[s], s) + for i in delta[s]: # add the paths from s to i and rescale sigma + if s != i: + delta[s][i] += 1 + if weight is not None: + sigma[s][i] = sigma[s][i] / 2 + # building the path betweenness matrix only for nodes that appear in the group + PB = dict.fromkeys(G) + for group_node1 in set_v: + PB[group_node1] = dict.fromkeys(G, 0.0) + for group_node2 in set_v: + if group_node2 not in D[group_node1]: + continue + for node in G: + # if node is connected to the two group nodes than continue + if group_node2 in D[node] and group_node1 in D[node]: + if ( + D[node][group_node2] + == D[node][group_node1] + D[group_node1][group_node2] + ): + PB[group_node1][group_node2] += ( + delta[node][group_node2] + * sigma[node][group_node1] + * sigma[group_node1][group_node2] + / sigma[node][group_node2] + ) + return PB, sigma, D + + +@nx._dispatch(edge_attrs="weight") +def prominent_group( + G, k, weight=None, C=None, endpoints=False, normalized=True, greedy=False +): + r"""Find the prominent group of size $k$ in graph $G$. The prominence of the + group is evaluated by the group betweenness centrality. + + Group betweenness centrality of a group of nodes $C$ is the sum of the + fraction of all-pairs shortest paths that pass through any vertex in $C$ + + .. math:: + + c_B(v) =\sum_{s,t \in V} \frac{\sigma(s, t|v)}{\sigma(s, t)} + + where $V$ is the set of nodes, $\sigma(s, t)$ is the number of + shortest $(s, t)$-paths, and $\sigma(s, t|C)$ is the number of + those paths passing through some node in group $C$. Note that + $(s, t)$ are not members of the group ($V-C$ is the set of nodes + in $V$ that are not in $C$). + + Parameters + ---------- + G : graph + A NetworkX graph. + + k : int + The number of nodes in the group. + + normalized : bool, optional (default=True) + If True, group betweenness is normalized by ``1/((|V|-|C|)(|V|-|C|-1))`` + where ``|V|`` is the number of nodes in G and ``|C|`` is the number of + nodes in C. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + The weight of an edge is treated as the length or distance between the two sides. + + endpoints : bool, optional (default=False) + If True include the endpoints in the shortest path counts. + + C : list or set, optional (default=None) + list of nodes which won't be candidates of the prominent group. + + greedy : bool, optional (default=False) + Using a naive greedy algorithm in order to find non-optimal prominent + group. For scale free networks the results are negligibly below the optimal + results. + + Raises + ------ + NodeNotFound + If node(s) in C are not present in G. + + Returns + ------- + max_GBC : float + The group betweenness centrality of the prominent group. + + max_group : list + The list of nodes in the prominent group. + + See Also + -------- + betweenness_centrality, group_betweenness_centrality + + Notes + ----- + Group betweenness centrality is described in [1]_ and its importance discussed in [3]_. + The algorithm is described in [2]_ and is based on techniques mentioned in [4]_. + + The number of nodes in the group must be a maximum of ``n - 2`` where ``n`` + is the total number of nodes in the graph. + + For weighted graphs the edge weights must be greater than zero. + Zero edge weights can produce an infinite number of equal length + paths between pairs of nodes. + + The total number of paths between source and target is counted + differently for directed and undirected graphs. Directed paths + between "u" and "v" are counted as two possible paths (one each + direction) while undirected paths between "u" and "v" are counted + as one path. Said another way, the sum in the expression above is + over all ``s != t`` for directed graphs and for ``s < t`` for undirected graphs. + + References + ---------- + .. [1] M G Everett and S P Borgatti: + The Centrality of Groups and Classes. + Journal of Mathematical Sociology. 23(3): 181-201. 1999. + http://www.analytictech.com/borgatti/group_centrality.htm + .. [2] Rami Puzis, Yuval Elovici, and Shlomi Dolev: + "Finding the Most Prominent Group in Complex Networks" + AI communications 20(4): 287-296, 2007. + https://www.researchgate.net/profile/Rami_Puzis2/publication/220308855 + .. [3] Sourav Medya et. al.: + Group Centrality Maximization via Network Design. + SIAM International Conference on Data Mining, SDM 2018, 126–134. + https://sites.cs.ucsb.edu/~arlei/pubs/sdm18.pdf + .. [4] Rami Puzis, Yuval Elovici, and Shlomi Dolev. + "Fast algorithm for successive computation of group betweenness centrality." + https://journals.aps.org/pre/pdf/10.1103/PhysRevE.76.056709 + """ + import numpy as np + import pandas as pd + + if C is not None: + C = set(C) + if C - G.nodes: # element(s) of C not in G + raise nx.NodeNotFound(f"The node(s) {C - G.nodes} are in C but not in G.") + nodes = list(G.nodes - C) + else: + nodes = list(G.nodes) + DF_tree = nx.Graph() + PB, sigma, D = _group_preprocessing(G, nodes, weight) + betweenness = pd.DataFrame.from_dict(PB) + if C is not None: + for node in C: + # remove from the betweenness all the nodes not part of the group + betweenness.drop(index=node, inplace=True) + betweenness.drop(columns=node, inplace=True) + CL = [node for _, node in sorted(zip(np.diag(betweenness), nodes), reverse=True)] + max_GBC = 0 + max_group = [] + DF_tree.add_node( + 1, + CL=CL, + betweenness=betweenness, + GBC=0, + GM=[], + sigma=sigma, + cont=dict(zip(nodes, np.diag(betweenness))), + ) + + # the algorithm + DF_tree.nodes[1]["heu"] = 0 + for i in range(k): + DF_tree.nodes[1]["heu"] += DF_tree.nodes[1]["cont"][DF_tree.nodes[1]["CL"][i]] + max_GBC, DF_tree, max_group = _dfbnb( + G, k, DF_tree, max_GBC, 1, D, max_group, nodes, greedy + ) + + v = len(G) + if not endpoints: + scale = 0 + # if the graph is connected then subtract the endpoints from + # the count for all the nodes in the graph. else count how many + # nodes are connected to the group's nodes and subtract that. + if nx.is_directed(G): + if nx.is_strongly_connected(G): + scale = k * (2 * v - k - 1) + elif nx.is_connected(G): + scale = k * (2 * v - k - 1) + if scale == 0: + for group_node1 in max_group: + for node in D[group_node1]: + if node != group_node1: + if node in max_group: + scale += 1 + else: + scale += 2 + max_GBC -= scale + + # normalized + if normalized: + scale = 1 / ((v - k) * (v - k - 1)) + max_GBC *= scale + + # If undirected then count only the undirected edges + elif not G.is_directed(): + max_GBC /= 2 + max_GBC = float("%.2f" % max_GBC) + return max_GBC, max_group + + +def _dfbnb(G, k, DF_tree, max_GBC, root, D, max_group, nodes, greedy): + # stopping condition - if we found a group of size k and with higher GBC then prune + if len(DF_tree.nodes[root]["GM"]) == k and DF_tree.nodes[root]["GBC"] > max_GBC: + return DF_tree.nodes[root]["GBC"], DF_tree, DF_tree.nodes[root]["GM"] + # stopping condition - if the size of group members equal to k or there are less than + # k - |GM| in the candidate list or the heuristic function plus the GBC is below the + # maximal GBC found then prune + if ( + len(DF_tree.nodes[root]["GM"]) == k + or len(DF_tree.nodes[root]["CL"]) <= k - len(DF_tree.nodes[root]["GM"]) + or DF_tree.nodes[root]["GBC"] + DF_tree.nodes[root]["heu"] <= max_GBC + ): + return max_GBC, DF_tree, max_group + + # finding the heuristic of both children + node_p, node_m, DF_tree = _heuristic(k, root, DF_tree, D, nodes, greedy) + + # finding the child with the bigger heuristic + GBC and expand + # that node first if greedy then only expand the plus node + if greedy: + max_GBC, DF_tree, max_group = _dfbnb( + G, k, DF_tree, max_GBC, node_p, D, max_group, nodes, greedy + ) + + elif ( + DF_tree.nodes[node_p]["GBC"] + DF_tree.nodes[node_p]["heu"] + > DF_tree.nodes[node_m]["GBC"] + DF_tree.nodes[node_m]["heu"] + ): + max_GBC, DF_tree, max_group = _dfbnb( + G, k, DF_tree, max_GBC, node_p, D, max_group, nodes, greedy + ) + max_GBC, DF_tree, max_group = _dfbnb( + G, k, DF_tree, max_GBC, node_m, D, max_group, nodes, greedy + ) + else: + max_GBC, DF_tree, max_group = _dfbnb( + G, k, DF_tree, max_GBC, node_m, D, max_group, nodes, greedy + ) + max_GBC, DF_tree, max_group = _dfbnb( + G, k, DF_tree, max_GBC, node_p, D, max_group, nodes, greedy + ) + return max_GBC, DF_tree, max_group + + +def _heuristic(k, root, DF_tree, D, nodes, greedy): + import numpy as np + + # This helper function add two nodes to DF_tree - one left son and the + # other right son, finds their heuristic, CL, GBC, and GM + node_p = DF_tree.number_of_nodes() + 1 + node_m = DF_tree.number_of_nodes() + 2 + added_node = DF_tree.nodes[root]["CL"][0] + + # adding the plus node + DF_tree.add_nodes_from([(node_p, deepcopy(DF_tree.nodes[root]))]) + DF_tree.nodes[node_p]["GM"].append(added_node) + DF_tree.nodes[node_p]["GBC"] += DF_tree.nodes[node_p]["cont"][added_node] + root_node = DF_tree.nodes[root] + for x in nodes: + for y in nodes: + dxvy = 0 + dxyv = 0 + dvxy = 0 + if not ( + root_node["sigma"][x][y] == 0 + or root_node["sigma"][x][added_node] == 0 + or root_node["sigma"][added_node][y] == 0 + ): + if D[x][added_node] == D[x][y] + D[y][added_node]: + dxyv = ( + root_node["sigma"][x][y] + * root_node["sigma"][y][added_node] + / root_node["sigma"][x][added_node] + ) + if D[x][y] == D[x][added_node] + D[added_node][y]: + dxvy = ( + root_node["sigma"][x][added_node] + * root_node["sigma"][added_node][y] + / root_node["sigma"][x][y] + ) + if D[added_node][y] == D[added_node][x] + D[x][y]: + dvxy = ( + root_node["sigma"][added_node][x] + * root_node["sigma"][x][y] + / root_node["sigma"][added_node][y] + ) + DF_tree.nodes[node_p]["sigma"][x][y] = root_node["sigma"][x][y] * (1 - dxvy) + DF_tree.nodes[node_p]["betweenness"][x][y] = ( + root_node["betweenness"][x][y] - root_node["betweenness"][x][y] * dxvy + ) + if y != added_node: + DF_tree.nodes[node_p]["betweenness"][x][y] -= ( + root_node["betweenness"][x][added_node] * dxyv + ) + if x != added_node: + DF_tree.nodes[node_p]["betweenness"][x][y] -= ( + root_node["betweenness"][added_node][y] * dvxy + ) + + DF_tree.nodes[node_p]["CL"] = [ + node + for _, node in sorted( + zip(np.diag(DF_tree.nodes[node_p]["betweenness"]), nodes), reverse=True + ) + if node not in DF_tree.nodes[node_p]["GM"] + ] + DF_tree.nodes[node_p]["cont"] = dict( + zip(nodes, np.diag(DF_tree.nodes[node_p]["betweenness"])) + ) + DF_tree.nodes[node_p]["heu"] = 0 + for i in range(k - len(DF_tree.nodes[node_p]["GM"])): + DF_tree.nodes[node_p]["heu"] += DF_tree.nodes[node_p]["cont"][ + DF_tree.nodes[node_p]["CL"][i] + ] + + # adding the minus node - don't insert the first node in the CL to GM + # Insert minus node only if isn't greedy type algorithm + if not greedy: + DF_tree.add_nodes_from([(node_m, deepcopy(DF_tree.nodes[root]))]) + DF_tree.nodes[node_m]["CL"].pop(0) + DF_tree.nodes[node_m]["cont"].pop(added_node) + DF_tree.nodes[node_m]["heu"] = 0 + for i in range(k - len(DF_tree.nodes[node_m]["GM"])): + DF_tree.nodes[node_m]["heu"] += DF_tree.nodes[node_m]["cont"][ + DF_tree.nodes[node_m]["CL"][i] + ] + else: + node_m = None + + return node_p, node_m, DF_tree + + +@nx._dispatch(edge_attrs="weight") +def group_closeness_centrality(G, S, weight=None): + r"""Compute the group closeness centrality for a group of nodes. + + Group closeness centrality of a group of nodes $S$ is a measure + of how close the group is to the other nodes in the graph. + + .. math:: + + c_{close}(S) = \frac{|V-S|}{\sum_{v \in V-S} d_{S, v}} + + d_{S, v} = min_{u \in S} (d_{u, v}) + + where $V$ is the set of nodes, $d_{S, v}$ is the distance of + the group $S$ from $v$ defined as above. ($V-S$ is the set of nodes + in $V$ that are not in $S$). + + Parameters + ---------- + G : graph + A NetworkX graph. + + S : list or set + S is a group of nodes which belong to G, for which group closeness + centrality is to be calculated. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + The weight of an edge is treated as the length or distance between the two sides. + + Raises + ------ + NodeNotFound + If node(s) in S are not present in G. + + Returns + ------- + closeness : float + Group closeness centrality of the group S. + + See Also + -------- + closeness_centrality + + Notes + ----- + The measure was introduced in [1]_. + The formula implemented here is described in [2]_. + + Higher values of closeness indicate greater centrality. + + It is assumed that 1 / 0 is 0 (required in the case of directed graphs, + or when a shortest path length is 0). + + The number of nodes in the group must be a maximum of n - 1 where `n` + is the total number of nodes in the graph. + + For directed graphs, the incoming distance is utilized here. To use the + outward distance, act on `G.reverse()`. + + For weighted graphs the edge weights must be greater than zero. + Zero edge weights can produce an infinite number of equal length + paths between pairs of nodes. + + References + ---------- + .. [1] M G Everett and S P Borgatti: + The Centrality of Groups and Classes. + Journal of Mathematical Sociology. 23(3): 181-201. 1999. + http://www.analytictech.com/borgatti/group_centrality.htm + .. [2] J. Zhao et. al.: + Measuring and Maximizing Group Closeness Centrality over + Disk Resident Graphs. + WWWConference Proceedings, 2014. 689-694. + https://doi.org/10.1145/2567948.2579356 + """ + if G.is_directed(): + G = G.reverse() # reverse view + closeness = 0 # initialize to 0 + V = set(G) # set of nodes in G + S = set(S) # set of nodes in group S + V_S = V - S # set of nodes in V but not S + shortest_path_lengths = nx.multi_source_dijkstra_path_length(G, S, weight=weight) + # accumulation + for v in V_S: + try: + closeness += shortest_path_lengths[v] + except KeyError: # no path exists + closeness += 0 + try: + closeness = len(V_S) / closeness + except ZeroDivisionError: # 1 / 0 assumed as 0 + closeness = 0 + return closeness + + +@nx._dispatch +def group_degree_centrality(G, S): + """Compute the group degree centrality for a group of nodes. + + Group degree centrality of a group of nodes $S$ is the fraction + of non-group members connected to group members. + + Parameters + ---------- + G : graph + A NetworkX graph. + + S : list or set + S is a group of nodes which belong to G, for which group degree + centrality is to be calculated. + + Raises + ------ + NetworkXError + If node(s) in S are not in G. + + Returns + ------- + centrality : float + Group degree centrality of the group S. + + See Also + -------- + degree_centrality + group_in_degree_centrality + group_out_degree_centrality + + Notes + ----- + The measure was introduced in [1]_. + + The number of nodes in the group must be a maximum of n - 1 where `n` + is the total number of nodes in the graph. + + References + ---------- + .. [1] M G Everett and S P Borgatti: + The Centrality of Groups and Classes. + Journal of Mathematical Sociology. 23(3): 181-201. 1999. + http://www.analytictech.com/borgatti/group_centrality.htm + """ + centrality = len(set().union(*[set(G.neighbors(i)) for i in S]) - set(S)) + centrality /= len(G.nodes()) - len(S) + return centrality + + +@not_implemented_for("undirected") +@nx._dispatch +def group_in_degree_centrality(G, S): + """Compute the group in-degree centrality for a group of nodes. + + Group in-degree centrality of a group of nodes $S$ is the fraction + of non-group members connected to group members by incoming edges. + + Parameters + ---------- + G : graph + A NetworkX graph. + + S : list or set + S is a group of nodes which belong to G, for which group in-degree + centrality is to be calculated. + + Returns + ------- + centrality : float + Group in-degree centrality of the group S. + + Raises + ------ + NetworkXNotImplemented + If G is undirected. + + NodeNotFound + If node(s) in S are not in G. + + See Also + -------- + degree_centrality + group_degree_centrality + group_out_degree_centrality + + Notes + ----- + The number of nodes in the group must be a maximum of n - 1 where `n` + is the total number of nodes in the graph. + + `G.neighbors(i)` gives nodes with an outward edge from i, in a DiGraph, + so for group in-degree centrality, the reverse graph is used. + """ + return group_degree_centrality(G.reverse(), S) + + +@not_implemented_for("undirected") +@nx._dispatch +def group_out_degree_centrality(G, S): + """Compute the group out-degree centrality for a group of nodes. + + Group out-degree centrality of a group of nodes $S$ is the fraction + of non-group members connected to group members by outgoing edges. + + Parameters + ---------- + G : graph + A NetworkX graph. + + S : list or set + S is a group of nodes which belong to G, for which group in-degree + centrality is to be calculated. + + Returns + ------- + centrality : float + Group out-degree centrality of the group S. + + Raises + ------ + NetworkXNotImplemented + If G is undirected. + + NodeNotFound + If node(s) in S are not in G. + + See Also + -------- + degree_centrality + group_degree_centrality + group_in_degree_centrality + + Notes + ----- + The number of nodes in the group must be a maximum of n - 1 where `n` + is the total number of nodes in the graph. + + `G.neighbors(i)` gives nodes with an outward edge from i, in a DiGraph, + so for group out-degree centrality, the graph itself is used. + """ + return group_degree_centrality(G, S) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/katz.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/katz.py new file mode 100644 index 0000000000000000000000000000000000000000..3c18e5aa2b25fbefb88411e691de3380bc94f012 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/katz.py @@ -0,0 +1,331 @@ +"""Katz centrality.""" +import math + +import networkx as nx +from networkx.utils import not_implemented_for + +__all__ = ["katz_centrality", "katz_centrality_numpy"] + + +@not_implemented_for("multigraph") +@nx._dispatch(edge_attrs="weight") +def katz_centrality( + G, + alpha=0.1, + beta=1.0, + max_iter=1000, + tol=1.0e-6, + nstart=None, + normalized=True, + weight=None, +): + r"""Compute the Katz centrality for the nodes of the graph G. + + Katz centrality computes the centrality for a node based on the centrality + of its neighbors. It is a generalization of the eigenvector centrality. The + Katz centrality for node $i$ is + + .. math:: + + x_i = \alpha \sum_{j} A_{ij} x_j + \beta, + + where $A$ is the adjacency matrix of graph G with eigenvalues $\lambda$. + + The parameter $\beta$ controls the initial centrality and + + .. math:: + + \alpha < \frac{1}{\lambda_{\max}}. + + Katz centrality computes the relative influence of a node within a + network by measuring the number of the immediate neighbors (first + degree nodes) and also all other nodes in the network that connect + to the node under consideration through these immediate neighbors. + + Extra weight can be provided to immediate neighbors through the + parameter $\beta$. Connections made with distant neighbors + are, however, penalized by an attenuation factor $\alpha$ which + should be strictly less than the inverse largest eigenvalue of the + adjacency matrix in order for the Katz centrality to be computed + correctly. More information is provided in [1]_. + + Parameters + ---------- + G : graph + A NetworkX graph. + + alpha : float, optional (default=0.1) + Attenuation factor + + beta : scalar or dictionary, optional (default=1.0) + Weight attributed to the immediate neighborhood. If not a scalar, the + dictionary must have an value for every node. + + max_iter : integer, optional (default=1000) + Maximum number of iterations in power method. + + tol : float, optional (default=1.0e-6) + Error tolerance used to check convergence in power method iteration. + + nstart : dictionary, optional + Starting value of Katz iteration for each node. + + normalized : bool, optional (default=True) + If True normalize the resulting values. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + In this measure the weight is interpreted as the connection strength. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with Katz centrality as the value. + + Raises + ------ + NetworkXError + If the parameter `beta` is not a scalar but lacks a value for at least + one node + + PowerIterationFailedConvergence + If the algorithm fails to converge to the specified tolerance + within the specified number of iterations of the power iteration + method. + + Examples + -------- + >>> import math + >>> G = nx.path_graph(4) + >>> phi = (1 + math.sqrt(5)) / 2.0 # largest eigenvalue of adj matrix + >>> centrality = nx.katz_centrality(G, 1 / phi - 0.01) + >>> for n, c in sorted(centrality.items()): + ... print(f"{n} {c:.2f}") + 0 0.37 + 1 0.60 + 2 0.60 + 3 0.37 + + See Also + -------- + katz_centrality_numpy + eigenvector_centrality + eigenvector_centrality_numpy + :func:`~networkx.algorithms.link_analysis.pagerank_alg.pagerank` + :func:`~networkx.algorithms.link_analysis.hits_alg.hits` + + Notes + ----- + Katz centrality was introduced by [2]_. + + This algorithm it uses the power method to find the eigenvector + corresponding to the largest eigenvalue of the adjacency matrix of ``G``. + The parameter ``alpha`` should be strictly less than the inverse of largest + eigenvalue of the adjacency matrix for the algorithm to converge. + You can use ``max(nx.adjacency_spectrum(G))`` to get $\lambda_{\max}$ the largest + eigenvalue of the adjacency matrix. + The iteration will stop after ``max_iter`` iterations or an error tolerance of + ``number_of_nodes(G) * tol`` has been reached. + + When $\alpha = 1/\lambda_{\max}$ and $\beta=0$, Katz centrality is the same + as eigenvector centrality. + + For directed graphs this finds "left" eigenvectors which corresponds + to the in-edges in the graph. For out-edges Katz centrality + first reverse the graph with ``G.reverse()``. + + References + ---------- + .. [1] Mark E. J. Newman: + Networks: An Introduction. + Oxford University Press, USA, 2010, p. 720. + .. [2] Leo Katz: + A New Status Index Derived from Sociometric Index. + Psychometrika 18(1):39–43, 1953 + https://link.springer.com/content/pdf/10.1007/BF02289026.pdf + """ + if len(G) == 0: + return {} + + nnodes = G.number_of_nodes() + + if nstart is None: + # choose starting vector with entries of 0 + x = {n: 0 for n in G} + else: + x = nstart + + try: + b = dict.fromkeys(G, float(beta)) + except (TypeError, ValueError, AttributeError) as err: + b = beta + if set(beta) != set(G): + raise nx.NetworkXError( + "beta dictionary " "must have a value for every node" + ) from err + + # make up to max_iter iterations + for _ in range(max_iter): + xlast = x + x = dict.fromkeys(xlast, 0) + # do the multiplication y^T = Alpha * x^T A + Beta + for n in x: + for nbr in G[n]: + x[nbr] += xlast[n] * G[n][nbr].get(weight, 1) + for n in x: + x[n] = alpha * x[n] + b[n] + + # check convergence + error = sum(abs(x[n] - xlast[n]) for n in x) + if error < nnodes * tol: + if normalized: + # normalize vector + try: + s = 1.0 / math.hypot(*x.values()) + # this should never be zero? + except ZeroDivisionError: + s = 1.0 + else: + s = 1 + for n in x: + x[n] *= s + return x + raise nx.PowerIterationFailedConvergence(max_iter) + + +@not_implemented_for("multigraph") +@nx._dispatch(edge_attrs="weight") +def katz_centrality_numpy(G, alpha=0.1, beta=1.0, normalized=True, weight=None): + r"""Compute the Katz centrality for the graph G. + + Katz centrality computes the centrality for a node based on the centrality + of its neighbors. It is a generalization of the eigenvector centrality. The + Katz centrality for node $i$ is + + .. math:: + + x_i = \alpha \sum_{j} A_{ij} x_j + \beta, + + where $A$ is the adjacency matrix of graph G with eigenvalues $\lambda$. + + The parameter $\beta$ controls the initial centrality and + + .. math:: + + \alpha < \frac{1}{\lambda_{\max}}. + + Katz centrality computes the relative influence of a node within a + network by measuring the number of the immediate neighbors (first + degree nodes) and also all other nodes in the network that connect + to the node under consideration through these immediate neighbors. + + Extra weight can be provided to immediate neighbors through the + parameter $\beta$. Connections made with distant neighbors + are, however, penalized by an attenuation factor $\alpha$ which + should be strictly less than the inverse largest eigenvalue of the + adjacency matrix in order for the Katz centrality to be computed + correctly. More information is provided in [1]_. + + Parameters + ---------- + G : graph + A NetworkX graph + + alpha : float + Attenuation factor + + beta : scalar or dictionary, optional (default=1.0) + Weight attributed to the immediate neighborhood. If not a scalar the + dictionary must have an value for every node. + + normalized : bool + If True normalize the resulting values. + + weight : None or string, optional + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + In this measure the weight is interpreted as the connection strength. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with Katz centrality as the value. + + Raises + ------ + NetworkXError + If the parameter `beta` is not a scalar but lacks a value for at least + one node + + Examples + -------- + >>> import math + >>> G = nx.path_graph(4) + >>> phi = (1 + math.sqrt(5)) / 2.0 # largest eigenvalue of adj matrix + >>> centrality = nx.katz_centrality_numpy(G, 1 / phi) + >>> for n, c in sorted(centrality.items()): + ... print(f"{n} {c:.2f}") + 0 0.37 + 1 0.60 + 2 0.60 + 3 0.37 + + See Also + -------- + katz_centrality + eigenvector_centrality_numpy + eigenvector_centrality + :func:`~networkx.algorithms.link_analysis.pagerank_alg.pagerank` + :func:`~networkx.algorithms.link_analysis.hits_alg.hits` + + Notes + ----- + Katz centrality was introduced by [2]_. + + This algorithm uses a direct linear solver to solve the above equation. + The parameter ``alpha`` should be strictly less than the inverse of largest + eigenvalue of the adjacency matrix for there to be a solution. + You can use ``max(nx.adjacency_spectrum(G))`` to get $\lambda_{\max}$ the largest + eigenvalue of the adjacency matrix. + + When $\alpha = 1/\lambda_{\max}$ and $\beta=0$, Katz centrality is the same + as eigenvector centrality. + + For directed graphs this finds "left" eigenvectors which corresponds + to the in-edges in the graph. For out-edges Katz centrality + first reverse the graph with ``G.reverse()``. + + References + ---------- + .. [1] Mark E. J. Newman: + Networks: An Introduction. + Oxford University Press, USA, 2010, p. 173. + .. [2] Leo Katz: + A New Status Index Derived from Sociometric Index. + Psychometrika 18(1):39–43, 1953 + https://link.springer.com/content/pdf/10.1007/BF02289026.pdf + """ + import numpy as np + + if len(G) == 0: + return {} + try: + nodelist = beta.keys() + if set(nodelist) != set(G): + raise nx.NetworkXError("beta dictionary must have a value for every node") + b = np.array(list(beta.values()), dtype=float) + except AttributeError: + nodelist = list(G) + try: + b = np.ones((len(nodelist), 1)) * beta + except (TypeError, ValueError, AttributeError) as err: + raise nx.NetworkXError("beta must be a number") from err + + A = nx.adjacency_matrix(G, nodelist=nodelist, weight=weight).todense().T + n = A.shape[0] + centrality = np.linalg.solve(np.eye(n, n) - (alpha * A), b).squeeze() + + # Normalize: rely on truediv to cast to float + norm = np.sign(sum(centrality)) * np.linalg.norm(centrality) if normalized else 1 + return dict(zip(nodelist, centrality / norm)) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/laplacian.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/laplacian.py new file mode 100644 index 0000000000000000000000000000000000000000..e0a9a6d517254b72b130474577688ceb3d02ad8c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/laplacian.py @@ -0,0 +1,146 @@ +""" +Laplacian centrality measures. +""" +import networkx as nx + +__all__ = ["laplacian_centrality"] + + +@nx._dispatch(edge_attrs="weight") +def laplacian_centrality( + G, normalized=True, nodelist=None, weight="weight", walk_type=None, alpha=0.95 +): + r"""Compute the Laplacian centrality for nodes in the graph `G`. + + The Laplacian Centrality of a node ``i`` is measured by the drop in the + Laplacian Energy after deleting node ``i`` from the graph. The Laplacian Energy + is the sum of the squared eigenvalues of a graph's Laplacian matrix. + + .. math:: + + C_L(u_i,G) = \frac{(\Delta E)_i}{E_L (G)} = \frac{E_L (G)-E_L (G_i)}{E_L (G)} + + E_L (G) = \sum_{i=0}^n \lambda_i^2 + + Where $E_L (G)$ is the Laplacian energy of graph `G`, + E_L (G_i) is the Laplacian energy of graph `G` after deleting node ``i`` + and $\lambda_i$ are the eigenvalues of `G`'s Laplacian matrix. + This formula shows the normalized value. Without normalization, + the numerator on the right side is returned. + + Parameters + ---------- + G : graph + A networkx graph + + normalized : bool (default = True) + If True the centrality score is scaled so the sum over all nodes is 1. + If False the centrality score for each node is the drop in Laplacian + energy when that node is removed. + + nodelist : list, optional (default = None) + The rows and columns are ordered according to the nodes in nodelist. + If nodelist is None, then the ordering is produced by G.nodes(). + + weight: string or None, optional (default=`weight`) + Optional parameter `weight` to compute the Laplacian matrix. + The edge data key used to compute each value in the matrix. + If None, then each edge has weight 1. + + walk_type : string or None, optional (default=None) + Optional parameter `walk_type` used when calling + :func:`directed_laplacian_matrix `. + If None, the transition matrix is selected depending on the properties + of the graph. Otherwise can be `random`, `lazy`, or `pagerank`. + + alpha : real (default = 0.95) + Optional parameter `alpha` used when calling + :func:`directed_laplacian_matrix `. + (1 - alpha) is the teleportation probability used with pagerank. + + Returns + ------- + nodes : dictionary + Dictionary of nodes with Laplacian centrality as the value. + + Examples + -------- + >>> G = nx.Graph() + >>> edges = [(0, 1, 4), (0, 2, 2), (2, 1, 1), (1, 3, 2), (1, 4, 2), (4, 5, 1)] + >>> G.add_weighted_edges_from(edges) + >>> sorted((v, f"{c:0.2f}") for v, c in laplacian_centrality(G).items()) + [(0, '0.70'), (1, '0.90'), (2, '0.28'), (3, '0.22'), (4, '0.26'), (5, '0.04')] + + Notes + ----- + The algorithm is implemented based on [1]_ with an extension to directed graphs + using the ``directed_laplacian_matrix`` function. + + Raises + ------ + NetworkXPointlessConcept + If the graph `G` is the null graph. + ZeroDivisionError + If the graph `G` has no edges (is empty) and normalization is requested. + + References + ---------- + .. [1] Qi, X., Fuller, E., Wu, Q., Wu, Y., and Zhang, C.-Q. (2012). + Laplacian centrality: A new centrality measure for weighted networks. + Information Sciences, 194:240-253. + https://math.wvu.edu/~cqzhang/Publication-files/my-paper/INS-2012-Laplacian-W.pdf + + See Also + -------- + :func:`~networkx.linalg.laplacianmatrix.directed_laplacian_matrix` + :func:`~networkx.linalg.laplacianmatrix.laplacian_matrix` + """ + import numpy as np + import scipy as sp + + if len(G) == 0: + raise nx.NetworkXPointlessConcept("null graph has no centrality defined") + if G.size(weight=weight) == 0: + if normalized: + raise ZeroDivisionError("graph with no edges has zero full energy") + return {n: 0 for n in G} + + if nodelist is not None: + nodeset = set(G.nbunch_iter(nodelist)) + if len(nodeset) != len(nodelist): + raise nx.NetworkXError("nodelist has duplicate nodes or nodes not in G") + nodes = nodelist + [n for n in G if n not in nodeset] + else: + nodelist = nodes = list(G) + + if G.is_directed(): + lap_matrix = nx.directed_laplacian_matrix(G, nodes, weight, walk_type, alpha) + else: + lap_matrix = nx.laplacian_matrix(G, nodes, weight).toarray() + + full_energy = np.power(sp.linalg.eigh(lap_matrix, eigvals_only=True), 2).sum() + + # calculate laplacian centrality + laplace_centralities_dict = {} + for i, node in enumerate(nodelist): + # remove row and col i from lap_matrix + all_but_i = list(np.arange(lap_matrix.shape[0])) + all_but_i.remove(i) + A_2 = lap_matrix[all_but_i, :][:, all_but_i] + + # Adjust diagonal for removed row + new_diag = lap_matrix.diagonal() - abs(lap_matrix[:, i]) + np.fill_diagonal(A_2, new_diag[all_but_i]) + + if len(all_but_i) > 0: # catches degenerate case of single node + new_energy = np.power(sp.linalg.eigh(A_2, eigvals_only=True), 2).sum() + else: + new_energy = 0.0 + + lapl_cent = full_energy - new_energy + if normalized: + lapl_cent = lapl_cent / full_energy + + laplace_centralities_dict[node] = lapl_cent + + return laplace_centralities_dict diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/percolation.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/percolation.py new file mode 100644 index 0000000000000000000000000000000000000000..cc5d5ce6d7ddc0f81fbbebc7512901dc82d858ef --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/percolation.py @@ -0,0 +1,128 @@ +"""Percolation centrality measures.""" + +import networkx as nx +from networkx.algorithms.centrality.betweenness import ( + _single_source_dijkstra_path_basic as dijkstra, +) +from networkx.algorithms.centrality.betweenness import ( + _single_source_shortest_path_basic as shortest_path, +) + +__all__ = ["percolation_centrality"] + + +@nx._dispatch(node_attrs="attribute", edge_attrs="weight") +def percolation_centrality(G, attribute="percolation", states=None, weight=None): + r"""Compute the percolation centrality for nodes. + + Percolation centrality of a node $v$, at a given time, is defined + as the proportion of ‘percolated paths’ that go through that node. + + This measure quantifies relative impact of nodes based on their + topological connectivity, as well as their percolation states. + + Percolation states of nodes are used to depict network percolation + scenarios (such as during infection transmission in a social network + of individuals, spreading of computer viruses on computer networks, or + transmission of disease over a network of towns) over time. In this + measure usually the percolation state is expressed as a decimal + between 0.0 and 1.0. + + When all nodes are in the same percolated state this measure is + equivalent to betweenness centrality. + + Parameters + ---------- + G : graph + A NetworkX graph. + + attribute : None or string, optional (default='percolation') + Name of the node attribute to use for percolation state, used + if `states` is None. If a node does not set the attribute the + state of that node will be set to the default value of 1. + If all nodes do not have the attribute all nodes will be set to + 1 and the centrality measure will be equivalent to betweenness centrality. + + states : None or dict, optional (default=None) + Specify percolation states for the nodes, nodes as keys states + as values. + + weight : None or string, optional (default=None) + If None, all edge weights are considered equal. + Otherwise holds the name of the edge attribute used as weight. + The weight of an edge is treated as the length or distance between the two sides. + + + Returns + ------- + nodes : dictionary + Dictionary of nodes with percolation centrality as the value. + + See Also + -------- + betweenness_centrality + + Notes + ----- + The algorithm is from Mahendra Piraveenan, Mikhail Prokopenko, and + Liaquat Hossain [1]_ + Pair dependencies are calculated and accumulated using [2]_ + + For weighted graphs the edge weights must be greater than zero. + Zero edge weights can produce an infinite number of equal length + paths between pairs of nodes. + + References + ---------- + .. [1] Mahendra Piraveenan, Mikhail Prokopenko, Liaquat Hossain + Percolation Centrality: Quantifying Graph-Theoretic Impact of Nodes + during Percolation in Networks + http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0053095 + .. [2] Ulrik Brandes: + A Faster Algorithm for Betweenness Centrality. + Journal of Mathematical Sociology 25(2):163-177, 2001. + https://doi.org/10.1080/0022250X.2001.9990249 + """ + percolation = dict.fromkeys(G, 0.0) # b[v]=0 for v in G + + nodes = G + + if states is None: + states = nx.get_node_attributes(nodes, attribute, default=1) + + # sum of all percolation states + p_sigma_x_t = 0.0 + for v in states.values(): + p_sigma_x_t += v + + for s in nodes: + # single source shortest paths + if weight is None: # use BFS + S, P, sigma, _ = shortest_path(G, s) + else: # use Dijkstra's algorithm + S, P, sigma, _ = dijkstra(G, s, weight) + # accumulation + percolation = _accumulate_percolation( + percolation, S, P, sigma, s, states, p_sigma_x_t + ) + + n = len(G) + + for v in percolation: + percolation[v] *= 1 / (n - 2) + + return percolation + + +def _accumulate_percolation(percolation, S, P, sigma, s, states, p_sigma_x_t): + delta = dict.fromkeys(S, 0) + while S: + w = S.pop() + coeff = (1 + delta[w]) / sigma[w] + for v in P[w]: + delta[v] += sigma[v] * coeff + if w != s: + # percolation weight + pw_s_w = states[s] / (p_sigma_x_t - states[w]) + percolation[w] += delta[w] * pw_s_w + return percolation diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/second_order.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/second_order.py new file mode 100644 index 0000000000000000000000000000000000000000..4bdb1f52141223f43d8e5eb6c0a4fddbd7e58e08 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/second_order.py @@ -0,0 +1,138 @@ +"""Copyright (c) 2015 – Thomson Licensing, SAS + +Redistribution and use in source and binary forms, with or without +modification, are permitted (subject to the limitations in the +disclaimer below) provided that the following conditions are met: + +* Redistributions of source code must retain the above copyright +notice, this list of conditions and the following disclaimer. + +* Redistributions in binary form must reproduce the above copyright +notice, this list of conditions and the following disclaimer in the +documentation and/or other materials provided with the distribution. + +* Neither the name of Thomson Licensing, or Technicolor, nor the names +of its contributors may be used to endorse or promote products derived +from this software without specific prior written permission. + +NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE +GRANTED BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT +HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED +WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR +BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, +WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE +OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN +IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +""" + +import networkx as nx +from networkx.utils import not_implemented_for + +# Authors: Erwan Le Merrer (erwan.lemerrer@technicolor.com) + +__all__ = ["second_order_centrality"] + + +@not_implemented_for("directed") +@nx._dispatch(edge_attrs="weight") +def second_order_centrality(G, weight="weight"): + """Compute the second order centrality for nodes of G. + + The second order centrality of a given node is the standard deviation of + the return times to that node of a perpetual random walk on G: + + Parameters + ---------- + G : graph + A NetworkX connected and undirected graph. + + weight : string or None, optional (default="weight") + The name of an edge attribute that holds the numerical value + used as a weight. If None then each edge has weight 1. + + Returns + ------- + nodes : dictionary + Dictionary keyed by node with second order centrality as the value. + + Examples + -------- + >>> G = nx.star_graph(10) + >>> soc = nx.second_order_centrality(G) + >>> print(sorted(soc.items(), key=lambda x: x[1])[0][0]) # pick first id + 0 + + Raises + ------ + NetworkXException + If the graph G is empty, non connected or has negative weights. + + See Also + -------- + betweenness_centrality + + Notes + ----- + Lower values of second order centrality indicate higher centrality. + + The algorithm is from Kermarrec, Le Merrer, Sericola and Trédan [1]_. + + This code implements the analytical version of the algorithm, i.e., + there is no simulation of a random walk process involved. The random walk + is here unbiased (corresponding to eq 6 of the paper [1]_), thus the + centrality values are the standard deviations for random walk return times + on the transformed input graph G (equal in-degree at each nodes by adding + self-loops). + + Complexity of this implementation, made to run locally on a single machine, + is O(n^3), with n the size of G, which makes it viable only for small + graphs. + + References + ---------- + .. [1] Anne-Marie Kermarrec, Erwan Le Merrer, Bruno Sericola, Gilles Trédan + "Second order centrality: Distributed assessment of nodes criticity in + complex networks", Elsevier Computer Communications 34(5):619-628, 2011. + """ + import numpy as np + + n = len(G) + + if n == 0: + raise nx.NetworkXException("Empty graph.") + if not nx.is_connected(G): + raise nx.NetworkXException("Non connected graph.") + if any(d.get(weight, 0) < 0 for u, v, d in G.edges(data=True)): + raise nx.NetworkXException("Graph has negative edge weights.") + + # balancing G for Metropolis-Hastings random walks + G = nx.DiGraph(G) + in_deg = dict(G.in_degree(weight=weight)) + d_max = max(in_deg.values()) + for i, deg in in_deg.items(): + if deg < d_max: + G.add_edge(i, i, weight=d_max - deg) + + P = nx.to_numpy_array(G) + P /= P.sum(axis=1)[:, np.newaxis] # to transition probability matrix + + def _Qj(P, j): + P = P.copy() + P[:, j] = 0 + return P + + M = np.empty([n, n]) + + for i in range(n): + M[:, i] = np.linalg.solve( + np.identity(n) - _Qj(P, i), np.ones([n, 1])[:, 0] + ) # eq 3 + + return dict( + zip(G.nodes, [np.sqrt(2 * np.sum(M[:, i]) - n * (n + 1)) for i in range(n)]) + ) # eq 6 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/subgraph_alg.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/subgraph_alg.py new file mode 100644 index 0000000000000000000000000000000000000000..c615b4892014e9a180eb6ff6028988a571284bc4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/subgraph_alg.py @@ -0,0 +1,340 @@ +""" +Subraph centrality and communicability betweenness. +""" +import networkx as nx +from networkx.utils import not_implemented_for + +__all__ = [ + "subgraph_centrality_exp", + "subgraph_centrality", + "communicability_betweenness_centrality", + "estrada_index", +] + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@nx._dispatch +def subgraph_centrality_exp(G): + r"""Returns the subgraph centrality for each node of G. + + Subgraph centrality of a node `n` is the sum of weighted closed + walks of all lengths starting and ending at node `n`. The weights + decrease with path length. Each closed walk is associated with a + connected subgraph ([1]_). + + Parameters + ---------- + G: graph + + Returns + ------- + nodes:dictionary + Dictionary of nodes with subgraph centrality as the value. + + Raises + ------ + NetworkXError + If the graph is not undirected and simple. + + See Also + -------- + subgraph_centrality: + Alternative algorithm of the subgraph centrality for each node of G. + + Notes + ----- + This version of the algorithm exponentiates the adjacency matrix. + + The subgraph centrality of a node `u` in G can be found using + the matrix exponential of the adjacency matrix of G [1]_, + + .. math:: + + SC(u)=(e^A)_{uu} . + + References + ---------- + .. [1] Ernesto Estrada, Juan A. Rodriguez-Velazquez, + "Subgraph centrality in complex networks", + Physical Review E 71, 056103 (2005). + https://arxiv.org/abs/cond-mat/0504730 + + Examples + -------- + (Example from [1]_) + >>> G = nx.Graph( + ... [ + ... (1, 2), + ... (1, 5), + ... (1, 8), + ... (2, 3), + ... (2, 8), + ... (3, 4), + ... (3, 6), + ... (4, 5), + ... (4, 7), + ... (5, 6), + ... (6, 7), + ... (7, 8), + ... ] + ... ) + >>> sc = nx.subgraph_centrality_exp(G) + >>> print([f"{node} {sc[node]:0.2f}" for node in sorted(sc)]) + ['1 3.90', '2 3.90', '3 3.64', '4 3.71', '5 3.64', '6 3.71', '7 3.64', '8 3.90'] + """ + # alternative implementation that calculates the matrix exponential + import scipy as sp + + nodelist = list(G) # ordering of nodes in matrix + A = nx.to_numpy_array(G, nodelist) + # convert to 0-1 matrix + A[A != 0.0] = 1 + expA = sp.linalg.expm(A) + # convert diagonal to dictionary keyed by node + sc = dict(zip(nodelist, map(float, expA.diagonal()))) + return sc + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@nx._dispatch +def subgraph_centrality(G): + r"""Returns subgraph centrality for each node in G. + + Subgraph centrality of a node `n` is the sum of weighted closed + walks of all lengths starting and ending at node `n`. The weights + decrease with path length. Each closed walk is associated with a + connected subgraph ([1]_). + + Parameters + ---------- + G: graph + + Returns + ------- + nodes : dictionary + Dictionary of nodes with subgraph centrality as the value. + + Raises + ------ + NetworkXError + If the graph is not undirected and simple. + + See Also + -------- + subgraph_centrality_exp: + Alternative algorithm of the subgraph centrality for each node of G. + + Notes + ----- + This version of the algorithm computes eigenvalues and eigenvectors + of the adjacency matrix. + + Subgraph centrality of a node `u` in G can be found using + a spectral decomposition of the adjacency matrix [1]_, + + .. math:: + + SC(u)=\sum_{j=1}^{N}(v_{j}^{u})^2 e^{\lambda_{j}}, + + where `v_j` is an eigenvector of the adjacency matrix `A` of G + corresponding to the eigenvalue `\lambda_j`. + + Examples + -------- + (Example from [1]_) + >>> G = nx.Graph( + ... [ + ... (1, 2), + ... (1, 5), + ... (1, 8), + ... (2, 3), + ... (2, 8), + ... (3, 4), + ... (3, 6), + ... (4, 5), + ... (4, 7), + ... (5, 6), + ... (6, 7), + ... (7, 8), + ... ] + ... ) + >>> sc = nx.subgraph_centrality(G) + >>> print([f"{node} {sc[node]:0.2f}" for node in sorted(sc)]) + ['1 3.90', '2 3.90', '3 3.64', '4 3.71', '5 3.64', '6 3.71', '7 3.64', '8 3.90'] + + References + ---------- + .. [1] Ernesto Estrada, Juan A. Rodriguez-Velazquez, + "Subgraph centrality in complex networks", + Physical Review E 71, 056103 (2005). + https://arxiv.org/abs/cond-mat/0504730 + + """ + import numpy as np + + nodelist = list(G) # ordering of nodes in matrix + A = nx.to_numpy_array(G, nodelist) + # convert to 0-1 matrix + A[np.nonzero(A)] = 1 + w, v = np.linalg.eigh(A) + vsquare = np.array(v) ** 2 + expw = np.exp(w) + xg = vsquare @ expw + # convert vector dictionary keyed by node + sc = dict(zip(nodelist, map(float, xg))) + return sc + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@nx._dispatch +def communicability_betweenness_centrality(G): + r"""Returns subgraph communicability for all pairs of nodes in G. + + Communicability betweenness measure makes use of the number of walks + connecting every pair of nodes as the basis of a betweenness centrality + measure. + + Parameters + ---------- + G: graph + + Returns + ------- + nodes : dictionary + Dictionary of nodes with communicability betweenness as the value. + + Raises + ------ + NetworkXError + If the graph is not undirected and simple. + + Notes + ----- + Let `G=(V,E)` be a simple undirected graph with `n` nodes and `m` edges, + and `A` denote the adjacency matrix of `G`. + + Let `G(r)=(V,E(r))` be the graph resulting from + removing all edges connected to node `r` but not the node itself. + + The adjacency matrix for `G(r)` is `A+E(r)`, where `E(r)` has nonzeros + only in row and column `r`. + + The subraph betweenness of a node `r` is [1]_ + + .. math:: + + \omega_{r} = \frac{1}{C}\sum_{p}\sum_{q}\frac{G_{prq}}{G_{pq}}, + p\neq q, q\neq r, + + where + `G_{prq}=(e^{A}_{pq} - (e^{A+E(r)})_{pq}` is the number of walks + involving node r, + `G_{pq}=(e^{A})_{pq}` is the number of closed walks starting + at node `p` and ending at node `q`, + and `C=(n-1)^{2}-(n-1)` is a normalization factor equal to the + number of terms in the sum. + + The resulting `\omega_{r}` takes values between zero and one. + The lower bound cannot be attained for a connected + graph, and the upper bound is attained in the star graph. + + References + ---------- + .. [1] Ernesto Estrada, Desmond J. Higham, Naomichi Hatano, + "Communicability Betweenness in Complex Networks" + Physica A 388 (2009) 764-774. + https://arxiv.org/abs/0905.4102 + + Examples + -------- + >>> G = nx.Graph([(0, 1), (1, 2), (1, 5), (5, 4), (2, 4), (2, 3), (4, 3), (3, 6)]) + >>> cbc = nx.communicability_betweenness_centrality(G) + >>> print([f"{node} {cbc[node]:0.2f}" for node in sorted(cbc)]) + ['0 0.03', '1 0.45', '2 0.51', '3 0.45', '4 0.40', '5 0.19', '6 0.03'] + """ + import numpy as np + import scipy as sp + + nodelist = list(G) # ordering of nodes in matrix + n = len(nodelist) + A = nx.to_numpy_array(G, nodelist) + # convert to 0-1 matrix + A[np.nonzero(A)] = 1 + expA = sp.linalg.expm(A) + mapping = dict(zip(nodelist, range(n))) + cbc = {} + for v in G: + # remove row and col of node v + i = mapping[v] + row = A[i, :].copy() + col = A[:, i].copy() + A[i, :] = 0 + A[:, i] = 0 + B = (expA - sp.linalg.expm(A)) / expA + # sum with row/col of node v and diag set to zero + B[i, :] = 0 + B[:, i] = 0 + B -= np.diag(np.diag(B)) + cbc[v] = B.sum() + # put row and col back + A[i, :] = row + A[:, i] = col + # rescale when more than two nodes + order = len(cbc) + if order > 2: + scale = 1.0 / ((order - 1.0) ** 2 - (order - 1.0)) + for v in cbc: + cbc[v] *= scale + return cbc + + +@nx._dispatch +def estrada_index(G): + r"""Returns the Estrada index of a the graph G. + + The Estrada Index is a topological index of folding or 3D "compactness" ([1]_). + + Parameters + ---------- + G: graph + + Returns + ------- + estrada index: float + + Raises + ------ + NetworkXError + If the graph is not undirected and simple. + + Notes + ----- + Let `G=(V,E)` be a simple undirected graph with `n` nodes and let + `\lambda_{1}\leq\lambda_{2}\leq\cdots\lambda_{n}` + be a non-increasing ordering of the eigenvalues of its adjacency + matrix `A`. The Estrada index is ([1]_, [2]_) + + .. math:: + EE(G)=\sum_{j=1}^n e^{\lambda _j}. + + References + ---------- + .. [1] E. Estrada, "Characterization of 3D molecular structure", + Chem. Phys. Lett. 319, 713 (2000). + https://doi.org/10.1016/S0009-2614(00)00158-5 + .. [2] José Antonio de la Peñaa, Ivan Gutman, Juan Rada, + "Estimating the Estrada index", + Linear Algebra and its Applications. 427, 1 (2007). + https://doi.org/10.1016/j.laa.2007.06.020 + + Examples + -------- + >>> G = nx.Graph([(0, 1), (1, 2), (1, 5), (5, 4), (2, 4), (2, 3), (4, 3), (3, 6)]) + >>> ei = nx.estrada_index(G) + >>> print(f"{ei:0.5}") + 20.55 + """ + return sum(subgraph_centrality(G).values()) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/__init__.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/__pycache__/test_betweenness_centrality_subset.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/__pycache__/test_betweenness_centrality_subset.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1a504b19a0ba0a545dea443533c7813fb9417463 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/__pycache__/test_betweenness_centrality_subset.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_betweenness_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_betweenness_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..4c059cf980666f7e14a80929f84c80bc38749432 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_betweenness_centrality.py @@ -0,0 +1,780 @@ +import pytest + +import networkx as nx + + +def weighted_G(): + G = nx.Graph() + G.add_edge(0, 1, weight=3) + G.add_edge(0, 2, weight=2) + G.add_edge(0, 3, weight=6) + G.add_edge(0, 4, weight=4) + G.add_edge(1, 3, weight=5) + G.add_edge(1, 5, weight=5) + G.add_edge(2, 4, weight=1) + G.add_edge(3, 4, weight=2) + G.add_edge(3, 5, weight=1) + G.add_edge(4, 5, weight=4) + return G + + +class TestBetweennessCentrality: + def test_K5(self): + """Betweenness centrality: K5""" + G = nx.complete_graph(5) + b = nx.betweenness_centrality(G, weight=None, normalized=False) + b_answer = {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_K5_endpoints(self): + """Betweenness centrality: K5 endpoints""" + G = nx.complete_graph(5) + b = nx.betweenness_centrality(G, weight=None, normalized=False, endpoints=True) + b_answer = {0: 4.0, 1: 4.0, 2: 4.0, 3: 4.0, 4: 4.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + # normalized = True case + b = nx.betweenness_centrality(G, weight=None, normalized=True, endpoints=True) + b_answer = {0: 0.4, 1: 0.4, 2: 0.4, 3: 0.4, 4: 0.4} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P3_normalized(self): + """Betweenness centrality: P3 normalized""" + G = nx.path_graph(3) + b = nx.betweenness_centrality(G, weight=None, normalized=True) + b_answer = {0: 0.0, 1: 1.0, 2: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P3(self): + """Betweenness centrality: P3""" + G = nx.path_graph(3) + b_answer = {0: 0.0, 1: 1.0, 2: 0.0} + b = nx.betweenness_centrality(G, weight=None, normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_sample_from_P3(self): + """Betweenness centrality: P3 sample""" + G = nx.path_graph(3) + b_answer = {0: 0.0, 1: 1.0, 2: 0.0} + b = nx.betweenness_centrality(G, k=3, weight=None, normalized=False, seed=1) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + b = nx.betweenness_centrality(G, k=2, weight=None, normalized=False, seed=1) + # python versions give different results with same seed + b_approx1 = {0: 0.0, 1: 1.5, 2: 0.0} + b_approx2 = {0: 0.0, 1: 0.75, 2: 0.0} + for n in sorted(G): + assert b[n] in (b_approx1[n], b_approx2[n]) + + def test_P3_endpoints(self): + """Betweenness centrality: P3 endpoints""" + G = nx.path_graph(3) + b_answer = {0: 2.0, 1: 3.0, 2: 2.0} + b = nx.betweenness_centrality(G, weight=None, normalized=False, endpoints=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + # normalized = True case + b_answer = {0: 2 / 3, 1: 1.0, 2: 2 / 3} + b = nx.betweenness_centrality(G, weight=None, normalized=True, endpoints=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_krackhardt_kite_graph(self): + """Betweenness centrality: Krackhardt kite graph""" + G = nx.krackhardt_kite_graph() + b_answer = { + 0: 1.667, + 1: 1.667, + 2: 0.000, + 3: 7.333, + 4: 0.000, + 5: 16.667, + 6: 16.667, + 7: 28.000, + 8: 16.000, + 9: 0.000, + } + for b in b_answer: + b_answer[b] /= 2 + b = nx.betweenness_centrality(G, weight=None, normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_krackhardt_kite_graph_normalized(self): + """Betweenness centrality: Krackhardt kite graph normalized""" + G = nx.krackhardt_kite_graph() + b_answer = { + 0: 0.023, + 1: 0.023, + 2: 0.000, + 3: 0.102, + 4: 0.000, + 5: 0.231, + 6: 0.231, + 7: 0.389, + 8: 0.222, + 9: 0.000, + } + b = nx.betweenness_centrality(G, weight=None, normalized=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_florentine_families_graph(self): + """Betweenness centrality: Florentine families graph""" + G = nx.florentine_families_graph() + b_answer = { + "Acciaiuoli": 0.000, + "Albizzi": 0.212, + "Barbadori": 0.093, + "Bischeri": 0.104, + "Castellani": 0.055, + "Ginori": 0.000, + "Guadagni": 0.255, + "Lamberteschi": 0.000, + "Medici": 0.522, + "Pazzi": 0.000, + "Peruzzi": 0.022, + "Ridolfi": 0.114, + "Salviati": 0.143, + "Strozzi": 0.103, + "Tornabuoni": 0.092, + } + + b = nx.betweenness_centrality(G, weight=None, normalized=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_les_miserables_graph(self): + """Betweenness centrality: Les Miserables graph""" + G = nx.les_miserables_graph() + b_answer = { + "Napoleon": 0.000, + "Myriel": 0.177, + "MlleBaptistine": 0.000, + "MmeMagloire": 0.000, + "CountessDeLo": 0.000, + "Geborand": 0.000, + "Champtercier": 0.000, + "Cravatte": 0.000, + "Count": 0.000, + "OldMan": 0.000, + "Valjean": 0.570, + "Labarre": 0.000, + "Marguerite": 0.000, + "MmeDeR": 0.000, + "Isabeau": 0.000, + "Gervais": 0.000, + "Listolier": 0.000, + "Tholomyes": 0.041, + "Fameuil": 0.000, + "Blacheville": 0.000, + "Favourite": 0.000, + "Dahlia": 0.000, + "Zephine": 0.000, + "Fantine": 0.130, + "MmeThenardier": 0.029, + "Thenardier": 0.075, + "Cosette": 0.024, + "Javert": 0.054, + "Fauchelevent": 0.026, + "Bamatabois": 0.008, + "Perpetue": 0.000, + "Simplice": 0.009, + "Scaufflaire": 0.000, + "Woman1": 0.000, + "Judge": 0.000, + "Champmathieu": 0.000, + "Brevet": 0.000, + "Chenildieu": 0.000, + "Cochepaille": 0.000, + "Pontmercy": 0.007, + "Boulatruelle": 0.000, + "Eponine": 0.011, + "Anzelma": 0.000, + "Woman2": 0.000, + "MotherInnocent": 0.000, + "Gribier": 0.000, + "MmeBurgon": 0.026, + "Jondrette": 0.000, + "Gavroche": 0.165, + "Gillenormand": 0.020, + "Magnon": 0.000, + "MlleGillenormand": 0.048, + "MmePontmercy": 0.000, + "MlleVaubois": 0.000, + "LtGillenormand": 0.000, + "Marius": 0.132, + "BaronessT": 0.000, + "Mabeuf": 0.028, + "Enjolras": 0.043, + "Combeferre": 0.001, + "Prouvaire": 0.000, + "Feuilly": 0.001, + "Courfeyrac": 0.005, + "Bahorel": 0.002, + "Bossuet": 0.031, + "Joly": 0.002, + "Grantaire": 0.000, + "MotherPlutarch": 0.000, + "Gueulemer": 0.005, + "Babet": 0.005, + "Claquesous": 0.005, + "Montparnasse": 0.004, + "Toussaint": 0.000, + "Child1": 0.000, + "Child2": 0.000, + "Brujon": 0.000, + "MmeHucheloup": 0.000, + } + + b = nx.betweenness_centrality(G, weight=None, normalized=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_ladder_graph(self): + """Betweenness centrality: Ladder graph""" + G = nx.Graph() # ladder_graph(3) + G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (2, 4), (4, 5), (3, 5)]) + b_answer = {0: 1.667, 1: 1.667, 2: 6.667, 3: 6.667, 4: 1.667, 5: 1.667} + for b in b_answer: + b_answer[b] /= 2 + b = nx.betweenness_centrality(G, weight=None, normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_disconnected_path(self): + """Betweenness centrality: disconnected path""" + G = nx.Graph() + nx.add_path(G, [0, 1, 2]) + nx.add_path(G, [3, 4, 5, 6]) + b_answer = {0: 0, 1: 1, 2: 0, 3: 0, 4: 2, 5: 2, 6: 0} + b = nx.betweenness_centrality(G, weight=None, normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_disconnected_path_endpoints(self): + """Betweenness centrality: disconnected path endpoints""" + G = nx.Graph() + nx.add_path(G, [0, 1, 2]) + nx.add_path(G, [3, 4, 5, 6]) + b_answer = {0: 2, 1: 3, 2: 2, 3: 3, 4: 5, 5: 5, 6: 3} + b = nx.betweenness_centrality(G, weight=None, normalized=False, endpoints=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + # normalized = True case + b = nx.betweenness_centrality(G, weight=None, normalized=True, endpoints=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n] / 21, abs=1e-7) + + def test_directed_path(self): + """Betweenness centrality: directed path""" + G = nx.DiGraph() + nx.add_path(G, [0, 1, 2]) + b = nx.betweenness_centrality(G, weight=None, normalized=False) + b_answer = {0: 0.0, 1: 1.0, 2: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_directed_path_normalized(self): + """Betweenness centrality: directed path normalized""" + G = nx.DiGraph() + nx.add_path(G, [0, 1, 2]) + b = nx.betweenness_centrality(G, weight=None, normalized=True) + b_answer = {0: 0.0, 1: 0.5, 2: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + +class TestWeightedBetweennessCentrality: + def test_K5(self): + """Weighted betweenness centrality: K5""" + G = nx.complete_graph(5) + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + b_answer = {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P3_normalized(self): + """Weighted betweenness centrality: P3 normalized""" + G = nx.path_graph(3) + b = nx.betweenness_centrality(G, weight="weight", normalized=True) + b_answer = {0: 0.0, 1: 1.0, 2: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P3(self): + """Weighted betweenness centrality: P3""" + G = nx.path_graph(3) + b_answer = {0: 0.0, 1: 1.0, 2: 0.0} + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_krackhardt_kite_graph(self): + """Weighted betweenness centrality: Krackhardt kite graph""" + G = nx.krackhardt_kite_graph() + b_answer = { + 0: 1.667, + 1: 1.667, + 2: 0.000, + 3: 7.333, + 4: 0.000, + 5: 16.667, + 6: 16.667, + 7: 28.000, + 8: 16.000, + 9: 0.000, + } + for b in b_answer: + b_answer[b] /= 2 + + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_krackhardt_kite_graph_normalized(self): + """Weighted betweenness centrality: + Krackhardt kite graph normalized + """ + G = nx.krackhardt_kite_graph() + b_answer = { + 0: 0.023, + 1: 0.023, + 2: 0.000, + 3: 0.102, + 4: 0.000, + 5: 0.231, + 6: 0.231, + 7: 0.389, + 8: 0.222, + 9: 0.000, + } + b = nx.betweenness_centrality(G, weight="weight", normalized=True) + + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_florentine_families_graph(self): + """Weighted betweenness centrality: + Florentine families graph""" + G = nx.florentine_families_graph() + b_answer = { + "Acciaiuoli": 0.000, + "Albizzi": 0.212, + "Barbadori": 0.093, + "Bischeri": 0.104, + "Castellani": 0.055, + "Ginori": 0.000, + "Guadagni": 0.255, + "Lamberteschi": 0.000, + "Medici": 0.522, + "Pazzi": 0.000, + "Peruzzi": 0.022, + "Ridolfi": 0.114, + "Salviati": 0.143, + "Strozzi": 0.103, + "Tornabuoni": 0.092, + } + + b = nx.betweenness_centrality(G, weight="weight", normalized=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_les_miserables_graph(self): + """Weighted betweenness centrality: Les Miserables graph""" + G = nx.les_miserables_graph() + b_answer = { + "Napoleon": 0.000, + "Myriel": 0.177, + "MlleBaptistine": 0.000, + "MmeMagloire": 0.000, + "CountessDeLo": 0.000, + "Geborand": 0.000, + "Champtercier": 0.000, + "Cravatte": 0.000, + "Count": 0.000, + "OldMan": 0.000, + "Valjean": 0.454, + "Labarre": 0.000, + "Marguerite": 0.009, + "MmeDeR": 0.000, + "Isabeau": 0.000, + "Gervais": 0.000, + "Listolier": 0.000, + "Tholomyes": 0.066, + "Fameuil": 0.000, + "Blacheville": 0.000, + "Favourite": 0.000, + "Dahlia": 0.000, + "Zephine": 0.000, + "Fantine": 0.114, + "MmeThenardier": 0.046, + "Thenardier": 0.129, + "Cosette": 0.075, + "Javert": 0.193, + "Fauchelevent": 0.026, + "Bamatabois": 0.080, + "Perpetue": 0.000, + "Simplice": 0.001, + "Scaufflaire": 0.000, + "Woman1": 0.000, + "Judge": 0.000, + "Champmathieu": 0.000, + "Brevet": 0.000, + "Chenildieu": 0.000, + "Cochepaille": 0.000, + "Pontmercy": 0.023, + "Boulatruelle": 0.000, + "Eponine": 0.023, + "Anzelma": 0.000, + "Woman2": 0.000, + "MotherInnocent": 0.000, + "Gribier": 0.000, + "MmeBurgon": 0.026, + "Jondrette": 0.000, + "Gavroche": 0.285, + "Gillenormand": 0.024, + "Magnon": 0.005, + "MlleGillenormand": 0.036, + "MmePontmercy": 0.005, + "MlleVaubois": 0.000, + "LtGillenormand": 0.015, + "Marius": 0.072, + "BaronessT": 0.004, + "Mabeuf": 0.089, + "Enjolras": 0.003, + "Combeferre": 0.000, + "Prouvaire": 0.000, + "Feuilly": 0.004, + "Courfeyrac": 0.001, + "Bahorel": 0.007, + "Bossuet": 0.028, + "Joly": 0.000, + "Grantaire": 0.036, + "MotherPlutarch": 0.000, + "Gueulemer": 0.025, + "Babet": 0.015, + "Claquesous": 0.042, + "Montparnasse": 0.050, + "Toussaint": 0.011, + "Child1": 0.000, + "Child2": 0.000, + "Brujon": 0.002, + "MmeHucheloup": 0.034, + } + + b = nx.betweenness_centrality(G, weight="weight", normalized=True) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_ladder_graph(self): + """Weighted betweenness centrality: Ladder graph""" + G = nx.Graph() # ladder_graph(3) + G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (2, 4), (4, 5), (3, 5)]) + b_answer = {0: 1.667, 1: 1.667, 2: 6.667, 3: 6.667, 4: 1.667, 5: 1.667} + for b in b_answer: + b_answer[b] /= 2 + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_G(self): + """Weighted betweenness centrality: G""" + G = weighted_G() + b_answer = {0: 2.0, 1: 0.0, 2: 4.0, 3: 3.0, 4: 4.0, 5: 0.0} + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_G2(self): + """Weighted betweenness centrality: G2""" + G = nx.DiGraph() + G.add_weighted_edges_from( + [ + ("s", "u", 10), + ("s", "x", 5), + ("u", "v", 1), + ("u", "x", 2), + ("v", "y", 1), + ("x", "u", 3), + ("x", "v", 5), + ("x", "y", 2), + ("y", "s", 7), + ("y", "v", 6), + ] + ) + + b_answer = {"y": 5.0, "x": 5.0, "s": 4.0, "u": 2.0, "v": 2.0} + + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_G3(self): + """Weighted betweenness centrality: G3""" + G = nx.MultiGraph(weighted_G()) + es = list(G.edges(data=True))[::2] # duplicate every other edge + G.add_edges_from(es) + b_answer = {0: 2.0, 1: 0.0, 2: 4.0, 3: 3.0, 4: 4.0, 5: 0.0} + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_G4(self): + """Weighted betweenness centrality: G4""" + G = nx.MultiDiGraph() + G.add_weighted_edges_from( + [ + ("s", "u", 10), + ("s", "x", 5), + ("s", "x", 6), + ("u", "v", 1), + ("u", "x", 2), + ("v", "y", 1), + ("v", "y", 1), + ("x", "u", 3), + ("x", "v", 5), + ("x", "y", 2), + ("x", "y", 3), + ("y", "s", 7), + ("y", "v", 6), + ("y", "v", 6), + ] + ) + + b_answer = {"y": 5.0, "x": 5.0, "s": 4.0, "u": 2.0, "v": 2.0} + + b = nx.betweenness_centrality(G, weight="weight", normalized=False) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + +class TestEdgeBetweennessCentrality: + def test_K5(self): + """Edge betweenness centrality: K5""" + G = nx.complete_graph(5) + b = nx.edge_betweenness_centrality(G, weight=None, normalized=False) + b_answer = dict.fromkeys(G.edges(), 1) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_normalized_K5(self): + """Edge betweenness centrality: K5""" + G = nx.complete_graph(5) + b = nx.edge_betweenness_centrality(G, weight=None, normalized=True) + b_answer = dict.fromkeys(G.edges(), 1 / 10) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_C4(self): + """Edge betweenness centrality: C4""" + G = nx.cycle_graph(4) + b = nx.edge_betweenness_centrality(G, weight=None, normalized=True) + b_answer = {(0, 1): 2, (0, 3): 2, (1, 2): 2, (2, 3): 2} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n] / 6, abs=1e-7) + + def test_P4(self): + """Edge betweenness centrality: P4""" + G = nx.path_graph(4) + b = nx.edge_betweenness_centrality(G, weight=None, normalized=False) + b_answer = {(0, 1): 3, (1, 2): 4, (2, 3): 3} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_normalized_P4(self): + """Edge betweenness centrality: P4""" + G = nx.path_graph(4) + b = nx.edge_betweenness_centrality(G, weight=None, normalized=True) + b_answer = {(0, 1): 3, (1, 2): 4, (2, 3): 3} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n] / 6, abs=1e-7) + + def test_balanced_tree(self): + """Edge betweenness centrality: balanced tree""" + G = nx.balanced_tree(r=2, h=2) + b = nx.edge_betweenness_centrality(G, weight=None, normalized=False) + b_answer = {(0, 1): 12, (0, 2): 12, (1, 3): 6, (1, 4): 6, (2, 5): 6, (2, 6): 6} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + +class TestWeightedEdgeBetweennessCentrality: + def test_K5(self): + """Edge betweenness centrality: K5""" + G = nx.complete_graph(5) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=False) + b_answer = dict.fromkeys(G.edges(), 1) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_C4(self): + """Edge betweenness centrality: C4""" + G = nx.cycle_graph(4) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=False) + b_answer = {(0, 1): 2, (0, 3): 2, (1, 2): 2, (2, 3): 2} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P4(self): + """Edge betweenness centrality: P4""" + G = nx.path_graph(4) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=False) + b_answer = {(0, 1): 3, (1, 2): 4, (2, 3): 3} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_balanced_tree(self): + """Edge betweenness centrality: balanced tree""" + G = nx.balanced_tree(r=2, h=2) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=False) + b_answer = {(0, 1): 12, (0, 2): 12, (1, 3): 6, (1, 4): 6, (2, 5): 6, (2, 6): 6} + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_weighted_graph(self): + """Edge betweenness centrality: weighted""" + eList = [ + (0, 1, 5), + (0, 2, 4), + (0, 3, 3), + (0, 4, 2), + (1, 2, 4), + (1, 3, 1), + (1, 4, 3), + (2, 4, 5), + (3, 4, 4), + ] + G = nx.Graph() + G.add_weighted_edges_from(eList) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=False) + b_answer = { + (0, 1): 0.0, + (0, 2): 1.0, + (0, 3): 2.0, + (0, 4): 1.0, + (1, 2): 2.0, + (1, 3): 3.5, + (1, 4): 1.5, + (2, 4): 1.0, + (3, 4): 0.5, + } + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_normalized_weighted_graph(self): + """Edge betweenness centrality: normalized weighted""" + eList = [ + (0, 1, 5), + (0, 2, 4), + (0, 3, 3), + (0, 4, 2), + (1, 2, 4), + (1, 3, 1), + (1, 4, 3), + (2, 4, 5), + (3, 4, 4), + ] + G = nx.Graph() + G.add_weighted_edges_from(eList) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=True) + b_answer = { + (0, 1): 0.0, + (0, 2): 1.0, + (0, 3): 2.0, + (0, 4): 1.0, + (1, 2): 2.0, + (1, 3): 3.5, + (1, 4): 1.5, + (2, 4): 1.0, + (3, 4): 0.5, + } + norm = len(G) * (len(G) - 1) / 2 + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n] / norm, abs=1e-7) + + def test_weighted_multigraph(self): + """Edge betweenness centrality: weighted multigraph""" + eList = [ + (0, 1, 5), + (0, 1, 4), + (0, 2, 4), + (0, 3, 3), + (0, 3, 3), + (0, 4, 2), + (1, 2, 4), + (1, 3, 1), + (1, 3, 2), + (1, 4, 3), + (1, 4, 4), + (2, 4, 5), + (3, 4, 4), + (3, 4, 4), + ] + G = nx.MultiGraph() + G.add_weighted_edges_from(eList) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=False) + b_answer = { + (0, 1, 0): 0.0, + (0, 1, 1): 0.5, + (0, 2, 0): 1.0, + (0, 3, 0): 0.75, + (0, 3, 1): 0.75, + (0, 4, 0): 1.0, + (1, 2, 0): 2.0, + (1, 3, 0): 3.0, + (1, 3, 1): 0.0, + (1, 4, 0): 1.5, + (1, 4, 1): 0.0, + (2, 4, 0): 1.0, + (3, 4, 0): 0.25, + (3, 4, 1): 0.25, + } + for n in sorted(G.edges(keys=True)): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_normalized_weighted_multigraph(self): + """Edge betweenness centrality: normalized weighted multigraph""" + eList = [ + (0, 1, 5), + (0, 1, 4), + (0, 2, 4), + (0, 3, 3), + (0, 3, 3), + (0, 4, 2), + (1, 2, 4), + (1, 3, 1), + (1, 3, 2), + (1, 4, 3), + (1, 4, 4), + (2, 4, 5), + (3, 4, 4), + (3, 4, 4), + ] + G = nx.MultiGraph() + G.add_weighted_edges_from(eList) + b = nx.edge_betweenness_centrality(G, weight="weight", normalized=True) + b_answer = { + (0, 1, 0): 0.0, + (0, 1, 1): 0.5, + (0, 2, 0): 1.0, + (0, 3, 0): 0.75, + (0, 3, 1): 0.75, + (0, 4, 0): 1.0, + (1, 2, 0): 2.0, + (1, 3, 0): 3.0, + (1, 3, 1): 0.0, + (1, 4, 0): 1.5, + (1, 4, 1): 0.0, + (2, 4, 0): 1.0, + (3, 4, 0): 0.25, + (3, 4, 1): 0.25, + } + norm = len(G) * (len(G) - 1) / 2 + for n in sorted(G.edges(keys=True)): + assert b[n] == pytest.approx(b_answer[n] / norm, abs=1e-7) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_betweenness_centrality_subset.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_betweenness_centrality_subset.py new file mode 100644 index 0000000000000000000000000000000000000000..a35a401a28e31d279c0d715f79f8a7cc5738050f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_betweenness_centrality_subset.py @@ -0,0 +1,340 @@ +import pytest + +import networkx as nx + + +class TestSubsetBetweennessCentrality: + def test_K5(self): + """Betweenness Centrality Subset: K5""" + G = nx.complete_graph(5) + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[1, 3], weight=None + ) + b_answer = {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P5_directed(self): + """Betweenness Centrality Subset: P5 directed""" + G = nx.DiGraph() + nx.add_path(G, range(5)) + b_answer = {0: 0, 1: 1, 2: 1, 3: 0, 4: 0, 5: 0} + b = nx.betweenness_centrality_subset(G, sources=[0], targets=[3], weight=None) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P5(self): + """Betweenness Centrality Subset: P5""" + G = nx.Graph() + nx.add_path(G, range(5)) + b_answer = {0: 0, 1: 0.5, 2: 0.5, 3: 0, 4: 0, 5: 0} + b = nx.betweenness_centrality_subset(G, sources=[0], targets=[3], weight=None) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P5_multiple_target(self): + """Betweenness Centrality Subset: P5 multiple target""" + G = nx.Graph() + nx.add_path(G, range(5)) + b_answer = {0: 0, 1: 1, 2: 1, 3: 0.5, 4: 0, 5: 0} + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[3, 4], weight=None + ) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_box(self): + """Betweenness Centrality Subset: box""" + G = nx.Graph() + G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3)]) + b_answer = {0: 0, 1: 0.25, 2: 0.25, 3: 0} + b = nx.betweenness_centrality_subset(G, sources=[0], targets=[3], weight=None) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_box_and_path(self): + """Betweenness Centrality Subset: box and path""" + G = nx.Graph() + G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (3, 4), (4, 5)]) + b_answer = {0: 0, 1: 0.5, 2: 0.5, 3: 0.5, 4: 0, 5: 0} + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[3, 4], weight=None + ) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_box_and_path2(self): + """Betweenness Centrality Subset: box and path multiple target""" + G = nx.Graph() + G.add_edges_from([(0, 1), (1, 2), (2, 3), (1, 20), (20, 3), (3, 4)]) + b_answer = {0: 0, 1: 1.0, 2: 0.5, 20: 0.5, 3: 0.5, 4: 0} + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[3, 4], weight=None + ) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_diamond_multi_path(self): + """Betweenness Centrality Subset: Diamond Multi Path""" + G = nx.Graph() + G.add_edges_from( + [ + (1, 2), + (1, 3), + (1, 4), + (1, 5), + (1, 10), + (10, 11), + (11, 12), + (12, 9), + (2, 6), + (3, 6), + (4, 6), + (5, 7), + (7, 8), + (6, 8), + (8, 9), + ] + ) + b = nx.betweenness_centrality_subset(G, sources=[1], targets=[9], weight=None) + + expected_b = { + 1: 0, + 2: 1.0 / 10, + 3: 1.0 / 10, + 4: 1.0 / 10, + 5: 1.0 / 10, + 6: 3.0 / 10, + 7: 1.0 / 10, + 8: 4.0 / 10, + 9: 0, + 10: 1.0 / 10, + 11: 1.0 / 10, + 12: 1.0 / 10, + } + + for n in sorted(G): + assert b[n] == pytest.approx(expected_b[n], abs=1e-7) + + def test_normalized_p2(self): + """ + Betweenness Centrality Subset: Normalized P2 + if n <= 2: no normalization, betweenness centrality should be 0 for all nodes. + """ + G = nx.Graph() + nx.add_path(G, range(2)) + b_answer = {0: 0, 1: 0.0} + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[1], normalized=True, weight=None + ) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_normalized_P5_directed(self): + """Betweenness Centrality Subset: Normalized Directed P5""" + G = nx.DiGraph() + nx.add_path(G, range(5)) + b_answer = {0: 0, 1: 1.0 / 12.0, 2: 1.0 / 12.0, 3: 0, 4: 0, 5: 0} + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[3], normalized=True, weight=None + ) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_weighted_graph(self): + """Betweenness Centrality Subset: Weighted Graph""" + G = nx.DiGraph() + G.add_edge(0, 1, weight=3) + G.add_edge(0, 2, weight=2) + G.add_edge(0, 3, weight=6) + G.add_edge(0, 4, weight=4) + G.add_edge(1, 3, weight=5) + G.add_edge(1, 5, weight=5) + G.add_edge(2, 4, weight=1) + G.add_edge(3, 4, weight=2) + G.add_edge(3, 5, weight=1) + G.add_edge(4, 5, weight=4) + b_answer = {0: 0.0, 1: 0.0, 2: 0.5, 3: 0.5, 4: 0.5, 5: 0.0} + b = nx.betweenness_centrality_subset( + G, sources=[0], targets=[5], normalized=False, weight="weight" + ) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + +class TestEdgeSubsetBetweennessCentrality: + def test_K5(self): + """Edge betweenness subset centrality: K5""" + G = nx.complete_graph(5) + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[1, 3], weight=None + ) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 3)] = b_answer[(0, 1)] = 0.5 + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P5_directed(self): + """Edge betweenness subset centrality: P5 directed""" + G = nx.DiGraph() + nx.add_path(G, range(5)) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = b_answer[(1, 2)] = b_answer[(2, 3)] = 1 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3], weight=None + ) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P5(self): + """Edge betweenness subset centrality: P5""" + G = nx.Graph() + nx.add_path(G, range(5)) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = b_answer[(1, 2)] = b_answer[(2, 3)] = 0.5 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3], weight=None + ) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P5_multiple_target(self): + """Edge betweenness subset centrality: P5 multiple target""" + G = nx.Graph() + nx.add_path(G, range(5)) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = b_answer[(1, 2)] = b_answer[(2, 3)] = 1 + b_answer[(3, 4)] = 0.5 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3, 4], weight=None + ) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_box(self): + """Edge betweenness subset centrality: box""" + G = nx.Graph() + G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3)]) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = b_answer[(0, 2)] = 0.25 + b_answer[(1, 3)] = b_answer[(2, 3)] = 0.25 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3], weight=None + ) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_box_and_path(self): + """Edge betweenness subset centrality: box and path""" + G = nx.Graph() + G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (3, 4), (4, 5)]) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = b_answer[(0, 2)] = 0.5 + b_answer[(1, 3)] = b_answer[(2, 3)] = 0.5 + b_answer[(3, 4)] = 0.5 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3, 4], weight=None + ) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_box_and_path2(self): + """Edge betweenness subset centrality: box and path multiple target""" + G = nx.Graph() + G.add_edges_from([(0, 1), (1, 2), (2, 3), (1, 20), (20, 3), (3, 4)]) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = 1.0 + b_answer[(1, 20)] = b_answer[(3, 20)] = 0.5 + b_answer[(1, 2)] = b_answer[(2, 3)] = 0.5 + b_answer[(3, 4)] = 0.5 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3, 4], weight=None + ) + for n in sorted(G.edges()): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_diamond_multi_path(self): + """Edge betweenness subset centrality: Diamond Multi Path""" + G = nx.Graph() + G.add_edges_from( + [ + (1, 2), + (1, 3), + (1, 4), + (1, 5), + (1, 10), + (10, 11), + (11, 12), + (12, 9), + (2, 6), + (3, 6), + (4, 6), + (5, 7), + (7, 8), + (6, 8), + (8, 9), + ] + ) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(8, 9)] = 0.4 + b_answer[(6, 8)] = b_answer[(7, 8)] = 0.2 + b_answer[(2, 6)] = b_answer[(3, 6)] = b_answer[(4, 6)] = 0.2 / 3.0 + b_answer[(1, 2)] = b_answer[(1, 3)] = b_answer[(1, 4)] = 0.2 / 3.0 + b_answer[(5, 7)] = 0.2 + b_answer[(1, 5)] = 0.2 + b_answer[(9, 12)] = 0.1 + b_answer[(11, 12)] = b_answer[(10, 11)] = b_answer[(1, 10)] = 0.1 + b = nx.edge_betweenness_centrality_subset( + G, sources=[1], targets=[9], weight=None + ) + for n in G.edges(): + sort_n = tuple(sorted(n)) + assert b[n] == pytest.approx(b_answer[sort_n], abs=1e-7) + + def test_normalized_p1(self): + """ + Edge betweenness subset centrality: P1 + if n <= 1: no normalization b=0 for all nodes + """ + G = nx.Graph() + nx.add_path(G, range(1)) + b_answer = dict.fromkeys(G.edges(), 0) + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[0], normalized=True, weight=None + ) + for n in G.edges(): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_normalized_P5_directed(self): + """Edge betweenness subset centrality: Normalized Directed P5""" + G = nx.DiGraph() + nx.add_path(G, range(5)) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 1)] = b_answer[(1, 2)] = b_answer[(2, 3)] = 0.05 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[3], normalized=True, weight=None + ) + for n in G.edges(): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_weighted_graph(self): + """Edge betweenness subset centrality: Weighted Graph""" + G = nx.DiGraph() + G.add_edge(0, 1, weight=3) + G.add_edge(0, 2, weight=2) + G.add_edge(0, 3, weight=6) + G.add_edge(0, 4, weight=4) + G.add_edge(1, 3, weight=5) + G.add_edge(1, 5, weight=5) + G.add_edge(2, 4, weight=1) + G.add_edge(3, 4, weight=2) + G.add_edge(3, 5, weight=1) + G.add_edge(4, 5, weight=4) + b_answer = dict.fromkeys(G.edges(), 0) + b_answer[(0, 2)] = b_answer[(2, 4)] = b_answer[(4, 5)] = 0.5 + b_answer[(0, 3)] = b_answer[(3, 5)] = 0.5 + b = nx.edge_betweenness_centrality_subset( + G, sources=[0], targets=[5], normalized=False, weight="weight" + ) + for n in G.edges(): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_closeness_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_closeness_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..d274206a7d6dffb6d9101378370210dd0cb8e01f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_closeness_centrality.py @@ -0,0 +1,306 @@ +""" +Tests for closeness centrality. +""" +import pytest + +import networkx as nx + + +class TestClosenessCentrality: + @classmethod + def setup_class(cls): + cls.K = nx.krackhardt_kite_graph() + cls.P3 = nx.path_graph(3) + cls.P4 = nx.path_graph(4) + cls.K5 = nx.complete_graph(5) + + cls.C4 = nx.cycle_graph(4) + cls.T = nx.balanced_tree(r=2, h=2) + cls.Gb = nx.Graph() + cls.Gb.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (2, 4), (4, 5), (3, 5)]) + + F = nx.florentine_families_graph() + cls.F = F + + cls.LM = nx.les_miserables_graph() + + # Create random undirected, unweighted graph for testing incremental version + cls.undirected_G = nx.fast_gnp_random_graph(n=100, p=0.6, seed=123) + cls.undirected_G_cc = nx.closeness_centrality(cls.undirected_G) + + def test_wf_improved(self): + G = nx.union(self.P4, nx.path_graph([4, 5, 6])) + c = nx.closeness_centrality(G) + cwf = nx.closeness_centrality(G, wf_improved=False) + res = {0: 0.25, 1: 0.375, 2: 0.375, 3: 0.25, 4: 0.222, 5: 0.333, 6: 0.222} + wf_res = {0: 0.5, 1: 0.75, 2: 0.75, 3: 0.5, 4: 0.667, 5: 1.0, 6: 0.667} + for n in G: + assert c[n] == pytest.approx(res[n], abs=1e-3) + assert cwf[n] == pytest.approx(wf_res[n], abs=1e-3) + + def test_digraph(self): + G = nx.path_graph(3, create_using=nx.DiGraph()) + c = nx.closeness_centrality(G) + cr = nx.closeness_centrality(G.reverse()) + d = {0: 0.0, 1: 0.500, 2: 0.667} + dr = {0: 0.667, 1: 0.500, 2: 0.0} + for n in sorted(self.P3): + assert c[n] == pytest.approx(d[n], abs=1e-3) + assert cr[n] == pytest.approx(dr[n], abs=1e-3) + + def test_k5_closeness(self): + c = nx.closeness_centrality(self.K5) + d = {0: 1.000, 1: 1.000, 2: 1.000, 3: 1.000, 4: 1.000} + for n in sorted(self.K5): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_p3_closeness(self): + c = nx.closeness_centrality(self.P3) + d = {0: 0.667, 1: 1.000, 2: 0.667} + for n in sorted(self.P3): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_krackhardt_closeness(self): + c = nx.closeness_centrality(self.K) + d = { + 0: 0.529, + 1: 0.529, + 2: 0.500, + 3: 0.600, + 4: 0.500, + 5: 0.643, + 6: 0.643, + 7: 0.600, + 8: 0.429, + 9: 0.310, + } + for n in sorted(self.K): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_florentine_families_closeness(self): + c = nx.closeness_centrality(self.F) + d = { + "Acciaiuoli": 0.368, + "Albizzi": 0.483, + "Barbadori": 0.4375, + "Bischeri": 0.400, + "Castellani": 0.389, + "Ginori": 0.333, + "Guadagni": 0.467, + "Lamberteschi": 0.326, + "Medici": 0.560, + "Pazzi": 0.286, + "Peruzzi": 0.368, + "Ridolfi": 0.500, + "Salviati": 0.389, + "Strozzi": 0.4375, + "Tornabuoni": 0.483, + } + for n in sorted(self.F): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_les_miserables_closeness(self): + c = nx.closeness_centrality(self.LM) + d = { + "Napoleon": 0.302, + "Myriel": 0.429, + "MlleBaptistine": 0.413, + "MmeMagloire": 0.413, + "CountessDeLo": 0.302, + "Geborand": 0.302, + "Champtercier": 0.302, + "Cravatte": 0.302, + "Count": 0.302, + "OldMan": 0.302, + "Valjean": 0.644, + "Labarre": 0.394, + "Marguerite": 0.413, + "MmeDeR": 0.394, + "Isabeau": 0.394, + "Gervais": 0.394, + "Listolier": 0.341, + "Tholomyes": 0.392, + "Fameuil": 0.341, + "Blacheville": 0.341, + "Favourite": 0.341, + "Dahlia": 0.341, + "Zephine": 0.341, + "Fantine": 0.461, + "MmeThenardier": 0.461, + "Thenardier": 0.517, + "Cosette": 0.478, + "Javert": 0.517, + "Fauchelevent": 0.402, + "Bamatabois": 0.427, + "Perpetue": 0.318, + "Simplice": 0.418, + "Scaufflaire": 0.394, + "Woman1": 0.396, + "Judge": 0.404, + "Champmathieu": 0.404, + "Brevet": 0.404, + "Chenildieu": 0.404, + "Cochepaille": 0.404, + "Pontmercy": 0.373, + "Boulatruelle": 0.342, + "Eponine": 0.396, + "Anzelma": 0.352, + "Woman2": 0.402, + "MotherInnocent": 0.398, + "Gribier": 0.288, + "MmeBurgon": 0.344, + "Jondrette": 0.257, + "Gavroche": 0.514, + "Gillenormand": 0.442, + "Magnon": 0.335, + "MlleGillenormand": 0.442, + "MmePontmercy": 0.315, + "MlleVaubois": 0.308, + "LtGillenormand": 0.365, + "Marius": 0.531, + "BaronessT": 0.352, + "Mabeuf": 0.396, + "Enjolras": 0.481, + "Combeferre": 0.392, + "Prouvaire": 0.357, + "Feuilly": 0.392, + "Courfeyrac": 0.400, + "Bahorel": 0.394, + "Bossuet": 0.475, + "Joly": 0.394, + "Grantaire": 0.358, + "MotherPlutarch": 0.285, + "Gueulemer": 0.463, + "Babet": 0.463, + "Claquesous": 0.452, + "Montparnasse": 0.458, + "Toussaint": 0.402, + "Child1": 0.342, + "Child2": 0.342, + "Brujon": 0.380, + "MmeHucheloup": 0.353, + } + for n in sorted(self.LM): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_weighted_closeness(self): + edges = [ + ("s", "u", 10), + ("s", "x", 5), + ("u", "v", 1), + ("u", "x", 2), + ("v", "y", 1), + ("x", "u", 3), + ("x", "v", 5), + ("x", "y", 2), + ("y", "s", 7), + ("y", "v", 6), + ] + XG = nx.Graph() + XG.add_weighted_edges_from(edges) + c = nx.closeness_centrality(XG, distance="weight") + d = {"y": 0.200, "x": 0.286, "s": 0.138, "u": 0.235, "v": 0.200} + for n in sorted(XG): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + # + # Tests for incremental closeness centrality. + # + @staticmethod + def pick_add_edge(g): + u = nx.utils.arbitrary_element(g) + possible_nodes = set(g.nodes()) + neighbors = list(g.neighbors(u)) + [u] + possible_nodes.difference_update(neighbors) + v = nx.utils.arbitrary_element(possible_nodes) + return (u, v) + + @staticmethod + def pick_remove_edge(g): + u = nx.utils.arbitrary_element(g) + possible_nodes = list(g.neighbors(u)) + v = nx.utils.arbitrary_element(possible_nodes) + return (u, v) + + def test_directed_raises(self): + with pytest.raises(nx.NetworkXNotImplemented): + dir_G = nx.gn_graph(n=5) + prev_cc = None + edge = self.pick_add_edge(dir_G) + insert = True + nx.incremental_closeness_centrality(dir_G, edge, prev_cc, insert) + + def test_wrong_size_prev_cc_raises(self): + with pytest.raises(nx.NetworkXError): + G = self.undirected_G.copy() + edge = self.pick_add_edge(G) + insert = True + prev_cc = self.undirected_G_cc.copy() + prev_cc.pop(0) + nx.incremental_closeness_centrality(G, edge, prev_cc, insert) + + def test_wrong_nodes_prev_cc_raises(self): + with pytest.raises(nx.NetworkXError): + G = self.undirected_G.copy() + edge = self.pick_add_edge(G) + insert = True + prev_cc = self.undirected_G_cc.copy() + num_nodes = len(prev_cc) + prev_cc.pop(0) + prev_cc[num_nodes] = 0.5 + nx.incremental_closeness_centrality(G, edge, prev_cc, insert) + + def test_zero_centrality(self): + G = nx.path_graph(3) + prev_cc = nx.closeness_centrality(G) + edge = self.pick_remove_edge(G) + test_cc = nx.incremental_closeness_centrality(G, edge, prev_cc, insertion=False) + G.remove_edges_from([edge]) + real_cc = nx.closeness_centrality(G) + shared_items = set(test_cc.items()) & set(real_cc.items()) + assert len(shared_items) == len(real_cc) + assert 0 in test_cc.values() + + def test_incremental(self): + # Check that incremental and regular give same output + G = self.undirected_G.copy() + prev_cc = None + for i in range(5): + if i % 2 == 0: + # Remove an edge + insert = False + edge = self.pick_remove_edge(G) + else: + # Add an edge + insert = True + edge = self.pick_add_edge(G) + + # start = timeit.default_timer() + test_cc = nx.incremental_closeness_centrality(G, edge, prev_cc, insert) + # inc_elapsed = (timeit.default_timer() - start) + # print(f"incremental time: {inc_elapsed}") + + if insert: + G.add_edges_from([edge]) + else: + G.remove_edges_from([edge]) + + # start = timeit.default_timer() + real_cc = nx.closeness_centrality(G) + # reg_elapsed = (timeit.default_timer() - start) + # print(f"regular time: {reg_elapsed}") + # Example output: + # incremental time: 0.208 + # regular time: 0.276 + # incremental time: 0.00683 + # regular time: 0.260 + # incremental time: 0.0224 + # regular time: 0.278 + # incremental time: 0.00804 + # regular time: 0.208 + # incremental time: 0.00947 + # regular time: 0.188 + + assert set(test_cc.items()) == set(real_cc.items()) + + prev_cc = test_cc diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_current_flow_closeness.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_current_flow_closeness.py new file mode 100644 index 0000000000000000000000000000000000000000..2528d622855938b8f569d4fb33309ebed1dbd7c8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_current_flow_closeness.py @@ -0,0 +1,43 @@ +import pytest + +pytest.importorskip("numpy") +pytest.importorskip("scipy") + +import networkx as nx + + +class TestFlowClosenessCentrality: + def test_K4(self): + """Closeness centrality: K4""" + G = nx.complete_graph(4) + b = nx.current_flow_closeness_centrality(G) + b_answer = {0: 2.0 / 3, 1: 2.0 / 3, 2: 2.0 / 3, 3: 2.0 / 3} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_P4(self): + """Closeness centrality: P4""" + G = nx.path_graph(4) + b = nx.current_flow_closeness_centrality(G) + b_answer = {0: 1.0 / 6, 1: 1.0 / 4, 2: 1.0 / 4, 3: 1.0 / 6} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_star(self): + """Closeness centrality: star""" + G = nx.Graph() + nx.add_star(G, ["a", "b", "c", "d"]) + b = nx.current_flow_closeness_centrality(G) + b_answer = {"a": 1.0 / 3, "b": 0.6 / 3, "c": 0.6 / 3, "d": 0.6 / 3} + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + def test_current_flow_closeness_centrality_not_connected(self): + G = nx.Graph() + G.add_nodes_from([1, 2, 3]) + with pytest.raises(nx.NetworkXError): + nx.current_flow_closeness_centrality(G) + + +class TestWeightedFlowClosenessCentrality: + pass diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_dispersion.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_dispersion.py new file mode 100644 index 0000000000000000000000000000000000000000..05de1c43659a44f2dbf45368bf2ee552dd61dd78 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_dispersion.py @@ -0,0 +1,73 @@ +import networkx as nx + + +def small_ego_G(): + """The sample network from https://arxiv.org/pdf/1310.6753v1.pdf""" + edges = [ + ("a", "b"), + ("a", "c"), + ("b", "c"), + ("b", "d"), + ("b", "e"), + ("b", "f"), + ("c", "d"), + ("c", "f"), + ("c", "h"), + ("d", "f"), + ("e", "f"), + ("f", "h"), + ("h", "j"), + ("h", "k"), + ("i", "j"), + ("i", "k"), + ("j", "k"), + ("u", "a"), + ("u", "b"), + ("u", "c"), + ("u", "d"), + ("u", "e"), + ("u", "f"), + ("u", "g"), + ("u", "h"), + ("u", "i"), + ("u", "j"), + ("u", "k"), + ] + G = nx.Graph() + G.add_edges_from(edges) + + return G + + +class TestDispersion: + def test_article(self): + """our algorithm matches article's""" + G = small_ego_G() + disp_uh = nx.dispersion(G, "u", "h", normalized=False) + disp_ub = nx.dispersion(G, "u", "b", normalized=False) + assert disp_uh == 4 + assert disp_ub == 1 + + def test_results_length(self): + """there is a result for every node""" + G = small_ego_G() + disp = nx.dispersion(G) + disp_Gu = nx.dispersion(G, "u") + disp_uv = nx.dispersion(G, "u", "h") + assert len(disp) == len(G) + assert len(disp_Gu) == len(G) - 1 + assert isinstance(disp_uv, float) + + def test_dispersion_v_only(self): + G = small_ego_G() + disp_G_h = nx.dispersion(G, v="h", normalized=False) + disp_G_h_normalized = nx.dispersion(G, v="h", normalized=True) + assert disp_G_h == {"c": 0, "f": 0, "j": 0, "k": 0, "u": 4} + assert disp_G_h_normalized == {"c": 0.0, "f": 0.0, "j": 0.0, "k": 0.0, "u": 1.0} + + def test_impossible_things(self): + G = nx.karate_club_graph() + disp = nx.dispersion(G) + for u in disp: + for v in disp[u]: + assert disp[u][v] >= 0 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_eigenvector_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_eigenvector_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..b8620056a94995100fae72a66bb7e0558aae953b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_eigenvector_centrality.py @@ -0,0 +1,175 @@ +import math + +import pytest + +np = pytest.importorskip("numpy") +pytest.importorskip("scipy") + + +import networkx as nx + + +class TestEigenvectorCentrality: + def test_K5(self): + """Eigenvector centrality: K5""" + G = nx.complete_graph(5) + b = nx.eigenvector_centrality(G) + v = math.sqrt(1 / 5.0) + b_answer = dict.fromkeys(G, v) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + nstart = {n: 1 for n in G} + b = nx.eigenvector_centrality(G, nstart=nstart) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-7) + + b = nx.eigenvector_centrality_numpy(G) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-3) + + def test_P3(self): + """Eigenvector centrality: P3""" + G = nx.path_graph(3) + b_answer = {0: 0.5, 1: 0.7071, 2: 0.5} + b = nx.eigenvector_centrality_numpy(G) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-4) + b = nx.eigenvector_centrality(G) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-4) + + def test_P3_unweighted(self): + """Eigenvector centrality: P3""" + G = nx.path_graph(3) + b_answer = {0: 0.5, 1: 0.7071, 2: 0.5} + b = nx.eigenvector_centrality_numpy(G, weight=None) + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-4) + + def test_maxiter(self): + with pytest.raises(nx.PowerIterationFailedConvergence): + G = nx.path_graph(3) + nx.eigenvector_centrality(G, max_iter=0) + + +class TestEigenvectorCentralityDirected: + @classmethod + def setup_class(cls): + G = nx.DiGraph() + + edges = [ + (1, 2), + (1, 3), + (2, 4), + (3, 2), + (3, 5), + (4, 2), + (4, 5), + (4, 6), + (5, 6), + (5, 7), + (5, 8), + (6, 8), + (7, 1), + (7, 5), + (7, 8), + (8, 6), + (8, 7), + ] + + G.add_edges_from(edges, weight=2.0) + cls.G = G.reverse() + cls.G.evc = [ + 0.25368793, + 0.19576478, + 0.32817092, + 0.40430835, + 0.48199885, + 0.15724483, + 0.51346196, + 0.32475403, + ] + + H = nx.DiGraph() + + edges = [ + (1, 2), + (1, 3), + (2, 4), + (3, 2), + (3, 5), + (4, 2), + (4, 5), + (4, 6), + (5, 6), + (5, 7), + (5, 8), + (6, 8), + (7, 1), + (7, 5), + (7, 8), + (8, 6), + (8, 7), + ] + + G.add_edges_from(edges) + cls.H = G.reverse() + cls.H.evc = [ + 0.25368793, + 0.19576478, + 0.32817092, + 0.40430835, + 0.48199885, + 0.15724483, + 0.51346196, + 0.32475403, + ] + + def test_eigenvector_centrality_weighted(self): + G = self.G + p = nx.eigenvector_centrality(G) + for a, b in zip(list(p.values()), self.G.evc): + assert a == pytest.approx(b, abs=1e-4) + + def test_eigenvector_centrality_weighted_numpy(self): + G = self.G + p = nx.eigenvector_centrality_numpy(G) + for a, b in zip(list(p.values()), self.G.evc): + assert a == pytest.approx(b, abs=1e-7) + + def test_eigenvector_centrality_unweighted(self): + G = self.H + p = nx.eigenvector_centrality(G) + for a, b in zip(list(p.values()), self.G.evc): + assert a == pytest.approx(b, abs=1e-4) + + def test_eigenvector_centrality_unweighted_numpy(self): + G = self.H + p = nx.eigenvector_centrality_numpy(G) + for a, b in zip(list(p.values()), self.G.evc): + assert a == pytest.approx(b, abs=1e-7) + + +class TestEigenvectorCentralityExceptions: + def test_multigraph(self): + with pytest.raises(nx.NetworkXException): + nx.eigenvector_centrality(nx.MultiGraph()) + + def test_multigraph_numpy(self): + with pytest.raises(nx.NetworkXException): + nx.eigenvector_centrality_numpy(nx.MultiGraph()) + + def test_empty(self): + with pytest.raises(nx.NetworkXException): + nx.eigenvector_centrality(nx.Graph()) + + def test_empty_numpy(self): + with pytest.raises(nx.NetworkXException): + nx.eigenvector_centrality_numpy(nx.Graph()) + + def test_zero_nstart(self): + G = nx.Graph([(1, 2), (1, 3), (2, 3)]) + with pytest.raises( + nx.NetworkXException, match="initial vector cannot have all zero values" + ): + nx.eigenvector_centrality(G, nstart={v: 0 for v in G}) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_harmonic_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_harmonic_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..450356ea970565eaee7612eb4c8c2d5364af50d7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_harmonic_centrality.py @@ -0,0 +1,115 @@ +""" +Tests for degree centrality. +""" +import pytest + +import networkx as nx +from networkx.algorithms.centrality import harmonic_centrality + + +class TestClosenessCentrality: + @classmethod + def setup_class(cls): + cls.P3 = nx.path_graph(3) + cls.P4 = nx.path_graph(4) + cls.K5 = nx.complete_graph(5) + + cls.C4 = nx.cycle_graph(4) + cls.C4_directed = nx.cycle_graph(4, create_using=nx.DiGraph) + + cls.C5 = nx.cycle_graph(5) + + cls.T = nx.balanced_tree(r=2, h=2) + + cls.Gb = nx.DiGraph() + cls.Gb.add_edges_from([(0, 1), (0, 2), (0, 4), (2, 1), (2, 3), (4, 3)]) + + def test_p3_harmonic(self): + c = harmonic_centrality(self.P3) + d = {0: 1.5, 1: 2, 2: 1.5} + for n in sorted(self.P3): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_p4_harmonic(self): + c = harmonic_centrality(self.P4) + d = {0: 1.8333333, 1: 2.5, 2: 2.5, 3: 1.8333333} + for n in sorted(self.P4): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_clique_complete(self): + c = harmonic_centrality(self.K5) + d = {0: 4, 1: 4, 2: 4, 3: 4, 4: 4} + for n in sorted(self.P3): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_cycle_C4(self): + c = harmonic_centrality(self.C4) + d = {0: 2.5, 1: 2.5, 2: 2.5, 3: 2.5} + for n in sorted(self.C4): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_cycle_C5(self): + c = harmonic_centrality(self.C5) + d = {0: 3, 1: 3, 2: 3, 3: 3, 4: 3, 5: 4} + for n in sorted(self.C5): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_bal_tree(self): + c = harmonic_centrality(self.T) + d = {0: 4.0, 1: 4.1666, 2: 4.1666, 3: 2.8333, 4: 2.8333, 5: 2.8333, 6: 2.8333} + for n in sorted(self.T): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_exampleGraph(self): + c = harmonic_centrality(self.Gb) + d = {0: 0, 1: 2, 2: 1, 3: 2.5, 4: 1} + for n in sorted(self.Gb): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_weighted_harmonic(self): + XG = nx.DiGraph() + XG.add_weighted_edges_from( + [ + ("a", "b", 10), + ("d", "c", 5), + ("a", "c", 1), + ("e", "f", 2), + ("f", "c", 1), + ("a", "f", 3), + ] + ) + c = harmonic_centrality(XG, distance="weight") + d = {"a": 0, "b": 0.1, "c": 2.533, "d": 0, "e": 0, "f": 0.83333} + for n in sorted(XG): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_empty(self): + G = nx.DiGraph() + c = harmonic_centrality(G, distance="weight") + d = {} + assert c == d + + def test_singleton(self): + G = nx.DiGraph() + G.add_node(0) + c = harmonic_centrality(G, distance="weight") + d = {0: 0} + assert c == d + + def test_cycle_c4_directed(self): + c = harmonic_centrality(self.C4_directed, nbunch=[0, 1], sources=[1, 2]) + d = {0: 0.833, 1: 0.333} + for n in [0, 1]: + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_p3_harmonic_subset(self): + c = harmonic_centrality(self.P3, sources=[0, 1]) + d = {0: 1, 1: 1, 2: 1.5} + for n in self.P3: + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_p4_harmonic_subset(self): + c = harmonic_centrality(self.P4, nbunch=[2, 3], sources=[0, 1]) + d = {2: 1.5, 3: 0.8333333} + for n in [2, 3]: + assert c[n] == pytest.approx(d[n], abs=1e-3) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_laplacian_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_laplacian_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..21aa28b0b7c155078ab9c1a25e14d9aafa65683d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_laplacian_centrality.py @@ -0,0 +1,221 @@ +import pytest + +import networkx as nx + +np = pytest.importorskip("numpy") +sp = pytest.importorskip("scipy") + + +def test_laplacian_centrality_null_graph(): + G = nx.Graph() + with pytest.raises(nx.NetworkXPointlessConcept): + d = nx.laplacian_centrality(G, normalized=False) + + +def test_laplacian_centrality_single_node(): + """See gh-6571""" + G = nx.empty_graph(1) + assert nx.laplacian_centrality(G, normalized=False) == {0: 0} + with pytest.raises(ZeroDivisionError): + nx.laplacian_centrality(G, normalized=True) + + +def test_laplacian_centrality_unconnected_nodes(): + """laplacian_centrality on a unconnected node graph should return 0 + + For graphs without edges, the Laplacian energy is 0 and is unchanged with + node removal, so:: + + LC(v) = LE(G) - LE(G - v) = 0 - 0 = 0 + """ + G = nx.empty_graph(3) + assert nx.laplacian_centrality(G, normalized=False) == {0: 0, 1: 0, 2: 0} + + +def test_laplacian_centrality_empty_graph(): + G = nx.empty_graph(3) + with pytest.raises(ZeroDivisionError): + d = nx.laplacian_centrality(G, normalized=True) + + +def test_laplacian_centrality_E(): + E = nx.Graph() + E.add_weighted_edges_from( + [(0, 1, 4), (4, 5, 1), (0, 2, 2), (2, 1, 1), (1, 3, 2), (1, 4, 2)] + ) + d = nx.laplacian_centrality(E) + exact = { + 0: 0.700000, + 1: 0.900000, + 2: 0.280000, + 3: 0.220000, + 4: 0.260000, + 5: 0.040000, + } + + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + # Check not normalized + full_energy = 200 + dnn = nx.laplacian_centrality(E, normalized=False) + for n, dc in dnn.items(): + assert exact[n] * full_energy == pytest.approx(dc, abs=1e-7) + + # Check unweighted not-normalized version + duw_nn = nx.laplacian_centrality(E, normalized=False, weight=None) + print(duw_nn) + exact_uw_nn = { + 0: 18, + 1: 34, + 2: 18, + 3: 10, + 4: 16, + 5: 6, + } + for n, dc in duw_nn.items(): + assert exact_uw_nn[n] == pytest.approx(dc, abs=1e-7) + + # Check unweighted version + duw = nx.laplacian_centrality(E, weight=None) + full_energy = 42 + for n, dc in duw.items(): + assert exact_uw_nn[n] / full_energy == pytest.approx(dc, abs=1e-7) + + +def test_laplacian_centrality_KC(): + KC = nx.karate_club_graph() + d = nx.laplacian_centrality(KC) + exact = { + 0: 0.2543593, + 1: 0.1724524, + 2: 0.2166053, + 3: 0.0964646, + 4: 0.0350344, + 5: 0.0571109, + 6: 0.0540713, + 7: 0.0788674, + 8: 0.1222204, + 9: 0.0217565, + 10: 0.0308751, + 11: 0.0215965, + 12: 0.0174372, + 13: 0.118861, + 14: 0.0366341, + 15: 0.0548712, + 16: 0.0172772, + 17: 0.0191969, + 18: 0.0225564, + 19: 0.0331147, + 20: 0.0279955, + 21: 0.0246361, + 22: 0.0382339, + 23: 0.1294193, + 24: 0.0227164, + 25: 0.0644697, + 26: 0.0281555, + 27: 0.075188, + 28: 0.0364742, + 29: 0.0707087, + 30: 0.0708687, + 31: 0.131019, + 32: 0.2370821, + 33: 0.3066709, + } + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + # Check not normalized + full_energy = 12502 + dnn = nx.laplacian_centrality(KC, normalized=False) + for n, dc in dnn.items(): + assert exact[n] * full_energy == pytest.approx(dc, abs=1e-3) + + +def test_laplacian_centrality_K(): + K = nx.krackhardt_kite_graph() + d = nx.laplacian_centrality(K) + exact = { + 0: 0.3010753, + 1: 0.3010753, + 2: 0.2258065, + 3: 0.483871, + 4: 0.2258065, + 5: 0.3870968, + 6: 0.3870968, + 7: 0.1935484, + 8: 0.0752688, + 9: 0.0322581, + } + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + # Check not normalized + full_energy = 186 + dnn = nx.laplacian_centrality(K, normalized=False) + for n, dc in dnn.items(): + assert exact[n] * full_energy == pytest.approx(dc, abs=1e-3) + + +def test_laplacian_centrality_P3(): + P3 = nx.path_graph(3) + d = nx.laplacian_centrality(P3) + exact = {0: 0.6, 1: 1.0, 2: 0.6} + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + +def test_laplacian_centrality_K5(): + K5 = nx.complete_graph(5) + d = nx.laplacian_centrality(K5) + exact = {0: 0.52, 1: 0.52, 2: 0.52, 3: 0.52, 4: 0.52} + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + +def test_laplacian_centrality_FF(): + FF = nx.florentine_families_graph() + d = nx.laplacian_centrality(FF) + exact = { + "Acciaiuoli": 0.0804598, + "Medici": 0.4022989, + "Castellani": 0.1724138, + "Peruzzi": 0.183908, + "Strozzi": 0.2528736, + "Barbadori": 0.137931, + "Ridolfi": 0.2183908, + "Tornabuoni": 0.2183908, + "Albizzi": 0.1954023, + "Salviati": 0.1149425, + "Pazzi": 0.0344828, + "Bischeri": 0.1954023, + "Guadagni": 0.2298851, + "Ginori": 0.045977, + "Lamberteschi": 0.0574713, + } + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + +def test_laplacian_centrality_DG(): + DG = nx.DiGraph([(0, 5), (1, 5), (2, 5), (3, 5), (4, 5), (5, 6), (5, 7), (5, 8)]) + d = nx.laplacian_centrality(DG) + exact = { + 0: 0.2123352, + 5: 0.515391, + 1: 0.2123352, + 2: 0.2123352, + 3: 0.2123352, + 4: 0.2123352, + 6: 0.2952031, + 7: 0.2952031, + 8: 0.2952031, + } + for n, dc in d.items(): + assert exact[n] == pytest.approx(dc, abs=1e-7) + + # Check not normalized + full_energy = 9.50704 + dnn = nx.laplacian_centrality(DG, normalized=False) + for n, dc in dnn.items(): + assert exact[n] * full_energy == pytest.approx(dc, abs=1e-4) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_load_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_load_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..bf096039cd76542cc4c963ab896ee8fc4b295224 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_load_centrality.py @@ -0,0 +1,344 @@ +import pytest + +import networkx as nx + + +class TestLoadCentrality: + @classmethod + def setup_class(cls): + G = nx.Graph() + G.add_edge(0, 1, weight=3) + G.add_edge(0, 2, weight=2) + G.add_edge(0, 3, weight=6) + G.add_edge(0, 4, weight=4) + G.add_edge(1, 3, weight=5) + G.add_edge(1, 5, weight=5) + G.add_edge(2, 4, weight=1) + G.add_edge(3, 4, weight=2) + G.add_edge(3, 5, weight=1) + G.add_edge(4, 5, weight=4) + cls.G = G + cls.exact_weighted = {0: 4.0, 1: 0.0, 2: 8.0, 3: 6.0, 4: 8.0, 5: 0.0} + cls.K = nx.krackhardt_kite_graph() + cls.P3 = nx.path_graph(3) + cls.P4 = nx.path_graph(4) + cls.K5 = nx.complete_graph(5) + cls.P2 = nx.path_graph(2) + + cls.C4 = nx.cycle_graph(4) + cls.T = nx.balanced_tree(r=2, h=2) + cls.Gb = nx.Graph() + cls.Gb.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (2, 4), (4, 5), (3, 5)]) + cls.F = nx.florentine_families_graph() + cls.LM = nx.les_miserables_graph() + cls.D = nx.cycle_graph(3, create_using=nx.DiGraph()) + cls.D.add_edges_from([(3, 0), (4, 3)]) + + def test_not_strongly_connected(self): + b = nx.load_centrality(self.D) + result = {0: 5.0 / 12, 1: 1.0 / 4, 2: 1.0 / 12, 3: 1.0 / 4, 4: 0.000} + for n in sorted(self.D): + assert result[n] == pytest.approx(b[n], abs=1e-3) + assert result[n] == pytest.approx(nx.load_centrality(self.D, n), abs=1e-3) + + def test_P2_normalized_load(self): + G = self.P2 + c = nx.load_centrality(G, normalized=True) + d = {0: 0.000, 1: 0.000} + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_weighted_load(self): + b = nx.load_centrality(self.G, weight="weight", normalized=False) + for n in sorted(self.G): + assert b[n] == self.exact_weighted[n] + + def test_k5_load(self): + G = self.K5 + c = nx.load_centrality(G) + d = {0: 0.000, 1: 0.000, 2: 0.000, 3: 0.000, 4: 0.000} + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_p3_load(self): + G = self.P3 + c = nx.load_centrality(G) + d = {0: 0.000, 1: 1.000, 2: 0.000} + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + c = nx.load_centrality(G, v=1) + assert c == pytest.approx(1.0, abs=1e-7) + c = nx.load_centrality(G, v=1, normalized=True) + assert c == pytest.approx(1.0, abs=1e-7) + + def test_p2_load(self): + G = nx.path_graph(2) + c = nx.load_centrality(G) + d = {0: 0.000, 1: 0.000} + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_krackhardt_load(self): + G = self.K + c = nx.load_centrality(G) + d = { + 0: 0.023, + 1: 0.023, + 2: 0.000, + 3: 0.102, + 4: 0.000, + 5: 0.231, + 6: 0.231, + 7: 0.389, + 8: 0.222, + 9: 0.000, + } + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_florentine_families_load(self): + G = self.F + c = nx.load_centrality(G) + d = { + "Acciaiuoli": 0.000, + "Albizzi": 0.211, + "Barbadori": 0.093, + "Bischeri": 0.104, + "Castellani": 0.055, + "Ginori": 0.000, + "Guadagni": 0.251, + "Lamberteschi": 0.000, + "Medici": 0.522, + "Pazzi": 0.000, + "Peruzzi": 0.022, + "Ridolfi": 0.117, + "Salviati": 0.143, + "Strozzi": 0.106, + "Tornabuoni": 0.090, + } + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_les_miserables_load(self): + G = self.LM + c = nx.load_centrality(G) + d = { + "Napoleon": 0.000, + "Myriel": 0.177, + "MlleBaptistine": 0.000, + "MmeMagloire": 0.000, + "CountessDeLo": 0.000, + "Geborand": 0.000, + "Champtercier": 0.000, + "Cravatte": 0.000, + "Count": 0.000, + "OldMan": 0.000, + "Valjean": 0.567, + "Labarre": 0.000, + "Marguerite": 0.000, + "MmeDeR": 0.000, + "Isabeau": 0.000, + "Gervais": 0.000, + "Listolier": 0.000, + "Tholomyes": 0.043, + "Fameuil": 0.000, + "Blacheville": 0.000, + "Favourite": 0.000, + "Dahlia": 0.000, + "Zephine": 0.000, + "Fantine": 0.128, + "MmeThenardier": 0.029, + "Thenardier": 0.075, + "Cosette": 0.024, + "Javert": 0.054, + "Fauchelevent": 0.026, + "Bamatabois": 0.008, + "Perpetue": 0.000, + "Simplice": 0.009, + "Scaufflaire": 0.000, + "Woman1": 0.000, + "Judge": 0.000, + "Champmathieu": 0.000, + "Brevet": 0.000, + "Chenildieu": 0.000, + "Cochepaille": 0.000, + "Pontmercy": 0.007, + "Boulatruelle": 0.000, + "Eponine": 0.012, + "Anzelma": 0.000, + "Woman2": 0.000, + "MotherInnocent": 0.000, + "Gribier": 0.000, + "MmeBurgon": 0.026, + "Jondrette": 0.000, + "Gavroche": 0.164, + "Gillenormand": 0.021, + "Magnon": 0.000, + "MlleGillenormand": 0.047, + "MmePontmercy": 0.000, + "MlleVaubois": 0.000, + "LtGillenormand": 0.000, + "Marius": 0.133, + "BaronessT": 0.000, + "Mabeuf": 0.028, + "Enjolras": 0.041, + "Combeferre": 0.001, + "Prouvaire": 0.000, + "Feuilly": 0.001, + "Courfeyrac": 0.006, + "Bahorel": 0.002, + "Bossuet": 0.032, + "Joly": 0.002, + "Grantaire": 0.000, + "MotherPlutarch": 0.000, + "Gueulemer": 0.005, + "Babet": 0.005, + "Claquesous": 0.005, + "Montparnasse": 0.004, + "Toussaint": 0.000, + "Child1": 0.000, + "Child2": 0.000, + "Brujon": 0.000, + "MmeHucheloup": 0.000, + } + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_unnormalized_k5_load(self): + G = self.K5 + c = nx.load_centrality(G, normalized=False) + d = {0: 0.000, 1: 0.000, 2: 0.000, 3: 0.000, 4: 0.000} + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_unnormalized_p3_load(self): + G = self.P3 + c = nx.load_centrality(G, normalized=False) + d = {0: 0.000, 1: 2.000, 2: 0.000} + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_unnormalized_krackhardt_load(self): + G = self.K + c = nx.load_centrality(G, normalized=False) + d = { + 0: 1.667, + 1: 1.667, + 2: 0.000, + 3: 7.333, + 4: 0.000, + 5: 16.667, + 6: 16.667, + 7: 28.000, + 8: 16.000, + 9: 0.000, + } + + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_unnormalized_florentine_families_load(self): + G = self.F + c = nx.load_centrality(G, normalized=False) + + d = { + "Acciaiuoli": 0.000, + "Albizzi": 38.333, + "Barbadori": 17.000, + "Bischeri": 19.000, + "Castellani": 10.000, + "Ginori": 0.000, + "Guadagni": 45.667, + "Lamberteschi": 0.000, + "Medici": 95.000, + "Pazzi": 0.000, + "Peruzzi": 4.000, + "Ridolfi": 21.333, + "Salviati": 26.000, + "Strozzi": 19.333, + "Tornabuoni": 16.333, + } + for n in sorted(G): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_load_betweenness_difference(self): + # Difference Between Load and Betweenness + # --------------------------------------- The smallest graph + # that shows the difference between load and betweenness is + # G=ladder_graph(3) (Graph B below) + + # Graph A and B are from Tao Zhou, Jian-Guo Liu, Bing-Hong + # Wang: Comment on "Scientific collaboration + # networks. II. Shortest paths, weighted networks, and + # centrality". https://arxiv.org/pdf/physics/0511084 + + # Notice that unlike here, their calculation adds to 1 to the + # betweenness of every node i for every path from i to every + # other node. This is exactly what it should be, based on + # Eqn. (1) in their paper: the eqn is B(v) = \sum_{s\neq t, + # s\neq v}{\frac{\sigma_{st}(v)}{\sigma_{st}}}, therefore, + # they allow v to be the target node. + + # We follow Brandes 2001, who follows Freeman 1977 that make + # the sum for betweenness of v exclude paths where v is either + # the source or target node. To agree with their numbers, we + # must additionally, remove edge (4,8) from the graph, see AC + # example following (there is a mistake in the figure in their + # paper - personal communication). + + # A = nx.Graph() + # A.add_edges_from([(0,1), (1,2), (1,3), (2,4), + # (3,5), (4,6), (4,7), (4,8), + # (5,8), (6,9), (7,9), (8,9)]) + B = nx.Graph() # ladder_graph(3) + B.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3), (2, 4), (4, 5), (3, 5)]) + c = nx.load_centrality(B, normalized=False) + d = {0: 1.750, 1: 1.750, 2: 6.500, 3: 6.500, 4: 1.750, 5: 1.750} + for n in sorted(B): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_c4_edge_load(self): + G = self.C4 + c = nx.edge_load_centrality(G) + d = {(0, 1): 6.000, (0, 3): 6.000, (1, 2): 6.000, (2, 3): 6.000} + for n in G.edges(): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_p4_edge_load(self): + G = self.P4 + c = nx.edge_load_centrality(G) + d = {(0, 1): 6.000, (1, 2): 8.000, (2, 3): 6.000} + for n in G.edges(): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_k5_edge_load(self): + G = self.K5 + c = nx.edge_load_centrality(G) + d = { + (0, 1): 5.000, + (0, 2): 5.000, + (0, 3): 5.000, + (0, 4): 5.000, + (1, 2): 5.000, + (1, 3): 5.000, + (1, 4): 5.000, + (2, 3): 5.000, + (2, 4): 5.000, + (3, 4): 5.000, + } + for n in G.edges(): + assert c[n] == pytest.approx(d[n], abs=1e-3) + + def test_tree_edge_load(self): + G = self.T + c = nx.edge_load_centrality(G) + d = { + (0, 1): 24.000, + (0, 2): 24.000, + (1, 3): 12.000, + (1, 4): 12.000, + (2, 5): 12.000, + (2, 6): 12.000, + } + for n in G.edges(): + assert c[n] == pytest.approx(d[n], abs=1e-3) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_percolation_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_percolation_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..0cb8f52965c975013d41be7c3de874cd86ee693a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_percolation_centrality.py @@ -0,0 +1,87 @@ +import pytest + +import networkx as nx + + +def example1a_G(): + G = nx.Graph() + G.add_node(1, percolation=0.1) + G.add_node(2, percolation=0.2) + G.add_node(3, percolation=0.2) + G.add_node(4, percolation=0.2) + G.add_node(5, percolation=0.3) + G.add_node(6, percolation=0.2) + G.add_node(7, percolation=0.5) + G.add_node(8, percolation=0.5) + G.add_edges_from([(1, 4), (2, 4), (3, 4), (4, 5), (5, 6), (6, 7), (6, 8)]) + return G + + +def example1b_G(): + G = nx.Graph() + G.add_node(1, percolation=0.3) + G.add_node(2, percolation=0.5) + G.add_node(3, percolation=0.5) + G.add_node(4, percolation=0.2) + G.add_node(5, percolation=0.3) + G.add_node(6, percolation=0.2) + G.add_node(7, percolation=0.1) + G.add_node(8, percolation=0.1) + G.add_edges_from([(1, 4), (2, 4), (3, 4), (4, 5), (5, 6), (6, 7), (6, 8)]) + return G + + +def test_percolation_example1a(): + """percolation centrality: example 1a""" + G = example1a_G() + p = nx.percolation_centrality(G) + p_answer = {4: 0.625, 6: 0.667} + for n, k in p_answer.items(): + assert p[n] == pytest.approx(k, abs=1e-3) + + +def test_percolation_example1b(): + """percolation centrality: example 1a""" + G = example1b_G() + p = nx.percolation_centrality(G) + p_answer = {4: 0.825, 6: 0.4} + for n, k in p_answer.items(): + assert p[n] == pytest.approx(k, abs=1e-3) + + +def test_converge_to_betweenness(): + """percolation centrality: should converge to betweenness + centrality when all nodes are percolated the same""" + # taken from betweenness test test_florentine_families_graph + G = nx.florentine_families_graph() + b_answer = { + "Acciaiuoli": 0.000, + "Albizzi": 0.212, + "Barbadori": 0.093, + "Bischeri": 0.104, + "Castellani": 0.055, + "Ginori": 0.000, + "Guadagni": 0.255, + "Lamberteschi": 0.000, + "Medici": 0.522, + "Pazzi": 0.000, + "Peruzzi": 0.022, + "Ridolfi": 0.114, + "Salviati": 0.143, + "Strozzi": 0.103, + "Tornabuoni": 0.092, + } + + # If no initial state is provided, state for + # every node defaults to 1 + p_answer = nx.percolation_centrality(G) + assert p_answer == pytest.approx(b_answer, abs=1e-3) + + p_states = {k: 0.3 for k, v in b_answer.items()} + p_answer = nx.percolation_centrality(G, states=p_states) + assert p_answer == pytest.approx(b_answer, abs=1e-3) + + +def test_default_percolation(): + G = nx.erdos_renyi_graph(42, 0.42, seed=42) + assert nx.percolation_centrality(G) == pytest.approx(nx.betweenness_centrality(G)) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_reaching.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_reaching.py new file mode 100644 index 0000000000000000000000000000000000000000..02ad8322cb6cf2a550afec0980ead8537abd55d5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_reaching.py @@ -0,0 +1,117 @@ +"""Unit tests for the :mod:`networkx.algorithms.centrality.reaching` module.""" +import pytest + +import networkx as nx + + +class TestGlobalReachingCentrality: + """Unit tests for the global reaching centrality function.""" + + def test_non_positive_weights(self): + with pytest.raises(nx.NetworkXError): + G = nx.DiGraph() + nx.global_reaching_centrality(G, weight="weight") + + def test_negatively_weighted(self): + with pytest.raises(nx.NetworkXError): + G = nx.Graph() + G.add_weighted_edges_from([(0, 1, -2), (1, 2, +1)]) + nx.global_reaching_centrality(G, weight="weight") + + def test_directed_star(self): + G = nx.DiGraph() + G.add_weighted_edges_from([(1, 2, 0.5), (1, 3, 0.5)]) + grc = nx.global_reaching_centrality + assert grc(G, normalized=False, weight="weight") == 0.5 + assert grc(G) == 1 + + def test_undirected_unweighted_star(self): + G = nx.star_graph(2) + grc = nx.global_reaching_centrality + assert grc(G, normalized=False, weight=None) == 0.25 + + def test_undirected_weighted_star(self): + G = nx.Graph() + G.add_weighted_edges_from([(1, 2, 1), (1, 3, 2)]) + grc = nx.global_reaching_centrality + assert grc(G, normalized=False, weight="weight") == 0.375 + + def test_cycle_directed_unweighted(self): + G = nx.DiGraph() + G.add_edge(1, 2) + G.add_edge(2, 1) + assert nx.global_reaching_centrality(G, weight=None) == 0 + + def test_cycle_undirected_unweighted(self): + G = nx.Graph() + G.add_edge(1, 2) + assert nx.global_reaching_centrality(G, weight=None) == 0 + + def test_cycle_directed_weighted(self): + G = nx.DiGraph() + G.add_weighted_edges_from([(1, 2, 1), (2, 1, 1)]) + assert nx.global_reaching_centrality(G) == 0 + + def test_cycle_undirected_weighted(self): + G = nx.Graph() + G.add_edge(1, 2, weight=1) + grc = nx.global_reaching_centrality + assert grc(G, normalized=False) == 0 + + def test_directed_weighted(self): + G = nx.DiGraph() + G.add_edge("A", "B", weight=5) + G.add_edge("B", "C", weight=1) + G.add_edge("B", "D", weight=0.25) + G.add_edge("D", "E", weight=1) + + denom = len(G) - 1 + A_local = sum([5, 3, 2.625, 2.0833333333333]) / denom + B_local = sum([1, 0.25, 0.625]) / denom + C_local = 0 + D_local = sum([1]) / denom + E_local = 0 + + local_reach_ctrs = [A_local, C_local, B_local, D_local, E_local] + max_local = max(local_reach_ctrs) + expected = sum(max_local - lrc for lrc in local_reach_ctrs) / denom + grc = nx.global_reaching_centrality + actual = grc(G, normalized=False, weight="weight") + assert expected == pytest.approx(actual, abs=1e-7) + + +class TestLocalReachingCentrality: + """Unit tests for the local reaching centrality function.""" + + def test_non_positive_weights(self): + with pytest.raises(nx.NetworkXError): + G = nx.DiGraph() + G.add_weighted_edges_from([(0, 1, 0)]) + nx.local_reaching_centrality(G, 0, weight="weight") + + def test_negatively_weighted(self): + with pytest.raises(nx.NetworkXError): + G = nx.Graph() + G.add_weighted_edges_from([(0, 1, -2), (1, 2, +1)]) + nx.local_reaching_centrality(G, 0, weight="weight") + + def test_undirected_unweighted_star(self): + G = nx.star_graph(2) + grc = nx.local_reaching_centrality + assert grc(G, 1, weight=None, normalized=False) == 0.75 + + def test_undirected_weighted_star(self): + G = nx.Graph() + G.add_weighted_edges_from([(1, 2, 1), (1, 3, 2)]) + centrality = nx.local_reaching_centrality( + G, 1, normalized=False, weight="weight" + ) + assert centrality == 1.5 + + def test_undirected_weighted_normalized(self): + G = nx.Graph() + G.add_weighted_edges_from([(1, 2, 1), (1, 3, 2)]) + centrality = nx.local_reaching_centrality( + G, 1, normalized=True, weight="weight" + ) + assert centrality == 1.0 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_second_order_centrality.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_second_order_centrality.py new file mode 100644 index 0000000000000000000000000000000000000000..cc3047866079fd9fe4cf43a6793cf160a0c0cdce --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_second_order_centrality.py @@ -0,0 +1,82 @@ +""" +Tests for second order centrality. +""" + +import pytest + +pytest.importorskip("numpy") +pytest.importorskip("scipy") + +import networkx as nx + + +def test_empty(): + with pytest.raises(nx.NetworkXException): + G = nx.empty_graph() + nx.second_order_centrality(G) + + +def test_non_connected(): + with pytest.raises(nx.NetworkXException): + G = nx.Graph() + G.add_node(0) + G.add_node(1) + nx.second_order_centrality(G) + + +def test_non_negative_edge_weights(): + with pytest.raises(nx.NetworkXException): + G = nx.path_graph(2) + G.add_edge(0, 1, weight=-1) + nx.second_order_centrality(G) + + +def test_weight_attribute(): + G = nx.Graph() + G.add_weighted_edges_from([(0, 1, 1.0), (1, 2, 3.5)], weight="w") + expected = {0: 3.431, 1: 3.082, 2: 5.612} + b = nx.second_order_centrality(G, weight="w") + + for n in sorted(G): + assert b[n] == pytest.approx(expected[n], abs=1e-2) + + +def test_one_node_graph(): + """Second order centrality: single node""" + G = nx.Graph() + G.add_node(0) + G.add_edge(0, 0) + assert nx.second_order_centrality(G)[0] == 0 + + +def test_P3(): + """Second order centrality: line graph, as defined in paper""" + G = nx.path_graph(3) + b_answer = {0: 3.741, 1: 1.414, 2: 3.741} + + b = nx.second_order_centrality(G) + + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-2) + + +def test_K3(): + """Second order centrality: complete graph, as defined in paper""" + G = nx.complete_graph(3) + b_answer = {0: 1.414, 1: 1.414, 2: 1.414} + + b = nx.second_order_centrality(G) + + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-2) + + +def test_ring_graph(): + """Second order centrality: ring graph, as defined in paper""" + G = nx.cycle_graph(5) + b_answer = {0: 4.472, 1: 4.472, 2: 4.472, 3: 4.472, 4: 4.472} + + b = nx.second_order_centrality(G) + + for n in sorted(G): + assert b[n] == pytest.approx(b_answer[n], abs=1e-2) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_voterank.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_voterank.py new file mode 100644 index 0000000000000000000000000000000000000000..12126818b4387a439493e8f66ba2e06e1a092416 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/tests/test_voterank.py @@ -0,0 +1,65 @@ +""" + Unit tests for VoteRank. +""" + + +import networkx as nx + + +class TestVoteRankCentrality: + # Example Graph present in reference paper + def test_voterank_centrality_1(self): + G = nx.Graph() + G.add_edges_from( + [ + (7, 8), + (7, 5), + (7, 9), + (5, 0), + (0, 1), + (0, 2), + (0, 3), + (0, 4), + (1, 6), + (2, 6), + (3, 6), + (4, 6), + ] + ) + assert [0, 7, 6] == nx.voterank(G) + + def test_voterank_emptygraph(self): + G = nx.Graph() + assert [] == nx.voterank(G) + + # Graph unit test + def test_voterank_centrality_2(self): + G = nx.florentine_families_graph() + d = nx.voterank(G, 4) + exact = ["Medici", "Strozzi", "Guadagni", "Castellani"] + assert exact == d + + # DiGraph unit test + def test_voterank_centrality_3(self): + G = nx.gnc_graph(10, seed=7) + d = nx.voterank(G, 4) + exact = [3, 6, 8] + assert exact == d + + # MultiGraph unit test + def test_voterank_centrality_4(self): + G = nx.MultiGraph() + G.add_edges_from( + [(0, 1), (0, 1), (1, 2), (2, 5), (2, 5), (5, 6), (5, 6), (2, 4), (4, 3)] + ) + exact = [2, 1, 5, 4] + assert exact == nx.voterank(G) + + # MultiDiGraph unit test + def test_voterank_centrality_5(self): + G = nx.MultiDiGraph() + G.add_edges_from( + [(0, 1), (0, 1), (1, 2), (2, 5), (2, 5), (5, 6), (5, 6), (2, 4), (4, 3)] + ) + exact = [2, 0, 5, 4] + assert exact == nx.voterank(G) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/trophic.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/trophic.py new file mode 100644 index 0000000000000000000000000000000000000000..cfc7ea4f20677696f7b6a68348c51a913f5de91e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/trophic.py @@ -0,0 +1,162 @@ +"""Trophic levels""" +import networkx as nx +from networkx.utils import not_implemented_for + +__all__ = ["trophic_levels", "trophic_differences", "trophic_incoherence_parameter"] + + +@not_implemented_for("undirected") +@nx._dispatch(edge_attrs="weight") +def trophic_levels(G, weight="weight"): + r"""Compute the trophic levels of nodes. + + The trophic level of a node $i$ is + + .. math:: + + s_i = 1 + \frac{1}{k^{in}_i} \sum_{j} a_{ij} s_j + + where $k^{in}_i$ is the in-degree of i + + .. math:: + + k^{in}_i = \sum_{j} a_{ij} + + and nodes with $k^{in}_i = 0$ have $s_i = 1$ by convention. + + These are calculated using the method outlined in Levine [1]_. + + Parameters + ---------- + G : DiGraph + A directed networkx graph + + Returns + ------- + nodes : dict + Dictionary of nodes with trophic level as the value. + + References + ---------- + .. [1] Stephen Levine (1980) J. theor. Biol. 83, 195-207 + """ + import numpy as np + + # find adjacency matrix + a = nx.adjacency_matrix(G, weight=weight).T.toarray() + + # drop rows/columns where in-degree is zero + rowsum = np.sum(a, axis=1) + p = a[rowsum != 0][:, rowsum != 0] + # normalise so sum of in-degree weights is 1 along each row + p = p / rowsum[rowsum != 0][:, np.newaxis] + + # calculate trophic levels + nn = p.shape[0] + i = np.eye(nn) + try: + n = np.linalg.inv(i - p) + except np.linalg.LinAlgError as err: + # LinAlgError is raised when there is a non-basal node + msg = ( + "Trophic levels are only defined for graphs where every " + + "node has a path from a basal node (basal nodes are nodes " + + "with no incoming edges)." + ) + raise nx.NetworkXError(msg) from err + y = n.sum(axis=1) + 1 + + levels = {} + + # all nodes with in-degree zero have trophic level == 1 + zero_node_ids = (node_id for node_id, degree in G.in_degree if degree == 0) + for node_id in zero_node_ids: + levels[node_id] = 1 + + # all other nodes have levels as calculated + nonzero_node_ids = (node_id for node_id, degree in G.in_degree if degree != 0) + for i, node_id in enumerate(nonzero_node_ids): + levels[node_id] = y[i] + + return levels + + +@not_implemented_for("undirected") +@nx._dispatch(edge_attrs="weight") +def trophic_differences(G, weight="weight"): + r"""Compute the trophic differences of the edges of a directed graph. + + The trophic difference $x_ij$ for each edge is defined in Johnson et al. + [1]_ as: + + .. math:: + x_ij = s_j - s_i + + Where $s_i$ is the trophic level of node $i$. + + Parameters + ---------- + G : DiGraph + A directed networkx graph + + Returns + ------- + diffs : dict + Dictionary of edges with trophic differences as the value. + + References + ---------- + .. [1] Samuel Johnson, Virginia Dominguez-Garcia, Luca Donetti, Miguel A. + Munoz (2014) PNAS "Trophic coherence determines food-web stability" + """ + levels = trophic_levels(G, weight=weight) + diffs = {} + for u, v in G.edges: + diffs[(u, v)] = levels[v] - levels[u] + return diffs + + +@not_implemented_for("undirected") +@nx._dispatch(edge_attrs="weight") +def trophic_incoherence_parameter(G, weight="weight", cannibalism=False): + r"""Compute the trophic incoherence parameter of a graph. + + Trophic coherence is defined as the homogeneity of the distribution of + trophic distances: the more similar, the more coherent. This is measured by + the standard deviation of the trophic differences and referred to as the + trophic incoherence parameter $q$ by [1]. + + Parameters + ---------- + G : DiGraph + A directed networkx graph + + cannibalism: Boolean + If set to False, self edges are not considered in the calculation + + Returns + ------- + trophic_incoherence_parameter : float + The trophic coherence of a graph + + References + ---------- + .. [1] Samuel Johnson, Virginia Dominguez-Garcia, Luca Donetti, Miguel A. + Munoz (2014) PNAS "Trophic coherence determines food-web stability" + """ + import numpy as np + + if cannibalism: + diffs = trophic_differences(G, weight=weight) + else: + # If no cannibalism, remove self-edges + self_loops = list(nx.selfloop_edges(G)) + if self_loops: + # Make a copy so we do not change G's edges in memory + G_2 = G.copy() + G_2.remove_edges_from(self_loops) + else: + # Avoid copy otherwise + G_2 = G + diffs = trophic_differences(G_2, weight=weight) + return np.std(list(diffs.values())) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/voterank_alg.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/voterank_alg.py new file mode 100644 index 0000000000000000000000000000000000000000..f9cf43c7813b91a53d63f2e15c0ef7a538d42f25 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/centrality/voterank_alg.py @@ -0,0 +1,94 @@ +"""Algorithm to select influential nodes in a graph using VoteRank.""" +import networkx as nx + +__all__ = ["voterank"] + + +@nx._dispatch +def voterank(G, number_of_nodes=None): + """Select a list of influential nodes in a graph using VoteRank algorithm + + VoteRank [1]_ computes a ranking of the nodes in a graph G based on a + voting scheme. With VoteRank, all nodes vote for each of its in-neighbours + and the node with the highest votes is elected iteratively. The voting + ability of out-neighbors of elected nodes is decreased in subsequent turns. + + Parameters + ---------- + G : graph + A NetworkX graph. + + number_of_nodes : integer, optional + Number of ranked nodes to extract (default all nodes). + + Returns + ------- + voterank : list + Ordered list of computed seeds. + Only nodes with positive number of votes are returned. + + Examples + -------- + >>> G = nx.Graph([(0, 1), (0, 2), (0, 3), (1, 4)]) + >>> nx.voterank(G) + [0, 1] + + The algorithm can be used both for undirected and directed graphs. + However, the directed version is different in two ways: + (i) nodes only vote for their in-neighbors and + (ii) only the voting ability of elected node and its out-neighbors are updated: + + >>> G = nx.DiGraph([(0, 1), (2, 1), (2, 3), (3, 4)]) + >>> nx.voterank(G) + [2, 3] + + Notes + ----- + Each edge is treated independently in case of multigraphs. + + References + ---------- + .. [1] Zhang, J.-X. et al. (2016). + Identifying a set of influential spreaders in complex networks. + Sci. Rep. 6, 27823; doi: 10.1038/srep27823. + """ + influential_nodes = [] + vote_rank = {} + if len(G) == 0: + return influential_nodes + if number_of_nodes is None or number_of_nodes > len(G): + number_of_nodes = len(G) + if G.is_directed(): + # For directed graphs compute average out-degree + avgDegree = sum(deg for _, deg in G.out_degree()) / len(G) + else: + # For undirected graphs compute average degree + avgDegree = sum(deg for _, deg in G.degree()) / len(G) + # step 1 - initiate all nodes to (0,1) (score, voting ability) + for n in G.nodes(): + vote_rank[n] = [0, 1] + # Repeat steps 1b to 4 until num_seeds are elected. + for _ in range(number_of_nodes): + # step 1b - reset rank + for n in G.nodes(): + vote_rank[n][0] = 0 + # step 2 - vote + for n, nbr in G.edges(): + # In directed graphs nodes only vote for their in-neighbors + vote_rank[n][0] += vote_rank[nbr][1] + if not G.is_directed(): + vote_rank[nbr][0] += vote_rank[n][1] + for n in influential_nodes: + vote_rank[n][0] = 0 + # step 3 - select top node + n = max(G.nodes, key=lambda x: vote_rank[x][0]) + if vote_rank[n][0] == 0: + return influential_nodes + influential_nodes.append(n) + # weaken the selected node + vote_rank[n] = [0, 0] + # step 4 - update voterank properties + for _, nbr in G.edges(n): + vote_rank[nbr][1] -= 1 / avgDegree + vote_rank[nbr][1] = max(vote_rank[nbr][1], 0) + return influential_nodes diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/cycles.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/cycles.py new file mode 100644 index 0000000000000000000000000000000000000000..9149e9eb10dcf4dfd99cfeab80f90ede47a71d95 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/cycles.py @@ -0,0 +1,1230 @@ +""" +======================== +Cycle finding algorithms +======================== +""" + +from collections import Counter, defaultdict +from itertools import combinations, product +from math import inf + +import networkx as nx +from networkx.utils import not_implemented_for, pairwise + +__all__ = [ + "cycle_basis", + "simple_cycles", + "recursive_simple_cycles", + "find_cycle", + "minimum_cycle_basis", + "chordless_cycles", + "girth", +] + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@nx._dispatch +def cycle_basis(G, root=None): + """Returns a list of cycles which form a basis for cycles of G. + + A basis for cycles of a network is a minimal collection of + cycles such that any cycle in the network can be written + as a sum of cycles in the basis. Here summation of cycles + is defined as "exclusive or" of the edges. Cycle bases are + useful, e.g. when deriving equations for electric circuits + using Kirchhoff's Laws. + + Parameters + ---------- + G : NetworkX Graph + root : node, optional + Specify starting node for basis. + + Returns + ------- + A list of cycle lists. Each cycle list is a list of nodes + which forms a cycle (loop) in G. + + Examples + -------- + >>> G = nx.Graph() + >>> nx.add_cycle(G, [0, 1, 2, 3]) + >>> nx.add_cycle(G, [0, 3, 4, 5]) + >>> nx.cycle_basis(G, 0) + [[3, 4, 5, 0], [1, 2, 3, 0]] + + Notes + ----- + This is adapted from algorithm CACM 491 [1]_. + + References + ---------- + .. [1] Paton, K. An algorithm for finding a fundamental set of + cycles of a graph. Comm. ACM 12, 9 (Sept 1969), 514-518. + + See Also + -------- + simple_cycles + """ + gnodes = dict.fromkeys(G) # set-like object that maintains node order + cycles = [] + while gnodes: # loop over connected components + if root is None: + root = gnodes.popitem()[0] + stack = [root] + pred = {root: root} + used = {root: set()} + while stack: # walk the spanning tree finding cycles + z = stack.pop() # use last-in so cycles easier to find + zused = used[z] + for nbr in G[z]: + if nbr not in used: # new node + pred[nbr] = z + stack.append(nbr) + used[nbr] = {z} + elif nbr == z: # self loops + cycles.append([z]) + elif nbr not in zused: # found a cycle + pn = used[nbr] + cycle = [nbr, z] + p = pred[z] + while p not in pn: + cycle.append(p) + p = pred[p] + cycle.append(p) + cycles.append(cycle) + used[nbr].add(z) + for node in pred: + gnodes.pop(node, None) + root = None + return cycles + + +@nx._dispatch +def simple_cycles(G, length_bound=None): + """Find simple cycles (elementary circuits) of a graph. + + A `simple cycle`, or `elementary circuit`, is a closed path where + no node appears twice. In a directed graph, two simple cycles are distinct + if they are not cyclic permutations of each other. In an undirected graph, + two simple cycles are distinct if they are not cyclic permutations of each + other nor of the other's reversal. + + Optionally, the cycles are bounded in length. In the unbounded case, we use + a nonrecursive, iterator/generator version of Johnson's algorithm [1]_. In + the bounded case, we use a version of the algorithm of Gupta and + Suzumura[2]_. There may be better algorithms for some cases [3]_ [4]_ [5]_. + + The algorithms of Johnson, and Gupta and Suzumura, are enhanced by some + well-known preprocessing techniques. When G is directed, we restrict our + attention to strongly connected components of G, generate all simple cycles + containing a certain node, remove that node, and further decompose the + remainder into strongly connected components. When G is undirected, we + restrict our attention to biconnected components, generate all simple cycles + containing a particular edge, remove that edge, and further decompose the + remainder into biconnected components. + + Note that multigraphs are supported by this function -- and in undirected + multigraphs, a pair of parallel edges is considered a cycle of length 2. + Likewise, self-loops are considered to be cycles of length 1. We define + cycles as sequences of nodes; so the presence of loops and parallel edges + does not change the number of simple cycles in a graph. + + Parameters + ---------- + G : NetworkX DiGraph + A directed graph + + length_bound : int or None, optional (default=None) + If length_bound is an int, generate all simple cycles of G with length at + most length_bound. Otherwise, generate all simple cycles of G. + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + + Examples + -------- + >>> edges = [(0, 0), (0, 1), (0, 2), (1, 2), (2, 0), (2, 1), (2, 2)] + >>> G = nx.DiGraph(edges) + >>> sorted(nx.simple_cycles(G)) + [[0], [0, 1, 2], [0, 2], [1, 2], [2]] + + To filter the cycles so that they don't include certain nodes or edges, + copy your graph and eliminate those nodes or edges before calling. + For example, to exclude self-loops from the above example: + + >>> H = G.copy() + >>> H.remove_edges_from(nx.selfloop_edges(G)) + >>> sorted(nx.simple_cycles(H)) + [[0, 1, 2], [0, 2], [1, 2]] + + Notes + ----- + When length_bound is None, the time complexity is $O((n+e)(c+1))$ for $n$ + nodes, $e$ edges and $c$ simple circuits. Otherwise, when length_bound > 1, + the time complexity is $O((c+n)(k-1)d^k)$ where $d$ is the average degree of + the nodes of G and $k$ = length_bound. + + Raises + ------ + ValueError + when length_bound < 0. + + References + ---------- + .. [1] Finding all the elementary circuits of a directed graph. + D. B. Johnson, SIAM Journal on Computing 4, no. 1, 77-84, 1975. + https://doi.org/10.1137/0204007 + .. [2] Finding All Bounded-Length Simple Cycles in a Directed Graph + A. Gupta and T. Suzumura https://arxiv.org/abs/2105.10094 + .. [3] Enumerating the cycles of a digraph: a new preprocessing strategy. + G. Loizou and P. Thanish, Information Sciences, v. 27, 163-182, 1982. + .. [4] A search strategy for the elementary cycles of a directed graph. + J.L. Szwarcfiter and P.E. Lauer, BIT NUMERICAL MATHEMATICS, + v. 16, no. 2, 192-204, 1976. + .. [5] Optimal Listing of Cycles and st-Paths in Undirected Graphs + R. Ferreira and R. Grossi and A. Marino and N. Pisanti and R. Rizzi and + G. Sacomoto https://arxiv.org/abs/1205.2766 + + See Also + -------- + cycle_basis + chordless_cycles + """ + + if length_bound is not None: + if length_bound == 0: + return + elif length_bound < 0: + raise ValueError("length bound must be non-negative") + + directed = G.is_directed() + yield from ([v] for v, Gv in G.adj.items() if v in Gv) + + if length_bound is not None and length_bound == 1: + return + + if G.is_multigraph() and not directed: + visited = set() + for u, Gu in G.adj.items(): + multiplicity = ((v, len(Guv)) for v, Guv in Gu.items() if v in visited) + yield from ([u, v] for v, m in multiplicity if m > 1) + visited.add(u) + + # explicitly filter out loops; implicitly filter out parallel edges + if directed: + G = nx.DiGraph((u, v) for u, Gu in G.adj.items() for v in Gu if v != u) + else: + G = nx.Graph((u, v) for u, Gu in G.adj.items() for v in Gu if v != u) + + # this case is not strictly necessary but improves performance + if length_bound is not None and length_bound == 2: + if directed: + visited = set() + for u, Gu in G.adj.items(): + yield from ( + [v, u] for v in visited.intersection(Gu) if G.has_edge(v, u) + ) + visited.add(u) + return + + if directed: + yield from _directed_cycle_search(G, length_bound) + else: + yield from _undirected_cycle_search(G, length_bound) + + +def _directed_cycle_search(G, length_bound): + """A dispatch function for `simple_cycles` for directed graphs. + + We generate all cycles of G through binary partition. + + 1. Pick a node v in G which belongs to at least one cycle + a. Generate all cycles of G which contain the node v. + b. Recursively generate all cycles of G \\ v. + + This is accomplished through the following: + + 1. Compute the strongly connected components SCC of G. + 2. Select and remove a biconnected component C from BCC. Select a + non-tree edge (u, v) of a depth-first search of G[C]. + 3. For each simple cycle P containing v in G[C], yield P. + 4. Add the biconnected components of G[C \\ v] to BCC. + + If the parameter length_bound is not None, then step 3 will be limited to + simple cycles of length at most length_bound. + + Parameters + ---------- + G : NetworkX DiGraph + A directed graph + + length_bound : int or None + If length_bound is an int, generate all simple cycles of G with length at most length_bound. + Otherwise, generate all simple cycles of G. + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + """ + + scc = nx.strongly_connected_components + components = [c for c in scc(G) if len(c) >= 2] + while components: + c = components.pop() + Gc = G.subgraph(c) + v = next(iter(c)) + if length_bound is None: + yield from _johnson_cycle_search(Gc, [v]) + else: + yield from _bounded_cycle_search(Gc, [v], length_bound) + # delete v after searching G, to make sure we can find v + G.remove_node(v) + components.extend(c for c in scc(Gc) if len(c) >= 2) + + +def _undirected_cycle_search(G, length_bound): + """A dispatch function for `simple_cycles` for undirected graphs. + + We generate all cycles of G through binary partition. + + 1. Pick an edge (u, v) in G which belongs to at least one cycle + a. Generate all cycles of G which contain the edge (u, v) + b. Recursively generate all cycles of G \\ (u, v) + + This is accomplished through the following: + + 1. Compute the biconnected components BCC of G. + 2. Select and remove a biconnected component C from BCC. Select a + non-tree edge (u, v) of a depth-first search of G[C]. + 3. For each (v -> u) path P remaining in G[C] \\ (u, v), yield P. + 4. Add the biconnected components of G[C] \\ (u, v) to BCC. + + If the parameter length_bound is not None, then step 3 will be limited to simple paths + of length at most length_bound. + + Parameters + ---------- + G : NetworkX Graph + An undirected graph + + length_bound : int or None + If length_bound is an int, generate all simple cycles of G with length at most length_bound. + Otherwise, generate all simple cycles of G. + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + """ + + bcc = nx.biconnected_components + components = [c for c in bcc(G) if len(c) >= 3] + while components: + c = components.pop() + Gc = G.subgraph(c) + uv = list(next(iter(Gc.edges))) + G.remove_edge(*uv) + # delete (u, v) before searching G, to avoid fake 3-cycles [u, v, u] + if length_bound is None: + yield from _johnson_cycle_search(Gc, uv) + else: + yield from _bounded_cycle_search(Gc, uv, length_bound) + components.extend(c for c in bcc(Gc) if len(c) >= 3) + + +class _NeighborhoodCache(dict): + """Very lightweight graph wrapper which caches neighborhoods as list. + + This dict subclass uses the __missing__ functionality to query graphs for + their neighborhoods, and store the result as a list. This is used to avoid + the performance penalty incurred by subgraph views. + """ + + def __init__(self, G): + self.G = G + + def __missing__(self, v): + Gv = self[v] = list(self.G[v]) + return Gv + + +def _johnson_cycle_search(G, path): + """The main loop of the cycle-enumeration algorithm of Johnson. + + Parameters + ---------- + G : NetworkX Graph or DiGraph + A graph + + path : list + A cycle prefix. All cycles generated will begin with this prefix. + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + + References + ---------- + .. [1] Finding all the elementary circuits of a directed graph. + D. B. Johnson, SIAM Journal on Computing 4, no. 1, 77-84, 1975. + https://doi.org/10.1137/0204007 + + """ + + G = _NeighborhoodCache(G) + blocked = set(path) + B = defaultdict(set) # graph portions that yield no elementary circuit + start = path[0] + stack = [iter(G[path[-1]])] + closed = [False] + while stack: + nbrs = stack[-1] + for w in nbrs: + if w == start: + yield path[:] + closed[-1] = True + elif w not in blocked: + path.append(w) + closed.append(False) + stack.append(iter(G[w])) + blocked.add(w) + break + else: # no more nbrs + stack.pop() + v = path.pop() + if closed.pop(): + if closed: + closed[-1] = True + unblock_stack = {v} + while unblock_stack: + u = unblock_stack.pop() + if u in blocked: + blocked.remove(u) + unblock_stack.update(B[u]) + B[u].clear() + else: + for w in G[v]: + B[w].add(v) + + +def _bounded_cycle_search(G, path, length_bound): + """The main loop of the cycle-enumeration algorithm of Gupta and Suzumura. + + Parameters + ---------- + G : NetworkX Graph or DiGraph + A graph + + path : list + A cycle prefix. All cycles generated will begin with this prefix. + + length_bound: int + A length bound. All cycles generated will have length at most length_bound. + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + + References + ---------- + .. [1] Finding All Bounded-Length Simple Cycles in a Directed Graph + A. Gupta and T. Suzumura https://arxiv.org/abs/2105.10094 + + """ + G = _NeighborhoodCache(G) + lock = {v: 0 for v in path} + B = defaultdict(set) + start = path[0] + stack = [iter(G[path[-1]])] + blen = [length_bound] + while stack: + nbrs = stack[-1] + for w in nbrs: + if w == start: + yield path[:] + blen[-1] = 1 + elif len(path) < lock.get(w, length_bound): + path.append(w) + blen.append(length_bound) + lock[w] = len(path) + stack.append(iter(G[w])) + break + else: + stack.pop() + v = path.pop() + bl = blen.pop() + if blen: + blen[-1] = min(blen[-1], bl) + if bl < length_bound: + relax_stack = [(bl, v)] + while relax_stack: + bl, u = relax_stack.pop() + if lock.get(u, length_bound) < length_bound - bl + 1: + lock[u] = length_bound - bl + 1 + relax_stack.extend((bl + 1, w) for w in B[u].difference(path)) + else: + for w in G[v]: + B[w].add(v) + + +@nx._dispatch +def chordless_cycles(G, length_bound=None): + """Find simple chordless cycles of a graph. + + A `simple cycle` is a closed path where no node appears twice. In a simple + cycle, a `chord` is an additional edge between two nodes in the cycle. A + `chordless cycle` is a simple cycle without chords. Said differently, a + chordless cycle is a cycle C in a graph G where the number of edges in the + induced graph G[C] is equal to the length of `C`. + + Note that some care must be taken in the case that G is not a simple graph + nor a simple digraph. Some authors limit the definition of chordless cycles + to have a prescribed minimum length; we do not. + + 1. We interpret self-loops to be chordless cycles, except in multigraphs + with multiple loops in parallel. Likewise, in a chordless cycle of + length greater than 1, there can be no nodes with self-loops. + + 2. We interpret directed two-cycles to be chordless cycles, except in + multi-digraphs when any edge in a two-cycle has a parallel copy. + + 3. We interpret parallel pairs of undirected edges as two-cycles, except + when a third (or more) parallel edge exists between the two nodes. + + 4. Generalizing the above, edges with parallel clones may not occur in + chordless cycles. + + In a directed graph, two chordless cycles are distinct if they are not + cyclic permutations of each other. In an undirected graph, two chordless + cycles are distinct if they are not cyclic permutations of each other nor of + the other's reversal. + + Optionally, the cycles are bounded in length. + + We use an algorithm strongly inspired by that of Dias et al [1]_. It has + been modified in the following ways: + + 1. Recursion is avoided, per Python's limitations + + 2. The labeling function is not necessary, because the starting paths + are chosen (and deleted from the host graph) to prevent multiple + occurrences of the same path + + 3. The search is optionally bounded at a specified length + + 4. Support for directed graphs is provided by extending cycles along + forward edges, and blocking nodes along forward and reverse edges + + 5. Support for multigraphs is provided by omitting digons from the set + of forward edges + + Parameters + ---------- + G : NetworkX DiGraph + A directed graph + + length_bound : int or None, optional (default=None) + If length_bound is an int, generate all simple cycles of G with length at + most length_bound. Otherwise, generate all simple cycles of G. + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + + Examples + -------- + >>> sorted(list(nx.chordless_cycles(nx.complete_graph(4)))) + [[1, 0, 2], [1, 0, 3], [2, 0, 3], [2, 1, 3]] + + Notes + ----- + When length_bound is None, and the graph is simple, the time complexity is + $O((n+e)(c+1))$ for $n$ nodes, $e$ edges and $c$ chordless cycles. + + Raises + ------ + ValueError + when length_bound < 0. + + References + ---------- + .. [1] Efficient enumeration of chordless cycles + E. Dias and D. Castonguay and H. Longo and W.A.R. Jradi + https://arxiv.org/abs/1309.1051 + + See Also + -------- + simple_cycles + """ + + if length_bound is not None: + if length_bound == 0: + return + elif length_bound < 0: + raise ValueError("length bound must be non-negative") + + directed = G.is_directed() + multigraph = G.is_multigraph() + + if multigraph: + yield from ([v] for v, Gv in G.adj.items() if len(Gv.get(v, ())) == 1) + else: + yield from ([v] for v, Gv in G.adj.items() if v in Gv) + + if length_bound is not None and length_bound == 1: + return + + # Nodes with loops cannot belong to longer cycles. Let's delete them here. + # also, we implicitly reduce the multiplicity of edges down to 1 in the case + # of multiedges. + if directed: + F = nx.DiGraph((u, v) for u, Gu in G.adj.items() if u not in Gu for v in Gu) + B = F.to_undirected(as_view=False) + else: + F = nx.Graph((u, v) for u, Gu in G.adj.items() if u not in Gu for v in Gu) + B = None + + # If we're given a multigraph, we have a few cases to consider with parallel + # edges. + # + # 1. If we have 2 or more edges in parallel between the nodes (u, v), we + # must not construct longer cycles along (u, v). + # 2. If G is not directed, then a pair of parallel edges between (u, v) is a + # chordless cycle unless there exists a third (or more) parallel edge. + # 3. If G is directed, then parallel edges do not form cycles, but do + # preclude back-edges from forming cycles (handled in the next section), + # Thus, if an edge (u, v) is duplicated and the reverse (v, u) is also + # present, then we remove both from F. + # + # In directed graphs, we need to consider both directions that edges can + # take, so iterate over all edges (u, v) and possibly (v, u). In undirected + # graphs, we need to be a little careful to only consider every edge once, + # so we use a "visited" set to emulate node-order comparisons. + + if multigraph: + if not directed: + B = F.copy() + visited = set() + for u, Gu in G.adj.items(): + if directed: + multiplicity = ((v, len(Guv)) for v, Guv in Gu.items()) + for v, m in multiplicity: + if m > 1: + F.remove_edges_from(((u, v), (v, u))) + else: + multiplicity = ((v, len(Guv)) for v, Guv in Gu.items() if v in visited) + for v, m in multiplicity: + if m == 2: + yield [u, v] + if m > 1: + F.remove_edge(u, v) + visited.add(u) + + # If we're given a directed graphs, we need to think about digons. If we + # have two edges (u, v) and (v, u), then that's a two-cycle. If either edge + # was duplicated above, then we removed both from F. So, any digons we find + # here are chordless. After finding digons, we remove their edges from F + # to avoid traversing them in the search for chordless cycles. + if directed: + for u, Fu in F.adj.items(): + digons = [[u, v] for v in Fu if F.has_edge(v, u)] + yield from digons + F.remove_edges_from(digons) + F.remove_edges_from(e[::-1] for e in digons) + + if length_bound is not None and length_bound == 2: + return + + # Now, we prepare to search for cycles. We have removed all cycles of + # lengths 1 and 2, so F is a simple graph or simple digraph. We repeatedly + # separate digraphs into their strongly connected components, and undirected + # graphs into their biconnected components. For each component, we pick a + # node v, search for chordless cycles based at each "stem" (u, v, w), and + # then remove v from that component before separating the graph again. + if directed: + separate = nx.strongly_connected_components + + # Directed stems look like (u -> v -> w), so we use the product of + # predecessors of v with successors of v. + def stems(C, v): + for u, w in product(C.pred[v], C.succ[v]): + if not G.has_edge(u, w): # omit stems with acyclic chords + yield [u, v, w], F.has_edge(w, u) + + else: + separate = nx.biconnected_components + + # Undirected stems look like (u ~ v ~ w), but we must not also search + # (w ~ v ~ u), so we use combinations of v's neighbors of length 2. + def stems(C, v): + yield from (([u, v, w], F.has_edge(w, u)) for u, w in combinations(C[v], 2)) + + components = [c for c in separate(F) if len(c) > 2] + while components: + c = components.pop() + v = next(iter(c)) + Fc = F.subgraph(c) + Fcc = Bcc = None + for S, is_triangle in stems(Fc, v): + if is_triangle: + yield S + else: + if Fcc is None: + Fcc = _NeighborhoodCache(Fc) + Bcc = Fcc if B is None else _NeighborhoodCache(B.subgraph(c)) + yield from _chordless_cycle_search(Fcc, Bcc, S, length_bound) + + components.extend(c for c in separate(F.subgraph(c - {v})) if len(c) > 2) + + +def _chordless_cycle_search(F, B, path, length_bound): + """The main loop for chordless cycle enumeration. + + This algorithm is strongly inspired by that of Dias et al [1]_. It has been + modified in the following ways: + + 1. Recursion is avoided, per Python's limitations + + 2. The labeling function is not necessary, because the starting paths + are chosen (and deleted from the host graph) to prevent multiple + occurrences of the same path + + 3. The search is optionally bounded at a specified length + + 4. Support for directed graphs is provided by extending cycles along + forward edges, and blocking nodes along forward and reverse edges + + 5. Support for multigraphs is provided by omitting digons from the set + of forward edges + + Parameters + ---------- + F : _NeighborhoodCache + A graph of forward edges to follow in constructing cycles + + B : _NeighborhoodCache + A graph of blocking edges to prevent the production of chordless cycles + + path : list + A cycle prefix. All cycles generated will begin with this prefix. + + length_bound : int + A length bound. All cycles generated will have length at most length_bound. + + + Yields + ------ + list of nodes + Each cycle is represented by a list of nodes along the cycle. + + References + ---------- + .. [1] Efficient enumeration of chordless cycles + E. Dias and D. Castonguay and H. Longo and W.A.R. Jradi + https://arxiv.org/abs/1309.1051 + + """ + blocked = defaultdict(int) + target = path[0] + blocked[path[1]] = 1 + for w in path[1:]: + for v in B[w]: + blocked[v] += 1 + + stack = [iter(F[path[2]])] + while stack: + nbrs = stack[-1] + for w in nbrs: + if blocked[w] == 1 and (length_bound is None or len(path) < length_bound): + Fw = F[w] + if target in Fw: + yield path + [w] + else: + Bw = B[w] + if target in Bw: + continue + for v in Bw: + blocked[v] += 1 + path.append(w) + stack.append(iter(Fw)) + break + else: + stack.pop() + for v in B[path.pop()]: + blocked[v] -= 1 + + +@not_implemented_for("undirected") +@nx._dispatch +def recursive_simple_cycles(G): + """Find simple cycles (elementary circuits) of a directed graph. + + A `simple cycle`, or `elementary circuit`, is a closed path where + no node appears twice. Two elementary circuits are distinct if they + are not cyclic permutations of each other. + + This version uses a recursive algorithm to build a list of cycles. + You should probably use the iterator version called simple_cycles(). + Warning: This recursive version uses lots of RAM! + It appears in NetworkX for pedagogical value. + + Parameters + ---------- + G : NetworkX DiGraph + A directed graph + + Returns + ------- + A list of cycles, where each cycle is represented by a list of nodes + along the cycle. + + Example: + + >>> edges = [(0, 0), (0, 1), (0, 2), (1, 2), (2, 0), (2, 1), (2, 2)] + >>> G = nx.DiGraph(edges) + >>> nx.recursive_simple_cycles(G) + [[0], [2], [0, 1, 2], [0, 2], [1, 2]] + + Notes + ----- + The implementation follows pp. 79-80 in [1]_. + + The time complexity is $O((n+e)(c+1))$ for $n$ nodes, $e$ edges and $c$ + elementary circuits. + + References + ---------- + .. [1] Finding all the elementary circuits of a directed graph. + D. B. Johnson, SIAM Journal on Computing 4, no. 1, 77-84, 1975. + https://doi.org/10.1137/0204007 + + See Also + -------- + simple_cycles, cycle_basis + """ + + # Jon Olav Vik, 2010-08-09 + def _unblock(thisnode): + """Recursively unblock and remove nodes from B[thisnode].""" + if blocked[thisnode]: + blocked[thisnode] = False + while B[thisnode]: + _unblock(B[thisnode].pop()) + + def circuit(thisnode, startnode, component): + closed = False # set to True if elementary path is closed + path.append(thisnode) + blocked[thisnode] = True + for nextnode in component[thisnode]: # direct successors of thisnode + if nextnode == startnode: + result.append(path[:]) + closed = True + elif not blocked[nextnode]: + if circuit(nextnode, startnode, component): + closed = True + if closed: + _unblock(thisnode) + else: + for nextnode in component[thisnode]: + if thisnode not in B[nextnode]: # TODO: use set for speedup? + B[nextnode].append(thisnode) + path.pop() # remove thisnode from path + return closed + + path = [] # stack of nodes in current path + blocked = defaultdict(bool) # vertex: blocked from search? + B = defaultdict(list) # graph portions that yield no elementary circuit + result = [] # list to accumulate the circuits found + + # Johnson's algorithm exclude self cycle edges like (v, v) + # To be backward compatible, we record those cycles in advance + # and then remove from subG + for v in G: + if G.has_edge(v, v): + result.append([v]) + G.remove_edge(v, v) + + # Johnson's algorithm requires some ordering of the nodes. + # They might not be sortable so we assign an arbitrary ordering. + ordering = dict(zip(G, range(len(G)))) + for s in ordering: + # Build the subgraph induced by s and following nodes in the ordering + subgraph = G.subgraph(node for node in G if ordering[node] >= ordering[s]) + # Find the strongly connected component in the subgraph + # that contains the least node according to the ordering + strongcomp = nx.strongly_connected_components(subgraph) + mincomp = min(strongcomp, key=lambda ns: min(ordering[n] for n in ns)) + component = G.subgraph(mincomp) + if len(component) > 1: + # smallest node in the component according to the ordering + startnode = min(component, key=ordering.__getitem__) + for node in component: + blocked[node] = False + B[node][:] = [] + dummy = circuit(startnode, startnode, component) + return result + + +@nx._dispatch +def find_cycle(G, source=None, orientation=None): + """Returns a cycle found via depth-first traversal. + + The cycle is a list of edges indicating the cyclic path. + Orientation of directed edges is controlled by `orientation`. + + Parameters + ---------- + G : graph + A directed/undirected graph/multigraph. + + source : node, list of nodes + The node from which the traversal begins. If None, then a source + is chosen arbitrarily and repeatedly until all edges from each node in + the graph are searched. + + orientation : None | 'original' | 'reverse' | 'ignore' (default: None) + For directed graphs and directed multigraphs, edge traversals need not + respect the original orientation of the edges. + When set to 'reverse' every edge is traversed in the reverse direction. + When set to 'ignore', every edge is treated as undirected. + When set to 'original', every edge is treated as directed. + In all three cases, the yielded edge tuples add a last entry to + indicate the direction in which that edge was traversed. + If orientation is None, the yielded edge has no direction indicated. + The direction is respected, but not reported. + + Returns + ------- + edges : directed edges + A list of directed edges indicating the path taken for the loop. + If no cycle is found, then an exception is raised. + For graphs, an edge is of the form `(u, v)` where `u` and `v` + are the tail and head of the edge as determined by the traversal. + For multigraphs, an edge is of the form `(u, v, key)`, where `key` is + the key of the edge. When the graph is directed, then `u` and `v` + are always in the order of the actual directed edge. + If orientation is not None then the edge tuple is extended to include + the direction of traversal ('forward' or 'reverse') on that edge. + + Raises + ------ + NetworkXNoCycle + If no cycle was found. + + Examples + -------- + In this example, we construct a DAG and find, in the first call, that there + are no directed cycles, and so an exception is raised. In the second call, + we ignore edge orientations and find that there is an undirected cycle. + Note that the second call finds a directed cycle while effectively + traversing an undirected graph, and so, we found an "undirected cycle". + This means that this DAG structure does not form a directed tree (which + is also known as a polytree). + + >>> G = nx.DiGraph([(0, 1), (0, 2), (1, 2)]) + >>> nx.find_cycle(G, orientation="original") + Traceback (most recent call last): + ... + networkx.exception.NetworkXNoCycle: No cycle found. + >>> list(nx.find_cycle(G, orientation="ignore")) + [(0, 1, 'forward'), (1, 2, 'forward'), (0, 2, 'reverse')] + + See Also + -------- + simple_cycles + """ + if not G.is_directed() or orientation in (None, "original"): + + def tailhead(edge): + return edge[:2] + + elif orientation == "reverse": + + def tailhead(edge): + return edge[1], edge[0] + + elif orientation == "ignore": + + def tailhead(edge): + if edge[-1] == "reverse": + return edge[1], edge[0] + return edge[:2] + + explored = set() + cycle = [] + final_node = None + for start_node in G.nbunch_iter(source): + if start_node in explored: + # No loop is possible. + continue + + edges = [] + # All nodes seen in this iteration of edge_dfs + seen = {start_node} + # Nodes in active path. + active_nodes = {start_node} + previous_head = None + + for edge in nx.edge_dfs(G, start_node, orientation): + # Determine if this edge is a continuation of the active path. + tail, head = tailhead(edge) + if head in explored: + # Then we've already explored it. No loop is possible. + continue + if previous_head is not None and tail != previous_head: + # This edge results from backtracking. + # Pop until we get a node whose head equals the current tail. + # So for example, we might have: + # (0, 1), (1, 2), (2, 3), (1, 4) + # which must become: + # (0, 1), (1, 4) + while True: + try: + popped_edge = edges.pop() + except IndexError: + edges = [] + active_nodes = {tail} + break + else: + popped_head = tailhead(popped_edge)[1] + active_nodes.remove(popped_head) + + if edges: + last_head = tailhead(edges[-1])[1] + if tail == last_head: + break + edges.append(edge) + + if head in active_nodes: + # We have a loop! + cycle.extend(edges) + final_node = head + break + else: + seen.add(head) + active_nodes.add(head) + previous_head = head + + if cycle: + break + else: + explored.update(seen) + + else: + assert len(cycle) == 0 + raise nx.exception.NetworkXNoCycle("No cycle found.") + + # We now have a list of edges which ends on a cycle. + # So we need to remove from the beginning edges that are not relevant. + + for i, edge in enumerate(cycle): + tail, head = tailhead(edge) + if tail == final_node: + break + + return cycle[i:] + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@nx._dispatch(edge_attrs="weight") +def minimum_cycle_basis(G, weight=None): + """Returns a minimum weight cycle basis for G + + Minimum weight means a cycle basis for which the total weight + (length for unweighted graphs) of all the cycles is minimum. + + Parameters + ---------- + G : NetworkX Graph + weight: string + name of the edge attribute to use for edge weights + + Returns + ------- + A list of cycle lists. Each cycle list is a list of nodes + which forms a cycle (loop) in G. Note that the nodes are not + necessarily returned in a order by which they appear in the cycle + + Examples + -------- + >>> G = nx.Graph() + >>> nx.add_cycle(G, [0, 1, 2, 3]) + >>> nx.add_cycle(G, [0, 3, 4, 5]) + >>> nx.minimum_cycle_basis(G) + [[5, 4, 3, 0], [3, 2, 1, 0]] + + References: + [1] Kavitha, Telikepalli, et al. "An O(m^2n) Algorithm for + Minimum Cycle Basis of Graphs." + http://link.springer.com/article/10.1007/s00453-007-9064-z + [2] de Pina, J. 1995. Applications of shortest path methods. + Ph.D. thesis, University of Amsterdam, Netherlands + + See Also + -------- + simple_cycles, cycle_basis + """ + # We first split the graph in connected subgraphs + return sum( + (_min_cycle_basis(G.subgraph(c), weight) for c in nx.connected_components(G)), + [], + ) + + +def _min_cycle_basis(G, weight): + cb = [] + # We extract the edges not in a spanning tree. We do not really need a + # *minimum* spanning tree. That is why we call the next function with + # weight=None. Depending on implementation, it may be faster as well + tree_edges = list(nx.minimum_spanning_edges(G, weight=None, data=False)) + chords = G.edges - tree_edges - {(v, u) for u, v in tree_edges} + + # We maintain a set of vectors orthogonal to sofar found cycles + set_orth = [{edge} for edge in chords] + while set_orth: + base = set_orth.pop() + # kth cycle is "parallel" to kth vector in set_orth + cycle_edges = _min_cycle(G, base, weight) + cb.append([v for u, v in cycle_edges]) + + # now update set_orth so that k+1,k+2... th elements are + # orthogonal to the newly found cycle, as per [p. 336, 1] + set_orth = [ + ( + {e for e in orth if e not in base if e[::-1] not in base} + | {e for e in base if e not in orth if e[::-1] not in orth} + ) + if sum((e in orth or e[::-1] in orth) for e in cycle_edges) % 2 + else orth + for orth in set_orth + ] + return cb + + +def _min_cycle(G, orth, weight): + """ + Computes the minimum weight cycle in G, + orthogonal to the vector orth as per [p. 338, 1] + Use (u, 1) to indicate the lifted copy of u (denoted u' in paper). + """ + Gi = nx.Graph() + + # Add 2 copies of each edge in G to Gi. + # If edge is in orth, add cross edge; otherwise in-plane edge + for u, v, wt in G.edges(data=weight, default=1): + if (u, v) in orth or (v, u) in orth: + Gi.add_edges_from([(u, (v, 1)), ((u, 1), v)], Gi_weight=wt) + else: + Gi.add_edges_from([(u, v), ((u, 1), (v, 1))], Gi_weight=wt) + + # find the shortest length in Gi between n and (n, 1) for each n + # Note: Use "Gi_weight" for name of weight attribute + spl = nx.shortest_path_length + lift = {n: spl(Gi, source=n, target=(n, 1), weight="Gi_weight") for n in G} + + # Now compute that short path in Gi, which translates to a cycle in G + start = min(lift, key=lift.get) + end = (start, 1) + min_path_i = nx.shortest_path(Gi, source=start, target=end, weight="Gi_weight") + + # Now we obtain the actual path, re-map nodes in Gi to those in G + min_path = [n if n in G else n[0] for n in min_path_i] + + # Now remove the edges that occur two times + # two passes: flag which edges get kept, then build it + edgelist = list(pairwise(min_path)) + edgeset = set() + for e in edgelist: + if e in edgeset: + edgeset.remove(e) + elif e[::-1] in edgeset: + edgeset.remove(e[::-1]) + else: + edgeset.add(e) + + min_edgelist = [] + for e in edgelist: + if e in edgeset: + min_edgelist.append(e) + edgeset.remove(e) + elif e[::-1] in edgeset: + min_edgelist.append(e[::-1]) + edgeset.remove(e[::-1]) + + return min_edgelist + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@nx._dispatch +def girth(G): + """Returns the girth of the graph. + + The girth of a graph is the length of its shortest cycle, or infinity if + the graph is acyclic. The algorithm follows the description given on the + Wikipedia page [1]_, and runs in time O(mn) on a graph with m edges and n + nodes. + + Parameters + ---------- + G : NetworkX Graph + + Returns + ------- + int or math.inf + + Examples + -------- + All examples below (except P_5) can easily be checked using Wikipedia, + which has a page for each of these famous graphs. + + >>> nx.girth(nx.chvatal_graph()) + 4 + >>> nx.girth(nx.tutte_graph()) + 4 + >>> nx.girth(nx.petersen_graph()) + 5 + >>> nx.girth(nx.heawood_graph()) + 6 + >>> nx.girth(nx.pappus_graph()) + 6 + >>> nx.girth(nx.path_graph(5)) + inf + + References + ---------- + .. [1] https://en.wikipedia.org/wiki/Girth_(graph_theory) + + """ + girth = depth_limit = inf + tree_edge = nx.algorithms.traversal.breadth_first_search.TREE_EDGE + level_edge = nx.algorithms.traversal.breadth_first_search.LEVEL_EDGE + for n in G: + # run a BFS from source n, keeping track of distances; since we want + # the shortest cycle, no need to explore beyond the current minimum length + depth = {n: 0} + for u, v, label in nx.bfs_labeled_edges(G, n): + du = depth[u] + if du > depth_limit: + break + if label is tree_edge: + depth[v] = du + 1 + else: + # if (u, v) is a level edge, the length is du + du + 1 (odd) + # otherwise, it's a forward edge; length is du + (du + 1) + 1 (even) + delta = label is level_edge + length = du + du + 2 - delta + if length < girth: + girth = length + depth_limit = du - delta + + return girth diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/__pycache__/dinitz_alg.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/__pycache__/dinitz_alg.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..43e3114315679507aea3a13158c0f25dc6dd616d Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/__pycache__/dinitz_alg.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/__pycache__/preflowpush.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/__pycache__/preflowpush.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..71a86f621ea83eaedc2f497a1f686399ec4a0a65 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/__pycache__/preflowpush.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/capacityscaling.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/capacityscaling.py new file mode 100644 index 0000000000000000000000000000000000000000..2c0002d86c11a83ca8d4b0209b817e7e9c1d4c88 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/capacityscaling.py @@ -0,0 +1,405 @@ +""" +Capacity scaling minimum cost flow algorithm. +""" + +__all__ = ["capacity_scaling"] + +from itertools import chain +from math import log + +import networkx as nx + +from ...utils import BinaryHeap, arbitrary_element, not_implemented_for + + +def _detect_unboundedness(R): + """Detect infinite-capacity negative cycles.""" + G = nx.DiGraph() + G.add_nodes_from(R) + + # Value simulating infinity. + inf = R.graph["inf"] + # True infinity. + f_inf = float("inf") + for u in R: + for v, e in R[u].items(): + # Compute the minimum weight of infinite-capacity (u, v) edges. + w = f_inf + for k, e in e.items(): + if e["capacity"] == inf: + w = min(w, e["weight"]) + if w != f_inf: + G.add_edge(u, v, weight=w) + + if nx.negative_edge_cycle(G): + raise nx.NetworkXUnbounded( + "Negative cost cycle of infinite capacity found. " + "Min cost flow may be unbounded below." + ) + + +@not_implemented_for("undirected") +def _build_residual_network(G, demand, capacity, weight): + """Build a residual network and initialize a zero flow.""" + if sum(G.nodes[u].get(demand, 0) for u in G) != 0: + raise nx.NetworkXUnfeasible("Sum of the demands should be 0.") + + R = nx.MultiDiGraph() + R.add_nodes_from( + (u, {"excess": -G.nodes[u].get(demand, 0), "potential": 0}) for u in G + ) + + inf = float("inf") + # Detect selfloops with infinite capacities and negative weights. + for u, v, e in nx.selfloop_edges(G, data=True): + if e.get(weight, 0) < 0 and e.get(capacity, inf) == inf: + raise nx.NetworkXUnbounded( + "Negative cost cycle of infinite capacity found. " + "Min cost flow may be unbounded below." + ) + + # Extract edges with positive capacities. Self loops excluded. + if G.is_multigraph(): + edge_list = [ + (u, v, k, e) + for u, v, k, e in G.edges(data=True, keys=True) + if u != v and e.get(capacity, inf) > 0 + ] + else: + edge_list = [ + (u, v, 0, e) + for u, v, e in G.edges(data=True) + if u != v and e.get(capacity, inf) > 0 + ] + # Simulate infinity with the larger of the sum of absolute node imbalances + # the sum of finite edge capacities or any positive value if both sums are + # zero. This allows the infinite-capacity edges to be distinguished for + # unboundedness detection and directly participate in residual capacity + # calculation. + inf = ( + max( + sum(abs(R.nodes[u]["excess"]) for u in R), + 2 + * sum( + e[capacity] + for u, v, k, e in edge_list + if capacity in e and e[capacity] != inf + ), + ) + or 1 + ) + for u, v, k, e in edge_list: + r = min(e.get(capacity, inf), inf) + w = e.get(weight, 0) + # Add both (u, v) and (v, u) into the residual network marked with the + # original key. (key[1] == True) indicates the (u, v) is in the + # original network. + R.add_edge(u, v, key=(k, True), capacity=r, weight=w, flow=0) + R.add_edge(v, u, key=(k, False), capacity=0, weight=-w, flow=0) + + # Record the value simulating infinity. + R.graph["inf"] = inf + + _detect_unboundedness(R) + + return R + + +def _build_flow_dict(G, R, capacity, weight): + """Build a flow dictionary from a residual network.""" + inf = float("inf") + flow_dict = {} + if G.is_multigraph(): + for u in G: + flow_dict[u] = {} + for v, es in G[u].items(): + flow_dict[u][v] = { + # Always saturate negative selfloops. + k: ( + 0 + if ( + u != v or e.get(capacity, inf) <= 0 or e.get(weight, 0) >= 0 + ) + else e[capacity] + ) + for k, e in es.items() + } + for v, es in R[u].items(): + if v in flow_dict[u]: + flow_dict[u][v].update( + (k[0], e["flow"]) for k, e in es.items() if e["flow"] > 0 + ) + else: + for u in G: + flow_dict[u] = { + # Always saturate negative selfloops. + v: ( + 0 + if (u != v or e.get(capacity, inf) <= 0 or e.get(weight, 0) >= 0) + else e[capacity] + ) + for v, e in G[u].items() + } + flow_dict[u].update( + (v, e["flow"]) + for v, es in R[u].items() + for e in es.values() + if e["flow"] > 0 + ) + return flow_dict + + +@nx._dispatch(node_attrs="demand", edge_attrs={"capacity": float("inf"), "weight": 0}) +def capacity_scaling( + G, demand="demand", capacity="capacity", weight="weight", heap=BinaryHeap +): + r"""Find a minimum cost flow satisfying all demands in digraph G. + + This is a capacity scaling successive shortest augmenting path algorithm. + + G is a digraph with edge costs and capacities and in which nodes + have demand, i.e., they want to send or receive some amount of + flow. A negative demand means that the node wants to send flow, a + positive demand means that the node want to receive flow. A flow on + the digraph G satisfies all demand if the net flow into each node + is equal to the demand of that node. + + Parameters + ---------- + G : NetworkX graph + DiGraph or MultiDiGraph on which a minimum cost flow satisfying all + demands is to be found. + + demand : string + Nodes of the graph G are expected to have an attribute demand + that indicates how much flow a node wants to send (negative + demand) or receive (positive demand). Note that the sum of the + demands should be 0 otherwise the problem in not feasible. If + this attribute is not present, a node is considered to have 0 + demand. Default value: 'demand'. + + capacity : string + Edges of the graph G are expected to have an attribute capacity + that indicates how much flow the edge can support. If this + attribute is not present, the edge is considered to have + infinite capacity. Default value: 'capacity'. + + weight : string + Edges of the graph G are expected to have an attribute weight + that indicates the cost incurred by sending one unit of flow on + that edge. If not present, the weight is considered to be 0. + Default value: 'weight'. + + heap : class + Type of heap to be used in the algorithm. It should be a subclass of + :class:`MinHeap` or implement a compatible interface. + + If a stock heap implementation is to be used, :class:`BinaryHeap` is + recommended over :class:`PairingHeap` for Python implementations without + optimized attribute accesses (e.g., CPython) despite a slower + asymptotic running time. For Python implementations with optimized + attribute accesses (e.g., PyPy), :class:`PairingHeap` provides better + performance. Default value: :class:`BinaryHeap`. + + Returns + ------- + flowCost : integer + Cost of a minimum cost flow satisfying all demands. + + flowDict : dictionary + If G is a digraph, a dict-of-dicts keyed by nodes such that + flowDict[u][v] is the flow on edge (u, v). + If G is a MultiDiGraph, a dict-of-dicts-of-dicts keyed by nodes + so that flowDict[u][v][key] is the flow on edge (u, v, key). + + Raises + ------ + NetworkXError + This exception is raised if the input graph is not directed, + not connected. + + NetworkXUnfeasible + This exception is raised in the following situations: + + * The sum of the demands is not zero. Then, there is no + flow satisfying all demands. + * There is no flow satisfying all demand. + + NetworkXUnbounded + This exception is raised if the digraph G has a cycle of + negative cost and infinite capacity. Then, the cost of a flow + satisfying all demands is unbounded below. + + Notes + ----- + This algorithm does not work if edge weights are floating-point numbers. + + See also + -------- + :meth:`network_simplex` + + Examples + -------- + A simple example of a min cost flow problem. + + >>> G = nx.DiGraph() + >>> G.add_node("a", demand=-5) + >>> G.add_node("d", demand=5) + >>> G.add_edge("a", "b", weight=3, capacity=4) + >>> G.add_edge("a", "c", weight=6, capacity=10) + >>> G.add_edge("b", "d", weight=1, capacity=9) + >>> G.add_edge("c", "d", weight=2, capacity=5) + >>> flowCost, flowDict = nx.capacity_scaling(G) + >>> flowCost + 24 + >>> flowDict + {'a': {'b': 4, 'c': 1}, 'd': {}, 'b': {'d': 4}, 'c': {'d': 1}} + + It is possible to change the name of the attributes used for the + algorithm. + + >>> G = nx.DiGraph() + >>> G.add_node("p", spam=-4) + >>> G.add_node("q", spam=2) + >>> G.add_node("a", spam=-2) + >>> G.add_node("d", spam=-1) + >>> G.add_node("t", spam=2) + >>> G.add_node("w", spam=3) + >>> G.add_edge("p", "q", cost=7, vacancies=5) + >>> G.add_edge("p", "a", cost=1, vacancies=4) + >>> G.add_edge("q", "d", cost=2, vacancies=3) + >>> G.add_edge("t", "q", cost=1, vacancies=2) + >>> G.add_edge("a", "t", cost=2, vacancies=4) + >>> G.add_edge("d", "w", cost=3, vacancies=4) + >>> G.add_edge("t", "w", cost=4, vacancies=1) + >>> flowCost, flowDict = nx.capacity_scaling( + ... G, demand="spam", capacity="vacancies", weight="cost" + ... ) + >>> flowCost + 37 + >>> flowDict + {'p': {'q': 2, 'a': 2}, 'q': {'d': 1}, 'a': {'t': 4}, 'd': {'w': 2}, 't': {'q': 1, 'w': 1}, 'w': {}} + """ + R = _build_residual_network(G, demand, capacity, weight) + + inf = float("inf") + # Account cost of negative selfloops. + flow_cost = sum( + 0 + if e.get(capacity, inf) <= 0 or e.get(weight, 0) >= 0 + else e[capacity] * e[weight] + for u, v, e in nx.selfloop_edges(G, data=True) + ) + + # Determine the maximum edge capacity. + wmax = max(chain([-inf], (e["capacity"] for u, v, e in R.edges(data=True)))) + if wmax == -inf: + # Residual network has no edges. + return flow_cost, _build_flow_dict(G, R, capacity, weight) + + R_nodes = R.nodes + R_succ = R.succ + + delta = 2 ** int(log(wmax, 2)) + while delta >= 1: + # Saturate Δ-residual edges with negative reduced costs to achieve + # Δ-optimality. + for u in R: + p_u = R_nodes[u]["potential"] + for v, es in R_succ[u].items(): + for k, e in es.items(): + flow = e["capacity"] - e["flow"] + if e["weight"] - p_u + R_nodes[v]["potential"] < 0: + flow = e["capacity"] - e["flow"] + if flow >= delta: + e["flow"] += flow + R_succ[v][u][(k[0], not k[1])]["flow"] -= flow + R_nodes[u]["excess"] -= flow + R_nodes[v]["excess"] += flow + # Determine the Δ-active nodes. + S = set() + T = set() + S_add = S.add + S_remove = S.remove + T_add = T.add + T_remove = T.remove + for u in R: + excess = R_nodes[u]["excess"] + if excess >= delta: + S_add(u) + elif excess <= -delta: + T_add(u) + # Repeatedly augment flow from S to T along shortest paths until + # Δ-feasibility is achieved. + while S and T: + s = arbitrary_element(S) + t = None + # Search for a shortest path in terms of reduce costs from s to + # any t in T in the Δ-residual network. + d = {} + pred = {s: None} + h = heap() + h_insert = h.insert + h_get = h.get + h_insert(s, 0) + while h: + u, d_u = h.pop() + d[u] = d_u + if u in T: + # Path found. + t = u + break + p_u = R_nodes[u]["potential"] + for v, es in R_succ[u].items(): + if v in d: + continue + wmin = inf + # Find the minimum-weighted (u, v) Δ-residual edge. + for k, e in es.items(): + if e["capacity"] - e["flow"] >= delta: + w = e["weight"] + if w < wmin: + wmin = w + kmin = k + emin = e + if wmin == inf: + continue + # Update the distance label of v. + d_v = d_u + wmin - p_u + R_nodes[v]["potential"] + if h_insert(v, d_v): + pred[v] = (u, kmin, emin) + if t is not None: + # Augment Δ units of flow from s to t. + while u != s: + v = u + u, k, e = pred[v] + e["flow"] += delta + R_succ[v][u][(k[0], not k[1])]["flow"] -= delta + # Account node excess and deficit. + R_nodes[s]["excess"] -= delta + R_nodes[t]["excess"] += delta + if R_nodes[s]["excess"] < delta: + S_remove(s) + if R_nodes[t]["excess"] > -delta: + T_remove(t) + # Update node potentials. + d_t = d[t] + for u, d_u in d.items(): + R_nodes[u]["potential"] -= d_u - d_t + else: + # Path not found. + S_remove(s) + delta //= 2 + + if any(R.nodes[u]["excess"] != 0 for u in R): + raise nx.NetworkXUnfeasible("No flow satisfying all demands.") + + # Calculate the flow cost. + for u in R: + for v, es in R_succ[u].items(): + for e in es.values(): + flow = e["flow"] + if flow > 0: + flow_cost += flow * e["weight"] + + return flow_cost, _build_flow_dict(G, R, capacity, weight) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/gomory_hu.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/gomory_hu.py new file mode 100644 index 0000000000000000000000000000000000000000..0be27d5649415b289e3ff4c5fa7f0cc012920bf4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/gomory_hu.py @@ -0,0 +1,177 @@ +""" +Gomory-Hu tree of undirected Graphs. +""" +import networkx as nx +from networkx.utils import not_implemented_for + +from .edmondskarp import edmonds_karp +from .utils import build_residual_network + +default_flow_func = edmonds_karp + +__all__ = ["gomory_hu_tree"] + + +@not_implemented_for("directed") +@nx._dispatch(edge_attrs={"capacity": float("inf")}) +def gomory_hu_tree(G, capacity="capacity", flow_func=None): + r"""Returns the Gomory-Hu tree of an undirected graph G. + + A Gomory-Hu tree of an undirected graph with capacities is a + weighted tree that represents the minimum s-t cuts for all s-t + pairs in the graph. + + It only requires `n-1` minimum cut computations instead of the + obvious `n(n-1)/2`. The tree represents all s-t cuts as the + minimum cut value among any pair of nodes is the minimum edge + weight in the shortest path between the two nodes in the + Gomory-Hu tree. + + The Gomory-Hu tree also has the property that removing the + edge with the minimum weight in the shortest path between + any two nodes leaves two connected components that form + a partition of the nodes in G that defines the minimum s-t + cut. + + See Examples section below for details. + + Parameters + ---------- + G : NetworkX graph + Undirected graph + + capacity : string + Edges of the graph G are expected to have an attribute capacity + that indicates how much flow the edge can support. If this + attribute is not present, the edge is considered to have + infinite capacity. Default value: 'capacity'. + + flow_func : function + Function to perform the underlying flow computations. Default value + :func:`edmonds_karp`. This function performs better in sparse graphs + with right tailed degree distributions. + :func:`shortest_augmenting_path` will perform better in denser + graphs. + + Returns + ------- + Tree : NetworkX graph + A NetworkX graph representing the Gomory-Hu tree of the input graph. + + Raises + ------ + NetworkXNotImplemented + Raised if the input graph is directed. + + NetworkXError + Raised if the input graph is an empty Graph. + + Examples + -------- + >>> G = nx.karate_club_graph() + >>> nx.set_edge_attributes(G, 1, "capacity") + >>> T = nx.gomory_hu_tree(G) + >>> # The value of the minimum cut between any pair + ... # of nodes in G is the minimum edge weight in the + ... # shortest path between the two nodes in the + ... # Gomory-Hu tree. + ... def minimum_edge_weight_in_shortest_path(T, u, v): + ... path = nx.shortest_path(T, u, v, weight="weight") + ... return min((T[u][v]["weight"], (u, v)) for (u, v) in zip(path, path[1:])) + >>> u, v = 0, 33 + >>> cut_value, edge = minimum_edge_weight_in_shortest_path(T, u, v) + >>> cut_value + 10 + >>> nx.minimum_cut_value(G, u, v) + 10 + >>> # The Gomory-Hu tree also has the property that removing the + ... # edge with the minimum weight in the shortest path between + ... # any two nodes leaves two connected components that form + ... # a partition of the nodes in G that defines the minimum s-t + ... # cut. + ... cut_value, edge = minimum_edge_weight_in_shortest_path(T, u, v) + >>> T.remove_edge(*edge) + >>> U, V = list(nx.connected_components(T)) + >>> # Thus U and V form a partition that defines a minimum cut + ... # between u and v in G. You can compute the edge cut set, + ... # that is, the set of edges that if removed from G will + ... # disconnect u from v in G, with this information: + ... cutset = set() + >>> for x, nbrs in ((n, G[n]) for n in U): + ... cutset.update((x, y) for y in nbrs if y in V) + >>> # Because we have set the capacities of all edges to 1 + ... # the cutset contains ten edges + ... len(cutset) + 10 + >>> # You can use any maximum flow algorithm for the underlying + ... # flow computations using the argument flow_func + ... from networkx.algorithms import flow + >>> T = nx.gomory_hu_tree(G, flow_func=flow.boykov_kolmogorov) + >>> cut_value, edge = minimum_edge_weight_in_shortest_path(T, u, v) + >>> cut_value + 10 + >>> nx.minimum_cut_value(G, u, v, flow_func=flow.boykov_kolmogorov) + 10 + + Notes + ----- + This implementation is based on Gusfield approach [1]_ to compute + Gomory-Hu trees, which does not require node contractions and has + the same computational complexity than the original method. + + See also + -------- + :func:`minimum_cut` + :func:`maximum_flow` + + References + ---------- + .. [1] Gusfield D: Very simple methods for all pairs network flow analysis. + SIAM J Comput 19(1):143-155, 1990. + + """ + if flow_func is None: + flow_func = default_flow_func + + if len(G) == 0: # empty graph + msg = "Empty Graph does not have a Gomory-Hu tree representation" + raise nx.NetworkXError(msg) + + # Start the tree as a star graph with an arbitrary node at the center + tree = {} + labels = {} + iter_nodes = iter(G) + root = next(iter_nodes) + for n in iter_nodes: + tree[n] = root + + # Reuse residual network + R = build_residual_network(G, capacity) + + # For all the leaves in the star graph tree (that is n-1 nodes). + for source in tree: + # Find neighbor in the tree + target = tree[source] + # compute minimum cut + cut_value, partition = nx.minimum_cut( + G, source, target, capacity=capacity, flow_func=flow_func, residual=R + ) + labels[(source, target)] = cut_value + # Update the tree + # Source will always be in partition[0] and target in partition[1] + for node in partition[0]: + if node != source and node in tree and tree[node] == target: + tree[node] = source + labels[node, source] = labels.get((node, target), cut_value) + # + if target != root and tree[target] in partition[0]: + labels[source, tree[target]] = labels[target, tree[target]] + labels[target, source] = cut_value + tree[source] = tree[target] + tree[target] = source + + # Build the tree + T = nx.Graph() + T.add_nodes_from(G) + T.add_weighted_edges_from(((u, v, labels[u, v]) for u, v in tree.items())) + return T diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/maxflow.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/maxflow.py new file mode 100644 index 0000000000000000000000000000000000000000..35f359ee3b04ca2d427de2c20666fe53d750f561 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/flow/maxflow.py @@ -0,0 +1,607 @@ +""" +Maximum flow (and minimum cut) algorithms on capacitated graphs. +""" +import networkx as nx + +from .boykovkolmogorov import boykov_kolmogorov +from .dinitz_alg import dinitz +from .edmondskarp import edmonds_karp +from .preflowpush import preflow_push +from .shortestaugmentingpath import shortest_augmenting_path +from .utils import build_flow_dict + +# Define the default flow function for computing maximum flow. +default_flow_func = preflow_push + +__all__ = ["maximum_flow", "maximum_flow_value", "minimum_cut", "minimum_cut_value"] + + +@nx._dispatch(graphs="flowG", edge_attrs={"capacity": float("inf")}) +def maximum_flow(flowG, _s, _t, capacity="capacity", flow_func=None, **kwargs): + """Find a maximum single-commodity flow. + + Parameters + ---------- + flowG : NetworkX graph + Edges of the graph are expected to have an attribute called + 'capacity'. If this attribute is not present, the edge is + considered to have infinite capacity. + + _s : node + Source node for the flow. + + _t : node + Sink node for the flow. + + capacity : string + Edges of the graph G are expected to have an attribute capacity + that indicates how much flow the edge can support. If this + attribute is not present, the edge is considered to have + infinite capacity. Default value: 'capacity'. + + flow_func : function + A function for computing the maximum flow among a pair of nodes + in a capacitated graph. The function has to accept at least three + parameters: a Graph or Digraph, a source node, and a target node. + And return a residual network that follows NetworkX conventions + (see Notes). If flow_func is None, the default maximum + flow function (:meth:`preflow_push`) is used. See below for + alternative algorithms. The choice of the default function may change + from version to version and should not be relied on. Default value: + None. + + kwargs : Any other keyword parameter is passed to the function that + computes the maximum flow. + + Returns + ------- + flow_value : integer, float + Value of the maximum flow, i.e., net outflow from the source. + + flow_dict : dict + A dictionary containing the value of the flow that went through + each edge. + + Raises + ------ + NetworkXError + The algorithm does not support MultiGraph and MultiDiGraph. If + the input graph is an instance of one of these two classes, a + NetworkXError is raised. + + NetworkXUnbounded + If the graph has a path of infinite capacity, the value of a + feasible flow on the graph is unbounded above and the function + raises a NetworkXUnbounded. + + See also + -------- + :meth:`maximum_flow_value` + :meth:`minimum_cut` + :meth:`minimum_cut_value` + :meth:`edmonds_karp` + :meth:`preflow_push` + :meth:`shortest_augmenting_path` + + Notes + ----- + The function used in the flow_func parameter has to return a residual + network that follows NetworkX conventions: + + The residual network :samp:`R` from an input graph :samp:`G` has the + same nodes as :samp:`G`. :samp:`R` is a DiGraph that contains a pair + of edges :samp:`(u, v)` and :samp:`(v, u)` iff :samp:`(u, v)` is not a + self-loop, and at least one of :samp:`(u, v)` and :samp:`(v, u)` exists + in :samp:`G`. + + For each edge :samp:`(u, v)` in :samp:`R`, :samp:`R[u][v]['capacity']` + is equal to the capacity of :samp:`(u, v)` in :samp:`G` if it exists + in :samp:`G` or zero otherwise. If the capacity is infinite, + :samp:`R[u][v]['capacity']` will have a high arbitrary finite value + that does not affect the solution of the problem. This value is stored in + :samp:`R.graph['inf']`. For each edge :samp:`(u, v)` in :samp:`R`, + :samp:`R[u][v]['flow']` represents the flow function of :samp:`(u, v)` and + satisfies :samp:`R[u][v]['flow'] == -R[v][u]['flow']`. + + The flow value, defined as the total flow into :samp:`t`, the sink, is + stored in :samp:`R.graph['flow_value']`. Reachability to :samp:`t` using + only edges :samp:`(u, v)` such that + :samp:`R[u][v]['flow'] < R[u][v]['capacity']` induces a minimum + :samp:`s`-:samp:`t` cut. + + Specific algorithms may store extra data in :samp:`R`. + + The function should supports an optional boolean parameter value_only. When + True, it can optionally terminate the algorithm as soon as the maximum flow + value and the minimum cut can be determined. + + Examples + -------- + >>> G = nx.DiGraph() + >>> G.add_edge("x", "a", capacity=3.0) + >>> G.add_edge("x", "b", capacity=1.0) + >>> G.add_edge("a", "c", capacity=3.0) + >>> G.add_edge("b", "c", capacity=5.0) + >>> G.add_edge("b", "d", capacity=4.0) + >>> G.add_edge("d", "e", capacity=2.0) + >>> G.add_edge("c", "y", capacity=2.0) + >>> G.add_edge("e", "y", capacity=3.0) + + maximum_flow returns both the value of the maximum flow and a + dictionary with all flows. + + >>> flow_value, flow_dict = nx.maximum_flow(G, "x", "y") + >>> flow_value + 3.0 + >>> print(flow_dict["x"]["b"]) + 1.0 + + You can also use alternative algorithms for computing the + maximum flow by using the flow_func parameter. + + >>> from networkx.algorithms.flow import shortest_augmenting_path + >>> flow_value == nx.maximum_flow(G, "x", "y", flow_func=shortest_augmenting_path)[ + ... 0 + ... ] + True + + """ + if flow_func is None: + if kwargs: + raise nx.NetworkXError( + "You have to explicitly set a flow_func if" + " you need to pass parameters via kwargs." + ) + flow_func = default_flow_func + + if not callable(flow_func): + raise nx.NetworkXError("flow_func has to be callable.") + + R = flow_func(flowG, _s, _t, capacity=capacity, value_only=False, **kwargs) + flow_dict = build_flow_dict(flowG, R) + + return (R.graph["flow_value"], flow_dict) + + +@nx._dispatch(graphs="flowG", edge_attrs={"capacity": float("inf")}) +def maximum_flow_value(flowG, _s, _t, capacity="capacity", flow_func=None, **kwargs): + """Find the value of maximum single-commodity flow. + + Parameters + ---------- + flowG : NetworkX graph + Edges of the graph are expected to have an attribute called + 'capacity'. If this attribute is not present, the edge is + considered to have infinite capacity. + + _s : node + Source node for the flow. + + _t : node + Sink node for the flow. + + capacity : string + Edges of the graph G are expected to have an attribute capacity + that indicates how much flow the edge can support. If this + attribute is not present, the edge is considered to have + infinite capacity. Default value: 'capacity'. + + flow_func : function + A function for computing the maximum flow among a pair of nodes + in a capacitated graph. The function has to accept at least three + parameters: a Graph or Digraph, a source node, and a target node. + And return a residual network that follows NetworkX conventions + (see Notes). If flow_func is None, the default maximum + flow function (:meth:`preflow_push`) is used. See below for + alternative algorithms. The choice of the default function may change + from version to version and should not be relied on. Default value: + None. + + kwargs : Any other keyword parameter is passed to the function that + computes the maximum flow. + + Returns + ------- + flow_value : integer, float + Value of the maximum flow, i.e., net outflow from the source. + + Raises + ------ + NetworkXError + The algorithm does not support MultiGraph and MultiDiGraph. If + the input graph is an instance of one of these two classes, a + NetworkXError is raised. + + NetworkXUnbounded + If the graph has a path of infinite capacity, the value of a + feasible flow on the graph is unbounded above and the function + raises a NetworkXUnbounded. + + See also + -------- + :meth:`maximum_flow` + :meth:`minimum_cut` + :meth:`minimum_cut_value` + :meth:`edmonds_karp` + :meth:`preflow_push` + :meth:`shortest_augmenting_path` + + Notes + ----- + The function used in the flow_func parameter has to return a residual + network that follows NetworkX conventions: + + The residual network :samp:`R` from an input graph :samp:`G` has the + same nodes as :samp:`G`. :samp:`R` is a DiGraph that contains a pair + of edges :samp:`(u, v)` and :samp:`(v, u)` iff :samp:`(u, v)` is not a + self-loop, and at least one of :samp:`(u, v)` and :samp:`(v, u)` exists + in :samp:`G`. + + For each edge :samp:`(u, v)` in :samp:`R`, :samp:`R[u][v]['capacity']` + is equal to the capacity of :samp:`(u, v)` in :samp:`G` if it exists + in :samp:`G` or zero otherwise. If the capacity is infinite, + :samp:`R[u][v]['capacity']` will have a high arbitrary finite value + that does not affect the solution of the problem. This value is stored in + :samp:`R.graph['inf']`. For each edge :samp:`(u, v)` in :samp:`R`, + :samp:`R[u][v]['flow']` represents the flow function of :samp:`(u, v)` and + satisfies :samp:`R[u][v]['flow'] == -R[v][u]['flow']`. + + The flow value, defined as the total flow into :samp:`t`, the sink, is + stored in :samp:`R.graph['flow_value']`. Reachability to :samp:`t` using + only edges :samp:`(u, v)` such that + :samp:`R[u][v]['flow'] < R[u][v]['capacity']` induces a minimum + :samp:`s`-:samp:`t` cut. + + Specific algorithms may store extra data in :samp:`R`. + + The function should supports an optional boolean parameter value_only. When + True, it can optionally terminate the algorithm as soon as the maximum flow + value and the minimum cut can be determined. + + Examples + -------- + >>> G = nx.DiGraph() + >>> G.add_edge("x", "a", capacity=3.0) + >>> G.add_edge("x", "b", capacity=1.0) + >>> G.add_edge("a", "c", capacity=3.0) + >>> G.add_edge("b", "c", capacity=5.0) + >>> G.add_edge("b", "d", capacity=4.0) + >>> G.add_edge("d", "e", capacity=2.0) + >>> G.add_edge("c", "y", capacity=2.0) + >>> G.add_edge("e", "y", capacity=3.0) + + maximum_flow_value computes only the value of the + maximum flow: + + >>> flow_value = nx.maximum_flow_value(G, "x", "y") + >>> flow_value + 3.0 + + You can also use alternative algorithms for computing the + maximum flow by using the flow_func parameter. + + >>> from networkx.algorithms.flow import shortest_augmenting_path + >>> flow_value == nx.maximum_flow_value( + ... G, "x", "y", flow_func=shortest_augmenting_path + ... ) + True + + """ + if flow_func is None: + if kwargs: + raise nx.NetworkXError( + "You have to explicitly set a flow_func if" + " you need to pass parameters via kwargs." + ) + flow_func = default_flow_func + + if not callable(flow_func): + raise nx.NetworkXError("flow_func has to be callable.") + + R = flow_func(flowG, _s, _t, capacity=capacity, value_only=True, **kwargs) + + return R.graph["flow_value"] + + +@nx._dispatch(graphs="flowG", edge_attrs={"capacity": float("inf")}) +def minimum_cut(flowG, _s, _t, capacity="capacity", flow_func=None, **kwargs): + """Compute the value and the node partition of a minimum (s, t)-cut. + + Use the max-flow min-cut theorem, i.e., the capacity of a minimum + capacity cut is equal to the flow value of a maximum flow. + + Parameters + ---------- + flowG : NetworkX graph + Edges of the graph are expected to have an attribute called + 'capacity'. If this attribute is not present, the edge is + considered to have infinite capacity. + + _s : node + Source node for the flow. + + _t : node + Sink node for the flow. + + capacity : string + Edges of the graph G are expected to have an attribute capacity + that indicates how much flow the edge can support. If this + attribute is not present, the edge is considered to have + infinite capacity. Default value: 'capacity'. + + flow_func : function + A function for computing the maximum flow among a pair of nodes + in a capacitated graph. The function has to accept at least three + parameters: a Graph or Digraph, a source node, and a target node. + And return a residual network that follows NetworkX conventions + (see Notes). If flow_func is None, the default maximum + flow function (:meth:`preflow_push`) is used. See below for + alternative algorithms. The choice of the default function may change + from version to version and should not be relied on. Default value: + None. + + kwargs : Any other keyword parameter is passed to the function that + computes the maximum flow. + + Returns + ------- + cut_value : integer, float + Value of the minimum cut. + + partition : pair of node sets + A partitioning of the nodes that defines a minimum cut. + + Raises + ------ + NetworkXUnbounded + If the graph has a path of infinite capacity, all cuts have + infinite capacity and the function raises a NetworkXError. + + See also + -------- + :meth:`maximum_flow` + :meth:`maximum_flow_value` + :meth:`minimum_cut_value` + :meth:`edmonds_karp` + :meth:`preflow_push` + :meth:`shortest_augmenting_path` + + Notes + ----- + The function used in the flow_func parameter has to return a residual + network that follows NetworkX conventions: + + The residual network :samp:`R` from an input graph :samp:`G` has the + same nodes as :samp:`G`. :samp:`R` is a DiGraph that contains a pair + of edges :samp:`(u, v)` and :samp:`(v, u)` iff :samp:`(u, v)` is not a + self-loop, and at least one of :samp:`(u, v)` and :samp:`(v, u)` exists + in :samp:`G`. + + For each edge :samp:`(u, v)` in :samp:`R`, :samp:`R[u][v]['capacity']` + is equal to the capacity of :samp:`(u, v)` in :samp:`G` if it exists + in :samp:`G` or zero otherwise. If the capacity is infinite, + :samp:`R[u][v]['capacity']` will have a high arbitrary finite value + that does not affect the solution of the problem. This value is stored in + :samp:`R.graph['inf']`. For each edge :samp:`(u, v)` in :samp:`R`, + :samp:`R[u][v]['flow']` represents the flow function of :samp:`(u, v)` and + satisfies :samp:`R[u][v]['flow'] == -R[v][u]['flow']`. + + The flow value, defined as the total flow into :samp:`t`, the sink, is + stored in :samp:`R.graph['flow_value']`. Reachability to :samp:`t` using + only edges :samp:`(u, v)` such that + :samp:`R[u][v]['flow'] < R[u][v]['capacity']` induces a minimum + :samp:`s`-:samp:`t` cut. + + Specific algorithms may store extra data in :samp:`R`. + + The function should supports an optional boolean parameter value_only. When + True, it can optionally terminate the algorithm as soon as the maximum flow + value and the minimum cut can be determined. + + Examples + -------- + >>> G = nx.DiGraph() + >>> G.add_edge("x", "a", capacity=3.0) + >>> G.add_edge("x", "b", capacity=1.0) + >>> G.add_edge("a", "c", capacity=3.0) + >>> G.add_edge("b", "c", capacity=5.0) + >>> G.add_edge("b", "d", capacity=4.0) + >>> G.add_edge("d", "e", capacity=2.0) + >>> G.add_edge("c", "y", capacity=2.0) + >>> G.add_edge("e", "y", capacity=3.0) + + minimum_cut computes both the value of the + minimum cut and the node partition: + + >>> cut_value, partition = nx.minimum_cut(G, "x", "y") + >>> reachable, non_reachable = partition + + 'partition' here is a tuple with the two sets of nodes that define + the minimum cut. You can compute the cut set of edges that induce + the minimum cut as follows: + + >>> cutset = set() + >>> for u, nbrs in ((n, G[n]) for n in reachable): + ... cutset.update((u, v) for v in nbrs if v in non_reachable) + >>> print(sorted(cutset)) + [('c', 'y'), ('x', 'b')] + >>> cut_value == sum(G.edges[u, v]["capacity"] for (u, v) in cutset) + True + + You can also use alternative algorithms for computing the + minimum cut by using the flow_func parameter. + + >>> from networkx.algorithms.flow import shortest_augmenting_path + >>> cut_value == nx.minimum_cut(G, "x", "y", flow_func=shortest_augmenting_path)[0] + True + + """ + if flow_func is None: + if kwargs: + raise nx.NetworkXError( + "You have to explicitly set a flow_func if" + " you need to pass parameters via kwargs." + ) + flow_func = default_flow_func + + if not callable(flow_func): + raise nx.NetworkXError("flow_func has to be callable.") + + if kwargs.get("cutoff") is not None and flow_func is preflow_push: + raise nx.NetworkXError("cutoff should not be specified.") + + R = flow_func(flowG, _s, _t, capacity=capacity, value_only=True, **kwargs) + # Remove saturated edges from the residual network + cutset = [(u, v, d) for u, v, d in R.edges(data=True) if d["flow"] == d["capacity"]] + R.remove_edges_from(cutset) + + # Then, reachable and non reachable nodes from source in the + # residual network form the node partition that defines + # the minimum cut. + non_reachable = set(dict(nx.shortest_path_length(R, target=_t))) + partition = (set(flowG) - non_reachable, non_reachable) + # Finally add again cutset edges to the residual network to make + # sure that it is reusable. + if cutset is not None: + R.add_edges_from(cutset) + return (R.graph["flow_value"], partition) + + +@nx._dispatch(graphs="flowG", edge_attrs={"capacity": float("inf")}) +def minimum_cut_value(flowG, _s, _t, capacity="capacity", flow_func=None, **kwargs): + """Compute the value of a minimum (s, t)-cut. + + Use the max-flow min-cut theorem, i.e., the capacity of a minimum + capacity cut is equal to the flow value of a maximum flow. + + Parameters + ---------- + flowG : NetworkX graph + Edges of the graph are expected to have an attribute called + 'capacity'. If this attribute is not present, the edge is + considered to have infinite capacity. + + _s : node + Source node for the flow. + + _t : node + Sink node for the flow. + + capacity : string + Edges of the graph G are expected to have an attribute capacity + that indicates how much flow the edge can support. If this + attribute is not present, the edge is considered to have + infinite capacity. Default value: 'capacity'. + + flow_func : function + A function for computing the maximum flow among a pair of nodes + in a capacitated graph. The function has to accept at least three + parameters: a Graph or Digraph, a source node, and a target node. + And return a residual network that follows NetworkX conventions + (see Notes). If flow_func is None, the default maximum + flow function (:meth:`preflow_push`) is used. See below for + alternative algorithms. The choice of the default function may change + from version to version and should not be relied on. Default value: + None. + + kwargs : Any other keyword parameter is passed to the function that + computes the maximum flow. + + Returns + ------- + cut_value : integer, float + Value of the minimum cut. + + Raises + ------ + NetworkXUnbounded + If the graph has a path of infinite capacity, all cuts have + infinite capacity and the function raises a NetworkXError. + + See also + -------- + :meth:`maximum_flow` + :meth:`maximum_flow_value` + :meth:`minimum_cut` + :meth:`edmonds_karp` + :meth:`preflow_push` + :meth:`shortest_augmenting_path` + + Notes + ----- + The function used in the flow_func parameter has to return a residual + network that follows NetworkX conventions: + + The residual network :samp:`R` from an input graph :samp:`G` has the + same nodes as :samp:`G`. :samp:`R` is a DiGraph that contains a pair + of edges :samp:`(u, v)` and :samp:`(v, u)` iff :samp:`(u, v)` is not a + self-loop, and at least one of :samp:`(u, v)` and :samp:`(v, u)` exists + in :samp:`G`. + + For each edge :samp:`(u, v)` in :samp:`R`, :samp:`R[u][v]['capacity']` + is equal to the capacity of :samp:`(u, v)` in :samp:`G` if it exists + in :samp:`G` or zero otherwise. If the capacity is infinite, + :samp:`R[u][v]['capacity']` will have a high arbitrary finite value + that does not affect the solution of the problem. This value is stored in + :samp:`R.graph['inf']`. For each edge :samp:`(u, v)` in :samp:`R`, + :samp:`R[u][v]['flow']` represents the flow function of :samp:`(u, v)` and + satisfies :samp:`R[u][v]['flow'] == -R[v][u]['flow']`. + + The flow value, defined as the total flow into :samp:`t`, the sink, is + stored in :samp:`R.graph['flow_value']`. Reachability to :samp:`t` using + only edges :samp:`(u, v)` such that + :samp:`R[u][v]['flow'] < R[u][v]['capacity']` induces a minimum + :samp:`s`-:samp:`t` cut. + + Specific algorithms may store extra data in :samp:`R`. + + The function should supports an optional boolean parameter value_only. When + True, it can optionally terminate the algorithm as soon as the maximum flow + value and the minimum cut can be determined. + + Examples + -------- + >>> G = nx.DiGraph() + >>> G.add_edge("x", "a", capacity=3.0) + >>> G.add_edge("x", "b", capacity=1.0) + >>> G.add_edge("a", "c", capacity=3.0) + >>> G.add_edge("b", "c", capacity=5.0) + >>> G.add_edge("b", "d", capacity=4.0) + >>> G.add_edge("d", "e", capacity=2.0) + >>> G.add_edge("c", "y", capacity=2.0) + >>> G.add_edge("e", "y", capacity=3.0) + + minimum_cut_value computes only the value of the + minimum cut: + + >>> cut_value = nx.minimum_cut_value(G, "x", "y") + >>> cut_value + 3.0 + + You can also use alternative algorithms for computing the + minimum cut by using the flow_func parameter. + + >>> from networkx.algorithms.flow import shortest_augmenting_path + >>> cut_value == nx.minimum_cut_value( + ... G, "x", "y", flow_func=shortest_augmenting_path + ... ) + True + + """ + if flow_func is None: + if kwargs: + raise nx.NetworkXError( + "You have to explicitly set a flow_func if" + " you need to pass parameters via kwargs." + ) + flow_func = default_flow_func + + if not callable(flow_func): + raise nx.NetworkXError("flow_func has to be callable.") + + if kwargs.get("cutoff") is not None and flow_func is preflow_push: + raise nx.NetworkXError("cutoff should not be specified.") + + R = flow_func(flowG, _s, _t, capacity=capacity, value_only=True, **kwargs) + + return R.graph["flow_value"] diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/link_analysis/tests/__init__.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/link_analysis/tests/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/polynomials.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/polynomials.py new file mode 100644 index 0000000000000000000000000000000000000000..57ecf0d09a976df4cc909d1ac9f0fe8780f66f32 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/polynomials.py @@ -0,0 +1,305 @@ +"""Provides algorithms supporting the computation of graph polynomials. + +Graph polynomials are polynomial-valued graph invariants that encode a wide +variety of structural information. Examples include the Tutte polynomial, +chromatic polynomial, characteristic polynomial, and matching polynomial. An +extensive treatment is provided in [1]_. + +For a simple example, the `~sympy.matrices.matrices.MatrixDeterminant.charpoly` +method can be used to compute the characteristic polynomial from the adjacency +matrix of a graph. Consider the complete graph ``K_4``: + +>>> import sympy +>>> x = sympy.Symbol("x") +>>> G = nx.complete_graph(4) +>>> A = nx.adjacency_matrix(G) +>>> M = sympy.SparseMatrix(A.todense()) +>>> M.charpoly(x).as_expr() +x**4 - 6*x**2 - 8*x - 3 + + +.. [1] Y. Shi, M. Dehmer, X. Li, I. Gutman, + "Graph Polynomials" +""" +from collections import deque + +import networkx as nx +from networkx.utils import not_implemented_for + +__all__ = ["tutte_polynomial", "chromatic_polynomial"] + + +@not_implemented_for("directed") +@nx._dispatch +def tutte_polynomial(G): + r"""Returns the Tutte polynomial of `G` + + This function computes the Tutte polynomial via an iterative version of + the deletion-contraction algorithm. + + The Tutte polynomial `T_G(x, y)` is a fundamental graph polynomial invariant in + two variables. It encodes a wide array of information related to the + edge-connectivity of a graph; "Many problems about graphs can be reduced to + problems of finding and evaluating the Tutte polynomial at certain values" [1]_. + In fact, every deletion-contraction-expressible feature of a graph is a + specialization of the Tutte polynomial [2]_ (see Notes for examples). + + There are several equivalent definitions; here are three: + + Def 1 (rank-nullity expansion): For `G` an undirected graph, `n(G)` the + number of vertices of `G`, `E` the edge set of `G`, `V` the vertex set of + `G`, and `c(A)` the number of connected components of the graph with vertex + set `V` and edge set `A` [3]_: + + .. math:: + + T_G(x, y) = \sum_{A \in E} (x-1)^{c(A) - c(E)} (y-1)^{c(A) + |A| - n(G)} + + Def 2 (spanning tree expansion): Let `G` be an undirected graph, `T` a spanning + tree of `G`, and `E` the edge set of `G`. Let `E` have an arbitrary strict + linear order `L`. Let `B_e` be the unique minimal nonempty edge cut of + $E \setminus T \cup {e}$. An edge `e` is internally active with respect to + `T` and `L` if `e` is the least edge in `B_e` according to the linear order + `L`. The internal activity of `T` (denoted `i(T)`) is the number of edges + in $E \setminus T$ that are internally active with respect to `T` and `L`. + Let `P_e` be the unique path in $T \cup {e}$ whose source and target vertex + are the same. An edge `e` is externally active with respect to `T` and `L` + if `e` is the least edge in `P_e` according to the linear order `L`. The + external activity of `T` (denoted `e(T)`) is the number of edges in + $E \setminus T$ that are externally active with respect to `T` and `L`. + Then [4]_ [5]_: + + .. math:: + + T_G(x, y) = \sum_{T \text{ a spanning tree of } G} x^{i(T)} y^{e(T)} + + Def 3 (deletion-contraction recurrence): For `G` an undirected graph, `G-e` + the graph obtained from `G` by deleting edge `e`, `G/e` the graph obtained + from `G` by contracting edge `e`, `k(G)` the number of cut-edges of `G`, + and `l(G)` the number of self-loops of `G`: + + .. math:: + T_G(x, y) = \begin{cases} + x^{k(G)} y^{l(G)}, & \text{if all edges are cut-edges or self-loops} \\ + T_{G-e}(x, y) + T_{G/e}(x, y), & \text{otherwise, for an arbitrary edge $e$ not a cut-edge or loop} + \end{cases} + + Parameters + ---------- + G : NetworkX graph + + Returns + ------- + instance of `sympy.core.add.Add` + A Sympy expression representing the Tutte polynomial for `G`. + + Examples + -------- + >>> C = nx.cycle_graph(5) + >>> nx.tutte_polynomial(C) + x**4 + x**3 + x**2 + x + y + + >>> D = nx.diamond_graph() + >>> nx.tutte_polynomial(D) + x**3 + 2*x**2 + 2*x*y + x + y**2 + y + + Notes + ----- + Some specializations of the Tutte polynomial: + + - `T_G(1, 1)` counts the number of spanning trees of `G` + - `T_G(1, 2)` counts the number of connected spanning subgraphs of `G` + - `T_G(2, 1)` counts the number of spanning forests in `G` + - `T_G(0, 2)` counts the number of strong orientations of `G` + - `T_G(2, 0)` counts the number of acyclic orientations of `G` + + Edge contraction is defined and deletion-contraction is introduced in [6]_. + Combinatorial meaning of the coefficients is introduced in [7]_. + Universality, properties, and applications are discussed in [8]_. + + Practically, up-front computation of the Tutte polynomial may be useful when + users wish to repeatedly calculate edge-connectivity-related information + about one or more graphs. + + References + ---------- + .. [1] M. Brandt, + "The Tutte Polynomial." + Talking About Combinatorial Objects Seminar, 2015 + https://math.berkeley.edu/~brandtm/talks/tutte.pdf + .. [2] A. Björklund, T. Husfeldt, P. Kaski, M. Koivisto, + "Computing the Tutte polynomial in vertex-exponential time" + 49th Annual IEEE Symposium on Foundations of Computer Science, 2008 + https://ieeexplore.ieee.org/abstract/document/4691000 + .. [3] Y. Shi, M. Dehmer, X. Li, I. Gutman, + "Graph Polynomials," p. 14 + .. [4] Y. Shi, M. Dehmer, X. Li, I. Gutman, + "Graph Polynomials," p. 46 + .. [5] A. Nešetril, J. Goodall, + "Graph invariants, homomorphisms, and the Tutte polynomial" + https://iuuk.mff.cuni.cz/~andrew/Tutte.pdf + .. [6] D. B. West, + "Introduction to Graph Theory," p. 84 + .. [7] G. Coutinho, + "A brief introduction to the Tutte polynomial" + Structural Analysis of Complex Networks, 2011 + https://homepages.dcc.ufmg.br/~gabriel/seminars/coutinho_tuttepolynomial_seminar.pdf + .. [8] J. A. Ellis-Monaghan, C. Merino, + "Graph polynomials and their applications I: The Tutte polynomial" + Structural Analysis of Complex Networks, 2011 + https://arxiv.org/pdf/0803.3079.pdf + """ + import sympy + + x = sympy.Symbol("x") + y = sympy.Symbol("y") + stack = deque() + stack.append(nx.MultiGraph(G)) + + polynomial = 0 + while stack: + G = stack.pop() + bridges = set(nx.bridges(G)) + + e = None + for i in G.edges: + if (i[0], i[1]) not in bridges and i[0] != i[1]: + e = i + break + if not e: + loops = list(nx.selfloop_edges(G, keys=True)) + polynomial += x ** len(bridges) * y ** len(loops) + else: + # deletion-contraction + C = nx.contracted_edge(G, e, self_loops=True) + C.remove_edge(e[0], e[0]) + G.remove_edge(*e) + stack.append(G) + stack.append(C) + return sympy.simplify(polynomial) + + +@not_implemented_for("directed") +@nx._dispatch +def chromatic_polynomial(G): + r"""Returns the chromatic polynomial of `G` + + This function computes the chromatic polynomial via an iterative version of + the deletion-contraction algorithm. + + The chromatic polynomial `X_G(x)` is a fundamental graph polynomial + invariant in one variable. Evaluating `X_G(k)` for an natural number `k` + enumerates the proper k-colorings of `G`. + + There are several equivalent definitions; here are three: + + Def 1 (explicit formula): + For `G` an undirected graph, `c(G)` the number of connected components of + `G`, `E` the edge set of `G`, and `G(S)` the spanning subgraph of `G` with + edge set `S` [1]_: + + .. math:: + + X_G(x) = \sum_{S \subseteq E} (-1)^{|S|} x^{c(G(S))} + + + Def 2 (interpolating polynomial): + For `G` an undirected graph, `n(G)` the number of vertices of `G`, `k_0 = 0`, + and `k_i` the number of distinct ways to color the vertices of `G` with `i` + unique colors (for `i` a natural number at most `n(G)`), `X_G(x)` is the + unique Lagrange interpolating polynomial of degree `n(G)` through the points + `(0, k_0), (1, k_1), \dots, (n(G), k_{n(G)})` [2]_. + + + Def 3 (chromatic recurrence): + For `G` an undirected graph, `G-e` the graph obtained from `G` by deleting + edge `e`, `G/e` the graph obtained from `G` by contracting edge `e`, `n(G)` + the number of vertices of `G`, and `e(G)` the number of edges of `G` [3]_: + + .. math:: + X_G(x) = \begin{cases} + x^{n(G)}, & \text{if $e(G)=0$} \\ + X_{G-e}(x) - X_{G/e}(x), & \text{otherwise, for an arbitrary edge $e$} + \end{cases} + + This formulation is also known as the Fundamental Reduction Theorem [4]_. + + + Parameters + ---------- + G : NetworkX graph + + Returns + ------- + instance of `sympy.core.add.Add` + A Sympy expression representing the chromatic polynomial for `G`. + + Examples + -------- + >>> C = nx.cycle_graph(5) + >>> nx.chromatic_polynomial(C) + x**5 - 5*x**4 + 10*x**3 - 10*x**2 + 4*x + + >>> G = nx.complete_graph(4) + >>> nx.chromatic_polynomial(G) + x**4 - 6*x**3 + 11*x**2 - 6*x + + Notes + ----- + Interpretation of the coefficients is discussed in [5]_. Several special + cases are listed in [2]_. + + The chromatic polynomial is a specialization of the Tutte polynomial; in + particular, ``X_G(x) = T_G(x, 0)`` [6]_. + + The chromatic polynomial may take negative arguments, though evaluations + may not have chromatic interpretations. For instance, ``X_G(-1)`` enumerates + the acyclic orientations of `G` [7]_. + + References + ---------- + .. [1] D. B. West, + "Introduction to Graph Theory," p. 222 + .. [2] E. W. Weisstein + "Chromatic Polynomial" + MathWorld--A Wolfram Web Resource + https://mathworld.wolfram.com/ChromaticPolynomial.html + .. [3] D. B. West, + "Introduction to Graph Theory," p. 221 + .. [4] J. Zhang, J. Goodall, + "An Introduction to Chromatic Polynomials" + https://math.mit.edu/~apost/courses/18.204_2018/Julie_Zhang_paper.pdf + .. [5] R. C. Read, + "An Introduction to Chromatic Polynomials" + Journal of Combinatorial Theory, 1968 + https://math.berkeley.edu/~mrklug/ReadChromatic.pdf + .. [6] W. T. Tutte, + "Graph-polynomials" + Advances in Applied Mathematics, 2004 + https://www.sciencedirect.com/science/article/pii/S0196885803000411 + .. [7] R. P. Stanley, + "Acyclic orientations of graphs" + Discrete Mathematics, 2006 + https://math.mit.edu/~rstan/pubs/pubfiles/18.pdf + """ + import sympy + + x = sympy.Symbol("x") + stack = deque() + stack.append(nx.MultiGraph(G, contraction_idx=0)) + + polynomial = 0 + while stack: + G = stack.pop() + edges = list(G.edges) + if not edges: + polynomial += (-1) ** G.graph["contraction_idx"] * x ** len(G) + else: + e = edges[0] + C = nx.contracted_edge(G, e, self_loops=True) + C.graph["contraction_idx"] = G.graph["contraction_idx"] + 1 + C.remove_edge(e[0], e[0]) + G.remove_edge(*e) + stack.append(G) + stack.append(C) + return polynomial diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__init__.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/__init__.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cce4cd36f666509638acf40ae939e1e60d84fa80 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/__init__.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/test_astar.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/test_astar.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..69cbb3b7d93b94b62b3557a3391707cbf9dccc47 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/test_astar.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/test_dense_numpy.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/test_dense_numpy.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a57a5dbe5df9450c4a17d6b7fe11466449489db4 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/__pycache__/test_dense_numpy.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/test_dense.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/test_dense.py new file mode 100644 index 0000000000000000000000000000000000000000..6923bfef856c83bd3e65573b97fe96ff16cdbc71 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/test_dense.py @@ -0,0 +1,212 @@ +import pytest + +import networkx as nx + + +class TestFloyd: + @classmethod + def setup_class(cls): + pass + + def test_floyd_warshall_predecessor_and_distance(self): + XG = nx.DiGraph() + XG.add_weighted_edges_from( + [ + ("s", "u", 10), + ("s", "x", 5), + ("u", "v", 1), + ("u", "x", 2), + ("v", "y", 1), + ("x", "u", 3), + ("x", "v", 5), + ("x", "y", 2), + ("y", "s", 7), + ("y", "v", 6), + ] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(XG) + assert dist["s"]["v"] == 9 + assert path["s"]["v"] == "u" + assert dist == { + "y": {"y": 0, "x": 12, "s": 7, "u": 15, "v": 6}, + "x": {"y": 2, "x": 0, "s": 9, "u": 3, "v": 4}, + "s": {"y": 7, "x": 5, "s": 0, "u": 8, "v": 9}, + "u": {"y": 2, "x": 2, "s": 9, "u": 0, "v": 1}, + "v": {"y": 1, "x": 13, "s": 8, "u": 16, "v": 0}, + } + + GG = XG.to_undirected() + # make sure we get lower weight + # to_undirected might choose either edge with weight 2 or weight 3 + GG["u"]["x"]["weight"] = 2 + path, dist = nx.floyd_warshall_predecessor_and_distance(GG) + assert dist["s"]["v"] == 8 + # skip this test, could be alternate path s-u-v + # assert_equal(path['s']['v'],'y') + + G = nx.DiGraph() # no weights + G.add_edges_from( + [ + ("s", "u"), + ("s", "x"), + ("u", "v"), + ("u", "x"), + ("v", "y"), + ("x", "u"), + ("x", "v"), + ("x", "y"), + ("y", "s"), + ("y", "v"), + ] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(G) + assert dist["s"]["v"] == 2 + # skip this test, could be alternate path s-u-v + # assert_equal(path['s']['v'],'x') + + # alternate interface + dist = nx.floyd_warshall(G) + assert dist["s"]["v"] == 2 + + # floyd_warshall_predecessor_and_distance returns + # dicts-of-defautdicts + # make sure we don't get empty dictionary + XG = nx.DiGraph() + XG.add_weighted_edges_from( + [("v", "x", 5.0), ("y", "x", 5.0), ("v", "y", 6.0), ("x", "u", 2.0)] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(XG) + inf = float("inf") + assert dist == { + "v": {"v": 0, "x": 5.0, "y": 6.0, "u": 7.0}, + "x": {"x": 0, "u": 2.0, "v": inf, "y": inf}, + "y": {"y": 0, "x": 5.0, "v": inf, "u": 7.0}, + "u": {"u": 0, "v": inf, "x": inf, "y": inf}, + } + assert path == { + "v": {"x": "v", "y": "v", "u": "x"}, + "x": {"u": "x"}, + "y": {"x": "y", "u": "x"}, + } + + def test_reconstruct_path(self): + with pytest.raises(KeyError): + XG = nx.DiGraph() + XG.add_weighted_edges_from( + [ + ("s", "u", 10), + ("s", "x", 5), + ("u", "v", 1), + ("u", "x", 2), + ("v", "y", 1), + ("x", "u", 3), + ("x", "v", 5), + ("x", "y", 2), + ("y", "s", 7), + ("y", "v", 6), + ] + ) + predecessors, _ = nx.floyd_warshall_predecessor_and_distance(XG) + + path = nx.reconstruct_path("s", "v", predecessors) + assert path == ["s", "x", "u", "v"] + + path = nx.reconstruct_path("s", "s", predecessors) + assert path == [] + + # this part raises the keyError + nx.reconstruct_path("1", "2", predecessors) + + def test_cycle(self): + path, dist = nx.floyd_warshall_predecessor_and_distance(nx.cycle_graph(7)) + assert dist[0][3] == 3 + assert path[0][3] == 2 + assert dist[0][4] == 3 + + def test_weighted(self): + XG3 = nx.Graph() + XG3.add_weighted_edges_from( + [[0, 1, 2], [1, 2, 12], [2, 3, 1], [3, 4, 5], [4, 5, 1], [5, 0, 10]] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(XG3) + assert dist[0][3] == 15 + assert path[0][3] == 2 + + def test_weighted2(self): + XG4 = nx.Graph() + XG4.add_weighted_edges_from( + [ + [0, 1, 2], + [1, 2, 2], + [2, 3, 1], + [3, 4, 1], + [4, 5, 1], + [5, 6, 1], + [6, 7, 1], + [7, 0, 1], + ] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(XG4) + assert dist[0][2] == 4 + assert path[0][2] == 1 + + def test_weight_parameter(self): + XG4 = nx.Graph() + XG4.add_edges_from( + [ + (0, 1, {"heavy": 2}), + (1, 2, {"heavy": 2}), + (2, 3, {"heavy": 1}), + (3, 4, {"heavy": 1}), + (4, 5, {"heavy": 1}), + (5, 6, {"heavy": 1}), + (6, 7, {"heavy": 1}), + (7, 0, {"heavy": 1}), + ] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(XG4, weight="heavy") + assert dist[0][2] == 4 + assert path[0][2] == 1 + + def test_zero_distance(self): + XG = nx.DiGraph() + XG.add_weighted_edges_from( + [ + ("s", "u", 10), + ("s", "x", 5), + ("u", "v", 1), + ("u", "x", 2), + ("v", "y", 1), + ("x", "u", 3), + ("x", "v", 5), + ("x", "y", 2), + ("y", "s", 7), + ("y", "v", 6), + ] + ) + path, dist = nx.floyd_warshall_predecessor_and_distance(XG) + + for u in XG: + assert dist[u][u] == 0 + + GG = XG.to_undirected() + # make sure we get lower weight + # to_undirected might choose either edge with weight 2 or weight 3 + GG["u"]["x"]["weight"] = 2 + path, dist = nx.floyd_warshall_predecessor_and_distance(GG) + + for u in GG: + dist[u][u] = 0 + + def test_zero_weight(self): + G = nx.DiGraph() + edges = [(1, 2, -2), (2, 3, -4), (1, 5, 1), (5, 4, 0), (4, 3, -5), (2, 5, -7)] + G.add_weighted_edges_from(edges) + dist = nx.floyd_warshall(G) + assert dist[1][3] == -14 + + G = nx.MultiDiGraph() + edges.append((2, 5, -7)) + G.add_weighted_edges_from(edges) + dist = nx.floyd_warshall(G) + assert dist[1][3] == -14 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/test_generic.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/test_generic.py new file mode 100644 index 0000000000000000000000000000000000000000..9cf7e7a50c4ea80f7a37c5a82291671e003f3efe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/shortest_paths/tests/test_generic.py @@ -0,0 +1,444 @@ +import pytest + +import networkx as nx + + +def validate_grid_path(r, c, s, t, p): + assert isinstance(p, list) + assert p[0] == s + assert p[-1] == t + s = ((s - 1) // c, (s - 1) % c) + t = ((t - 1) // c, (t - 1) % c) + assert len(p) == abs(t[0] - s[0]) + abs(t[1] - s[1]) + 1 + p = [((u - 1) // c, (u - 1) % c) for u in p] + for u in p: + assert 0 <= u[0] < r + assert 0 <= u[1] < c + for u, v in zip(p[:-1], p[1:]): + assert (abs(v[0] - u[0]), abs(v[1] - u[1])) in [(0, 1), (1, 0)] + + +class TestGenericPath: + @classmethod + def setup_class(cls): + from networkx import convert_node_labels_to_integers as cnlti + + cls.grid = cnlti(nx.grid_2d_graph(4, 4), first_label=1, ordering="sorted") + cls.cycle = nx.cycle_graph(7) + cls.directed_cycle = nx.cycle_graph(7, create_using=nx.DiGraph()) + cls.neg_weights = nx.DiGraph() + cls.neg_weights.add_edge(0, 1, weight=1) + cls.neg_weights.add_edge(0, 2, weight=3) + cls.neg_weights.add_edge(1, 3, weight=1) + cls.neg_weights.add_edge(2, 3, weight=-2) + + def test_shortest_path(self): + assert nx.shortest_path(self.cycle, 0, 3) == [0, 1, 2, 3] + assert nx.shortest_path(self.cycle, 0, 4) == [0, 6, 5, 4] + validate_grid_path(4, 4, 1, 12, nx.shortest_path(self.grid, 1, 12)) + assert nx.shortest_path(self.directed_cycle, 0, 3) == [0, 1, 2, 3] + # now with weights + assert nx.shortest_path(self.cycle, 0, 3, weight="weight") == [0, 1, 2, 3] + assert nx.shortest_path(self.cycle, 0, 4, weight="weight") == [0, 6, 5, 4] + validate_grid_path( + 4, 4, 1, 12, nx.shortest_path(self.grid, 1, 12, weight="weight") + ) + assert nx.shortest_path(self.directed_cycle, 0, 3, weight="weight") == [ + 0, + 1, + 2, + 3, + ] + # weights and method specified + assert nx.shortest_path( + self.directed_cycle, 0, 3, weight="weight", method="dijkstra" + ) == [0, 1, 2, 3] + assert nx.shortest_path( + self.directed_cycle, 0, 3, weight="weight", method="bellman-ford" + ) == [0, 1, 2, 3] + # when Dijkstra's will probably (depending on precise implementation) + # incorrectly return [0, 1, 3] instead + assert nx.shortest_path( + self.neg_weights, 0, 3, weight="weight", method="bellman-ford" + ) == [0, 2, 3] + # confirm bad method rejection + pytest.raises(ValueError, nx.shortest_path, self.cycle, method="SPAM") + # confirm absent source rejection + pytest.raises(nx.NodeNotFound, nx.shortest_path, self.cycle, 8) + + def test_shortest_path_target(self): + answer = {0: [0, 1], 1: [1], 2: [2, 1]} + sp = nx.shortest_path(nx.path_graph(3), target=1) + assert sp == answer + # with weights + sp = nx.shortest_path(nx.path_graph(3), target=1, weight="weight") + assert sp == answer + # weights and method specified + sp = nx.shortest_path( + nx.path_graph(3), target=1, weight="weight", method="dijkstra" + ) + assert sp == answer + sp = nx.shortest_path( + nx.path_graph(3), target=1, weight="weight", method="bellman-ford" + ) + assert sp == answer + + def test_shortest_path_length(self): + assert nx.shortest_path_length(self.cycle, 0, 3) == 3 + assert nx.shortest_path_length(self.grid, 1, 12) == 5 + assert nx.shortest_path_length(self.directed_cycle, 0, 4) == 4 + # now with weights + assert nx.shortest_path_length(self.cycle, 0, 3, weight="weight") == 3 + assert nx.shortest_path_length(self.grid, 1, 12, weight="weight") == 5 + assert nx.shortest_path_length(self.directed_cycle, 0, 4, weight="weight") == 4 + # weights and method specified + assert ( + nx.shortest_path_length( + self.cycle, 0, 3, weight="weight", method="dijkstra" + ) + == 3 + ) + assert ( + nx.shortest_path_length( + self.cycle, 0, 3, weight="weight", method="bellman-ford" + ) + == 3 + ) + # confirm bad method rejection + pytest.raises(ValueError, nx.shortest_path_length, self.cycle, method="SPAM") + # confirm absent source rejection + pytest.raises(nx.NodeNotFound, nx.shortest_path_length, self.cycle, 8) + + def test_shortest_path_length_target(self): + answer = {0: 1, 1: 0, 2: 1} + sp = dict(nx.shortest_path_length(nx.path_graph(3), target=1)) + assert sp == answer + # with weights + sp = nx.shortest_path_length(nx.path_graph(3), target=1, weight="weight") + assert sp == answer + # weights and method specified + sp = nx.shortest_path_length( + nx.path_graph(3), target=1, weight="weight", method="dijkstra" + ) + assert sp == answer + sp = nx.shortest_path_length( + nx.path_graph(3), target=1, weight="weight", method="bellman-ford" + ) + assert sp == answer + + def test_single_source_shortest_path(self): + p = nx.shortest_path(self.cycle, 0) + assert p[3] == [0, 1, 2, 3] + assert p == nx.single_source_shortest_path(self.cycle, 0) + p = nx.shortest_path(self.grid, 1) + validate_grid_path(4, 4, 1, 12, p[12]) + # now with weights + p = nx.shortest_path(self.cycle, 0, weight="weight") + assert p[3] == [0, 1, 2, 3] + assert p == nx.single_source_dijkstra_path(self.cycle, 0) + p = nx.shortest_path(self.grid, 1, weight="weight") + validate_grid_path(4, 4, 1, 12, p[12]) + # weights and method specified + p = nx.shortest_path(self.cycle, 0, method="dijkstra", weight="weight") + assert p[3] == [0, 1, 2, 3] + assert p == nx.single_source_shortest_path(self.cycle, 0) + p = nx.shortest_path(self.cycle, 0, method="bellman-ford", weight="weight") + assert p[3] == [0, 1, 2, 3] + assert p == nx.single_source_shortest_path(self.cycle, 0) + + def test_single_source_shortest_path_length(self): + ans = dict(nx.shortest_path_length(self.cycle, 0)) + assert ans == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.single_source_shortest_path_length(self.cycle, 0)) + ans = dict(nx.shortest_path_length(self.grid, 1)) + assert ans[16] == 6 + # now with weights + ans = dict(nx.shortest_path_length(self.cycle, 0, weight="weight")) + assert ans == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.single_source_dijkstra_path_length(self.cycle, 0)) + ans = dict(nx.shortest_path_length(self.grid, 1, weight="weight")) + assert ans[16] == 6 + # weights and method specified + ans = dict( + nx.shortest_path_length(self.cycle, 0, weight="weight", method="dijkstra") + ) + assert ans == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.single_source_dijkstra_path_length(self.cycle, 0)) + ans = dict( + nx.shortest_path_length( + self.cycle, 0, weight="weight", method="bellman-ford" + ) + ) + assert ans == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.single_source_bellman_ford_path_length(self.cycle, 0)) + + def test_single_source_all_shortest_paths(self): + cycle_ans = {0: [[0]], 1: [[0, 1]], 2: [[0, 1, 2], [0, 3, 2]], 3: [[0, 3]]} + ans = dict(nx.single_source_all_shortest_paths(nx.cycle_graph(4), 0)) + assert sorted(ans[2]) == cycle_ans[2] + ans = dict(nx.single_source_all_shortest_paths(self.grid, 1)) + grid_ans = [ + [1, 2, 3, 7, 11], + [1, 2, 6, 7, 11], + [1, 2, 6, 10, 11], + [1, 5, 6, 7, 11], + [1, 5, 6, 10, 11], + [1, 5, 9, 10, 11], + ] + assert sorted(ans[11]) == grid_ans + ans = dict( + nx.single_source_all_shortest_paths(nx.cycle_graph(4), 0, weight="weight") + ) + assert sorted(ans[2]) == cycle_ans[2] + ans = dict( + nx.single_source_all_shortest_paths( + nx.cycle_graph(4), 0, method="bellman-ford", weight="weight" + ) + ) + assert sorted(ans[2]) == cycle_ans[2] + ans = dict(nx.single_source_all_shortest_paths(self.grid, 1, weight="weight")) + assert sorted(ans[11]) == grid_ans + ans = dict( + nx.single_source_all_shortest_paths( + self.grid, 1, method="bellman-ford", weight="weight" + ) + ) + assert sorted(ans[11]) == grid_ans + G = nx.cycle_graph(4) + G.add_node(4) + ans = dict(nx.single_source_all_shortest_paths(G, 0)) + assert sorted(ans[2]) == [[0, 1, 2], [0, 3, 2]] + ans = dict(nx.single_source_all_shortest_paths(G, 4)) + assert sorted(ans[4]) == [[4]] + + def test_all_pairs_shortest_path(self): + p = nx.shortest_path(self.cycle) + assert p[0][3] == [0, 1, 2, 3] + assert p == dict(nx.all_pairs_shortest_path(self.cycle)) + p = nx.shortest_path(self.grid) + validate_grid_path(4, 4, 1, 12, p[1][12]) + # now with weights + p = nx.shortest_path(self.cycle, weight="weight") + assert p[0][3] == [0, 1, 2, 3] + assert p == dict(nx.all_pairs_dijkstra_path(self.cycle)) + p = nx.shortest_path(self.grid, weight="weight") + validate_grid_path(4, 4, 1, 12, p[1][12]) + # weights and method specified + p = nx.shortest_path(self.cycle, weight="weight", method="dijkstra") + assert p[0][3] == [0, 1, 2, 3] + assert p == dict(nx.all_pairs_dijkstra_path(self.cycle)) + p = nx.shortest_path(self.cycle, weight="weight", method="bellman-ford") + assert p[0][3] == [0, 1, 2, 3] + assert p == dict(nx.all_pairs_bellman_ford_path(self.cycle)) + + def test_all_pairs_shortest_path_length(self): + ans = dict(nx.shortest_path_length(self.cycle)) + assert ans[0] == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.all_pairs_shortest_path_length(self.cycle)) + ans = dict(nx.shortest_path_length(self.grid)) + assert ans[1][16] == 6 + # now with weights + ans = dict(nx.shortest_path_length(self.cycle, weight="weight")) + assert ans[0] == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.all_pairs_dijkstra_path_length(self.cycle)) + ans = dict(nx.shortest_path_length(self.grid, weight="weight")) + assert ans[1][16] == 6 + # weights and method specified + ans = dict( + nx.shortest_path_length(self.cycle, weight="weight", method="dijkstra") + ) + assert ans[0] == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.all_pairs_dijkstra_path_length(self.cycle)) + ans = dict( + nx.shortest_path_length(self.cycle, weight="weight", method="bellman-ford") + ) + assert ans[0] == {0: 0, 1: 1, 2: 2, 3: 3, 4: 3, 5: 2, 6: 1} + assert ans == dict(nx.all_pairs_bellman_ford_path_length(self.cycle)) + + def test_all_pairs_all_shortest_paths(self): + ans = dict(nx.all_pairs_all_shortest_paths(nx.cycle_graph(4))) + assert sorted(ans[1][3]) == [[1, 0, 3], [1, 2, 3]] + ans = dict(nx.all_pairs_all_shortest_paths(nx.cycle_graph(4)), weight="weight") + assert sorted(ans[1][3]) == [[1, 0, 3], [1, 2, 3]] + ans = dict( + nx.all_pairs_all_shortest_paths(nx.cycle_graph(4)), + method="bellman-ford", + weight="weight", + ) + assert sorted(ans[1][3]) == [[1, 0, 3], [1, 2, 3]] + G = nx.cycle_graph(4) + G.add_node(4) + ans = dict(nx.all_pairs_all_shortest_paths(G)) + assert sorted(ans[4][4]) == [[4]] + + def test_has_path(self): + G = nx.Graph() + nx.add_path(G, range(3)) + nx.add_path(G, range(3, 5)) + assert nx.has_path(G, 0, 2) + assert not nx.has_path(G, 0, 4) + + def test_all_shortest_paths(self): + G = nx.Graph() + nx.add_path(G, [0, 1, 2, 3]) + nx.add_path(G, [0, 10, 20, 3]) + assert [[0, 1, 2, 3], [0, 10, 20, 3]] == sorted(nx.all_shortest_paths(G, 0, 3)) + # with weights + G = nx.Graph() + nx.add_path(G, [0, 1, 2, 3]) + nx.add_path(G, [0, 10, 20, 3]) + assert [[0, 1, 2, 3], [0, 10, 20, 3]] == sorted( + nx.all_shortest_paths(G, 0, 3, weight="weight") + ) + # weights and method specified + G = nx.Graph() + nx.add_path(G, [0, 1, 2, 3]) + nx.add_path(G, [0, 10, 20, 3]) + assert [[0, 1, 2, 3], [0, 10, 20, 3]] == sorted( + nx.all_shortest_paths(G, 0, 3, weight="weight", method="dijkstra") + ) + G = nx.Graph() + nx.add_path(G, [0, 1, 2, 3]) + nx.add_path(G, [0, 10, 20, 3]) + assert [[0, 1, 2, 3], [0, 10, 20, 3]] == sorted( + nx.all_shortest_paths(G, 0, 3, weight="weight", method="bellman-ford") + ) + + def test_all_shortest_paths_raise(self): + with pytest.raises(nx.NetworkXNoPath): + G = nx.path_graph(4) + G.add_node(4) + list(nx.all_shortest_paths(G, 0, 4)) + + def test_bad_method(self): + with pytest.raises(ValueError): + G = nx.path_graph(2) + list(nx.all_shortest_paths(G, 0, 1, weight="weight", method="SPAM")) + + def test_single_source_all_shortest_paths_bad_method(self): + with pytest.raises(ValueError): + G = nx.path_graph(2) + dict( + nx.single_source_all_shortest_paths( + G, 0, weight="weight", method="SPAM" + ) + ) + + def test_all_shortest_paths_zero_weight_edge(self): + g = nx.Graph() + nx.add_path(g, [0, 1, 3]) + nx.add_path(g, [0, 1, 2, 3]) + g.edges[1, 2]["weight"] = 0 + paths30d = list( + nx.all_shortest_paths(g, 3, 0, weight="weight", method="dijkstra") + ) + paths03d = list( + nx.all_shortest_paths(g, 0, 3, weight="weight", method="dijkstra") + ) + paths30b = list( + nx.all_shortest_paths(g, 3, 0, weight="weight", method="bellman-ford") + ) + paths03b = list( + nx.all_shortest_paths(g, 0, 3, weight="weight", method="bellman-ford") + ) + assert sorted(paths03d) == sorted(p[::-1] for p in paths30d) + assert sorted(paths03d) == sorted(p[::-1] for p in paths30b) + assert sorted(paths03b) == sorted(p[::-1] for p in paths30b) + + +class TestAverageShortestPathLength: + def test_cycle_graph(self): + ans = nx.average_shortest_path_length(nx.cycle_graph(7)) + assert ans == pytest.approx(2, abs=1e-7) + + def test_path_graph(self): + ans = nx.average_shortest_path_length(nx.path_graph(5)) + assert ans == pytest.approx(2, abs=1e-7) + + def test_weighted(self): + G = nx.Graph() + nx.add_cycle(G, range(7), weight=2) + ans = nx.average_shortest_path_length(G, weight="weight") + assert ans == pytest.approx(4, abs=1e-7) + G = nx.Graph() + nx.add_path(G, range(5), weight=2) + ans = nx.average_shortest_path_length(G, weight="weight") + assert ans == pytest.approx(4, abs=1e-7) + + def test_specified_methods(self): + G = nx.Graph() + nx.add_cycle(G, range(7), weight=2) + ans = nx.average_shortest_path_length(G, weight="weight", method="dijkstra") + assert ans == pytest.approx(4, abs=1e-7) + ans = nx.average_shortest_path_length(G, weight="weight", method="bellman-ford") + assert ans == pytest.approx(4, abs=1e-7) + ans = nx.average_shortest_path_length( + G, weight="weight", method="floyd-warshall" + ) + assert ans == pytest.approx(4, abs=1e-7) + + G = nx.Graph() + nx.add_path(G, range(5), weight=2) + ans = nx.average_shortest_path_length(G, weight="weight", method="dijkstra") + assert ans == pytest.approx(4, abs=1e-7) + ans = nx.average_shortest_path_length(G, weight="weight", method="bellman-ford") + assert ans == pytest.approx(4, abs=1e-7) + ans = nx.average_shortest_path_length( + G, weight="weight", method="floyd-warshall" + ) + assert ans == pytest.approx(4, abs=1e-7) + + def test_directed_not_strongly_connected(self): + G = nx.DiGraph([(0, 1)]) + with pytest.raises(nx.NetworkXError, match="Graph is not strongly connected"): + nx.average_shortest_path_length(G) + + def test_undirected_not_connected(self): + g = nx.Graph() + g.add_nodes_from(range(3)) + g.add_edge(0, 1) + pytest.raises(nx.NetworkXError, nx.average_shortest_path_length, g) + + def test_trivial_graph(self): + """Tests that the trivial graph has average path length zero, + since there is exactly one path of length zero in the trivial + graph. + + For more information, see issue #1960. + + """ + G = nx.trivial_graph() + assert nx.average_shortest_path_length(G) == 0 + + def test_null_graph(self): + with pytest.raises(nx.NetworkXPointlessConcept): + nx.average_shortest_path_length(nx.null_graph()) + + def test_bad_method(self): + with pytest.raises(ValueError): + G = nx.path_graph(2) + nx.average_shortest_path_length(G, weight="weight", method="SPAM") + + +class TestAverageShortestPathLengthNumpy: + @classmethod + def setup_class(cls): + global np + import pytest + + np = pytest.importorskip("numpy") + + def test_specified_methods_numpy(self): + G = nx.Graph() + nx.add_cycle(G, range(7), weight=2) + ans = nx.average_shortest_path_length( + G, weight="weight", method="floyd-warshall-numpy" + ) + np.testing.assert_almost_equal(ans, 4) + + G = nx.Graph() + nx.add_path(G, range(5), weight=2) + ans = nx.average_shortest_path_length( + G, weight="weight", method="floyd-warshall-numpy" + ) + np.testing.assert_almost_equal(ans, 4) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/similarity.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/similarity.py new file mode 100644 index 0000000000000000000000000000000000000000..3d943c20d7e2a1a5e01b9f825802cb6d6a99047e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/similarity.py @@ -0,0 +1,1710 @@ +""" Functions measuring similarity using graph edit distance. + +The graph edit distance is the number of edge/node changes needed +to make two graphs isomorphic. + +The default algorithm/implementation is sub-optimal for some graphs. +The problem of finding the exact Graph Edit Distance (GED) is NP-hard +so it is often slow. If the simple interface `graph_edit_distance` +takes too long for your graph, try `optimize_graph_edit_distance` +and/or `optimize_edit_paths`. + +At the same time, I encourage capable people to investigate +alternative GED algorithms, in order to improve the choices available. +""" + +import math +import time +import warnings +from dataclasses import dataclass +from itertools import product + +import networkx as nx + +__all__ = [ + "graph_edit_distance", + "optimal_edit_paths", + "optimize_graph_edit_distance", + "optimize_edit_paths", + "simrank_similarity", + "panther_similarity", + "generate_random_paths", +] + + +def debug_print(*args, **kwargs): + print(*args, **kwargs) + + +@nx._dispatch( + graphs={"G1": 0, "G2": 1}, preserve_edge_attrs=True, preserve_node_attrs=True +) +def graph_edit_distance( + G1, + G2, + node_match=None, + edge_match=None, + node_subst_cost=None, + node_del_cost=None, + node_ins_cost=None, + edge_subst_cost=None, + edge_del_cost=None, + edge_ins_cost=None, + roots=None, + upper_bound=None, + timeout=None, +): + """Returns GED (graph edit distance) between graphs G1 and G2. + + Graph edit distance is a graph similarity measure analogous to + Levenshtein distance for strings. It is defined as minimum cost + of edit path (sequence of node and edge edit operations) + transforming graph G1 to graph isomorphic to G2. + + Parameters + ---------- + G1, G2: graphs + The two graphs G1 and G2 must be of the same type. + + node_match : callable + A function that returns True if node n1 in G1 and n2 in G2 + should be considered equal during matching. + + The function will be called like + + node_match(G1.nodes[n1], G2.nodes[n2]). + + That is, the function will receive the node attribute + dictionaries for n1 and n2 as inputs. + + Ignored if node_subst_cost is specified. If neither + node_match nor node_subst_cost are specified then node + attributes are not considered. + + edge_match : callable + A function that returns True if the edge attribute dictionaries + for the pair of nodes (u1, v1) in G1 and (u2, v2) in G2 should + be considered equal during matching. + + The function will be called like + + edge_match(G1[u1][v1], G2[u2][v2]). + + That is, the function will receive the edge attribute + dictionaries of the edges under consideration. + + Ignored if edge_subst_cost is specified. If neither + edge_match nor edge_subst_cost are specified then edge + attributes are not considered. + + node_subst_cost, node_del_cost, node_ins_cost : callable + Functions that return the costs of node substitution, node + deletion, and node insertion, respectively. + + The functions will be called like + + node_subst_cost(G1.nodes[n1], G2.nodes[n2]), + node_del_cost(G1.nodes[n1]), + node_ins_cost(G2.nodes[n2]). + + That is, the functions will receive the node attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function node_subst_cost overrides node_match if specified. + If neither node_match nor node_subst_cost are specified then + default node substitution cost of 0 is used (node attributes + are not considered during matching). + + If node_del_cost is not specified then default node deletion + cost of 1 is used. If node_ins_cost is not specified then + default node insertion cost of 1 is used. + + edge_subst_cost, edge_del_cost, edge_ins_cost : callable + Functions that return the costs of edge substitution, edge + deletion, and edge insertion, respectively. + + The functions will be called like + + edge_subst_cost(G1[u1][v1], G2[u2][v2]), + edge_del_cost(G1[u1][v1]), + edge_ins_cost(G2[u2][v2]). + + That is, the functions will receive the edge attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function edge_subst_cost overrides edge_match if specified. + If neither edge_match nor edge_subst_cost are specified then + default edge substitution cost of 0 is used (edge attributes + are not considered during matching). + + If edge_del_cost is not specified then default edge deletion + cost of 1 is used. If edge_ins_cost is not specified then + default edge insertion cost of 1 is used. + + roots : 2-tuple + Tuple where first element is a node in G1 and the second + is a node in G2. + These nodes are forced to be matched in the comparison to + allow comparison between rooted graphs. + + upper_bound : numeric + Maximum edit distance to consider. Return None if no edit + distance under or equal to upper_bound exists. + + timeout : numeric + Maximum number of seconds to execute. + After timeout is met, the current best GED is returned. + + Examples + -------- + >>> G1 = nx.cycle_graph(6) + >>> G2 = nx.wheel_graph(7) + >>> nx.graph_edit_distance(G1, G2) + 7.0 + + >>> G1 = nx.star_graph(5) + >>> G2 = nx.star_graph(5) + >>> nx.graph_edit_distance(G1, G2, roots=(0, 0)) + 0.0 + >>> nx.graph_edit_distance(G1, G2, roots=(1, 0)) + 8.0 + + See Also + -------- + optimal_edit_paths, optimize_graph_edit_distance, + + is_isomorphic: test for graph edit distance of 0 + + References + ---------- + .. [1] Zeina Abu-Aisheh, Romain Raveaux, Jean-Yves Ramel, Patrick + Martineau. An Exact Graph Edit Distance Algorithm for Solving + Pattern Recognition Problems. 4th International Conference on + Pattern Recognition Applications and Methods 2015, Jan 2015, + Lisbon, Portugal. 2015, + <10.5220/0005209202710278>. + https://hal.archives-ouvertes.fr/hal-01168816 + + """ + bestcost = None + for _, _, cost in optimize_edit_paths( + G1, + G2, + node_match, + edge_match, + node_subst_cost, + node_del_cost, + node_ins_cost, + edge_subst_cost, + edge_del_cost, + edge_ins_cost, + upper_bound, + True, + roots, + timeout, + ): + # assert bestcost is None or cost < bestcost + bestcost = cost + return bestcost + + +@nx._dispatch(graphs={"G1": 0, "G2": 1}) +def optimal_edit_paths( + G1, + G2, + node_match=None, + edge_match=None, + node_subst_cost=None, + node_del_cost=None, + node_ins_cost=None, + edge_subst_cost=None, + edge_del_cost=None, + edge_ins_cost=None, + upper_bound=None, +): + """Returns all minimum-cost edit paths transforming G1 to G2. + + Graph edit path is a sequence of node and edge edit operations + transforming graph G1 to graph isomorphic to G2. Edit operations + include substitutions, deletions, and insertions. + + Parameters + ---------- + G1, G2: graphs + The two graphs G1 and G2 must be of the same type. + + node_match : callable + A function that returns True if node n1 in G1 and n2 in G2 + should be considered equal during matching. + + The function will be called like + + node_match(G1.nodes[n1], G2.nodes[n2]). + + That is, the function will receive the node attribute + dictionaries for n1 and n2 as inputs. + + Ignored if node_subst_cost is specified. If neither + node_match nor node_subst_cost are specified then node + attributes are not considered. + + edge_match : callable + A function that returns True if the edge attribute dictionaries + for the pair of nodes (u1, v1) in G1 and (u2, v2) in G2 should + be considered equal during matching. + + The function will be called like + + edge_match(G1[u1][v1], G2[u2][v2]). + + That is, the function will receive the edge attribute + dictionaries of the edges under consideration. + + Ignored if edge_subst_cost is specified. If neither + edge_match nor edge_subst_cost are specified then edge + attributes are not considered. + + node_subst_cost, node_del_cost, node_ins_cost : callable + Functions that return the costs of node substitution, node + deletion, and node insertion, respectively. + + The functions will be called like + + node_subst_cost(G1.nodes[n1], G2.nodes[n2]), + node_del_cost(G1.nodes[n1]), + node_ins_cost(G2.nodes[n2]). + + That is, the functions will receive the node attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function node_subst_cost overrides node_match if specified. + If neither node_match nor node_subst_cost are specified then + default node substitution cost of 0 is used (node attributes + are not considered during matching). + + If node_del_cost is not specified then default node deletion + cost of 1 is used. If node_ins_cost is not specified then + default node insertion cost of 1 is used. + + edge_subst_cost, edge_del_cost, edge_ins_cost : callable + Functions that return the costs of edge substitution, edge + deletion, and edge insertion, respectively. + + The functions will be called like + + edge_subst_cost(G1[u1][v1], G2[u2][v2]), + edge_del_cost(G1[u1][v1]), + edge_ins_cost(G2[u2][v2]). + + That is, the functions will receive the edge attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function edge_subst_cost overrides edge_match if specified. + If neither edge_match nor edge_subst_cost are specified then + default edge substitution cost of 0 is used (edge attributes + are not considered during matching). + + If edge_del_cost is not specified then default edge deletion + cost of 1 is used. If edge_ins_cost is not specified then + default edge insertion cost of 1 is used. + + upper_bound : numeric + Maximum edit distance to consider. + + Returns + ------- + edit_paths : list of tuples (node_edit_path, edge_edit_path) + node_edit_path : list of tuples (u, v) + edge_edit_path : list of tuples ((u1, v1), (u2, v2)) + + cost : numeric + Optimal edit path cost (graph edit distance). + + Examples + -------- + >>> G1 = nx.cycle_graph(4) + >>> G2 = nx.wheel_graph(5) + >>> paths, cost = nx.optimal_edit_paths(G1, G2) + >>> len(paths) + 40 + >>> cost + 5.0 + + See Also + -------- + graph_edit_distance, optimize_edit_paths + + References + ---------- + .. [1] Zeina Abu-Aisheh, Romain Raveaux, Jean-Yves Ramel, Patrick + Martineau. An Exact Graph Edit Distance Algorithm for Solving + Pattern Recognition Problems. 4th International Conference on + Pattern Recognition Applications and Methods 2015, Jan 2015, + Lisbon, Portugal. 2015, + <10.5220/0005209202710278>. + https://hal.archives-ouvertes.fr/hal-01168816 + + """ + paths = [] + bestcost = None + for vertex_path, edge_path, cost in optimize_edit_paths( + G1, + G2, + node_match, + edge_match, + node_subst_cost, + node_del_cost, + node_ins_cost, + edge_subst_cost, + edge_del_cost, + edge_ins_cost, + upper_bound, + False, + ): + # assert bestcost is None or cost <= bestcost + if bestcost is not None and cost < bestcost: + paths = [] + paths.append((vertex_path, edge_path)) + bestcost = cost + return paths, bestcost + + +@nx._dispatch(graphs={"G1": 0, "G2": 1}) +def optimize_graph_edit_distance( + G1, + G2, + node_match=None, + edge_match=None, + node_subst_cost=None, + node_del_cost=None, + node_ins_cost=None, + edge_subst_cost=None, + edge_del_cost=None, + edge_ins_cost=None, + upper_bound=None, +): + """Returns consecutive approximations of GED (graph edit distance) + between graphs G1 and G2. + + Graph edit distance is a graph similarity measure analogous to + Levenshtein distance for strings. It is defined as minimum cost + of edit path (sequence of node and edge edit operations) + transforming graph G1 to graph isomorphic to G2. + + Parameters + ---------- + G1, G2: graphs + The two graphs G1 and G2 must be of the same type. + + node_match : callable + A function that returns True if node n1 in G1 and n2 in G2 + should be considered equal during matching. + + The function will be called like + + node_match(G1.nodes[n1], G2.nodes[n2]). + + That is, the function will receive the node attribute + dictionaries for n1 and n2 as inputs. + + Ignored if node_subst_cost is specified. If neither + node_match nor node_subst_cost are specified then node + attributes are not considered. + + edge_match : callable + A function that returns True if the edge attribute dictionaries + for the pair of nodes (u1, v1) in G1 and (u2, v2) in G2 should + be considered equal during matching. + + The function will be called like + + edge_match(G1[u1][v1], G2[u2][v2]). + + That is, the function will receive the edge attribute + dictionaries of the edges under consideration. + + Ignored if edge_subst_cost is specified. If neither + edge_match nor edge_subst_cost are specified then edge + attributes are not considered. + + node_subst_cost, node_del_cost, node_ins_cost : callable + Functions that return the costs of node substitution, node + deletion, and node insertion, respectively. + + The functions will be called like + + node_subst_cost(G1.nodes[n1], G2.nodes[n2]), + node_del_cost(G1.nodes[n1]), + node_ins_cost(G2.nodes[n2]). + + That is, the functions will receive the node attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function node_subst_cost overrides node_match if specified. + If neither node_match nor node_subst_cost are specified then + default node substitution cost of 0 is used (node attributes + are not considered during matching). + + If node_del_cost is not specified then default node deletion + cost of 1 is used. If node_ins_cost is not specified then + default node insertion cost of 1 is used. + + edge_subst_cost, edge_del_cost, edge_ins_cost : callable + Functions that return the costs of edge substitution, edge + deletion, and edge insertion, respectively. + + The functions will be called like + + edge_subst_cost(G1[u1][v1], G2[u2][v2]), + edge_del_cost(G1[u1][v1]), + edge_ins_cost(G2[u2][v2]). + + That is, the functions will receive the edge attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function edge_subst_cost overrides edge_match if specified. + If neither edge_match nor edge_subst_cost are specified then + default edge substitution cost of 0 is used (edge attributes + are not considered during matching). + + If edge_del_cost is not specified then default edge deletion + cost of 1 is used. If edge_ins_cost is not specified then + default edge insertion cost of 1 is used. + + upper_bound : numeric + Maximum edit distance to consider. + + Returns + ------- + Generator of consecutive approximations of graph edit distance. + + Examples + -------- + >>> G1 = nx.cycle_graph(6) + >>> G2 = nx.wheel_graph(7) + >>> for v in nx.optimize_graph_edit_distance(G1, G2): + ... minv = v + >>> minv + 7.0 + + See Also + -------- + graph_edit_distance, optimize_edit_paths + + References + ---------- + .. [1] Zeina Abu-Aisheh, Romain Raveaux, Jean-Yves Ramel, Patrick + Martineau. An Exact Graph Edit Distance Algorithm for Solving + Pattern Recognition Problems. 4th International Conference on + Pattern Recognition Applications and Methods 2015, Jan 2015, + Lisbon, Portugal. 2015, + <10.5220/0005209202710278>. + https://hal.archives-ouvertes.fr/hal-01168816 + """ + for _, _, cost in optimize_edit_paths( + G1, + G2, + node_match, + edge_match, + node_subst_cost, + node_del_cost, + node_ins_cost, + edge_subst_cost, + edge_del_cost, + edge_ins_cost, + upper_bound, + True, + ): + yield cost + + +@nx._dispatch( + graphs={"G1": 0, "G2": 1}, preserve_edge_attrs=True, preserve_node_attrs=True +) +def optimize_edit_paths( + G1, + G2, + node_match=None, + edge_match=None, + node_subst_cost=None, + node_del_cost=None, + node_ins_cost=None, + edge_subst_cost=None, + edge_del_cost=None, + edge_ins_cost=None, + upper_bound=None, + strictly_decreasing=True, + roots=None, + timeout=None, +): + """GED (graph edit distance) calculation: advanced interface. + + Graph edit path is a sequence of node and edge edit operations + transforming graph G1 to graph isomorphic to G2. Edit operations + include substitutions, deletions, and insertions. + + Graph edit distance is defined as minimum cost of edit path. + + Parameters + ---------- + G1, G2: graphs + The two graphs G1 and G2 must be of the same type. + + node_match : callable + A function that returns True if node n1 in G1 and n2 in G2 + should be considered equal during matching. + + The function will be called like + + node_match(G1.nodes[n1], G2.nodes[n2]). + + That is, the function will receive the node attribute + dictionaries for n1 and n2 as inputs. + + Ignored if node_subst_cost is specified. If neither + node_match nor node_subst_cost are specified then node + attributes are not considered. + + edge_match : callable + A function that returns True if the edge attribute dictionaries + for the pair of nodes (u1, v1) in G1 and (u2, v2) in G2 should + be considered equal during matching. + + The function will be called like + + edge_match(G1[u1][v1], G2[u2][v2]). + + That is, the function will receive the edge attribute + dictionaries of the edges under consideration. + + Ignored if edge_subst_cost is specified. If neither + edge_match nor edge_subst_cost are specified then edge + attributes are not considered. + + node_subst_cost, node_del_cost, node_ins_cost : callable + Functions that return the costs of node substitution, node + deletion, and node insertion, respectively. + + The functions will be called like + + node_subst_cost(G1.nodes[n1], G2.nodes[n2]), + node_del_cost(G1.nodes[n1]), + node_ins_cost(G2.nodes[n2]). + + That is, the functions will receive the node attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function node_subst_cost overrides node_match if specified. + If neither node_match nor node_subst_cost are specified then + default node substitution cost of 0 is used (node attributes + are not considered during matching). + + If node_del_cost is not specified then default node deletion + cost of 1 is used. If node_ins_cost is not specified then + default node insertion cost of 1 is used. + + edge_subst_cost, edge_del_cost, edge_ins_cost : callable + Functions that return the costs of edge substitution, edge + deletion, and edge insertion, respectively. + + The functions will be called like + + edge_subst_cost(G1[u1][v1], G2[u2][v2]), + edge_del_cost(G1[u1][v1]), + edge_ins_cost(G2[u2][v2]). + + That is, the functions will receive the edge attribute + dictionaries as inputs. The functions are expected to return + positive numeric values. + + Function edge_subst_cost overrides edge_match if specified. + If neither edge_match nor edge_subst_cost are specified then + default edge substitution cost of 0 is used (edge attributes + are not considered during matching). + + If edge_del_cost is not specified then default edge deletion + cost of 1 is used. If edge_ins_cost is not specified then + default edge insertion cost of 1 is used. + + upper_bound : numeric + Maximum edit distance to consider. + + strictly_decreasing : bool + If True, return consecutive approximations of strictly + decreasing cost. Otherwise, return all edit paths of cost + less than or equal to the previous minimum cost. + + roots : 2-tuple + Tuple where first element is a node in G1 and the second + is a node in G2. + These nodes are forced to be matched in the comparison to + allow comparison between rooted graphs. + + timeout : numeric + Maximum number of seconds to execute. + After timeout is met, the current best GED is returned. + + Returns + ------- + Generator of tuples (node_edit_path, edge_edit_path, cost) + node_edit_path : list of tuples (u, v) + edge_edit_path : list of tuples ((u1, v1), (u2, v2)) + cost : numeric + + See Also + -------- + graph_edit_distance, optimize_graph_edit_distance, optimal_edit_paths + + References + ---------- + .. [1] Zeina Abu-Aisheh, Romain Raveaux, Jean-Yves Ramel, Patrick + Martineau. An Exact Graph Edit Distance Algorithm for Solving + Pattern Recognition Problems. 4th International Conference on + Pattern Recognition Applications and Methods 2015, Jan 2015, + Lisbon, Portugal. 2015, + <10.5220/0005209202710278>. + https://hal.archives-ouvertes.fr/hal-01168816 + + """ + # TODO: support DiGraph + + import numpy as np + import scipy as sp + + @dataclass + class CostMatrix: + C: ... + lsa_row_ind: ... + lsa_col_ind: ... + ls: ... + + def make_CostMatrix(C, m, n): + # assert(C.shape == (m + n, m + n)) + lsa_row_ind, lsa_col_ind = sp.optimize.linear_sum_assignment(C) + + # Fixup dummy assignments: + # each substitution i<->j should have dummy assignment m+j<->n+i + # NOTE: fast reduce of Cv relies on it + # assert len(lsa_row_ind) == len(lsa_col_ind) + indexes = zip(range(len(lsa_row_ind)), lsa_row_ind, lsa_col_ind) + subst_ind = [k for k, i, j in indexes if i < m and j < n] + indexes = zip(range(len(lsa_row_ind)), lsa_row_ind, lsa_col_ind) + dummy_ind = [k for k, i, j in indexes if i >= m and j >= n] + # assert len(subst_ind) == len(dummy_ind) + lsa_row_ind[dummy_ind] = lsa_col_ind[subst_ind] + m + lsa_col_ind[dummy_ind] = lsa_row_ind[subst_ind] + n + + return CostMatrix( + C, lsa_row_ind, lsa_col_ind, C[lsa_row_ind, lsa_col_ind].sum() + ) + + def extract_C(C, i, j, m, n): + # assert(C.shape == (m + n, m + n)) + row_ind = [k in i or k - m in j for k in range(m + n)] + col_ind = [k in j or k - n in i for k in range(m + n)] + return C[row_ind, :][:, col_ind] + + def reduce_C(C, i, j, m, n): + # assert(C.shape == (m + n, m + n)) + row_ind = [k not in i and k - m not in j for k in range(m + n)] + col_ind = [k not in j and k - n not in i for k in range(m + n)] + return C[row_ind, :][:, col_ind] + + def reduce_ind(ind, i): + # assert set(ind) == set(range(len(ind))) + rind = ind[[k not in i for k in ind]] + for k in set(i): + rind[rind >= k] -= 1 + return rind + + def match_edges(u, v, pending_g, pending_h, Ce, matched_uv=None): + """ + Parameters: + u, v: matched vertices, u=None or v=None for + deletion/insertion + pending_g, pending_h: lists of edges not yet mapped + Ce: CostMatrix of pending edge mappings + matched_uv: partial vertex edit path + list of tuples (u, v) of previously matched vertex + mappings u<->v, u=None or v=None for + deletion/insertion + + Returns: + list of (i, j): indices of edge mappings g<->h + localCe: local CostMatrix of edge mappings + (basically submatrix of Ce at cross of rows i, cols j) + """ + M = len(pending_g) + N = len(pending_h) + # assert Ce.C.shape == (M + N, M + N) + + # only attempt to match edges after one node match has been made + # this will stop self-edges on the first node being automatically deleted + # even when a substitution is the better option + if matched_uv is None or len(matched_uv) == 0: + g_ind = [] + h_ind = [] + else: + g_ind = [ + i + for i in range(M) + if pending_g[i][:2] == (u, u) + or any( + pending_g[i][:2] in ((p, u), (u, p), (p, p)) for p, q in matched_uv + ) + ] + h_ind = [ + j + for j in range(N) + if pending_h[j][:2] == (v, v) + or any( + pending_h[j][:2] in ((q, v), (v, q), (q, q)) for p, q in matched_uv + ) + ] + + m = len(g_ind) + n = len(h_ind) + + if m or n: + C = extract_C(Ce.C, g_ind, h_ind, M, N) + # assert C.shape == (m + n, m + n) + + # Forbid structurally invalid matches + # NOTE: inf remembered from Ce construction + for k, i in enumerate(g_ind): + g = pending_g[i][:2] + for l, j in enumerate(h_ind): + h = pending_h[j][:2] + if nx.is_directed(G1) or nx.is_directed(G2): + if any( + g == (p, u) and h == (q, v) or g == (u, p) and h == (v, q) + for p, q in matched_uv + ): + continue + else: + if any( + g in ((p, u), (u, p)) and h in ((q, v), (v, q)) + for p, q in matched_uv + ): + continue + if g == (u, u) or any(g == (p, p) for p, q in matched_uv): + continue + if h == (v, v) or any(h == (q, q) for p, q in matched_uv): + continue + C[k, l] = inf + + localCe = make_CostMatrix(C, m, n) + ij = [ + ( + g_ind[k] if k < m else M + h_ind[l], + h_ind[l] if l < n else N + g_ind[k], + ) + for k, l in zip(localCe.lsa_row_ind, localCe.lsa_col_ind) + if k < m or l < n + ] + + else: + ij = [] + localCe = CostMatrix(np.empty((0, 0)), [], [], 0) + + return ij, localCe + + def reduce_Ce(Ce, ij, m, n): + if len(ij): + i, j = zip(*ij) + m_i = m - sum(1 for t in i if t < m) + n_j = n - sum(1 for t in j if t < n) + return make_CostMatrix(reduce_C(Ce.C, i, j, m, n), m_i, n_j) + return Ce + + def get_edit_ops( + matched_uv, pending_u, pending_v, Cv, pending_g, pending_h, Ce, matched_cost + ): + """ + Parameters: + matched_uv: partial vertex edit path + list of tuples (u, v) of vertex mappings u<->v, + u=None or v=None for deletion/insertion + pending_u, pending_v: lists of vertices not yet mapped + Cv: CostMatrix of pending vertex mappings + pending_g, pending_h: lists of edges not yet mapped + Ce: CostMatrix of pending edge mappings + matched_cost: cost of partial edit path + + Returns: + sequence of + (i, j): indices of vertex mapping u<->v + Cv_ij: reduced CostMatrix of pending vertex mappings + (basically Cv with row i, col j removed) + list of (x, y): indices of edge mappings g<->h + Ce_xy: reduced CostMatrix of pending edge mappings + (basically Ce with rows x, cols y removed) + cost: total cost of edit operation + NOTE: most promising ops first + """ + m = len(pending_u) + n = len(pending_v) + # assert Cv.C.shape == (m + n, m + n) + + # 1) a vertex mapping from optimal linear sum assignment + i, j = min( + (k, l) for k, l in zip(Cv.lsa_row_ind, Cv.lsa_col_ind) if k < m or l < n + ) + xy, localCe = match_edges( + pending_u[i] if i < m else None, + pending_v[j] if j < n else None, + pending_g, + pending_h, + Ce, + matched_uv, + ) + Ce_xy = reduce_Ce(Ce, xy, len(pending_g), len(pending_h)) + # assert Ce.ls <= localCe.ls + Ce_xy.ls + if prune(matched_cost + Cv.ls + localCe.ls + Ce_xy.ls): + pass + else: + # get reduced Cv efficiently + Cv_ij = CostMatrix( + reduce_C(Cv.C, (i,), (j,), m, n), + reduce_ind(Cv.lsa_row_ind, (i, m + j)), + reduce_ind(Cv.lsa_col_ind, (j, n + i)), + Cv.ls - Cv.C[i, j], + ) + yield (i, j), Cv_ij, xy, Ce_xy, Cv.C[i, j] + localCe.ls + + # 2) other candidates, sorted by lower-bound cost estimate + other = [] + fixed_i, fixed_j = i, j + if m <= n: + candidates = ( + (t, fixed_j) + for t in range(m + n) + if t != fixed_i and (t < m or t == m + fixed_j) + ) + else: + candidates = ( + (fixed_i, t) + for t in range(m + n) + if t != fixed_j and (t < n or t == n + fixed_i) + ) + for i, j in candidates: + if prune(matched_cost + Cv.C[i, j] + Ce.ls): + continue + Cv_ij = make_CostMatrix( + reduce_C(Cv.C, (i,), (j,), m, n), + m - 1 if i < m else m, + n - 1 if j < n else n, + ) + # assert Cv.ls <= Cv.C[i, j] + Cv_ij.ls + if prune(matched_cost + Cv.C[i, j] + Cv_ij.ls + Ce.ls): + continue + xy, localCe = match_edges( + pending_u[i] if i < m else None, + pending_v[j] if j < n else None, + pending_g, + pending_h, + Ce, + matched_uv, + ) + if prune(matched_cost + Cv.C[i, j] + Cv_ij.ls + localCe.ls): + continue + Ce_xy = reduce_Ce(Ce, xy, len(pending_g), len(pending_h)) + # assert Ce.ls <= localCe.ls + Ce_xy.ls + if prune(matched_cost + Cv.C[i, j] + Cv_ij.ls + localCe.ls + Ce_xy.ls): + continue + other.append(((i, j), Cv_ij, xy, Ce_xy, Cv.C[i, j] + localCe.ls)) + + yield from sorted(other, key=lambda t: t[4] + t[1].ls + t[3].ls) + + def get_edit_paths( + matched_uv, + pending_u, + pending_v, + Cv, + matched_gh, + pending_g, + pending_h, + Ce, + matched_cost, + ): + """ + Parameters: + matched_uv: partial vertex edit path + list of tuples (u, v) of vertex mappings u<->v, + u=None or v=None for deletion/insertion + pending_u, pending_v: lists of vertices not yet mapped + Cv: CostMatrix of pending vertex mappings + matched_gh: partial edge edit path + list of tuples (g, h) of edge mappings g<->h, + g=None or h=None for deletion/insertion + pending_g, pending_h: lists of edges not yet mapped + Ce: CostMatrix of pending edge mappings + matched_cost: cost of partial edit path + + Returns: + sequence of (vertex_path, edge_path, cost) + vertex_path: complete vertex edit path + list of tuples (u, v) of vertex mappings u<->v, + u=None or v=None for deletion/insertion + edge_path: complete edge edit path + list of tuples (g, h) of edge mappings g<->h, + g=None or h=None for deletion/insertion + cost: total cost of edit path + NOTE: path costs are non-increasing + """ + # debug_print('matched-uv:', matched_uv) + # debug_print('matched-gh:', matched_gh) + # debug_print('matched-cost:', matched_cost) + # debug_print('pending-u:', pending_u) + # debug_print('pending-v:', pending_v) + # debug_print(Cv.C) + # assert list(sorted(G1.nodes)) == list(sorted(list(u for u, v in matched_uv if u is not None) + pending_u)) + # assert list(sorted(G2.nodes)) == list(sorted(list(v for u, v in matched_uv if v is not None) + pending_v)) + # debug_print('pending-g:', pending_g) + # debug_print('pending-h:', pending_h) + # debug_print(Ce.C) + # assert list(sorted(G1.edges)) == list(sorted(list(g for g, h in matched_gh if g is not None) + pending_g)) + # assert list(sorted(G2.edges)) == list(sorted(list(h for g, h in matched_gh if h is not None) + pending_h)) + # debug_print() + + if prune(matched_cost + Cv.ls + Ce.ls): + return + + if not max(len(pending_u), len(pending_v)): + # assert not len(pending_g) + # assert not len(pending_h) + # path completed! + # assert matched_cost <= maxcost_value + nonlocal maxcost_value + maxcost_value = min(maxcost_value, matched_cost) + yield matched_uv, matched_gh, matched_cost + + else: + edit_ops = get_edit_ops( + matched_uv, + pending_u, + pending_v, + Cv, + pending_g, + pending_h, + Ce, + matched_cost, + ) + for ij, Cv_ij, xy, Ce_xy, edit_cost in edit_ops: + i, j = ij + # assert Cv.C[i, j] + sum(Ce.C[t] for t in xy) == edit_cost + if prune(matched_cost + edit_cost + Cv_ij.ls + Ce_xy.ls): + continue + + # dive deeper + u = pending_u.pop(i) if i < len(pending_u) else None + v = pending_v.pop(j) if j < len(pending_v) else None + matched_uv.append((u, v)) + for x, y in xy: + len_g = len(pending_g) + len_h = len(pending_h) + matched_gh.append( + ( + pending_g[x] if x < len_g else None, + pending_h[y] if y < len_h else None, + ) + ) + sortedx = sorted(x for x, y in xy) + sortedy = sorted(y for x, y in xy) + G = [ + (pending_g.pop(x) if x < len(pending_g) else None) + for x in reversed(sortedx) + ] + H = [ + (pending_h.pop(y) if y < len(pending_h) else None) + for y in reversed(sortedy) + ] + + yield from get_edit_paths( + matched_uv, + pending_u, + pending_v, + Cv_ij, + matched_gh, + pending_g, + pending_h, + Ce_xy, + matched_cost + edit_cost, + ) + + # backtrack + if u is not None: + pending_u.insert(i, u) + if v is not None: + pending_v.insert(j, v) + matched_uv.pop() + for x, g in zip(sortedx, reversed(G)): + if g is not None: + pending_g.insert(x, g) + for y, h in zip(sortedy, reversed(H)): + if h is not None: + pending_h.insert(y, h) + for _ in xy: + matched_gh.pop() + + # Initialization + + pending_u = list(G1.nodes) + pending_v = list(G2.nodes) + + initial_cost = 0 + if roots: + root_u, root_v = roots + if root_u not in pending_u or root_v not in pending_v: + raise nx.NodeNotFound("Root node not in graph.") + + # remove roots from pending + pending_u.remove(root_u) + pending_v.remove(root_v) + + # cost matrix of vertex mappings + m = len(pending_u) + n = len(pending_v) + C = np.zeros((m + n, m + n)) + if node_subst_cost: + C[0:m, 0:n] = np.array( + [ + node_subst_cost(G1.nodes[u], G2.nodes[v]) + for u in pending_u + for v in pending_v + ] + ).reshape(m, n) + if roots: + initial_cost = node_subst_cost(G1.nodes[root_u], G2.nodes[root_v]) + elif node_match: + C[0:m, 0:n] = np.array( + [ + 1 - int(node_match(G1.nodes[u], G2.nodes[v])) + for u in pending_u + for v in pending_v + ] + ).reshape(m, n) + if roots: + initial_cost = 1 - node_match(G1.nodes[root_u], G2.nodes[root_v]) + else: + # all zeroes + pass + # assert not min(m, n) or C[0:m, 0:n].min() >= 0 + if node_del_cost: + del_costs = [node_del_cost(G1.nodes[u]) for u in pending_u] + else: + del_costs = [1] * len(pending_u) + # assert not m or min(del_costs) >= 0 + if node_ins_cost: + ins_costs = [node_ins_cost(G2.nodes[v]) for v in pending_v] + else: + ins_costs = [1] * len(pending_v) + # assert not n or min(ins_costs) >= 0 + inf = C[0:m, 0:n].sum() + sum(del_costs) + sum(ins_costs) + 1 + C[0:m, n : n + m] = np.array( + [del_costs[i] if i == j else inf for i in range(m) for j in range(m)] + ).reshape(m, m) + C[m : m + n, 0:n] = np.array( + [ins_costs[i] if i == j else inf for i in range(n) for j in range(n)] + ).reshape(n, n) + Cv = make_CostMatrix(C, m, n) + # debug_print(f"Cv: {m} x {n}") + # debug_print(Cv.C) + + pending_g = list(G1.edges) + pending_h = list(G2.edges) + + # cost matrix of edge mappings + m = len(pending_g) + n = len(pending_h) + C = np.zeros((m + n, m + n)) + if edge_subst_cost: + C[0:m, 0:n] = np.array( + [ + edge_subst_cost(G1.edges[g], G2.edges[h]) + for g in pending_g + for h in pending_h + ] + ).reshape(m, n) + elif edge_match: + C[0:m, 0:n] = np.array( + [ + 1 - int(edge_match(G1.edges[g], G2.edges[h])) + for g in pending_g + for h in pending_h + ] + ).reshape(m, n) + else: + # all zeroes + pass + # assert not min(m, n) or C[0:m, 0:n].min() >= 0 + if edge_del_cost: + del_costs = [edge_del_cost(G1.edges[g]) for g in pending_g] + else: + del_costs = [1] * len(pending_g) + # assert not m or min(del_costs) >= 0 + if edge_ins_cost: + ins_costs = [edge_ins_cost(G2.edges[h]) for h in pending_h] + else: + ins_costs = [1] * len(pending_h) + # assert not n or min(ins_costs) >= 0 + inf = C[0:m, 0:n].sum() + sum(del_costs) + sum(ins_costs) + 1 + C[0:m, n : n + m] = np.array( + [del_costs[i] if i == j else inf for i in range(m) for j in range(m)] + ).reshape(m, m) + C[m : m + n, 0:n] = np.array( + [ins_costs[i] if i == j else inf for i in range(n) for j in range(n)] + ).reshape(n, n) + Ce = make_CostMatrix(C, m, n) + # debug_print(f'Ce: {m} x {n}') + # debug_print(Ce.C) + # debug_print() + + maxcost_value = Cv.C.sum() + Ce.C.sum() + 1 + + if timeout is not None: + if timeout <= 0: + raise nx.NetworkXError("Timeout value must be greater than 0") + start = time.perf_counter() + + def prune(cost): + if timeout is not None: + if time.perf_counter() - start > timeout: + return True + if upper_bound is not None: + if cost > upper_bound: + return True + if cost > maxcost_value: + return True + if strictly_decreasing and cost >= maxcost_value: + return True + return False + + # Now go! + + done_uv = [] if roots is None else [roots] + + for vertex_path, edge_path, cost in get_edit_paths( + done_uv, pending_u, pending_v, Cv, [], pending_g, pending_h, Ce, initial_cost + ): + # assert sorted(G1.nodes) == sorted(u for u, v in vertex_path if u is not None) + # assert sorted(G2.nodes) == sorted(v for u, v in vertex_path if v is not None) + # assert sorted(G1.edges) == sorted(g for g, h in edge_path if g is not None) + # assert sorted(G2.edges) == sorted(h for g, h in edge_path if h is not None) + # print(vertex_path, edge_path, cost, file = sys.stderr) + # assert cost == maxcost_value + yield list(vertex_path), list(edge_path), cost + + +@nx._dispatch +def simrank_similarity( + G, + source=None, + target=None, + importance_factor=0.9, + max_iterations=1000, + tolerance=1e-4, +): + """Returns the SimRank similarity of nodes in the graph ``G``. + + SimRank is a similarity metric that says "two objects are considered + to be similar if they are referenced by similar objects." [1]_. + + The pseudo-code definition from the paper is:: + + def simrank(G, u, v): + in_neighbors_u = G.predecessors(u) + in_neighbors_v = G.predecessors(v) + scale = C / (len(in_neighbors_u) * len(in_neighbors_v)) + return scale * sum(simrank(G, w, x) + for w, x in product(in_neighbors_u, + in_neighbors_v)) + + where ``G`` is the graph, ``u`` is the source, ``v`` is the target, + and ``C`` is a float decay or importance factor between 0 and 1. + + The SimRank algorithm for determining node similarity is defined in + [2]_. + + Parameters + ---------- + G : NetworkX graph + A NetworkX graph + + source : node + If this is specified, the returned dictionary maps each node + ``v`` in the graph to the similarity between ``source`` and + ``v``. + + target : node + If both ``source`` and ``target`` are specified, the similarity + value between ``source`` and ``target`` is returned. If + ``target`` is specified but ``source`` is not, this argument is + ignored. + + importance_factor : float + The relative importance of indirect neighbors with respect to + direct neighbors. + + max_iterations : integer + Maximum number of iterations. + + tolerance : float + Error tolerance used to check convergence. When an iteration of + the algorithm finds that no similarity value changes more than + this amount, the algorithm halts. + + Returns + ------- + similarity : dictionary or float + If ``source`` and ``target`` are both ``None``, this returns a + dictionary of dictionaries, where keys are node pairs and value + are similarity of the pair of nodes. + + If ``source`` is not ``None`` but ``target`` is, this returns a + dictionary mapping node to the similarity of ``source`` and that + node. + + If neither ``source`` nor ``target`` is ``None``, this returns + the similarity value for the given pair of nodes. + + Examples + -------- + >>> G = nx.cycle_graph(2) + >>> nx.simrank_similarity(G) + {0: {0: 1.0, 1: 0.0}, 1: {0: 0.0, 1: 1.0}} + >>> nx.simrank_similarity(G, source=0) + {0: 1.0, 1: 0.0} + >>> nx.simrank_similarity(G, source=0, target=0) + 1.0 + + The result of this function can be converted to a numpy array + representing the SimRank matrix by using the node order of the + graph to determine which row and column represent each node. + Other ordering of nodes is also possible. + + >>> import numpy as np + >>> sim = nx.simrank_similarity(G) + >>> np.array([[sim[u][v] for v in G] for u in G]) + array([[1., 0.], + [0., 1.]]) + >>> sim_1d = nx.simrank_similarity(G, source=0) + >>> np.array([sim[0][v] for v in G]) + array([1., 0.]) + + References + ---------- + .. [1] https://en.wikipedia.org/wiki/SimRank + .. [2] G. Jeh and J. Widom. + "SimRank: a measure of structural-context similarity", + In KDD'02: Proceedings of the Eighth ACM SIGKDD + International Conference on Knowledge Discovery and Data Mining, + pp. 538--543. ACM Press, 2002. + """ + import numpy as np + + nodelist = list(G) + s_indx = None if source is None else nodelist.index(source) + t_indx = None if target is None else nodelist.index(target) + + x = _simrank_similarity_numpy( + G, s_indx, t_indx, importance_factor, max_iterations, tolerance + ) + + if isinstance(x, np.ndarray): + if x.ndim == 1: + return dict(zip(G, x)) + # else x.ndim == 2 + return {u: dict(zip(G, row)) for u, row in zip(G, x)} + return x + + +def _simrank_similarity_python( + G, + source=None, + target=None, + importance_factor=0.9, + max_iterations=1000, + tolerance=1e-4, +): + """Returns the SimRank similarity of nodes in the graph ``G``. + + This pure Python version is provided for pedagogical purposes. + + Examples + -------- + >>> G = nx.cycle_graph(2) + >>> nx.similarity._simrank_similarity_python(G) + {0: {0: 1, 1: 0.0}, 1: {0: 0.0, 1: 1}} + >>> nx.similarity._simrank_similarity_python(G, source=0) + {0: 1, 1: 0.0} + >>> nx.similarity._simrank_similarity_python(G, source=0, target=0) + 1 + """ + # build up our similarity adjacency dictionary output + newsim = {u: {v: 1 if u == v else 0 for v in G} for u in G} + + # These functions compute the update to the similarity value of the nodes + # `u` and `v` with respect to the previous similarity values. + def avg_sim(s): + return sum(newsim[w][x] for (w, x) in s) / len(s) if s else 0.0 + + Gadj = G.pred if G.is_directed() else G.adj + + def sim(u, v): + return importance_factor * avg_sim(list(product(Gadj[u], Gadj[v]))) + + for its in range(max_iterations): + oldsim = newsim + newsim = {u: {v: sim(u, v) if u != v else 1 for v in G} for u in G} + is_close = all( + all( + abs(newsim[u][v] - old) <= tolerance * (1 + abs(old)) + for v, old in nbrs.items() + ) + for u, nbrs in oldsim.items() + ) + if is_close: + break + + if its + 1 == max_iterations: + raise nx.ExceededMaxIterations( + f"simrank did not converge after {max_iterations} iterations." + ) + + if source is not None and target is not None: + return newsim[source][target] + if source is not None: + return newsim[source] + return newsim + + +def _simrank_similarity_numpy( + G, + source=None, + target=None, + importance_factor=0.9, + max_iterations=1000, + tolerance=1e-4, +): + """Calculate SimRank of nodes in ``G`` using matrices with ``numpy``. + + The SimRank algorithm for determining node similarity is defined in + [1]_. + + Parameters + ---------- + G : NetworkX graph + A NetworkX graph + + source : node + If this is specified, the returned dictionary maps each node + ``v`` in the graph to the similarity between ``source`` and + ``v``. + + target : node + If both ``source`` and ``target`` are specified, the similarity + value between ``source`` and ``target`` is returned. If + ``target`` is specified but ``source`` is not, this argument is + ignored. + + importance_factor : float + The relative importance of indirect neighbors with respect to + direct neighbors. + + max_iterations : integer + Maximum number of iterations. + + tolerance : float + Error tolerance used to check convergence. When an iteration of + the algorithm finds that no similarity value changes more than + this amount, the algorithm halts. + + Returns + ------- + similarity : numpy array or float + If ``source`` and ``target`` are both ``None``, this returns a + 2D array containing SimRank scores of the nodes. + + If ``source`` is not ``None`` but ``target`` is, this returns an + 1D array containing SimRank scores of ``source`` and that + node. + + If neither ``source`` nor ``target`` is ``None``, this returns + the similarity value for the given pair of nodes. + + Examples + -------- + >>> G = nx.cycle_graph(2) + >>> nx.similarity._simrank_similarity_numpy(G) + array([[1., 0.], + [0., 1.]]) + >>> nx.similarity._simrank_similarity_numpy(G, source=0) + array([1., 0.]) + >>> nx.similarity._simrank_similarity_numpy(G, source=0, target=0) + 1.0 + + References + ---------- + .. [1] G. Jeh and J. Widom. + "SimRank: a measure of structural-context similarity", + In KDD'02: Proceedings of the Eighth ACM SIGKDD + International Conference on Knowledge Discovery and Data Mining, + pp. 538--543. ACM Press, 2002. + """ + # This algorithm follows roughly + # + # S = max{C * (A.T * S * A), I} + # + # where C is the importance factor, A is the column normalized + # adjacency matrix, and I is the identity matrix. + import numpy as np + + adjacency_matrix = nx.to_numpy_array(G) + + # column-normalize the ``adjacency_matrix`` + s = np.array(adjacency_matrix.sum(axis=0)) + s[s == 0] = 1 + adjacency_matrix /= s # adjacency_matrix.sum(axis=0) + + newsim = np.eye(len(G), dtype=np.float64) + for its in range(max_iterations): + prevsim = newsim.copy() + newsim = importance_factor * ((adjacency_matrix.T @ prevsim) @ adjacency_matrix) + np.fill_diagonal(newsim, 1.0) + + if np.allclose(prevsim, newsim, atol=tolerance): + break + + if its + 1 == max_iterations: + raise nx.ExceededMaxIterations( + f"simrank did not converge after {max_iterations} iterations." + ) + + if source is not None and target is not None: + return newsim[source, target] + if source is not None: + return newsim[source] + return newsim + + +@nx._dispatch(edge_attrs="weight") +def panther_similarity( + G, source, k=5, path_length=5, c=0.5, delta=0.1, eps=None, weight="weight" +): + r"""Returns the Panther similarity of nodes in the graph `G` to node ``v``. + + Panther is a similarity metric that says "two objects are considered + to be similar if they frequently appear on the same paths." [1]_. + + Parameters + ---------- + G : NetworkX graph + A NetworkX graph + source : node + Source node for which to find the top `k` similar other nodes + k : int (default = 5) + The number of most similar nodes to return + path_length : int (default = 5) + How long the randomly generated paths should be (``T`` in [1]_) + c : float (default = 0.5) + A universal positive constant used to scale the number + of sample random paths to generate. + delta : float (default = 0.1) + The probability that the similarity $S$ is not an epsilon-approximation to (R, phi), + where $R$ is the number of random paths and $\phi$ is the probability + that an element sampled from a set $A \subseteq D$, where $D$ is the domain. + eps : float or None (default = None) + The error bound. Per [1]_, a good value is ``sqrt(1/|E|)``. Therefore, + if no value is provided, the recommended computed value will be used. + weight : string or None, optional (default="weight") + The name of an edge attribute that holds the numerical value + used as a weight. If None then each edge has weight 1. + + Returns + ------- + similarity : dictionary + Dictionary of nodes to similarity scores (as floats). Note: + the self-similarity (i.e., ``v``) will not be included in + the returned dictionary. + + Examples + -------- + >>> G = nx.star_graph(10) + >>> sim = nx.panther_similarity(G, 0) + + References + ---------- + .. [1] Zhang, J., Tang, J., Ma, C., Tong, H., Jing, Y., & Li, J. + Panther: Fast top-k similarity search on large networks. + In Proceedings of the ACM SIGKDD International Conference + on Knowledge Discovery and Data Mining (Vol. 2015-August, pp. 1445–1454). + Association for Computing Machinery. https://doi.org/10.1145/2783258.2783267. + """ + import numpy as np + + num_nodes = G.number_of_nodes() + if num_nodes < k: + warnings.warn( + f"Number of nodes is {num_nodes}, but requested k is {k}. " + "Setting k to number of nodes." + ) + k = num_nodes + # According to [1], they empirically determined + # a good value for ``eps`` to be sqrt( 1 / |E| ) + if eps is None: + eps = np.sqrt(1.0 / G.number_of_edges()) + + inv_node_map = {name: index for index, name in enumerate(G.nodes)} + node_map = np.array(G) + + # Calculate the sample size ``R`` for how many paths + # to randomly generate + t_choose_2 = math.comb(path_length, 2) + sample_size = int((c / eps**2) * (np.log2(t_choose_2) + 1 + np.log(1 / delta))) + index_map = {} + _ = list( + generate_random_paths( + G, sample_size, path_length=path_length, index_map=index_map, weight=weight + ) + ) + S = np.zeros(num_nodes) + + inv_sample_size = 1 / sample_size + + source_paths = set(index_map[source]) + + # Calculate the path similarities + # between ``source`` (v) and ``node`` (v_j) + # using our inverted index mapping of + # vertices to paths + for node, paths in index_map.items(): + # Only consider paths where both + # ``node`` and ``source`` are present + common_paths = source_paths.intersection(paths) + S[inv_node_map[node]] = len(common_paths) * inv_sample_size + + # Retrieve top ``k`` similar + # Note: the below performed anywhere from 4-10x faster + # (depending on input sizes) vs the equivalent ``np.argsort(S)[::-1]`` + top_k_unsorted = np.argpartition(S, -k)[-k:] + top_k_sorted = top_k_unsorted[np.argsort(S[top_k_unsorted])][::-1] + + # Add back the similarity scores + top_k_sorted_names = (node_map[n] for n in top_k_sorted) + top_k_with_val = dict(zip(top_k_sorted_names, S[top_k_sorted])) + + # Remove the self-similarity + top_k_with_val.pop(source, None) + return top_k_with_val + + +@nx._dispatch(edge_attrs="weight") +def generate_random_paths( + G, sample_size, path_length=5, index_map=None, weight="weight" +): + """Randomly generate `sample_size` paths of length `path_length`. + + Parameters + ---------- + G : NetworkX graph + A NetworkX graph + sample_size : integer + The number of paths to generate. This is ``R`` in [1]_. + path_length : integer (default = 5) + The maximum size of the path to randomly generate. + This is ``T`` in [1]_. According to the paper, ``T >= 5`` is + recommended. + index_map : dictionary, optional + If provided, this will be populated with the inverted + index of nodes mapped to the set of generated random path + indices within ``paths``. + weight : string or None, optional (default="weight") + The name of an edge attribute that holds the numerical value + used as a weight. If None then each edge has weight 1. + + Returns + ------- + paths : generator of lists + Generator of `sample_size` paths each with length `path_length`. + + Examples + -------- + Note that the return value is the list of paths: + + >>> G = nx.star_graph(3) + >>> random_path = nx.generate_random_paths(G, 2) + + By passing a dictionary into `index_map`, it will build an + inverted index mapping of nodes to the paths in which that node is present: + + >>> G = nx.star_graph(3) + >>> index_map = {} + >>> random_path = nx.generate_random_paths(G, 3, index_map=index_map) + >>> paths_containing_node_0 = [random_path[path_idx] for path_idx in index_map.get(0, [])] + + References + ---------- + .. [1] Zhang, J., Tang, J., Ma, C., Tong, H., Jing, Y., & Li, J. + Panther: Fast top-k similarity search on large networks. + In Proceedings of the ACM SIGKDD International Conference + on Knowledge Discovery and Data Mining (Vol. 2015-August, pp. 1445–1454). + Association for Computing Machinery. https://doi.org/10.1145/2783258.2783267. + """ + import numpy as np + + # Calculate transition probabilities between + # every pair of vertices according to Eq. (3) + adj_mat = nx.to_numpy_array(G, weight=weight) + inv_row_sums = np.reciprocal(adj_mat.sum(axis=1)).reshape(-1, 1) + transition_probabilities = adj_mat * inv_row_sums + + node_map = np.array(G) + num_nodes = G.number_of_nodes() + + for path_index in range(sample_size): + # Sample current vertex v = v_i uniformly at random + node_index = np.random.randint(0, high=num_nodes) + node = node_map[node_index] + + # Add v into p_r and add p_r into the path set + # of v, i.e., P_v + path = [node] + + # Build the inverted index (P_v) of vertices to paths + if index_map is not None: + if node in index_map: + index_map[node].add(path_index) + else: + index_map[node] = {path_index} + + starting_index = node_index + for _ in range(path_length): + # Randomly sample a neighbor (v_j) according + # to transition probabilities from ``node`` (v) to its neighbors + neighbor_index = np.random.choice( + num_nodes, p=transition_probabilities[starting_index] + ) + + # Set current vertex (v = v_j) + starting_index = neighbor_index + + # Add v into p_r + neighbor_node = node_map[neighbor_index] + path.append(neighbor_node) + + # Add p_r into P_v + if index_map is not None: + if neighbor_node in index_map: + index_map[neighbor_node].add(path_index) + else: + index_map[neighbor_node] = {path_index} + + yield path diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/sparsifiers.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/sparsifiers.py new file mode 100644 index 0000000000000000000000000000000000000000..a94aee0d09d65edb9591037bb7b9e3b59972d0d2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/sparsifiers.py @@ -0,0 +1,295 @@ +"""Functions for computing sparsifiers of graphs.""" +import math + +import networkx as nx +from networkx.utils import not_implemented_for, py_random_state + +__all__ = ["spanner"] + + +@not_implemented_for("directed") +@not_implemented_for("multigraph") +@py_random_state(3) +@nx._dispatch(edge_attrs="weight") +def spanner(G, stretch, weight=None, seed=None): + """Returns a spanner of the given graph with the given stretch. + + A spanner of a graph G = (V, E) with stretch t is a subgraph + H = (V, E_S) such that E_S is a subset of E and the distance between + any pair of nodes in H is at most t times the distance between the + nodes in G. + + Parameters + ---------- + G : NetworkX graph + An undirected simple graph. + + stretch : float + The stretch of the spanner. + + weight : object + The edge attribute to use as distance. + + seed : integer, random_state, or None (default) + Indicator of random number generation state. + See :ref:`Randomness`. + + Returns + ------- + NetworkX graph + A spanner of the given graph with the given stretch. + + Raises + ------ + ValueError + If a stretch less than 1 is given. + + Notes + ----- + This function implements the spanner algorithm by Baswana and Sen, + see [1]. + + This algorithm is a randomized las vegas algorithm: The expected + running time is O(km) where k = (stretch + 1) // 2 and m is the + number of edges in G. The returned graph is always a spanner of the + given graph with the specified stretch. For weighted graphs the + number of edges in the spanner is O(k * n^(1 + 1 / k)) where k is + defined as above and n is the number of nodes in G. For unweighted + graphs the number of edges is O(n^(1 + 1 / k) + kn). + + References + ---------- + [1] S. Baswana, S. Sen. A Simple and Linear Time Randomized + Algorithm for Computing Sparse Spanners in Weighted Graphs. + Random Struct. Algorithms 30(4): 532-563 (2007). + """ + if stretch < 1: + raise ValueError("stretch must be at least 1") + + k = (stretch + 1) // 2 + + # initialize spanner H with empty edge set + H = nx.empty_graph() + H.add_nodes_from(G.nodes) + + # phase 1: forming the clusters + # the residual graph has V' from the paper as its node set + # and E' from the paper as its edge set + residual_graph = _setup_residual_graph(G, weight) + # clustering is a dictionary that maps nodes in a cluster to the + # cluster center + clustering = {v: v for v in G.nodes} + sample_prob = math.pow(G.number_of_nodes(), -1 / k) + size_limit = 2 * math.pow(G.number_of_nodes(), 1 + 1 / k) + + i = 0 + while i < k - 1: + # step 1: sample centers + sampled_centers = set() + for center in set(clustering.values()): + if seed.random() < sample_prob: + sampled_centers.add(center) + + # combined loop for steps 2 and 3 + edges_to_add = set() + edges_to_remove = set() + new_clustering = {} + for v in residual_graph.nodes: + if clustering[v] in sampled_centers: + continue + + # step 2: find neighboring (sampled) clusters and + # lightest edges to them + lightest_edge_neighbor, lightest_edge_weight = _lightest_edge_dicts( + residual_graph, clustering, v + ) + neighboring_sampled_centers = ( + set(lightest_edge_weight.keys()) & sampled_centers + ) + + # step 3: add edges to spanner + if not neighboring_sampled_centers: + # connect to each neighboring center via lightest edge + for neighbor in lightest_edge_neighbor.values(): + edges_to_add.add((v, neighbor)) + # remove all incident edges + for neighbor in residual_graph.adj[v]: + edges_to_remove.add((v, neighbor)) + + else: # there is a neighboring sampled center + closest_center = min( + neighboring_sampled_centers, key=lightest_edge_weight.get + ) + closest_center_weight = lightest_edge_weight[closest_center] + closest_center_neighbor = lightest_edge_neighbor[closest_center] + + edges_to_add.add((v, closest_center_neighbor)) + new_clustering[v] = closest_center + + # connect to centers with edge weight less than + # closest_center_weight + for center, edge_weight in lightest_edge_weight.items(): + if edge_weight < closest_center_weight: + neighbor = lightest_edge_neighbor[center] + edges_to_add.add((v, neighbor)) + + # remove edges to centers with edge weight less than + # closest_center_weight + for neighbor in residual_graph.adj[v]: + neighbor_cluster = clustering[neighbor] + neighbor_weight = lightest_edge_weight[neighbor_cluster] + if ( + neighbor_cluster == closest_center + or neighbor_weight < closest_center_weight + ): + edges_to_remove.add((v, neighbor)) + + # check whether iteration added too many edges to spanner, + # if so repeat + if len(edges_to_add) > size_limit: + # an iteration is repeated O(1) times on expectation + continue + + # iteration succeeded + i = i + 1 + + # actually add edges to spanner + for u, v in edges_to_add: + _add_edge_to_spanner(H, residual_graph, u, v, weight) + + # actually delete edges from residual graph + residual_graph.remove_edges_from(edges_to_remove) + + # copy old clustering data to new_clustering + for node, center in clustering.items(): + if center in sampled_centers: + new_clustering[node] = center + clustering = new_clustering + + # step 4: remove intra-cluster edges + for u in residual_graph.nodes: + for v in list(residual_graph.adj[u]): + if clustering[u] == clustering[v]: + residual_graph.remove_edge(u, v) + + # update residual graph node set + for v in list(residual_graph.nodes): + if v not in clustering: + residual_graph.remove_node(v) + + # phase 2: vertex-cluster joining + for v in residual_graph.nodes: + lightest_edge_neighbor, _ = _lightest_edge_dicts(residual_graph, clustering, v) + for neighbor in lightest_edge_neighbor.values(): + _add_edge_to_spanner(H, residual_graph, v, neighbor, weight) + + return H + + +def _setup_residual_graph(G, weight): + """Setup residual graph as a copy of G with unique edges weights. + + The node set of the residual graph corresponds to the set V' from + the Baswana-Sen paper and the edge set corresponds to the set E' + from the paper. + + This function associates distinct weights to the edges of the + residual graph (even for unweighted input graphs), as required by + the algorithm. + + Parameters + ---------- + G : NetworkX graph + An undirected simple graph. + + weight : object + The edge attribute to use as distance. + + Returns + ------- + NetworkX graph + The residual graph used for the Baswana-Sen algorithm. + """ + residual_graph = G.copy() + + # establish unique edge weights, even for unweighted graphs + for u, v in G.edges(): + if not weight: + residual_graph[u][v]["weight"] = (id(u), id(v)) + else: + residual_graph[u][v]["weight"] = (G[u][v][weight], id(u), id(v)) + + return residual_graph + + +def _lightest_edge_dicts(residual_graph, clustering, node): + """Find the lightest edge to each cluster. + + Searches for the minimum-weight edge to each cluster adjacent to + the given node. + + Parameters + ---------- + residual_graph : NetworkX graph + The residual graph used by the Baswana-Sen algorithm. + + clustering : dictionary + The current clustering of the nodes. + + node : node + The node from which the search originates. + + Returns + ------- + lightest_edge_neighbor, lightest_edge_weight : dictionary, dictionary + lightest_edge_neighbor is a dictionary that maps a center C to + a node v in the corresponding cluster such that the edge from + the given node to v is the lightest edge from the given node to + any node in cluster. lightest_edge_weight maps a center C to the + weight of the aforementioned edge. + + Notes + ----- + If a cluster has no node that is adjacent to the given node in the + residual graph then the center of the cluster is not a key in the + returned dictionaries. + """ + lightest_edge_neighbor = {} + lightest_edge_weight = {} + for neighbor in residual_graph.adj[node]: + neighbor_center = clustering[neighbor] + weight = residual_graph[node][neighbor]["weight"] + if ( + neighbor_center not in lightest_edge_weight + or weight < lightest_edge_weight[neighbor_center] + ): + lightest_edge_neighbor[neighbor_center] = neighbor + lightest_edge_weight[neighbor_center] = weight + return lightest_edge_neighbor, lightest_edge_weight + + +def _add_edge_to_spanner(H, residual_graph, u, v, weight): + """Add the edge {u, v} to the spanner H and take weight from + the residual graph. + + Parameters + ---------- + H : NetworkX graph + The spanner under construction. + + residual_graph : NetworkX graph + The residual graph used by the Baswana-Sen algorithm. The weight + for the edge is taken from this graph. + + u : node + One endpoint of the edge. + + v : node + The other endpoint of the edge. + + weight : object + The edge attribute to use as distance. + """ + H.add_edge(u, v) + if weight: + H[u][v][weight] = residual_graph[u][v]["weight"][0] diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_chains.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_chains.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..67e118e85e8f01a5f629715ffd55e8f95bc051d4 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_chains.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_chordal.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_chordal.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4325a49940e5c615eb241180fcbb7b73b35e71fc Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_chordal.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_clique.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_clique.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9678b64f8ab7481a669a07d31c079e4b4bad5406 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_clique.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_cluster.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_cluster.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..27c4e2b8ea1f50058eb7432f7684da1d70c338d7 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_cluster.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_covering.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_covering.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..10c3e1375c5ea595efc5bb47e5545d036638b9f4 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_covering.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_distance_measures.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_distance_measures.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ef54f438a4f5f3c88bd6911a9b927f6755df93af Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_distance_measures.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_dominance.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_dominance.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fef449ee454c1078cb05d6aa127186c30ec8c3d7 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_dominance.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_euler.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_euler.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0a381dc6e37c656515ce1781ea89a86906627daa Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_euler.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_isolate.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_isolate.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a08f0e8bff07bb79674117e91a9c0e9dcb5d809f Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_isolate.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_matching.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_matching.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2d9440f4515c10a19928cb8ddc6ca15debb8f80b Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_matching.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_max_weight_clique.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_max_weight_clique.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5a6600e7da19796ec2b47f353cc6af09e333717c Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_max_weight_clique.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_mis.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_mis.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..36e16590291d06227090373155d9a21f83a578fb Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_mis.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_moral.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_moral.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7245fd4acea76a82b946b8acd3f4a57eee099f77 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_moral.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_node_classification.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_node_classification.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4f8f90c36e7b463fb332c4462fefe9cdf389b61c Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_node_classification.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_regular.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_regular.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..850d2dab2ccbafc996b70d1f782b84065ba8b4ec Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_regular.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_similarity.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_similarity.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eba2935b5fcb9e0398cc237bf300598db5b6d1ba Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_similarity.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_summarization.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_summarization.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..be7d6f07531f4859251c1d6412ce4a442ea11d82 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/algorithms/tests/__pycache__/test_summarization.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/classes/__pycache__/function.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/classes/__pycache__/function.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ed76eb6580f1aeaab5562a6f4d773a0d2a07e202 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/classes/__pycache__/function.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/__pycache__/graph6.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/__pycache__/graph6.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a9fc96fb748c129a15d3a555d5aec4db46f868e6 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/__pycache__/graph6.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tests/__pycache__/test_cytoscape.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tests/__pycache__/test_cytoscape.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9932950605818b585c0f22f08e95777f970d15fe Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tests/__pycache__/test_cytoscape.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tests/test_node_link.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tests/test_node_link.py new file mode 100644 index 0000000000000000000000000000000000000000..a432666b650a44013a7b5c385d516585e4d6cab3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tests/test_node_link.py @@ -0,0 +1,144 @@ +import json + +import pytest + +import networkx as nx +from networkx.readwrite.json_graph import node_link_data, node_link_graph + + +class TestNodeLink: + # TODO: To be removed when signature change complete + def test_custom_attrs_dep(self): + G = nx.path_graph(4) + G.add_node(1, color="red") + G.add_edge(1, 2, width=7) + G.graph[1] = "one" + G.graph["foo"] = "bar" + + attrs = { + "source": "c_source", + "target": "c_target", + "name": "c_id", + "key": "c_key", + "link": "c_links", + } + + H = node_link_graph(node_link_data(G, **attrs), multigraph=False, **attrs) + assert nx.is_isomorphic(G, H) + assert H.graph["foo"] == "bar" + assert H.nodes[1]["color"] == "red" + assert H[1][2]["width"] == 7 + + # provide only a partial dictionary of keywords. + # This is similar to an example in the doc string + attrs = { + "link": "c_links", + "source": "c_source", + "target": "c_target", + } + H = node_link_graph(node_link_data(G, **attrs), multigraph=False, **attrs) + assert nx.is_isomorphic(G, H) + assert H.graph["foo"] == "bar" + assert H.nodes[1]["color"] == "red" + assert H[1][2]["width"] == 7 + + def test_exception_dep(self): + with pytest.raises(nx.NetworkXError): + G = nx.MultiDiGraph() + node_link_data(G, name="node", source="node", target="node", key="node") + + def test_graph(self): + G = nx.path_graph(4) + H = node_link_graph(node_link_data(G)) + assert nx.is_isomorphic(G, H) + + def test_graph_attributes(self): + G = nx.path_graph(4) + G.add_node(1, color="red") + G.add_edge(1, 2, width=7) + G.graph[1] = "one" + G.graph["foo"] = "bar" + + H = node_link_graph(node_link_data(G)) + assert H.graph["foo"] == "bar" + assert H.nodes[1]["color"] == "red" + assert H[1][2]["width"] == 7 + + d = json.dumps(node_link_data(G)) + H = node_link_graph(json.loads(d)) + assert H.graph["foo"] == "bar" + assert H.graph["1"] == "one" + assert H.nodes[1]["color"] == "red" + assert H[1][2]["width"] == 7 + + def test_digraph(self): + G = nx.DiGraph() + H = node_link_graph(node_link_data(G)) + assert H.is_directed() + + def test_multigraph(self): + G = nx.MultiGraph() + G.add_edge(1, 2, key="first") + G.add_edge(1, 2, key="second", color="blue") + H = node_link_graph(node_link_data(G)) + assert nx.is_isomorphic(G, H) + assert H[1][2]["second"]["color"] == "blue" + + def test_graph_with_tuple_nodes(self): + G = nx.Graph() + G.add_edge((0, 0), (1, 0), color=[255, 255, 0]) + d = node_link_data(G) + dumped_d = json.dumps(d) + dd = json.loads(dumped_d) + H = node_link_graph(dd) + assert H.nodes[(0, 0)] == G.nodes[(0, 0)] + assert H[(0, 0)][(1, 0)]["color"] == [255, 255, 0] + + def test_unicode_keys(self): + q = "qualité" + G = nx.Graph() + G.add_node(1, **{q: q}) + s = node_link_data(G) + output = json.dumps(s, ensure_ascii=False) + data = json.loads(output) + H = node_link_graph(data) + assert H.nodes[1][q] == q + + def test_exception(self): + with pytest.raises(nx.NetworkXError): + G = nx.MultiDiGraph() + attrs = {"name": "node", "source": "node", "target": "node", "key": "node"} + node_link_data(G, **attrs) + + def test_string_ids(self): + q = "qualité" + G = nx.DiGraph() + G.add_node("A") + G.add_node(q) + G.add_edge("A", q) + data = node_link_data(G) + assert data["links"][0]["source"] == "A" + assert data["links"][0]["target"] == q + H = node_link_graph(data) + assert nx.is_isomorphic(G, H) + + def test_custom_attrs(self): + G = nx.path_graph(4) + G.add_node(1, color="red") + G.add_edge(1, 2, width=7) + G.graph[1] = "one" + G.graph["foo"] = "bar" + + attrs = { + "source": "c_source", + "target": "c_target", + "name": "c_id", + "key": "c_key", + "link": "c_links", + } + + H = node_link_graph(node_link_data(G, **attrs), multigraph=False, **attrs) + assert nx.is_isomorphic(G, H) + assert H.graph["foo"] == "bar" + assert H.nodes[1]["color"] == "red" + assert H[1][2]["width"] == 7 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tree.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tree.py new file mode 100644 index 0000000000000000000000000000000000000000..c0b3af183786c79a0a8e1836467248ee80a1e153 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/json_graph/tree.py @@ -0,0 +1,137 @@ +from itertools import chain + +import networkx as nx + +__all__ = ["tree_data", "tree_graph"] + + +def tree_data(G, root, ident="id", children="children"): + """Returns data in tree format that is suitable for JSON serialization + and use in JavaScript documents. + + Parameters + ---------- + G : NetworkX graph + G must be an oriented tree + + root : node + The root of the tree + + ident : string + Attribute name for storing NetworkX-internal graph data. `ident` must + have a different value than `children`. The default is 'id'. + + children : string + Attribute name for storing NetworkX-internal graph data. `children` + must have a different value than `ident`. The default is 'children'. + + Returns + ------- + data : dict + A dictionary with node-link formatted data. + + Raises + ------ + NetworkXError + If `children` and `ident` attributes are identical. + + Examples + -------- + >>> from networkx.readwrite import json_graph + >>> G = nx.DiGraph([(1, 2)]) + >>> data = json_graph.tree_data(G, root=1) + + To serialize with json + + >>> import json + >>> s = json.dumps(data) + + Notes + ----- + Node attributes are stored in this format but keys + for attributes must be strings if you want to serialize with JSON. + + Graph and edge attributes are not stored. + + See Also + -------- + tree_graph, node_link_data, adjacency_data + """ + if G.number_of_nodes() != G.number_of_edges() + 1: + raise TypeError("G is not a tree.") + if not G.is_directed(): + raise TypeError("G is not directed.") + if not nx.is_weakly_connected(G): + raise TypeError("G is not weakly connected.") + + if ident == children: + raise nx.NetworkXError("The values for `id` and `children` must be different.") + + def add_children(n, G): + nbrs = G[n] + if len(nbrs) == 0: + return [] + children_ = [] + for child in nbrs: + d = {**G.nodes[child], ident: child} + c = add_children(child, G) + if c: + d[children] = c + children_.append(d) + return children_ + + return {**G.nodes[root], ident: root, children: add_children(root, G)} + + +@nx._dispatch(graphs=None) +def tree_graph(data, ident="id", children="children"): + """Returns graph from tree data format. + + Parameters + ---------- + data : dict + Tree formatted graph data + + ident : string + Attribute name for storing NetworkX-internal graph data. `ident` must + have a different value than `children`. The default is 'id'. + + children : string + Attribute name for storing NetworkX-internal graph data. `children` + must have a different value than `ident`. The default is 'children'. + + Returns + ------- + G : NetworkX DiGraph + + Examples + -------- + >>> from networkx.readwrite import json_graph + >>> G = nx.DiGraph([(1, 2)]) + >>> data = json_graph.tree_data(G, root=1) + >>> H = json_graph.tree_graph(data) + + See Also + -------- + tree_data, node_link_data, adjacency_data + """ + graph = nx.DiGraph() + + def add_children(parent, children_): + for data in children_: + child = data[ident] + graph.add_edge(parent, child) + grandchildren = data.get(children, []) + if grandchildren: + add_children(child, grandchildren) + nodedata = { + str(k): v for k, v in data.items() if k != ident and k != children + } + graph.add_node(child, **nodedata) + + root = data[ident] + children_ = data.get(children, []) + nodedata = {str(k): v for k, v in data.items() if k != ident and k != children} + graph.add_node(root, **nodedata) + add_children(root, children_) + return graph diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/__pycache__/test_leda.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/__pycache__/test_leda.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4678d28595479e3deabd94fcb5ab71a930d7c21b Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/__pycache__/test_leda.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/__pycache__/test_sparse6.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/__pycache__/test_sparse6.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1176afbe077e21ef4a656f39e7494125701f8228 Binary files /dev/null and b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/__pycache__/test_sparse6.cpython-311.pyc differ diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_leda.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_leda.py new file mode 100644 index 0000000000000000000000000000000000000000..8ac5ecc34bf9b42bd49e316bdc72e0e56c76a616 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_leda.py @@ -0,0 +1,30 @@ +import io + +import networkx as nx + + +class TestLEDA: + def test_parse_leda(self): + data = """#header section \nLEDA.GRAPH \nstring\nint\n-1\n#nodes section\n5 \n|{v1}| \n|{v2}| \n|{v3}| \n|{v4}| \n|{v5}| \n\n#edges section\n7 \n1 2 0 |{4}| \n1 3 0 |{3}| \n2 3 0 |{2}| \n3 4 0 |{3}| \n3 5 0 |{7}| \n4 5 0 |{6}| \n5 1 0 |{foo}|""" + G = nx.parse_leda(data) + G = nx.parse_leda(data.split("\n")) + assert sorted(G.nodes()) == ["v1", "v2", "v3", "v4", "v5"] + assert sorted(G.edges(data=True)) == [ + ("v1", "v2", {"label": "4"}), + ("v1", "v3", {"label": "3"}), + ("v2", "v3", {"label": "2"}), + ("v3", "v4", {"label": "3"}), + ("v3", "v5", {"label": "7"}), + ("v4", "v5", {"label": "6"}), + ("v5", "v1", {"label": "foo"}), + ] + + def test_read_LEDA(self): + fh = io.BytesIO() + data = """#header section \nLEDA.GRAPH \nstring\nint\n-1\n#nodes section\n5 \n|{v1}| \n|{v2}| \n|{v3}| \n|{v4}| \n|{v5}| \n\n#edges section\n7 \n1 2 0 |{4}| \n1 3 0 |{3}| \n2 3 0 |{2}| \n3 4 0 |{3}| \n3 5 0 |{7}| \n4 5 0 |{6}| \n5 1 0 |{foo}|""" + G = nx.parse_leda(data) + fh.write(data.encode("UTF-8")) + fh.seek(0) + Gin = nx.read_leda(fh) + assert sorted(G.nodes()) == sorted(Gin.nodes()) + assert sorted(G.edges()) == sorted(Gin.edges()) diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_pajek.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_pajek.py new file mode 100644 index 0000000000000000000000000000000000000000..e617c3fc75c2de8c635ef2a963bd61b33286fcb0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_pajek.py @@ -0,0 +1,130 @@ +""" +Pajek tests +""" +import os +import tempfile + +import networkx as nx +from networkx.utils import edges_equal, nodes_equal + + +class TestPajek: + @classmethod + def setup_class(cls): + cls.data = """*network Tralala\n*vertices 4\n 1 "A1" 0.0938 0.0896 ellipse x_fact 1 y_fact 1\n 2 "Bb" 0.8188 0.2458 ellipse x_fact 1 y_fact 1\n 3 "C" 0.3688 0.7792 ellipse x_fact 1\n 4 "D2" 0.9583 0.8563 ellipse x_fact 1\n*arcs\n1 1 1 h2 0 w 3 c Blue s 3 a1 -130 k1 0.6 a2 -130 k2 0.6 ap 0.5 l "Bezier loop" lc BlueViolet fos 20 lr 58 lp 0.3 la 360\n2 1 1 h2 0 a1 120 k1 1.3 a2 -120 k2 0.3 ap 25 l "Bezier arc" lphi 270 la 180 lr 19 lp 0.5\n1 2 1 h2 0 a1 40 k1 2.8 a2 30 k2 0.8 ap 25 l "Bezier arc" lphi 90 la 0 lp 0.65\n4 2 -1 h2 0 w 1 k1 -2 k2 250 ap 25 l "Circular arc" c Red lc OrangeRed\n3 4 1 p Dashed h2 0 w 2 c OliveGreen ap 25 l "Straight arc" lc PineGreen\n1 3 1 p Dashed h2 0 w 5 k1 -1 k2 -20 ap 25 l "Oval arc" c Brown lc Black\n3 3 -1 h1 6 w 1 h2 12 k1 -2 k2 -15 ap 0.5 l "Circular loop" c Red lc OrangeRed lphi 270 la 180""" + cls.G = nx.MultiDiGraph() + cls.G.add_nodes_from(["A1", "Bb", "C", "D2"]) + cls.G.add_edges_from( + [ + ("A1", "A1"), + ("A1", "Bb"), + ("A1", "C"), + ("Bb", "A1"), + ("C", "C"), + ("C", "D2"), + ("D2", "Bb"), + ] + ) + + cls.G.graph["name"] = "Tralala" + (fd, cls.fname) = tempfile.mkstemp() + with os.fdopen(fd, "wb") as fh: + fh.write(cls.data.encode("UTF-8")) + + @classmethod + def teardown_class(cls): + os.unlink(cls.fname) + + def test_parse_pajek_simple(self): + # Example without node positions or shape + data = """*Vertices 2\n1 "1"\n2 "2"\n*Edges\n1 2\n2 1""" + G = nx.parse_pajek(data) + assert sorted(G.nodes()) == ["1", "2"] + assert edges_equal(G.edges(), [("1", "2"), ("1", "2")]) + + def test_parse_pajek(self): + G = nx.parse_pajek(self.data) + assert sorted(G.nodes()) == ["A1", "Bb", "C", "D2"] + assert edges_equal( + G.edges(), + [ + ("A1", "A1"), + ("A1", "Bb"), + ("A1", "C"), + ("Bb", "A1"), + ("C", "C"), + ("C", "D2"), + ("D2", "Bb"), + ], + ) + + def test_parse_pajet_mat(self): + data = """*Vertices 3\n1 "one"\n2 "two"\n3 "three"\n*Matrix\n1 1 0\n0 1 0\n0 1 0\n""" + G = nx.parse_pajek(data) + assert set(G.nodes()) == {"one", "two", "three"} + assert G.nodes["two"] == {"id": "2"} + assert edges_equal( + set(G.edges()), + {("one", "one"), ("two", "one"), ("two", "two"), ("two", "three")}, + ) + + def test_read_pajek(self): + G = nx.parse_pajek(self.data) + Gin = nx.read_pajek(self.fname) + assert sorted(G.nodes()) == sorted(Gin.nodes()) + assert edges_equal(G.edges(), Gin.edges()) + assert self.G.graph == Gin.graph + for n in G: + assert G.nodes[n] == Gin.nodes[n] + + def test_write_pajek(self): + import io + + G = nx.parse_pajek(self.data) + fh = io.BytesIO() + nx.write_pajek(G, fh) + fh.seek(0) + H = nx.read_pajek(fh) + assert nodes_equal(list(G), list(H)) + assert edges_equal(list(G.edges()), list(H.edges())) + # Graph name is left out for now, therefore it is not tested. + # assert_equal(G.graph, H.graph) + + def test_ignored_attribute(self): + import io + + G = nx.Graph() + fh = io.BytesIO() + G.add_node(1, int_attr=1) + G.add_node(2, empty_attr=" ") + G.add_edge(1, 2, int_attr=2) + G.add_edge(2, 3, empty_attr=" ") + + import warnings + + with warnings.catch_warnings(record=True) as w: + nx.write_pajek(G, fh) + assert len(w) == 4 + + def test_noname(self): + # Make sure we can parse a line such as: *network + # Issue #952 + line = "*network\n" + other_lines = self.data.split("\n")[1:] + data = line + "\n".join(other_lines) + G = nx.parse_pajek(data) + + def test_unicode(self): + import io + + G = nx.Graph() + name1 = chr(2344) + chr(123) + chr(6543) + name2 = chr(5543) + chr(1543) + chr(324) + G.add_edge(name1, "Radiohead", foo=name2) + fh = io.BytesIO() + nx.write_pajek(G, fh) + fh.seek(0) + H = nx.read_pajek(fh) + assert nodes_equal(list(G), list(H)) + assert edges_equal(list(G.edges()), list(H.edges())) + assert G.graph == H.graph diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_sparse6.py b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_sparse6.py new file mode 100644 index 0000000000000000000000000000000000000000..c8b5e4de93ed16139c4766c3127f9397e0a4ff39 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/networkx/readwrite/tests/test_sparse6.py @@ -0,0 +1,173 @@ +import tempfile +from io import BytesIO + +import pytest + +import networkx as nx +from networkx.utils import edges_equal, nodes_equal + + +class TestSparseGraph6: + def test_from_sparse6_bytes(self): + data = b":Q___eDcdFcDeFcE`GaJ`IaHbKNbLM" + G = nx.from_sparse6_bytes(data) + assert nodes_equal( + sorted(G.nodes()), + [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17], + ) + assert edges_equal( + G.edges(), + [ + (0, 1), + (0, 2), + (0, 3), + (1, 12), + (1, 14), + (2, 13), + (2, 15), + (3, 16), + (3, 17), + (4, 7), + (4, 9), + (4, 11), + (5, 6), + (5, 8), + (5, 9), + (6, 10), + (6, 11), + (7, 8), + (7, 10), + (8, 12), + (9, 15), + (10, 14), + (11, 13), + (12, 16), + (13, 17), + (14, 17), + (15, 16), + ], + ) + + def test_from_bytes_multigraph_graph(self): + graph_data = b":An" + G = nx.from_sparse6_bytes(graph_data) + assert type(G) == nx.Graph + multigraph_data = b":Ab" + M = nx.from_sparse6_bytes(multigraph_data) + assert type(M) == nx.MultiGraph + + def test_read_sparse6(self): + data = b":Q___eDcdFcDeFcE`GaJ`IaHbKNbLM" + G = nx.from_sparse6_bytes(data) + fh = BytesIO(data) + Gin = nx.read_sparse6(fh) + assert nodes_equal(G.nodes(), Gin.nodes()) + assert edges_equal(G.edges(), Gin.edges()) + + def test_read_many_graph6(self): + # Read many graphs into list + data = b":Q___eDcdFcDeFcE`GaJ`IaHbKNbLM\n" b":Q___dCfDEdcEgcbEGbFIaJ`JaHN`IM" + fh = BytesIO(data) + glist = nx.read_sparse6(fh) + assert len(glist) == 2 + for G in glist: + assert nodes_equal( + G.nodes(), + [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17], + ) + + +class TestWriteSparse6: + """Unit tests for writing graphs in the sparse6 format. + + Most of the test cases were checked against the sparse6 encoder in Sage. + + """ + + def test_null_graph(self): + G = nx.null_graph() + result = BytesIO() + nx.write_sparse6(G, result) + assert result.getvalue() == b">>sparse6<<:?\n" + + def test_trivial_graph(self): + G = nx.trivial_graph() + result = BytesIO() + nx.write_sparse6(G, result) + assert result.getvalue() == b">>sparse6<<:@\n" + + def test_empty_graph(self): + G = nx.empty_graph(5) + result = BytesIO() + nx.write_sparse6(G, result) + assert result.getvalue() == b">>sparse6<<:D\n" + + def test_large_empty_graph(self): + G = nx.empty_graph(68) + result = BytesIO() + nx.write_sparse6(G, result) + assert result.getvalue() == b">>sparse6<<:~?@C\n" + + def test_very_large_empty_graph(self): + G = nx.empty_graph(258049) + result = BytesIO() + nx.write_sparse6(G, result) + assert result.getvalue() == b">>sparse6<<:~~???~?@\n" + + def test_complete_graph(self): + G = nx.complete_graph(4) + result = BytesIO() + nx.write_sparse6(G, result) + assert result.getvalue() == b">>sparse6<<:CcKI\n" + + def test_no_header(self): + G = nx.complete_graph(4) + result = BytesIO() + nx.write_sparse6(G, result, header=False) + assert result.getvalue() == b":CcKI\n" + + def test_padding(self): + codes = (b":Cdv", b":DaYn", b":EaYnN", b":FaYnL", b":GaYnLz") + for n, code in enumerate(codes, start=4): + G = nx.path_graph(n) + result = BytesIO() + nx.write_sparse6(G, result, header=False) + assert result.getvalue() == code + b"\n" + + def test_complete_bipartite(self): + G = nx.complete_bipartite_graph(6, 9) + result = BytesIO() + nx.write_sparse6(G, result) + # Compared with sage + expected = b">>sparse6<<:Nk" + b"?G`cJ" * 9 + b"\n" + assert result.getvalue() == expected + + def test_read_write_inverse(self): + for i in list(range(13)) + [31, 47, 62, 63, 64, 72]: + m = min(2 * i, i * i // 2) + g = nx.random_graphs.gnm_random_graph(i, m, seed=i) + gstr = BytesIO() + nx.write_sparse6(g, gstr, header=False) + # Strip the trailing newline. + gstr = gstr.getvalue().rstrip() + g2 = nx.from_sparse6_bytes(gstr) + assert g2.order() == g.order() + assert edges_equal(g2.edges(), g.edges()) + + def test_no_directed_graphs(self): + with pytest.raises(nx.NetworkXNotImplemented): + nx.write_sparse6(nx.DiGraph(), BytesIO()) + + def test_write_path(self): + # On Windows, we can't reopen a file that is open + # So, for test we get a valid name from tempfile but close it. + with tempfile.NamedTemporaryFile() as f: + fullfilename = f.name + # file should be closed now, so write_sparse6 can open it + nx.write_sparse6(nx.null_graph(), fullfilename) + fh = open(fullfilename, mode="rb") + assert fh.read() == b">>sparse6<<:?\n" + fh.close() + import os + + os.remove(fullfilename)