Add files using upload-large-folder tool

pythonProject/.venv/Lib/site-packages/networkx/algorithms/efficiency_measures.py

@@ -0,0 +1,168 @@
+"""Provides functions for computing the efficiency of nodes and graphs."""
+
+import networkx as nx
+from networkx.exception import NetworkXNoPath
+
+from ..utils import not_implemented_for
+
+__all__ = ["efficiency", "local_efficiency", "global_efficiency"]
+
+
+@not_implemented_for("directed")
+@nx._dispatchable
+def efficiency(G, u, v):
+    """Returns the efficiency of a pair of nodes in a graph.
+
+    The *efficiency* of a pair of nodes is the multiplicative inverse of the
+    shortest path distance between the nodes [1]_. Returns 0 if no path
+    between nodes.
+
+    Parameters
+    ----------
+    G : :class:`networkx.Graph`
+        An undirected graph for which to compute the average local efficiency.
+    u, v : node
+        Nodes in the graph ``G``.
+
+    Returns
+    -------
+    float
+        Multiplicative inverse of the shortest path distance between the nodes.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)])
+    >>> nx.efficiency(G, 2, 3)  # this gives efficiency for node 2 and 3
+    0.5
+
+    Notes
+    -----
+    Edge weights are ignored when computing the shortest path distances.
+
+    See also
+    --------
+    local_efficiency
+    global_efficiency
+
+    References
+    ----------
+    .. [1] Latora, Vito, and Massimo Marchiori.
+           "Efficient behavior of small-world networks."
+           *Physical Review Letters* 87.19 (2001): 198701.
+           <https://doi.org/10.1103/PhysRevLett.87.198701>
+
+    """
+    try:
+        eff = 1 / nx.shortest_path_length(G, u, v)
+    except NetworkXNoPath:
+        eff = 0
+    return eff
+
+
+@not_implemented_for("directed")
+@nx._dispatchable
+def global_efficiency(G):
+    """Returns the average global efficiency of the graph.
+
+    The *efficiency* of a pair of nodes in a graph is the multiplicative
+    inverse of the shortest path distance between the nodes. The *average
+    global efficiency* of a graph is the average efficiency of all pairs of
+    nodes [1]_.
+
+    Parameters
+    ----------
+    G : :class:`networkx.Graph`
+        An undirected graph for which to compute the average global efficiency.
+
+    Returns
+    -------
+    float
+        The average global efficiency of the graph.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)])
+    >>> round(nx.global_efficiency(G), 12)
+    0.916666666667
+
+    Notes
+    -----
+    Edge weights are ignored when computing the shortest path distances.
+
+    See also
+    --------
+    local_efficiency
+
+    References
+    ----------
+    .. [1] Latora, Vito, and Massimo Marchiori.
+           "Efficient behavior of small-world networks."
+           *Physical Review Letters* 87.19 (2001): 198701.
+           <https://doi.org/10.1103/PhysRevLett.87.198701>
+
+    """
+    n = len(G)
+    denom = n * (n - 1)
+    if denom != 0:
+        lengths = nx.all_pairs_shortest_path_length(G)
+        g_eff = 0
+        for source, targets in lengths:
+            for target, distance in targets.items():
+                if distance > 0:
+                    g_eff += 1 / distance
+        g_eff /= denom
+        # g_eff = sum(1 / d for s, tgts in lengths
+        #                   for t, d in tgts.items() if d > 0) / denom
+    else:
+        g_eff = 0
+    # TODO This can be made more efficient by computing all pairs shortest
+    # path lengths in parallel.
+    return g_eff
+
+
+@not_implemented_for("directed")
+@nx._dispatchable
+def local_efficiency(G):
+    """Returns the average local efficiency of the graph.
+
+    The *efficiency* of a pair of nodes in a graph is the multiplicative
+    inverse of the shortest path distance between the nodes. The *local
+    efficiency* of a node in the graph is the average global efficiency of the
+    subgraph induced by the neighbors of the node. The *average local
+    efficiency* is the average of the local efficiencies of each node [1]_.
+
+    Parameters
+    ----------
+    G : :class:`networkx.Graph`
+        An undirected graph for which to compute the average local efficiency.
+
+    Returns
+    -------
+    float
+        The average local efficiency of the graph.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(0, 1), (0, 2), (0, 3), (1, 2), (1, 3)])
+    >>> nx.local_efficiency(G)
+    0.9166666666666667
+
+    Notes
+    -----
+    Edge weights are ignored when computing the shortest path distances.
+
+    See also
+    --------
+    global_efficiency
+
+    References
+    ----------
+    .. [1] Latora, Vito, and Massimo Marchiori.
+           "Efficient behavior of small-world networks."
+           *Physical Review Letters* 87.19 (2001): 198701.
+           <https://doi.org/10.1103/PhysRevLett.87.198701>
+
+    """
+    # TODO This summation can be trivially parallelized.
+    efficiency_list = (global_efficiency(G.subgraph(G[v])) for v in G)
+    return sum(efficiency_list) / len(G)

pythonProject/.venv/Lib/site-packages/networkx/algorithms/euler.py

@@ -0,0 +1,469 @@
+"""
+Eulerian circuits and graphs.
+"""
+from itertools import combinations
+
+import networkx as nx
+
+from ..utils import arbitrary_element, not_implemented_for
+
+__all__ = [
+    "is_eulerian",
+    "eulerian_circuit",
+    "eulerize",
+    "is_semieulerian",
+    "has_eulerian_path",
+    "eulerian_path",
+]
+
+
+@nx._dispatchable
+def is_eulerian(G):
+    """Returns True if and only if `G` is Eulerian.
+
+    A graph is *Eulerian* if it has an Eulerian circuit. An *Eulerian
+    circuit* is a closed walk that includes each edge of a graph exactly
+    once.
+
+    Graphs with isolated vertices (i.e. vertices with zero degree) are not
+    considered to have Eulerian circuits. Therefore, if the graph is not
+    connected (or not strongly connected, for directed graphs), this function
+    returns False.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+       A graph, either directed or undirected.
+
+    Examples
+    --------
+    >>> nx.is_eulerian(nx.DiGraph({0: [3], 1: [2], 2: [3], 3: [0, 1]}))
+    True
+    >>> nx.is_eulerian(nx.complete_graph(5))
+    True
+    >>> nx.is_eulerian(nx.petersen_graph())
+    False
+
+    If you prefer to allow graphs with isolated vertices to have Eulerian circuits,
+    you can first remove such vertices and then call `is_eulerian` as below example shows.
+
+    >>> G = nx.Graph([(0, 1), (1, 2), (0, 2)])
+    >>> G.add_node(3)
+    >>> nx.is_eulerian(G)
+    False
+
+    >>> G.remove_nodes_from(list(nx.isolates(G)))
+    >>> nx.is_eulerian(G)
+    True
+
+
+    """
+    if G.is_directed():
+        # Every node must have equal in degree and out degree and the
+        # graph must be strongly connected
+        return all(
+            G.in_degree(n) == G.out_degree(n) for n in G
+        ) and nx.is_strongly_connected(G)
+    # An undirected Eulerian graph has no vertices of odd degree and
+    # must be connected.
+    return all(d % 2 == 0 for v, d in G.degree()) and nx.is_connected(G)
+
+
+@nx._dispatchable
+def is_semieulerian(G):
+    """Return True iff `G` is semi-Eulerian.
+
+    G is semi-Eulerian if it has an Eulerian path but no Eulerian circuit.
+
+    See Also
+    --------
+    has_eulerian_path
+    is_eulerian
+    """
+    return has_eulerian_path(G) and not is_eulerian(G)
+
+
+def _find_path_start(G):
+    """Return a suitable starting vertex for an Eulerian path.
+
+    If no path exists, return None.
+    """
+    if not has_eulerian_path(G):
+        return None
+
+    if is_eulerian(G):
+        return arbitrary_element(G)
+
+    if G.is_directed():
+        v1, v2 = (v for v in G if G.in_degree(v) != G.out_degree(v))
+        # Determines which is the 'start' node (as opposed to the 'end')
+        if G.out_degree(v1) > G.in_degree(v1):
+            return v1
+        else:
+            return v2
+
+    else:
+        # In an undirected graph randomly choose one of the possibilities
+        start = [v for v in G if G.degree(v) % 2 != 0][0]
+        return start
+
+
+def _simplegraph_eulerian_circuit(G, source):
+    if G.is_directed():
+        degree = G.out_degree
+        edges = G.out_edges
+    else:
+        degree = G.degree
+        edges = G.edges
+    vertex_stack = [source]
+    last_vertex = None
+    while vertex_stack:
+        current_vertex = vertex_stack[-1]
+        if degree(current_vertex) == 0:
+            if last_vertex is not None:
+                yield (last_vertex, current_vertex)
+            last_vertex = current_vertex
+            vertex_stack.pop()
+        else:
+            _, next_vertex = arbitrary_element(edges(current_vertex))
+            vertex_stack.append(next_vertex)
+            G.remove_edge(current_vertex, next_vertex)
+
+
+def _multigraph_eulerian_circuit(G, source):
+    if G.is_directed():
+        degree = G.out_degree
+        edges = G.out_edges
+    else:
+        degree = G.degree
+        edges = G.edges
+    vertex_stack = [(source, None)]
+    last_vertex = None
+    last_key = None
+    while vertex_stack:
+        current_vertex, current_key = vertex_stack[-1]
+        if degree(current_vertex) == 0:
+            if last_vertex is not None:
+                yield (last_vertex, current_vertex, last_key)
+            last_vertex, last_key = current_vertex, current_key
+            vertex_stack.pop()
+        else:
+            triple = arbitrary_element(edges(current_vertex, keys=True))
+            _, next_vertex, next_key = triple
+            vertex_stack.append((next_vertex, next_key))
+            G.remove_edge(current_vertex, next_vertex, next_key)
+
+
+@nx._dispatchable
+def eulerian_circuit(G, source=None, keys=False):
+    """Returns an iterator over the edges of an Eulerian circuit in `G`.
+
+    An *Eulerian circuit* is a closed walk that includes each edge of a
+    graph exactly once.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+       A graph, either directed or undirected.
+
+    source : node, optional
+       Starting node for circuit.
+
+    keys : bool
+       If False, edges generated by this function will be of the form
+       ``(u, v)``. Otherwise, edges will be of the form ``(u, v, k)``.
+       This option is ignored unless `G` is a multigraph.
+
+    Returns
+    -------
+    edges : iterator
+       An iterator over edges in the Eulerian circuit.
+
+    Raises
+    ------
+    NetworkXError
+       If the graph is not Eulerian.
+
+    See Also
+    --------
+    is_eulerian
+
+    Notes
+    -----
+    This is a linear time implementation of an algorithm adapted from [1]_.
+
+    For general information about Euler tours, see [2]_.
+
+    References
+    ----------
+    .. [1] J. Edmonds, E. L. Johnson.
+       Matching, Euler tours and the Chinese postman.
+       Mathematical programming, Volume 5, Issue 1 (1973), 111-114.
+    .. [2] https://en.wikipedia.org/wiki/Eulerian_path
+
+    Examples
+    --------
+    To get an Eulerian circuit in an undirected graph::
+
+        >>> G = nx.complete_graph(3)
+        >>> list(nx.eulerian_circuit(G))
+        [(0, 2), (2, 1), (1, 0)]
+        >>> list(nx.eulerian_circuit(G, source=1))
+        [(1, 2), (2, 0), (0, 1)]
+
+    To get the sequence of vertices in an Eulerian circuit::
+
+        >>> [u for u, v in nx.eulerian_circuit(G)]
+        [0, 2, 1]
+
+    """
+    if not is_eulerian(G):
+        raise nx.NetworkXError("G is not Eulerian.")
+    if G.is_directed():
+        G = G.reverse()
+    else:
+        G = G.copy()
+    if source is None:
+        source = arbitrary_element(G)
+    if G.is_multigraph():
+        for u, v, k in _multigraph_eulerian_circuit(G, source):
+            if keys:
+                yield u, v, k
+            else:
+                yield u, v
+    else:
+        yield from _simplegraph_eulerian_circuit(G, source)
+
+
+@nx._dispatchable
+def has_eulerian_path(G, source=None):
+    """Return True iff `G` has an Eulerian path.
+
+    An Eulerian path is a path in a graph which uses each edge of a graph
+    exactly once. If `source` is specified, then this function checks
+    whether an Eulerian path that starts at node `source` exists.
+
+    A directed graph has an Eulerian path iff:
+        - at most one vertex has out_degree - in_degree = 1,
+        - at most one vertex has in_degree - out_degree = 1,
+        - every other vertex has equal in_degree and out_degree,
+        - and all of its vertices belong to a single connected
+          component of the underlying undirected graph.
+
+    If `source` is not None, an Eulerian path starting at `source` exists if no
+    other node has out_degree - in_degree = 1. This is equivalent to either
+    there exists an Eulerian circuit or `source` has out_degree - in_degree = 1
+    and the conditions above hold.
+
+    An undirected graph has an Eulerian path iff:
+        - exactly zero or two vertices have odd degree,
+        - and all of its vertices belong to a single connected component.
+
+    If `source` is not None, an Eulerian path starting at `source` exists if
+    either there exists an Eulerian circuit or `source` has an odd degree and the
+    conditions above hold.
+
+    Graphs with isolated vertices (i.e. vertices with zero degree) are not considered
+    to have an Eulerian path. Therefore, if the graph is not connected (or not strongly
+    connected, for directed graphs), this function returns False.
+
+    Parameters
+    ----------
+    G : NetworkX Graph
+        The graph to find an euler path in.
+
+    source : node, optional
+        Starting node for path.
+
+    Returns
+    -------
+    Bool : True if G has an Eulerian path.
+
+    Examples
+    --------
+    If you prefer to allow graphs with isolated vertices to have Eulerian path,
+    you can first remove such vertices and then call `has_eulerian_path` as below example shows.
+
+    >>> G = nx.Graph([(0, 1), (1, 2), (0, 2)])
+    >>> G.add_node(3)
+    >>> nx.has_eulerian_path(G)
+    False
+
+    >>> G.remove_nodes_from(list(nx.isolates(G)))
+    >>> nx.has_eulerian_path(G)
+    True
+
+    See Also
+    --------
+    is_eulerian
+    eulerian_path
+    """
+    if nx.is_eulerian(G):
+        return True
+
+    if G.is_directed():
+        ins = G.in_degree
+        outs = G.out_degree
+        # Since we know it is not eulerian, outs - ins must be 1 for source
+        if source is not None and outs[source] - ins[source] != 1:
+            return False
+
+        unbalanced_ins = 0
+        unbalanced_outs = 0
+        for v in G:
+            if ins[v] - outs[v] == 1:
+                unbalanced_ins += 1
+            elif outs[v] - ins[v] == 1:
+                unbalanced_outs += 1
+            elif ins[v] != outs[v]:
+                return False
+
+        return (
+            unbalanced_ins <= 1 and unbalanced_outs <= 1 and nx.is_weakly_connected(G)
+        )
+    else:
+        # We know it is not eulerian, so degree of source must be odd.
+        if source is not None and G.degree[source] % 2 != 1:
+            return False
+
+        # Sum is 2 since we know it is not eulerian (which implies sum is 0)
+        return sum(d % 2 == 1 for v, d in G.degree()) == 2 and nx.is_connected(G)
+
+
+@nx._dispatchable
+def eulerian_path(G, source=None, keys=False):
+    """Return an iterator over the edges of an Eulerian path in `G`.
+
+    Parameters
+    ----------
+    G : NetworkX Graph
+        The graph in which to look for an eulerian path.
+    source : node or None (default: None)
+        The node at which to start the search. None means search over all
+        starting nodes.
+    keys : Bool (default: False)
+        Indicates whether to yield edge 3-tuples (u, v, edge_key).
+        The default yields edge 2-tuples
+
+    Yields
+    ------
+    Edge tuples along the eulerian path.
+
+    Warning: If `source` provided is not the start node of an Euler path
+    will raise error even if an Euler Path exists.
+    """
+    if not has_eulerian_path(G, source):
+        raise nx.NetworkXError("Graph has no Eulerian paths.")
+    if G.is_directed():
+        G = G.reverse()
+        if source is None or nx.is_eulerian(G) is False:
+            source = _find_path_start(G)
+        if G.is_multigraph():
+            for u, v, k in _multigraph_eulerian_circuit(G, source):
+                if keys:
+                    yield u, v, k
+                else:
+                    yield u, v
+        else:
+            yield from _simplegraph_eulerian_circuit(G, source)
+    else:
+        G = G.copy()
+        if source is None:
+            source = _find_path_start(G)
+        if G.is_multigraph():
+            if keys:
+                yield from reversed(
+                    [(v, u, k) for u, v, k in _multigraph_eulerian_circuit(G, source)]
+                )
+            else:
+                yield from reversed(
+                    [(v, u) for u, v, k in _multigraph_eulerian_circuit(G, source)]
+                )
+        else:
+            yield from reversed(
+                [(v, u) for u, v in _simplegraph_eulerian_circuit(G, source)]
+            )
+
+
+@not_implemented_for("directed")
+@nx._dispatchable(returns_graph=True)
+def eulerize(G):
+    """Transforms a graph into an Eulerian graph.
+
+    If `G` is Eulerian the result is `G` as a MultiGraph, otherwise the result is a smallest
+    (in terms of the number of edges) multigraph whose underlying simple graph is `G`.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+       An undirected graph
+
+    Returns
+    -------
+    G : NetworkX multigraph
+
+    Raises
+    ------
+    NetworkXError
+       If the graph is not connected.
+
+    See Also
+    --------
+    is_eulerian
+    eulerian_circuit
+
+    References
+    ----------
+    .. [1] J. Edmonds, E. L. Johnson.
+       Matching, Euler tours and the Chinese postman.
+       Mathematical programming, Volume 5, Issue 1 (1973), 111-114.
+    .. [2] https://en.wikipedia.org/wiki/Eulerian_path
+    .. [3] http://web.math.princeton.edu/math_alive/5/Notes1.pdf
+
+    Examples
+    --------
+        >>> G = nx.complete_graph(10)
+        >>> H = nx.eulerize(G)
+        >>> nx.is_eulerian(H)
+        True
+
+    """
+    if G.order() == 0:
+        raise nx.NetworkXPointlessConcept("Cannot Eulerize null graph")
+    if not nx.is_connected(G):
+        raise nx.NetworkXError("G is not connected")
+    odd_degree_nodes = [n for n, d in G.degree() if d % 2 == 1]
+    G = nx.MultiGraph(G)
+    if len(odd_degree_nodes) == 0:
+        return G
+
+    # get all shortest paths between vertices of odd degree
+    odd_deg_pairs_paths = [
+        (m, {n: nx.shortest_path(G, source=m, target=n)})
+        for m, n in combinations(odd_degree_nodes, 2)
+    ]
+
+    # use the number of vertices in a graph + 1 as an upper bound on
+    # the maximum length of a path in G
+    upper_bound_on_max_path_length = len(G) + 1
+
+    # use "len(G) + 1 - len(P)",
+    # where P is a shortest path between vertices n and m,
+    # as edge-weights in a new graph
+    # store the paths in the graph for easy indexing later
+    Gp = nx.Graph()
+    for n, Ps in odd_deg_pairs_paths:
+        for m, P in Ps.items():
+            if n != m:
+                Gp.add_edge(
+                    m, n, weight=upper_bound_on_max_path_length - len(P), path=P
+                )
+
+    # find the minimum weight matching of edges in the weighted graph
+    best_matching = nx.Graph(list(nx.max_weight_matching(Gp)))
+
+    # duplicate each edge along each path in the set of paths in Gp
+    for m, n in best_matching.edges():
+        path = Gp[m][n]["path"]
+        G.add_edges_from(nx.utils.pairwise(path))
+    return G

pythonProject/.venv/Lib/site-packages/networkx/algorithms/graph_hashing.py

@@ -0,0 +1,322 @@
+"""
+Functions for hashing graphs to strings.
+Isomorphic graphs should be assigned identical hashes.
+For now, only Weisfeiler-Lehman hashing is implemented.
+"""
+
+from collections import Counter, defaultdict
+from hashlib import blake2b
+
+import networkx as nx
+
+__all__ = ["weisfeiler_lehman_graph_hash", "weisfeiler_lehman_subgraph_hashes"]
+
+
+def _hash_label(label, digest_size):
+    return blake2b(label.encode("ascii"), digest_size=digest_size).hexdigest()
+
+
+def _init_node_labels(G, edge_attr, node_attr):
+    if node_attr:
+        return {u: str(dd[node_attr]) for u, dd in G.nodes(data=True)}
+    elif edge_attr:
+        return {u: "" for u in G}
+    else:
+        return {u: str(deg) for u, deg in G.degree()}
+
+
+def _neighborhood_aggregate(G, node, node_labels, edge_attr=None):
+    """
+    Compute new labels for given node by aggregating
+    the labels of each node's neighbors.
+    """
+    label_list = []
+    for nbr in G.neighbors(node):
+        prefix = "" if edge_attr is None else str(G[node][nbr][edge_attr])
+        label_list.append(prefix + node_labels[nbr])
+    return node_labels[node] + "".join(sorted(label_list))
+
+
+@nx._dispatchable(edge_attrs={"edge_attr": None}, node_attrs="node_attr")
+def weisfeiler_lehman_graph_hash(
+    G, edge_attr=None, node_attr=None, iterations=3, digest_size=16
+):
+    """Return Weisfeiler Lehman (WL) graph hash.
+
+    The function iteratively aggregates and hashes neighborhoods of each node.
+    After each node's neighbors are hashed to obtain updated node labels,
+    a hashed histogram of resulting labels is returned as the final hash.
+
+    Hashes are identical for isomorphic graphs and strong guarantees that
+    non-isomorphic graphs will get different hashes. See [1]_ for details.
+
+    If no node or edge attributes are provided, the degree of each node
+    is used as its initial label.
+    Otherwise, node and/or edge labels are used to compute the hash.
+
+    Parameters
+    ----------
+    G : graph
+        The graph to be hashed.
+        Can have node and/or edge attributes. Can also have no attributes.
+    edge_attr : string, optional (default=None)
+        The key in edge attribute dictionary to be used for hashing.
+        If None, edge labels are ignored.
+    node_attr: string, optional (default=None)
+        The key in node attribute dictionary to be used for hashing.
+        If None, and no edge_attr given, use the degrees of the nodes as labels.
+    iterations: int, optional (default=3)
+        Number of neighbor aggregations to perform.
+        Should be larger for larger graphs.
+    digest_size: int, optional (default=16)
+        Size (in bits) of blake2b hash digest to use for hashing node labels.
+
+    Returns
+    -------
+    h : string
+        Hexadecimal string corresponding to hash of the input graph.
+
+    Examples
+    --------
+    Two graphs with edge attributes that are isomorphic, except for
+    differences in the edge labels.
+
+    >>> G1 = nx.Graph()
+    >>> G1.add_edges_from(
+    ...     [
+    ...         (1, 2, {"label": "A"}),
+    ...         (2, 3, {"label": "A"}),
+    ...         (3, 1, {"label": "A"}),
+    ...         (1, 4, {"label": "B"}),
+    ...     ]
+    ... )
+    >>> G2 = nx.Graph()
+    >>> G2.add_edges_from(
+    ...     [
+    ...         (5, 6, {"label": "B"}),
+    ...         (6, 7, {"label": "A"}),
+    ...         (7, 5, {"label": "A"}),
+    ...         (7, 8, {"label": "A"}),
+    ...     ]
+    ... )
+
+    Omitting the `edge_attr` option, results in identical hashes.
+
+    >>> nx.weisfeiler_lehman_graph_hash(G1)
+    '7bc4dde9a09d0b94c5097b219891d81a'
+    >>> nx.weisfeiler_lehman_graph_hash(G2)
+    '7bc4dde9a09d0b94c5097b219891d81a'
+
+    With edge labels, the graphs are no longer assigned
+    the same hash digest.
+
+    >>> nx.weisfeiler_lehman_graph_hash(G1, edge_attr="label")
+    'c653d85538bcf041d88c011f4f905f10'
+    >>> nx.weisfeiler_lehman_graph_hash(G2, edge_attr="label")
+    '3dcd84af1ca855d0eff3c978d88e7ec7'
+
+    Notes
+    -----
+    To return the WL hashes of each subgraph of a graph, use
+    `weisfeiler_lehman_subgraph_hashes`
+
+    Similarity between hashes does not imply similarity between graphs.
+
+    References
+    ----------
+    .. [1] Shervashidze, Nino, Pascal Schweitzer, Erik Jan Van Leeuwen,
+       Kurt Mehlhorn, and Karsten M. Borgwardt. Weisfeiler Lehman
+       Graph Kernels. Journal of Machine Learning Research. 2011.
+       http://www.jmlr.org/papers/volume12/shervashidze11a/shervashidze11a.pdf
+
+    See also
+    --------
+    weisfeiler_lehman_subgraph_hashes
+    """
+
+    def weisfeiler_lehman_step(G, labels, edge_attr=None):
+        """
+        Apply neighborhood aggregation to each node
+        in the graph.
+        Computes a dictionary with labels for each node.
+        """
+        new_labels = {}
+        for node in G.nodes():
+            label = _neighborhood_aggregate(G, node, labels, edge_attr=edge_attr)
+            new_labels[node] = _hash_label(label, digest_size)
+        return new_labels
+
+    # set initial node labels
+    node_labels = _init_node_labels(G, edge_attr, node_attr)
+
+    subgraph_hash_counts = []
+    for _ in range(iterations):
+        node_labels = weisfeiler_lehman_step(G, node_labels, edge_attr=edge_attr)
+        counter = Counter(node_labels.values())
+        # sort the counter, extend total counts
+        subgraph_hash_counts.extend(sorted(counter.items(), key=lambda x: x[0]))
+
+    # hash the final counter
+    return _hash_label(str(tuple(subgraph_hash_counts)), digest_size)
+
+
+@nx._dispatchable(edge_attrs={"edge_attr": None}, node_attrs="node_attr")
+def weisfeiler_lehman_subgraph_hashes(
+    G,
+    edge_attr=None,
+    node_attr=None,
+    iterations=3,
+    digest_size=16,
+    include_initial_labels=False,
+):
+    """
+    Return a dictionary of subgraph hashes by node.
+
+    Dictionary keys are nodes in `G`, and values are a list of hashes.
+    Each hash corresponds to a subgraph rooted at a given node u in `G`.
+    Lists of subgraph hashes are sorted in increasing order of depth from
+    their root node, with the hash at index i corresponding to a subgraph
+    of nodes at most i edges distance from u. Thus, each list will contain
+    `iterations` elements - a hash for a subgraph at each depth. If
+    `include_initial_labels` is set to `True`, each list will additionally
+    have contain a hash of the initial node label (or equivalently a
+    subgraph of depth 0) prepended, totalling ``iterations + 1`` elements.
+
+    The function iteratively aggregates and hashes neighborhoods of each node.
+    This is achieved for each step by replacing for each node its label from
+    the previous iteration with its hashed 1-hop neighborhood aggregate.
+    The new node label is then appended to a list of node labels for each
+    node.
+
+    To aggregate neighborhoods for a node $u$ at each step, all labels of
+    nodes adjacent to $u$ are concatenated. If the `edge_attr` parameter is set,
+    labels for each neighboring node are prefixed with the value of this attribute
+    along the connecting edge from this neighbor to node $u$. The resulting string
+    is then hashed to compress this information into a fixed digest size.
+
+    Thus, at the $i$-th iteration, nodes within $i$ hops influence any given
+    hashed node label. We can therefore say that at depth $i$ for node $u$
+    we have a hash for a subgraph induced by the $i$-hop neighborhood of $u$.
+
+    The output can be used to to create general Weisfeiler-Lehman graph kernels,
+    or generate features for graphs or nodes - for example to generate 'words' in
+    a graph as seen in the 'graph2vec' algorithm.
+    See [1]_ & [2]_ respectively for details.
+
+    Hashes are identical for isomorphic subgraphs and there exist strong
+    guarantees that non-isomorphic graphs will get different hashes.
+    See [1]_ for details.
+
+    If no node or edge attributes are provided, the degree of each node
+    is used as its initial label.
+    Otherwise, node and/or edge labels are used to compute the hash.
+
+    Parameters
+    ----------
+    G : graph
+        The graph to be hashed.
+        Can have node and/or edge attributes. Can also have no attributes.
+    edge_attr : string, optional (default=None)
+        The key in edge attribute dictionary to be used for hashing.
+        If None, edge labels are ignored.
+    node_attr : string, optional (default=None)
+        The key in node attribute dictionary to be used for hashing.
+        If None, and no edge_attr given, use the degrees of the nodes as labels.
+        If None, and edge_attr is given, each node starts with an identical label.
+    iterations : int, optional (default=3)
+        Number of neighbor aggregations to perform.
+        Should be larger for larger graphs.
+    digest_size : int, optional (default=16)
+        Size (in bits) of blake2b hash digest to use for hashing node labels.
+        The default size is 16 bits.
+    include_initial_labels : bool, optional (default=False)
+        If True, include the hashed initial node label as the first subgraph
+        hash for each node.
+
+    Returns
+    -------
+    node_subgraph_hashes : dict
+        A dictionary with each key given by a node in G, and each value given
+        by the subgraph hashes in order of depth from the key node.
+
+    Examples
+    --------
+    Finding similar nodes in different graphs:
+
+    >>> G1 = nx.Graph()
+    >>> G1.add_edges_from([(1, 2), (2, 3), (2, 4), (3, 5), (4, 6), (5, 7), (6, 7)])
+    >>> G2 = nx.Graph()
+    >>> G2.add_edges_from([(1, 3), (2, 3), (1, 6), (1, 5), (4, 6)])
+    >>> g1_hashes = nx.weisfeiler_lehman_subgraph_hashes(G1, iterations=3, digest_size=8)
+    >>> g2_hashes = nx.weisfeiler_lehman_subgraph_hashes(G2, iterations=3, digest_size=8)
+
+    Even though G1 and G2 are not isomorphic (they have different numbers of edges),
+    the hash sequence of depth 3 for node 1 in G1 and node 5 in G2 are similar:
+
+    >>> g1_hashes[1]
+    ['a93b64973cfc8897', 'db1b43ae35a1878f', '57872a7d2059c1c0']
+    >>> g2_hashes[5]
+    ['a93b64973cfc8897', 'db1b43ae35a1878f', '1716d2a4012fa4bc']
+
+    The first 2 WL subgraph hashes match. From this we can conclude that it's very
+    likely the neighborhood of 2 hops around these nodes are isomorphic.
+
+    However the 3-hop neighborhoods of ``G1`` and ``G2`` are not isomorphic since the
+    3rd hashes in the lists above are not equal.
+
+    These nodes may be candidates to be classified together since their local topology
+    is similar.
+
+    Notes
+    -----
+    To hash the full graph when subgraph hashes are not needed, use
+    `weisfeiler_lehman_graph_hash` for efficiency.
+
+    Similarity between hashes does not imply similarity between graphs.
+
+    References
+    ----------
+    .. [1] Shervashidze, Nino, Pascal Schweitzer, Erik Jan Van Leeuwen,
+       Kurt Mehlhorn, and Karsten M. Borgwardt. Weisfeiler Lehman
+       Graph Kernels. Journal of Machine Learning Research. 2011.
+       http://www.jmlr.org/papers/volume12/shervashidze11a/shervashidze11a.pdf
+    .. [2] Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan,
+       Lihui Chen, Yang Liu and Shantanu Jaiswa. graph2vec: Learning
+       Distributed Representations of Graphs. arXiv. 2017
+       https://arxiv.org/pdf/1707.05005.pdf
+
+    See also
+    --------
+    weisfeiler_lehman_graph_hash
+    """
+
+    def weisfeiler_lehman_step(G, labels, node_subgraph_hashes, edge_attr=None):
+        """
+        Apply neighborhood aggregation to each node
+        in the graph.
+        Computes a dictionary with labels for each node.
+        Appends the new hashed label to the dictionary of subgraph hashes
+        originating from and indexed by each node in G
+        """
+        new_labels = {}
+        for node in G.nodes():
+            label = _neighborhood_aggregate(G, node, labels, edge_attr=edge_attr)
+            hashed_label = _hash_label(label, digest_size)
+            new_labels[node] = hashed_label
+            node_subgraph_hashes[node].append(hashed_label)
+        return new_labels
+
+    node_labels = _init_node_labels(G, edge_attr, node_attr)
+    if include_initial_labels:
+        node_subgraph_hashes = {
+            k: [_hash_label(v, digest_size)] for k, v in node_labels.items()
+        }
+    else:
+        node_subgraph_hashes = defaultdict(list)
+
+    for _ in range(iterations):
+        node_labels = weisfeiler_lehman_step(
+            G, node_labels, node_subgraph_hashes, edge_attr
+        )
+
+    return dict(node_subgraph_hashes)

pythonProject/.venv/Lib/site-packages/networkx/algorithms/graphical.py

@@ -0,0 +1,483 @@
+"""Test sequences for graphiness.
+"""
+import heapq
+
+import networkx as nx
+
+__all__ = [
+    "is_graphical",
+    "is_multigraphical",
+    "is_pseudographical",
+    "is_digraphical",
+    "is_valid_degree_sequence_erdos_gallai",
+    "is_valid_degree_sequence_havel_hakimi",
+]
+
+
+@nx._dispatchable(graphs=None)
+def is_graphical(sequence, method="eg"):
+    """Returns True if sequence is a valid degree sequence.
+
+    A degree sequence is valid if some graph can realize it.
+
+    Parameters
+    ----------
+    sequence : list or iterable container
+        A sequence of integer node degrees
+
+    method : "eg" | "hh"  (default: 'eg')
+        The method used to validate the degree sequence.
+        "eg" corresponds to the Erdős-Gallai algorithm
+        [EG1960]_, [choudum1986]_, and
+        "hh" to the Havel-Hakimi algorithm
+        [havel1955]_, [hakimi1962]_, [CL1996]_.
+
+    Returns
+    -------
+    valid : bool
+        True if the sequence is a valid degree sequence and False if not.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(4)
+    >>> sequence = (d for n, d in G.degree())
+    >>> nx.is_graphical(sequence)
+    True
+
+    To test a non-graphical sequence:
+    >>> sequence_list = [d for n, d in G.degree()]
+    >>> sequence_list[-1] += 1
+    >>> nx.is_graphical(sequence_list)
+    False
+
+    References
+    ----------
+    .. [EG1960] Erdős and Gallai, Mat. Lapok 11 264, 1960.
+    .. [choudum1986] S.A. Choudum. "A simple proof of the Erdős-Gallai theorem on
+       graph sequences." Bulletin of the Australian Mathematical Society, 33,
+       pp 67-70, 1986. https://doi.org/10.1017/S0004972700002872
+    .. [havel1955] Havel, V. "A Remark on the Existence of Finite Graphs"
+       Casopis Pest. Mat. 80, 477-480, 1955.
+    .. [hakimi1962] Hakimi, S. "On the Realizability of a Set of Integers as
+       Degrees of the Vertices of a Graph." SIAM J. Appl. Math. 10, 496-506, 1962.
+    .. [CL1996] G. Chartrand and L. Lesniak, "Graphs and Digraphs",
+       Chapman and Hall/CRC, 1996.
+    """
+    if method == "eg":
+        valid = is_valid_degree_sequence_erdos_gallai(list(sequence))
+    elif method == "hh":
+        valid = is_valid_degree_sequence_havel_hakimi(list(sequence))
+    else:
+        msg = "`method` must be 'eg' or 'hh'"
+        raise nx.NetworkXException(msg)
+    return valid
+
+
+def _basic_graphical_tests(deg_sequence):
+    # Sort and perform some simple tests on the sequence
+    deg_sequence = nx.utils.make_list_of_ints(deg_sequence)
+    p = len(deg_sequence)
+    num_degs = [0] * p
+    dmax, dmin, dsum, n = 0, p, 0, 0
+    for d in deg_sequence:
+        # Reject if degree is negative or larger than the sequence length
+        if d < 0 or d >= p:
+            raise nx.NetworkXUnfeasible
+        # Process only the non-zero integers
+        elif d > 0:
+            dmax, dmin, dsum, n = max(dmax, d), min(dmin, d), dsum + d, n + 1
+            num_degs[d] += 1
+    # Reject sequence if it has odd sum or is oversaturated
+    if dsum % 2 or dsum > n * (n - 1):
+        raise nx.NetworkXUnfeasible
+    return dmax, dmin, dsum, n, num_degs
+
+
+@nx._dispatchable(graphs=None)
+def is_valid_degree_sequence_havel_hakimi(deg_sequence):
+    r"""Returns True if deg_sequence can be realized by a simple graph.
+
+    The validation proceeds using the Havel-Hakimi theorem
+    [havel1955]_, [hakimi1962]_, [CL1996]_.
+    Worst-case run time is $O(s)$ where $s$ is the sum of the sequence.
+
+    Parameters
+    ----------
+    deg_sequence : list
+        A list of integers where each element specifies the degree of a node
+        in a graph.
+
+    Returns
+    -------
+    valid : bool
+        True if deg_sequence is graphical and False if not.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (3, 4), (4, 2), (5, 1), (5, 4)])
+    >>> sequence = (d for _, d in G.degree())
+    >>> nx.is_valid_degree_sequence_havel_hakimi(sequence)
+    True
+
+    To test a non-valid sequence:
+    >>> sequence_list = [d for _, d in G.degree()]
+    >>> sequence_list[-1] += 1
+    >>> nx.is_valid_degree_sequence_havel_hakimi(sequence_list)
+    False
+
+    Notes
+    -----
+    The ZZ condition says that for the sequence d if
+
+    .. math::
+        |d| >= \frac{(\max(d) + \min(d) + 1)^2}{4*\min(d)}
+
+    then d is graphical.  This was shown in Theorem 6 in [1]_.
+
+    References
+    ----------
+    .. [1] I.E. Zverovich and V.E. Zverovich. "Contributions to the theory
+       of graphic sequences", Discrete Mathematics, 105, pp. 292-303 (1992).
+    .. [havel1955] Havel, V. "A Remark on the Existence of Finite Graphs"
+       Casopis Pest. Mat. 80, 477-480, 1955.
+    .. [hakimi1962] Hakimi, S. "On the Realizability of a Set of Integers as
+       Degrees of the Vertices of a Graph." SIAM J. Appl. Math. 10, 496-506, 1962.
+    .. [CL1996] G. Chartrand and L. Lesniak, "Graphs and Digraphs",
+       Chapman and Hall/CRC, 1996.
+    """
+    try:
+        dmax, dmin, dsum, n, num_degs = _basic_graphical_tests(deg_sequence)
+    except nx.NetworkXUnfeasible:
+        return False
+    # Accept if sequence has no non-zero degrees or passes the ZZ condition
+    if n == 0 or 4 * dmin * n >= (dmax + dmin + 1) * (dmax + dmin + 1):
+        return True
+
+    modstubs = [0] * (dmax + 1)
+    # Successively reduce degree sequence by removing the maximum degree
+    while n > 0:
+        # Retrieve the maximum degree in the sequence
+        while num_degs[dmax] == 0:
+            dmax -= 1
+        # If there are not enough stubs to connect to, then the sequence is
+        # not graphical
+        if dmax > n - 1:
+            return False
+
+        # Remove largest stub in list
+        num_degs[dmax], n = num_degs[dmax] - 1, n - 1
+        # Reduce the next dmax largest stubs
+        mslen = 0
+        k = dmax
+        for i in range(dmax):
+            while num_degs[k] == 0:
+                k -= 1
+            num_degs[k], n = num_degs[k] - 1, n - 1
+            if k > 1:
+                modstubs[mslen] = k - 1
+                mslen += 1
+        # Add back to the list any non-zero stubs that were removed
+        for i in range(mslen):
+            stub = modstubs[i]
+            num_degs[stub], n = num_degs[stub] + 1, n + 1
+    return True
+
+
+@nx._dispatchable(graphs=None)
+def is_valid_degree_sequence_erdos_gallai(deg_sequence):
+    r"""Returns True if deg_sequence can be realized by a simple graph.
+
+    The validation is done using the Erdős-Gallai theorem [EG1960]_.
+
+    Parameters
+    ----------
+    deg_sequence : list
+        A list of integers
+
+    Returns
+    -------
+    valid : bool
+        True if deg_sequence is graphical and False if not.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (3, 4), (4, 2), (5, 1), (5, 4)])
+    >>> sequence = (d for _, d in G.degree())
+    >>> nx.is_valid_degree_sequence_erdos_gallai(sequence)
+    True
+
+    To test a non-valid sequence:
+    >>> sequence_list = [d for _, d in G.degree()]
+    >>> sequence_list[-1] += 1
+    >>> nx.is_valid_degree_sequence_erdos_gallai(sequence_list)
+    False
+
+    Notes
+    -----
+
+    This implementation uses an equivalent form of the Erdős-Gallai criterion.
+    Worst-case run time is $O(n)$ where $n$ is the length of the sequence.
+
+    Specifically, a sequence d is graphical if and only if the
+    sum of the sequence is even and for all strong indices k in the sequence,
+
+     .. math::
+
+       \sum_{i=1}^{k} d_i \leq k(k-1) + \sum_{j=k+1}^{n} \min(d_i,k)
+             = k(n-1) - ( k \sum_{j=0}^{k-1} n_j - \sum_{j=0}^{k-1} j n_j )
+
+    A strong index k is any index where d_k >= k and the value n_j is the
+    number of occurrences of j in d.  The maximal strong index is called the
+    Durfee index.
+
+    This particular rearrangement comes from the proof of Theorem 3 in [2]_.
+
+    The ZZ condition says that for the sequence d if
+
+    .. math::
+        |d| >= \frac{(\max(d) + \min(d) + 1)^2}{4*\min(d)}
+
+    then d is graphical.  This was shown in Theorem 6 in [2]_.
+
+    References
+    ----------
+    .. [1] A. Tripathi and S. Vijay. "A note on a theorem of Erdős & Gallai",
+       Discrete Mathematics, 265, pp. 417-420 (2003).
+    .. [2] I.E. Zverovich and V.E. Zverovich. "Contributions to the theory
+       of graphic sequences", Discrete Mathematics, 105, pp. 292-303 (1992).
+    .. [EG1960] Erdős and Gallai, Mat. Lapok 11 264, 1960.
+    """
+    try:
+        dmax, dmin, dsum, n, num_degs = _basic_graphical_tests(deg_sequence)
+    except nx.NetworkXUnfeasible:
+        return False
+    # Accept if sequence has no non-zero degrees or passes the ZZ condition
+    if n == 0 or 4 * dmin * n >= (dmax + dmin + 1) * (dmax + dmin + 1):
+        return True
+
+    # Perform the EG checks using the reformulation of Zverovich and Zverovich
+    k, sum_deg, sum_nj, sum_jnj = 0, 0, 0, 0
+    for dk in range(dmax, dmin - 1, -1):
+        if dk < k + 1:  # Check if already past Durfee index
+            return True
+        if num_degs[dk] > 0:
+            run_size = num_degs[dk]  # Process a run of identical-valued degrees
+            if dk < k + run_size:  # Check if end of run is past Durfee index
+                run_size = dk - k  # Adjust back to Durfee index
+            sum_deg += run_size * dk
+            for v in range(run_size):
+                sum_nj += num_degs[k + v]
+                sum_jnj += (k + v) * num_degs[k + v]
+            k += run_size
+            if sum_deg > k * (n - 1) - k * sum_nj + sum_jnj:
+                return False
+    return True
+
+
+@nx._dispatchable(graphs=None)
+def is_multigraphical(sequence):
+    """Returns True if some multigraph can realize the sequence.
+
+    Parameters
+    ----------
+    sequence : list
+        A list of integers
+
+    Returns
+    -------
+    valid : bool
+        True if deg_sequence is a multigraphic degree sequence and False if not.
+
+    Examples
+    --------
+    >>> G = nx.MultiGraph([(1, 2), (1, 3), (2, 3), (3, 4), (4, 2), (5, 1), (5, 4)])
+    >>> sequence = (d for _, d in G.degree())
+    >>> nx.is_multigraphical(sequence)
+    True
+
+    To test a non-multigraphical sequence:
+    >>> sequence_list = [d for _, d in G.degree()]
+    >>> sequence_list[-1] += 1
+    >>> nx.is_multigraphical(sequence_list)
+    False
+
+    Notes
+    -----
+    The worst-case run time is $O(n)$ where $n$ is the length of the sequence.
+
+    References
+    ----------
+    .. [1] S. L. Hakimi. "On the realizability of a set of integers as
+       degrees of the vertices of a linear graph", J. SIAM, 10, pp. 496-506
+       (1962).
+    """
+    try:
+        deg_sequence = nx.utils.make_list_of_ints(sequence)
+    except nx.NetworkXError:
+        return False
+    dsum, dmax = 0, 0
+    for d in deg_sequence:
+        if d < 0:
+            return False
+        dsum, dmax = dsum + d, max(dmax, d)
+    if dsum % 2 or dsum < 2 * dmax:
+        return False
+    return True
+
+
+@nx._dispatchable(graphs=None)
+def is_pseudographical(sequence):
+    """Returns True if some pseudograph can realize the sequence.
+
+    Every nonnegative integer sequence with an even sum is pseudographical
+    (see [1]_).
+
+    Parameters
+    ----------
+    sequence : list or iterable container
+        A sequence of integer node degrees
+
+    Returns
+    -------
+    valid : bool
+      True if the sequence is a pseudographic degree sequence and False if not.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (3, 4), (4, 2), (5, 1), (5, 4)])
+    >>> sequence = (d for _, d in G.degree())
+    >>> nx.is_pseudographical(sequence)
+    True
+
+    To test a non-pseudographical sequence:
+    >>> sequence_list = [d for _, d in G.degree()]
+    >>> sequence_list[-1] += 1
+    >>> nx.is_pseudographical(sequence_list)
+    False
+
+    Notes
+    -----
+    The worst-case run time is $O(n)$ where n is the length of the sequence.
+
+    References
+    ----------
+    .. [1] F. Boesch and F. Harary. "Line removal algorithms for graphs
+       and their degree lists", IEEE Trans. Circuits and Systems, CAS-23(12),
+       pp. 778-782 (1976).
+    """
+    try:
+        deg_sequence = nx.utils.make_list_of_ints(sequence)
+    except nx.NetworkXError:
+        return False
+    return sum(deg_sequence) % 2 == 0 and min(deg_sequence) >= 0
+
+
+@nx._dispatchable(graphs=None)
+def is_digraphical(in_sequence, out_sequence):
+    r"""Returns True if some directed graph can realize the in- and out-degree
+    sequences.
+
+    Parameters
+    ----------
+    in_sequence : list or iterable container
+        A sequence of integer node in-degrees
+
+    out_sequence : list or iterable container
+        A sequence of integer node out-degrees
+
+    Returns
+    -------
+    valid : bool
+      True if in and out-sequences are digraphic False if not.
+
+    Examples
+    --------
+    >>> G = nx.DiGraph([(1, 2), (1, 3), (2, 3), (3, 4), (4, 2), (5, 1), (5, 4)])
+    >>> in_seq = (d for n, d in G.in_degree())
+    >>> out_seq = (d for n, d in G.out_degree())
+    >>> nx.is_digraphical(in_seq, out_seq)
+    True
+
+    To test a non-digraphical scenario:
+    >>> in_seq_list = [d for n, d in G.in_degree()]
+    >>> in_seq_list[-1] += 1
+    >>> nx.is_digraphical(in_seq_list, out_seq)
+    False
+
+    Notes
+    -----
+    This algorithm is from Kleitman and Wang [1]_.
+    The worst case runtime is $O(s \times \log n)$ where $s$ and $n$ are the
+    sum and length of the sequences respectively.
+
+    References
+    ----------
+    .. [1] D.J. Kleitman and D.L. Wang
+       Algorithms for Constructing Graphs and Digraphs with Given Valences
+       and Factors, Discrete Mathematics, 6(1), pp. 79-88 (1973)
+    """
+    try:
+        in_deg_sequence = nx.utils.make_list_of_ints(in_sequence)
+        out_deg_sequence = nx.utils.make_list_of_ints(out_sequence)
+    except nx.NetworkXError:
+        return False
+    # Process the sequences and form two heaps to store degree pairs with
+    # either zero or non-zero out degrees
+    sumin, sumout, nin, nout = 0, 0, len(in_deg_sequence), len(out_deg_sequence)
+    maxn = max(nin, nout)
+    maxin = 0
+    if maxn == 0:
+        return True
+    stubheap, zeroheap = [], []
+    for n in range(maxn):
+        in_deg, out_deg = 0, 0
+        if n < nout:
+            out_deg = out_deg_sequence[n]
+        if n < nin:
+            in_deg = in_deg_sequence[n]
+        if in_deg < 0 or out_deg < 0:
+            return False
+        sumin, sumout, maxin = sumin + in_deg, sumout + out_deg, max(maxin, in_deg)
+        if in_deg > 0:
+            stubheap.append((-1 * out_deg, -1 * in_deg))
+        elif out_deg > 0:
+            zeroheap.append(-1 * out_deg)
+    if sumin != sumout:
+        return False
+    heapq.heapify(stubheap)
+    heapq.heapify(zeroheap)
+
+    modstubs = [(0, 0)] * (maxin + 1)
+    # Successively reduce degree sequence by removing the maximum out degree
+    while stubheap:
+        # Take the first value in the sequence with non-zero in degree
+        (freeout, freein) = heapq.heappop(stubheap)
+        freein *= -1
+        if freein > len(stubheap) + len(zeroheap):
+            return False
+
+        # Attach out stubs to the nodes with the most in stubs
+        mslen = 0
+        for i in range(freein):
+            if zeroheap and (not stubheap or stubheap[0][0] > zeroheap[0]):
+                stubout = heapq.heappop(zeroheap)
+                stubin = 0
+            else:
+                (stubout, stubin) = heapq.heappop(stubheap)
+            if stubout == 0:
+                return False
+            # Check if target is now totally connected
+            if stubout + 1 < 0 or stubin < 0:
+                modstubs[mslen] = (stubout + 1, stubin)
+                mslen += 1
+
+        # Add back the nodes to the heap that still have available stubs
+        for i in range(mslen):
+            stub = modstubs[i]
+            if stub[1] < 0:
+                heapq.heappush(stubheap, stub)
+            else:
+                heapq.heappush(zeroheap, stub[0])
+        if freeout < 0:
+            heapq.heappush(zeroheap, freeout)
+    return True

pythonProject/.venv/Lib/site-packages/networkx/algorithms/hierarchy.py

@@ -0,0 +1,48 @@
+"""
+Flow Hierarchy.
+"""
+import networkx as nx
+
+__all__ = ["flow_hierarchy"]
+
+
+@nx._dispatchable(edge_attrs="weight")
+def flow_hierarchy(G, weight=None):
+    """Returns the flow hierarchy of a directed network.
+
+    Flow hierarchy is defined as the fraction of edges not participating
+    in cycles in a directed graph [1]_.
+
+    Parameters
+    ----------
+    G : DiGraph or MultiDiGraph
+       A directed graph
+
+    weight : string, optional (default=None)
+       Attribute to use for edge weights. If None the weight defaults to 1.
+
+    Returns
+    -------
+    h : float
+       Flow hierarchy value
+
+    Notes
+    -----
+    The algorithm described in [1]_ computes the flow hierarchy through
+    exponentiation of the adjacency matrix.  This function implements an
+    alternative approach that finds strongly connected components.
+    An edge is in a cycle if and only if it is in a strongly connected
+    component, which can be found in $O(m)$ time using Tarjan's algorithm.
+
+    References
+    ----------
+    .. [1] Luo, J.; Magee, C.L. (2011),
+       Detecting evolving patterns of self-organizing networks by flow
+       hierarchy measurement, Complexity, Volume 16 Issue 6 53-61.
+       DOI: 10.1002/cplx.20368
+       http://web.mit.edu/~cmagee/www/documents/28-DetectingEvolvingPatterns_FlowHierarchy.pdf
+    """
+    if not G.is_directed():
+        raise nx.NetworkXError("G must be a digraph in flow_hierarchy")
+    scc = nx.strongly_connected_components(G)
+    return 1 - sum(G.subgraph(c).size(weight) for c in scc) / G.size(weight)

pythonProject/.venv/Lib/site-packages/networkx/algorithms/hybrid.py

@@ -0,0 +1,195 @@
+"""
+Provides functions for finding and testing for locally `(k, l)`-connected
+graphs.
+
+"""
+import copy
+
+import networkx as nx
+
+__all__ = ["kl_connected_subgraph", "is_kl_connected"]
+
+
+@nx._dispatchable(returns_graph=True)
+def kl_connected_subgraph(G, k, l, low_memory=False, same_as_graph=False):
+    """Returns the maximum locally `(k, l)`-connected subgraph of `G`.
+
+    A graph is locally `(k, l)`-connected if for each edge `(u, v)` in the
+    graph there are at least `l` edge-disjoint paths of length at most `k`
+    joining `u` to `v`.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+        The graph in which to find a maximum locally `(k, l)`-connected
+        subgraph.
+
+    k : integer
+        The maximum length of paths to consider. A higher number means a looser
+        connectivity requirement.
+
+    l : integer
+        The number of edge-disjoint paths. A higher number means a stricter
+        connectivity requirement.
+
+    low_memory : bool
+        If this is True, this function uses an algorithm that uses slightly
+        more time but less memory.
+
+    same_as_graph : bool
+        If True then return a tuple of the form `(H, is_same)`,
+        where `H` is the maximum locally `(k, l)`-connected subgraph and
+        `is_same` is a Boolean representing whether `G` is locally `(k,
+        l)`-connected (and hence, whether `H` is simply a copy of the input
+        graph `G`).
+
+    Returns
+    -------
+    NetworkX graph or two-tuple
+        If `same_as_graph` is True, then this function returns a
+        two-tuple as described above. Otherwise, it returns only the maximum
+        locally `(k, l)`-connected subgraph.
+
+    See also
+    --------
+    is_kl_connected
+
+    References
+    ----------
+    .. [1] Chung, Fan and Linyuan Lu. "The Small World Phenomenon in Hybrid
+           Power Law Graphs." *Complex Networks*. Springer Berlin Heidelberg,
+           2004. 89--104.
+
+    """
+    H = copy.deepcopy(G)  # subgraph we construct by removing from G
+
+    graphOK = True
+    deleted_some = True  # hack to start off the while loop
+    while deleted_some:
+        deleted_some = False
+        # We use `for edge in list(H.edges()):` instead of
+        # `for edge in H.edges():` because we edit the graph `H` in
+        # the loop. Hence using an iterator will result in
+        # `RuntimeError: dictionary changed size during iteration`
+        for edge in list(H.edges()):
+            (u, v) = edge
+            # Get copy of graph needed for this search
+            if low_memory:
+                verts = {u, v}
+                for i in range(k):
+                    for w in verts.copy():
+                        verts.update(G[w])
+                G2 = G.subgraph(verts).copy()
+            else:
+                G2 = copy.deepcopy(G)
+            ###
+            path = [u, v]
+            cnt = 0
+            accept = 0
+            while path:
+                cnt += 1  # Found a path
+                if cnt >= l:
+                    accept = 1
+                    break
+                # record edges along this graph
+                prev = u
+                for w in path:
+                    if prev != w:
+                        G2.remove_edge(prev, w)
+                        prev = w
+                #                path = shortest_path(G2, u, v, k) # ??? should "Cutoff" be k+1?
+                try:
+                    path = nx.shortest_path(G2, u, v)  # ??? should "Cutoff" be k+1?
+                except nx.NetworkXNoPath:
+                    path = False
+            # No Other Paths
+            if accept == 0:
+                H.remove_edge(u, v)
+                deleted_some = True
+                if graphOK:
+                    graphOK = False
+    # We looked through all edges and removed none of them.
+    # So, H is the maximal (k,l)-connected subgraph of G
+    if same_as_graph:
+        return (H, graphOK)
+    return H
+
+
+@nx._dispatchable
+def is_kl_connected(G, k, l, low_memory=False):
+    """Returns True if and only if `G` is locally `(k, l)`-connected.
+
+    A graph is locally `(k, l)`-connected if for each edge `(u, v)` in the
+    graph there are at least `l` edge-disjoint paths of length at most `k`
+    joining `u` to `v`.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+        The graph to test for local `(k, l)`-connectedness.
+
+    k : integer
+        The maximum length of paths to consider. A higher number means a looser
+        connectivity requirement.
+
+    l : integer
+        The number of edge-disjoint paths. A higher number means a stricter
+        connectivity requirement.
+
+    low_memory : bool
+        If this is True, this function uses an algorithm that uses slightly
+        more time but less memory.
+
+    Returns
+    -------
+    bool
+        Whether the graph is locally `(k, l)`-connected subgraph.
+
+    See also
+    --------
+    kl_connected_subgraph
+
+    References
+    ----------
+    .. [1] Chung, Fan and Linyuan Lu. "The Small World Phenomenon in Hybrid
+           Power Law Graphs." *Complex Networks*. Springer Berlin Heidelberg,
+           2004. 89--104.
+
+    """
+    graphOK = True
+    for edge in G.edges():
+        (u, v) = edge
+        # Get copy of graph needed for this search
+        if low_memory:
+            verts = {u, v}
+            for i in range(k):
+                [verts.update(G.neighbors(w)) for w in verts.copy()]
+            G2 = G.subgraph(verts)
+        else:
+            G2 = copy.deepcopy(G)
+        ###
+        path = [u, v]
+        cnt = 0
+        accept = 0
+        while path:
+            cnt += 1  # Found a path
+            if cnt >= l:
+                accept = 1
+                break
+            # record edges along this graph
+            prev = u
+            for w in path:
+                if w != prev:
+                    G2.remove_edge(prev, w)
+                    prev = w
+            #            path = shortest_path(G2, u, v, k) # ??? should "Cutoff" be k+1?
+            try:
+                path = nx.shortest_path(G2, u, v)  # ??? should "Cutoff" be k+1?
+            except nx.NetworkXNoPath:
+                path = False
+        # No Other Paths
+        if accept == 0:
+            graphOK = False
+            break
+    # return status
+    return graphOK

pythonProject/.venv/Lib/site-packages/networkx/algorithms/isolate.py

@@ -0,0 +1,107 @@
+"""
+Functions for identifying isolate (degree zero) nodes.
+"""
+import networkx as nx
+
+__all__ = ["is_isolate", "isolates", "number_of_isolates"]
+
+
+@nx._dispatchable
+def is_isolate(G, n):
+    """Determines whether a node is an isolate.
+
+    An *isolate* is a node with no neighbors (that is, with degree
+    zero). For directed graphs, this means no in-neighbors and no
+    out-neighbors.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    n : node
+        A node in `G`.
+
+    Returns
+    -------
+    is_isolate : bool
+       True if and only if `n` has no neighbors.
+
+    Examples
+    --------
+    >>> G = nx.Graph()
+    >>> G.add_edge(1, 2)
+    >>> G.add_node(3)
+    >>> nx.is_isolate(G, 2)
+    False
+    >>> nx.is_isolate(G, 3)
+    True
+    """
+    return G.degree(n) == 0
+
+
+@nx._dispatchable
+def isolates(G):
+    """Iterator over isolates in the graph.
+
+    An *isolate* is a node with no neighbors (that is, with degree
+    zero). For directed graphs, this means no in-neighbors and no
+    out-neighbors.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    Returns
+    -------
+    iterator
+        An iterator over the isolates of `G`.
+
+    Examples
+    --------
+    To get a list of all isolates of a graph, use the :class:`list`
+    constructor::
+
+        >>> G = nx.Graph()
+        >>> G.add_edge(1, 2)
+        >>> G.add_node(3)
+        >>> list(nx.isolates(G))
+        [3]
+
+    To remove all isolates in the graph, first create a list of the
+    isolates, then use :meth:`Graph.remove_nodes_from`::
+
+        >>> G.remove_nodes_from(list(nx.isolates(G)))
+        >>> list(G)
+        [1, 2]
+
+    For digraphs, isolates have zero in-degree and zero out_degre::
+
+        >>> G = nx.DiGraph([(0, 1), (1, 2)])
+        >>> G.add_node(3)
+        >>> list(nx.isolates(G))
+        [3]
+
+    """
+    return (n for n, d in G.degree() if d == 0)
+
+
+@nx._dispatchable
+def number_of_isolates(G):
+    """Returns the number of isolates in the graph.
+
+    An *isolate* is a node with no neighbors (that is, with degree
+    zero). For directed graphs, this means no in-neighbors and no
+    out-neighbors.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    Returns
+    -------
+    int
+        The number of degree zero nodes in the graph `G`.
+
+    """
+    # TODO This can be parallelized.
+    return sum(1 for v in isolates(G))

pythonProject/.venv/Lib/site-packages/networkx/algorithms/link_prediction.py

@@ -0,0 +1,688 @@
+"""
+Link prediction algorithms.
+"""
+
+
+from math import log
+
+import networkx as nx
+from networkx.utils import not_implemented_for
+
+__all__ = [
+    "resource_allocation_index",
+    "jaccard_coefficient",
+    "adamic_adar_index",
+    "preferential_attachment",
+    "cn_soundarajan_hopcroft",
+    "ra_index_soundarajan_hopcroft",
+    "within_inter_cluster",
+    "common_neighbor_centrality",
+]
+
+
+def _apply_prediction(G, func, ebunch=None):
+    """Applies the given function to each edge in the specified iterable
+    of edges.
+
+    `G` is an instance of :class:`networkx.Graph`.
+
+    `func` is a function on two inputs, each of which is a node in the
+    graph. The function can return anything, but it should return a
+    value representing a prediction of the likelihood of a "link"
+    joining the two nodes.
+
+    `ebunch` is an iterable of pairs of nodes. If not specified, all
+    non-edges in the graph `G` will be used.
+
+    """
+    if ebunch is None:
+        ebunch = nx.non_edges(G)
+    else:
+        for u, v in ebunch:
+            if u not in G:
+                raise nx.NodeNotFound(f"Node {u} not in G.")
+            if v not in G:
+                raise nx.NodeNotFound(f"Node {v} not in G.")
+    return ((u, v, func(u, v)) for u, v in ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable
+def resource_allocation_index(G, ebunch=None):
+    r"""Compute the resource allocation index of all node pairs in ebunch.
+
+    Resource allocation index of `u` and `v` is defined as
+
+    .. math::
+
+        \sum_{w \in \Gamma(u) \cap \Gamma(v)} \frac{1}{|\Gamma(w)|}
+
+    where $\Gamma(u)$ denotes the set of neighbors of $u$.
+
+    Parameters
+    ----------
+    G : graph
+        A NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        Resource allocation index will be computed for each pair of
+        nodes given in the iterable. The pairs must be given as
+        2-tuples (u, v) where u and v are nodes in the graph. If ebunch
+        is None then all nonexistent edges in the graph will be used.
+        Default value: None.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their resource allocation index.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.complete_graph(5)
+    >>> preds = nx.resource_allocation_index(G, [(0, 1), (2, 3)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p:.8f}")
+    (0, 1) -> 0.75000000
+    (2, 3) -> 0.75000000
+
+    References
+    ----------
+    .. [1] T. Zhou, L. Lu, Y.-C. Zhang.
+       Predicting missing links via local information.
+       Eur. Phys. J. B 71 (2009) 623.
+       https://arxiv.org/pdf/0901.0553.pdf
+    """
+
+    def predict(u, v):
+        return sum(1 / G.degree(w) for w in nx.common_neighbors(G, u, v))
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable
+def jaccard_coefficient(G, ebunch=None):
+    r"""Compute the Jaccard coefficient of all node pairs in ebunch.
+
+    Jaccard coefficient of nodes `u` and `v` is defined as
+
+    .. math::
+
+        \frac{|\Gamma(u) \cap \Gamma(v)|}{|\Gamma(u) \cup \Gamma(v)|}
+
+    where $\Gamma(u)$ denotes the set of neighbors of $u$.
+
+    Parameters
+    ----------
+    G : graph
+        A NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        Jaccard coefficient will be computed for each pair of nodes
+        given in the iterable. The pairs must be given as 2-tuples
+        (u, v) where u and v are nodes in the graph. If ebunch is None
+        then all nonexistent edges in the graph will be used.
+        Default value: None.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their Jaccard coefficient.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.complete_graph(5)
+    >>> preds = nx.jaccard_coefficient(G, [(0, 1), (2, 3)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p:.8f}")
+    (0, 1) -> 0.60000000
+    (2, 3) -> 0.60000000
+
+    References
+    ----------
+    .. [1] D. Liben-Nowell, J. Kleinberg.
+           The Link Prediction Problem for Social Networks (2004).
+           http://www.cs.cornell.edu/home/kleinber/link-pred.pdf
+    """
+
+    def predict(u, v):
+        union_size = len(set(G[u]) | set(G[v]))
+        if union_size == 0:
+            return 0
+        return len(nx.common_neighbors(G, u, v)) / union_size
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable
+def adamic_adar_index(G, ebunch=None):
+    r"""Compute the Adamic-Adar index of all node pairs in ebunch.
+
+    Adamic-Adar index of `u` and `v` is defined as
+
+    .. math::
+
+        \sum_{w \in \Gamma(u) \cap \Gamma(v)} \frac{1}{\log |\Gamma(w)|}
+
+    where $\Gamma(u)$ denotes the set of neighbors of $u$.
+    This index leads to zero-division for nodes only connected via self-loops.
+    It is intended to be used when no self-loops are present.
+
+    Parameters
+    ----------
+    G : graph
+        NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        Adamic-Adar index will be computed for each pair of nodes given
+        in the iterable. The pairs must be given as 2-tuples (u, v)
+        where u and v are nodes in the graph. If ebunch is None then all
+        nonexistent edges in the graph will be used.
+        Default value: None.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their Adamic-Adar index.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.complete_graph(5)
+    >>> preds = nx.adamic_adar_index(G, [(0, 1), (2, 3)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p:.8f}")
+    (0, 1) -> 2.16404256
+    (2, 3) -> 2.16404256
+
+    References
+    ----------
+    .. [1] D. Liben-Nowell, J. Kleinberg.
+           The Link Prediction Problem for Social Networks (2004).
+           http://www.cs.cornell.edu/home/kleinber/link-pred.pdf
+    """
+
+    def predict(u, v):
+        return sum(1 / log(G.degree(w)) for w in nx.common_neighbors(G, u, v))
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable
+def common_neighbor_centrality(G, ebunch=None, alpha=0.8):
+    r"""Return the CCPA score for each pair of nodes.
+
+    Compute the Common Neighbor and Centrality based Parameterized Algorithm(CCPA)
+    score of all node pairs in ebunch.
+
+    CCPA score of `u` and `v` is defined as
+
+    .. math::
+
+        \alpha \cdot (|\Gamma (u){\cap }^{}\Gamma (v)|)+(1-\alpha )\cdot \frac{N}{{d}_{uv}}
+
+    where $\Gamma(u)$ denotes the set of neighbors of $u$, $\Gamma(v)$ denotes the
+    set of neighbors of $v$, $\alpha$ is  parameter varies between [0,1], $N$ denotes
+    total number of nodes in the Graph and ${d}_{uv}$ denotes shortest distance
+    between $u$ and $v$.
+
+    This algorithm is based on two vital properties of nodes, namely the number
+    of common neighbors and their centrality. Common neighbor refers to the common
+    nodes between two nodes. Centrality refers to the prestige that a node enjoys
+    in a network.
+
+    .. seealso::
+
+        :func:`common_neighbors`
+
+    Parameters
+    ----------
+    G : graph
+        NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        Preferential attachment score will be computed for each pair of
+        nodes given in the iterable. The pairs must be given as
+        2-tuples (u, v) where u and v are nodes in the graph. If ebunch
+        is None then all nonexistent edges in the graph will be used.
+        Default value: None.
+
+    alpha : Parameter defined for participation of Common Neighbor
+            and Centrality Algorithm share. Values for alpha should
+            normally be between 0 and 1. Default value set to 0.8
+            because author found better performance at 0.8 for all the
+            dataset.
+            Default value: 0.8
+
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their Common Neighbor and Centrality based
+        Parameterized Algorithm(CCPA) score.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NetworkXAlgorithmError
+        If self loops exsists in `ebunch` or in `G` (if `ebunch` is `None`).
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.complete_graph(5)
+    >>> preds = nx.common_neighbor_centrality(G, [(0, 1), (2, 3)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p}")
+    (0, 1) -> 3.4000000000000004
+    (2, 3) -> 3.4000000000000004
+
+    References
+    ----------
+    .. [1] Ahmad, I., Akhtar, M.U., Noor, S. et al.
+           Missing Link Prediction using Common Neighbor and Centrality based Parameterized Algorithm.
+           Sci Rep 10, 364 (2020).
+           https://doi.org/10.1038/s41598-019-57304-y
+    """
+
+    # When alpha == 1, the CCPA score simplifies to the number of common neighbors.
+    if alpha == 1:
+
+        def predict(u, v):
+            if u == v:
+                raise nx.NetworkXAlgorithmError("Self loops are not supported")
+
+            return len(nx.common_neighbors(G, u, v))
+
+    else:
+        spl = dict(nx.shortest_path_length(G))
+        inf = float("inf")
+
+        def predict(u, v):
+            if u == v:
+                raise nx.NetworkXAlgorithmError("Self loops are not supported")
+            path_len = spl[u].get(v, inf)
+
+            n_nbrs = len(nx.common_neighbors(G, u, v))
+            return alpha * n_nbrs + (1 - alpha) * len(G) / path_len
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable
+def preferential_attachment(G, ebunch=None):
+    r"""Compute the preferential attachment score of all node pairs in ebunch.
+
+    Preferential attachment score of `u` and `v` is defined as
+
+    .. math::
+
+        |\Gamma(u)| |\Gamma(v)|
+
+    where $\Gamma(u)$ denotes the set of neighbors of $u$.
+
+    Parameters
+    ----------
+    G : graph
+        NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        Preferential attachment score will be computed for each pair of
+        nodes given in the iterable. The pairs must be given as
+        2-tuples (u, v) where u and v are nodes in the graph. If ebunch
+        is None then all nonexistent edges in the graph will be used.
+        Default value: None.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their preferential attachment score.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.complete_graph(5)
+    >>> preds = nx.preferential_attachment(G, [(0, 1), (2, 3)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p}")
+    (0, 1) -> 16
+    (2, 3) -> 16
+
+    References
+    ----------
+    .. [1] D. Liben-Nowell, J. Kleinberg.
+           The Link Prediction Problem for Social Networks (2004).
+           http://www.cs.cornell.edu/home/kleinber/link-pred.pdf
+    """
+
+    def predict(u, v):
+        return G.degree(u) * G.degree(v)
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable(node_attrs="community")
+def cn_soundarajan_hopcroft(G, ebunch=None, community="community"):
+    r"""Count the number of common neighbors of all node pairs in ebunch
+        using community information.
+
+    For two nodes $u$ and $v$, this function computes the number of
+    common neighbors and bonus one for each common neighbor belonging to
+    the same community as $u$ and $v$. Mathematically,
+
+    .. math::
+
+        |\Gamma(u) \cap \Gamma(v)| + \sum_{w \in \Gamma(u) \cap \Gamma(v)} f(w)
+
+    where $f(w)$ equals 1 if $w$ belongs to the same community as $u$
+    and $v$ or 0 otherwise and $\Gamma(u)$ denotes the set of
+    neighbors of $u$.
+
+    Parameters
+    ----------
+    G : graph
+        A NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        The score will be computed for each pair of nodes given in the
+        iterable. The pairs must be given as 2-tuples (u, v) where u
+        and v are nodes in the graph. If ebunch is None then all
+        nonexistent edges in the graph will be used.
+        Default value: None.
+
+    community : string, optional (default = 'community')
+        Nodes attribute name containing the community information.
+        G[u][community] identifies which community u belongs to. Each
+        node belongs to at most one community. Default value: 'community'.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their score.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NetworkXAlgorithmError
+        If no community information is available for a node in `ebunch` or in `G` (if `ebunch` is `None`).
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(3)
+    >>> G.nodes[0]["community"] = 0
+    >>> G.nodes[1]["community"] = 0
+    >>> G.nodes[2]["community"] = 0
+    >>> preds = nx.cn_soundarajan_hopcroft(G, [(0, 2)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p}")
+    (0, 2) -> 2
+
+    References
+    ----------
+    .. [1] Sucheta Soundarajan and John Hopcroft.
+       Using community information to improve the precision of link
+       prediction methods.
+       In Proceedings of the 21st international conference companion on
+       World Wide Web (WWW '12 Companion). ACM, New York, NY, USA, 607-608.
+       http://doi.acm.org/10.1145/2187980.2188150
+    """
+
+    def predict(u, v):
+        Cu = _community(G, u, community)
+        Cv = _community(G, v, community)
+        cnbors = nx.common_neighbors(G, u, v)
+        neighbors = (
+            sum(_community(G, w, community) == Cu for w in cnbors) if Cu == Cv else 0
+        )
+        return len(cnbors) + neighbors
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable(node_attrs="community")
+def ra_index_soundarajan_hopcroft(G, ebunch=None, community="community"):
+    r"""Compute the resource allocation index of all node pairs in
+    ebunch using community information.
+
+    For two nodes $u$ and $v$, this function computes the resource
+    allocation index considering only common neighbors belonging to the
+    same community as $u$ and $v$. Mathematically,
+
+    .. math::
+
+        \sum_{w \in \Gamma(u) \cap \Gamma(v)} \frac{f(w)}{|\Gamma(w)|}
+
+    where $f(w)$ equals 1 if $w$ belongs to the same community as $u$
+    and $v$ or 0 otherwise and $\Gamma(u)$ denotes the set of
+    neighbors of $u$.
+
+    Parameters
+    ----------
+    G : graph
+        A NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        The score will be computed for each pair of nodes given in the
+        iterable. The pairs must be given as 2-tuples (u, v) where u
+        and v are nodes in the graph. If ebunch is None then all
+        nonexistent edges in the graph will be used.
+        Default value: None.
+
+    community : string, optional (default = 'community')
+        Nodes attribute name containing the community information.
+        G[u][community] identifies which community u belongs to. Each
+        node belongs to at most one community. Default value: 'community'.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their score.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NetworkXAlgorithmError
+        If no community information is available for a node in `ebunch` or in `G` (if `ebunch` is `None`).
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.Graph()
+    >>> G.add_edges_from([(0, 1), (0, 2), (1, 3), (2, 3)])
+    >>> G.nodes[0]["community"] = 0
+    >>> G.nodes[1]["community"] = 0
+    >>> G.nodes[2]["community"] = 1
+    >>> G.nodes[3]["community"] = 0
+    >>> preds = nx.ra_index_soundarajan_hopcroft(G, [(0, 3)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p:.8f}")
+    (0, 3) -> 0.50000000
+
+    References
+    ----------
+    .. [1] Sucheta Soundarajan and John Hopcroft.
+       Using community information to improve the precision of link
+       prediction methods.
+       In Proceedings of the 21st international conference companion on
+       World Wide Web (WWW '12 Companion). ACM, New York, NY, USA, 607-608.
+       http://doi.acm.org/10.1145/2187980.2188150
+    """
+
+    def predict(u, v):
+        Cu = _community(G, u, community)
+        Cv = _community(G, v, community)
+        if Cu != Cv:
+            return 0
+        cnbors = nx.common_neighbors(G, u, v)
+        return sum(1 / G.degree(w) for w in cnbors if _community(G, w, community) == Cu)
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable(node_attrs="community")
+def within_inter_cluster(G, ebunch=None, delta=0.001, community="community"):
+    """Compute the ratio of within- and inter-cluster common neighbors
+    of all node pairs in ebunch.
+
+    For two nodes `u` and `v`, if a common neighbor `w` belongs to the
+    same community as them, `w` is considered as within-cluster common
+    neighbor of `u` and `v`. Otherwise, it is considered as
+    inter-cluster common neighbor of `u` and `v`. The ratio between the
+    size of the set of within- and inter-cluster common neighbors is
+    defined as the WIC measure. [1]_
+
+    Parameters
+    ----------
+    G : graph
+        A NetworkX undirected graph.
+
+    ebunch : iterable of node pairs, optional (default = None)
+        The WIC measure will be computed for each pair of nodes given in
+        the iterable. The pairs must be given as 2-tuples (u, v) where
+        u and v are nodes in the graph. If ebunch is None then all
+        nonexistent edges in the graph will be used.
+        Default value: None.
+
+    delta : float, optional (default = 0.001)
+        Value to prevent division by zero in case there is no
+        inter-cluster common neighbor between two nodes. See [1]_ for
+        details. Default value: 0.001.
+
+    community : string, optional (default = 'community')
+        Nodes attribute name containing the community information.
+        G[u][community] identifies which community u belongs to. Each
+        node belongs to at most one community. Default value: 'community'.
+
+    Returns
+    -------
+    piter : iterator
+        An iterator of 3-tuples in the form (u, v, p) where (u, v) is a
+        pair of nodes and p is their WIC measure.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is a `DiGraph`, a `Multigraph` or a `MultiDiGraph`.
+
+    NetworkXAlgorithmError
+        - If `delta` is less than or equal to zero.
+        - If no community information is available for a node in `ebunch` or in `G` (if `ebunch` is `None`).
+
+    NodeNotFound
+        If `ebunch` has a node that is not in `G`.
+
+    Examples
+    --------
+    >>> G = nx.Graph()
+    >>> G.add_edges_from([(0, 1), (0, 2), (0, 3), (1, 4), (2, 4), (3, 4)])
+    >>> G.nodes[0]["community"] = 0
+    >>> G.nodes[1]["community"] = 1
+    >>> G.nodes[2]["community"] = 0
+    >>> G.nodes[3]["community"] = 0
+    >>> G.nodes[4]["community"] = 0
+    >>> preds = nx.within_inter_cluster(G, [(0, 4)])
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p:.8f}")
+    (0, 4) -> 1.99800200
+    >>> preds = nx.within_inter_cluster(G, [(0, 4)], delta=0.5)
+    >>> for u, v, p in preds:
+    ...     print(f"({u}, {v}) -> {p:.8f}")
+    (0, 4) -> 1.33333333
+
+    References
+    ----------
+    .. [1] Jorge Carlos Valverde-Rebaza and Alneu de Andrade Lopes.
+       Link prediction in complex networks based on cluster information.
+       In Proceedings of the 21st Brazilian conference on Advances in
+       Artificial Intelligence (SBIA'12)
+       https://doi.org/10.1007/978-3-642-34459-6_10
+    """
+    if delta <= 0:
+        raise nx.NetworkXAlgorithmError("Delta must be greater than zero")
+
+    def predict(u, v):
+        Cu = _community(G, u, community)
+        Cv = _community(G, v, community)
+        if Cu != Cv:
+            return 0
+        cnbors = nx.common_neighbors(G, u, v)
+        within = {w for w in cnbors if _community(G, w, community) == Cu}
+        inter = cnbors - within
+        return len(within) / (len(inter) + delta)
+
+    return _apply_prediction(G, predict, ebunch)
+
+
+def _community(G, u, community):
+    """Get the community of the given node."""
+    node_u = G.nodes[u]
+    try:
+        return node_u[community]
+    except KeyError as err:
+        raise nx.NetworkXAlgorithmError(
+            f"No community information available for Node {u}"
+        ) from err

pythonProject/.venv/Lib/site-packages/networkx/algorithms/lowest_common_ancestors.py

@@ -0,0 +1,268 @@
+"""Algorithms for finding the lowest common ancestor of trees and DAGs."""
+from collections import defaultdict
+from collections.abc import Mapping, Set
+from itertools import combinations_with_replacement
+
+import networkx as nx
+from networkx.utils import UnionFind, arbitrary_element, not_implemented_for
+
+__all__ = [
+    "all_pairs_lowest_common_ancestor",
+    "tree_all_pairs_lowest_common_ancestor",
+    "lowest_common_ancestor",
+]
+
+
+@not_implemented_for("undirected")
+@nx._dispatchable
+def all_pairs_lowest_common_ancestor(G, pairs=None):
+    """Return the lowest common ancestor of all pairs or the provided pairs
+
+    Parameters
+    ----------
+    G : NetworkX directed graph
+
+    pairs : iterable of pairs of nodes, optional (default: all pairs)
+        The pairs of nodes of interest.
+        If None, will find the LCA of all pairs of nodes.
+
+    Yields
+    ------
+    ((node1, node2), lca) : 2-tuple
+        Where lca is least common ancestor of node1 and node2.
+        Note that for the default case, the order of the node pair is not considered,
+        e.g. you will not get both ``(a, b)`` and ``(b, a)``
+
+    Raises
+    ------
+    NetworkXPointlessConcept
+        If `G` is null.
+    NetworkXError
+        If `G` is not a DAG.
+
+    Examples
+    --------
+    The default behavior is to yield the lowest common ancestor for all
+    possible combinations of nodes in `G`, including self-pairings:
+
+    >>> G = nx.DiGraph([(0, 1), (0, 3), (1, 2)])
+    >>> dict(nx.all_pairs_lowest_common_ancestor(G))
+    {(0, 0): 0, (0, 1): 0, (0, 3): 0, (0, 2): 0, (1, 1): 1, (1, 3): 0, (1, 2): 1, (3, 3): 3, (3, 2): 0, (2, 2): 2}
+
+    The pairs argument can be used to limit the output to only the
+    specified node pairings:
+
+    >>> dict(nx.all_pairs_lowest_common_ancestor(G, pairs=[(1, 2), (2, 3)]))
+    {(1, 2): 1, (2, 3): 0}
+
+    Notes
+    -----
+    Only defined on non-null directed acyclic graphs.
+
+    See Also
+    --------
+    lowest_common_ancestor
+    """
+    if not nx.is_directed_acyclic_graph(G):
+        raise nx.NetworkXError("LCA only defined on directed acyclic graphs.")
+    if len(G) == 0:
+        raise nx.NetworkXPointlessConcept("LCA meaningless on null graphs.")
+
+    if pairs is None:
+        pairs = combinations_with_replacement(G, 2)
+    else:
+        # Convert iterator to iterable, if necessary. Trim duplicates.
+        pairs = dict.fromkeys(pairs)
+        # Verify that each of the nodes in the provided pairs is in G
+        nodeset = set(G)
+        for pair in pairs:
+            if set(pair) - nodeset:
+                raise nx.NodeNotFound(
+                    f"Node(s) {set(pair) - nodeset} from pair {pair} not in G."
+                )
+
+    # Once input validation is done, construct the generator
+    def generate_lca_from_pairs(G, pairs):
+        ancestor_cache = {}
+
+        for v, w in pairs:
+            if v not in ancestor_cache:
+                ancestor_cache[v] = nx.ancestors(G, v)
+                ancestor_cache[v].add(v)
+            if w not in ancestor_cache:
+                ancestor_cache[w] = nx.ancestors(G, w)
+                ancestor_cache[w].add(w)
+
+            common_ancestors = ancestor_cache[v] & ancestor_cache[w]
+
+            if common_ancestors:
+                common_ancestor = next(iter(common_ancestors))
+                while True:
+                    successor = None
+                    for lower_ancestor in G.successors(common_ancestor):
+                        if lower_ancestor in common_ancestors:
+                            successor = lower_ancestor
+                            break
+                    if successor is None:
+                        break
+                    common_ancestor = successor
+                yield ((v, w), common_ancestor)
+
+    return generate_lca_from_pairs(G, pairs)
+
+
+@not_implemented_for("undirected")
+@nx._dispatchable
+def lowest_common_ancestor(G, node1, node2, default=None):
+    """Compute the lowest common ancestor of the given pair of nodes.
+
+    Parameters
+    ----------
+    G : NetworkX directed graph
+
+    node1, node2 : nodes in the graph.
+
+    default : object
+        Returned if no common ancestor between `node1` and `node2`
+
+    Returns
+    -------
+    The lowest common ancestor of node1 and node2,
+    or default if they have no common ancestors.
+
+    Examples
+    --------
+    >>> G = nx.DiGraph()
+    >>> nx.add_path(G, (0, 1, 2, 3))
+    >>> nx.add_path(G, (0, 4, 3))
+    >>> nx.lowest_common_ancestor(G, 2, 4)
+    0
+
+    See Also
+    --------
+    all_pairs_lowest_common_ancestor"""
+
+    ans = list(all_pairs_lowest_common_ancestor(G, pairs=[(node1, node2)]))
+    if ans:
+        assert len(ans) == 1
+        return ans[0][1]
+    return default
+
+
+@not_implemented_for("undirected")
+@nx._dispatchable
+def tree_all_pairs_lowest_common_ancestor(G, root=None, pairs=None):
+    r"""Yield the lowest common ancestor for sets of pairs in a tree.
+
+    Parameters
+    ----------
+    G : NetworkX directed graph (must be a tree)
+
+    root : node, optional (default: None)
+        The root of the subtree to operate on.
+        If None, assume the entire graph has exactly one source and use that.
+
+    pairs : iterable or iterator of pairs of nodes, optional (default: None)
+        The pairs of interest. If None, Defaults to all pairs of nodes
+        under `root` that have a lowest common ancestor.
+
+    Returns
+    -------
+    lcas : generator of tuples `((u, v), lca)` where `u` and `v` are nodes
+        in `pairs` and `lca` is their lowest common ancestor.
+
+    Examples
+    --------
+    >>> import pprint
+    >>> G = nx.DiGraph([(1, 3), (2, 4), (1, 2)])
+    >>> pprint.pprint(dict(nx.tree_all_pairs_lowest_common_ancestor(G)))
+    {(1, 1): 1,
+     (2, 1): 1,
+     (2, 2): 2,
+     (3, 1): 1,
+     (3, 2): 1,
+     (3, 3): 3,
+     (3, 4): 1,
+     (4, 1): 1,
+     (4, 2): 2,
+     (4, 4): 4}
+
+    We can also use `pairs` argument to specify the pairs of nodes for which we
+    want to compute lowest common ancestors. Here is an example:
+
+    >>> dict(nx.tree_all_pairs_lowest_common_ancestor(G, pairs=[(1, 4), (2, 3)]))
+    {(2, 3): 1, (1, 4): 1}
+
+    Notes
+    -----
+    Only defined on non-null trees represented with directed edges from
+    parents to children. Uses Tarjan's off-line lowest-common-ancestors
+    algorithm. Runs in time $O(4 \times (V + E + P))$ time, where 4 is the largest
+    value of the inverse Ackermann function likely to ever come up in actual
+    use, and $P$ is the number of pairs requested (or $V^2$ if all are needed).
+
+    Tarjan, R. E. (1979), "Applications of path compression on balanced trees",
+    Journal of the ACM 26 (4): 690-715, doi:10.1145/322154.322161.
+
+    See Also
+    --------
+    all_pairs_lowest_common_ancestor: similar routine for general DAGs
+    lowest_common_ancestor: just a single pair for general DAGs
+    """
+    if len(G) == 0:
+        raise nx.NetworkXPointlessConcept("LCA meaningless on null graphs.")
+
+    # Index pairs of interest for efficient lookup from either side.
+    if pairs is not None:
+        pair_dict = defaultdict(set)
+        # See note on all_pairs_lowest_common_ancestor.
+        if not isinstance(pairs, Mapping | Set):
+            pairs = set(pairs)
+        for u, v in pairs:
+            for n in (u, v):
+                if n not in G:
+                    msg = f"The node {str(n)} is not in the digraph."
+                    raise nx.NodeNotFound(msg)
+            pair_dict[u].add(v)
+            pair_dict[v].add(u)
+
+    # If root is not specified, find the exactly one node with in degree 0 and
+    # use it. Raise an error if none are found, or more than one is. Also check
+    # for any nodes with in degree larger than 1, which would imply G is not a
+    # tree.
+    if root is None:
+        for n, deg in G.in_degree:
+            if deg == 0:
+                if root is not None:
+                    msg = "No root specified and tree has multiple sources."
+                    raise nx.NetworkXError(msg)
+                root = n
+            # checking deg>1 is not sufficient for MultiDiGraphs
+            elif deg > 1 and len(G.pred[n]) > 1:
+                msg = "Tree LCA only defined on trees; use DAG routine."
+                raise nx.NetworkXError(msg)
+    if root is None:
+        raise nx.NetworkXError("Graph contains a cycle.")
+
+    # Iterative implementation of Tarjan's offline lca algorithm
+    # as described in CLRS on page 521 (2nd edition)/page 584 (3rd edition)
+    uf = UnionFind()
+    ancestors = {}
+    for node in G:
+        ancestors[node] = uf[node]
+
+    colors = defaultdict(bool)
+    for node in nx.dfs_postorder_nodes(G, root):
+        colors[node] = True
+        for v in pair_dict[node] if pairs is not None else G:
+            if colors[v]:
+                # If the user requested both directions of a pair, give it.
+                # Otherwise, just give one.
+                if pairs is not None and (node, v) in pairs:
+                    yield (node, v), ancestors[uf[v]]
+                if pairs is None or (v, node) in pairs:
+                    yield (v, node), ancestors[uf[v]]
+        if node != root:
+            parent = arbitrary_element(G.pred[node])
+            uf.union(parent, node)
+            ancestors[uf[parent]] = parent

pythonProject/.venv/Lib/site-packages/networkx/algorithms/matching.py

@@ -0,0 +1,1151 @@
+"""Functions for computing and verifying matchings in a graph."""
+from collections import Counter
+from itertools import combinations, repeat
+
+import networkx as nx
+from networkx.utils import not_implemented_for
+
+__all__ = [
+    "is_matching",
+    "is_maximal_matching",
+    "is_perfect_matching",
+    "max_weight_matching",
+    "min_weight_matching",
+    "maximal_matching",
+]
+
+
+@not_implemented_for("multigraph")
+@not_implemented_for("directed")
+@nx._dispatchable
+def maximal_matching(G):
+    r"""Find a maximal matching in the graph.
+
+    A matching is a subset of edges in which no node occurs more than once.
+    A maximal matching cannot add more edges and still be a matching.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+        Undirected graph
+
+    Returns
+    -------
+    matching : set
+        A maximal matching of the graph.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (2, 4), (3, 5), (4, 5)])
+    >>> sorted(nx.maximal_matching(G))
+    [(1, 2), (3, 5)]
+
+    Notes
+    -----
+    The algorithm greedily selects a maximal matching M of the graph G
+    (i.e. no superset of M exists). It runs in $O(|E|)$ time.
+    """
+    matching = set()
+    nodes = set()
+    for edge in G.edges():
+        # If the edge isn't covered, add it to the matching
+        # then remove neighborhood of u and v from consideration.
+        u, v = edge
+        if u not in nodes and v not in nodes and u != v:
+            matching.add(edge)
+            nodes.update(edge)
+    return matching
+
+
+def matching_dict_to_set(matching):
+    """Converts matching dict format to matching set format
+
+    Converts a dictionary representing a matching (as returned by
+    :func:`max_weight_matching`) to a set representing a matching (as
+    returned by :func:`maximal_matching`).
+
+    In the definition of maximal matching adopted by NetworkX,
+    self-loops are not allowed, so the provided dictionary is expected
+    to never have any mapping from a key to itself. However, the
+    dictionary is expected to have mirrored key/value pairs, for
+    example, key ``u`` with value ``v`` and key ``v`` with value ``u``.
+
+    """
+    edges = set()
+    for edge in matching.items():
+        u, v = edge
+        if (v, u) in edges or edge in edges:
+            continue
+        if u == v:
+            raise nx.NetworkXError(f"Selfloops cannot appear in matchings {edge}")
+        edges.add(edge)
+    return edges
+
+
+@nx._dispatchable
+def is_matching(G, matching):
+    """Return True if ``matching`` is a valid matching of ``G``
+
+    A *matching* in a graph is a set of edges in which no two distinct
+    edges share a common endpoint. Each node is incident to at most one
+    edge in the matching. The edges are said to be independent.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    matching : dict or set
+        A dictionary or set representing a matching. If a dictionary, it
+        must have ``matching[u] == v`` and ``matching[v] == u`` for each
+        edge ``(u, v)`` in the matching. If a set, it must have elements
+        of the form ``(u, v)``, where ``(u, v)`` is an edge in the
+        matching.
+
+    Returns
+    -------
+    bool
+        Whether the given set or dictionary represents a valid matching
+        in the graph.
+
+    Raises
+    ------
+    NetworkXError
+        If the proposed matching has an edge to a node not in G.
+        Or if the matching is not a collection of 2-tuple edges.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (2, 4), (3, 5), (4, 5)])
+    >>> nx.is_maximal_matching(G, {1: 3, 2: 4})  # using dict to represent matching
+    True
+
+    >>> nx.is_matching(G, {(1, 3), (2, 4)})  # using set to represent matching
+    True
+
+    """
+    if isinstance(matching, dict):
+        matching = matching_dict_to_set(matching)
+
+    nodes = set()
+    for edge in matching:
+        if len(edge) != 2:
+            raise nx.NetworkXError(f"matching has non-2-tuple edge {edge}")
+        u, v = edge
+        if u not in G or v not in G:
+            raise nx.NetworkXError(f"matching contains edge {edge} with node not in G")
+        if u == v:
+            return False
+        if not G.has_edge(u, v):
+            return False
+        if u in nodes or v in nodes:
+            return False
+        nodes.update(edge)
+    return True
+
+
+@nx._dispatchable
+def is_maximal_matching(G, matching):
+    """Return True if ``matching`` is a maximal matching of ``G``
+
+    A *maximal matching* in a graph is a matching in which adding any
+    edge would cause the set to no longer be a valid matching.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    matching : dict or set
+        A dictionary or set representing a matching. If a dictionary, it
+        must have ``matching[u] == v`` and ``matching[v] == u`` for each
+        edge ``(u, v)`` in the matching. If a set, it must have elements
+        of the form ``(u, v)``, where ``(u, v)`` is an edge in the
+        matching.
+
+    Returns
+    -------
+    bool
+        Whether the given set or dictionary represents a valid maximal
+        matching in the graph.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (3, 4), (3, 5)])
+    >>> nx.is_maximal_matching(G, {(1, 2), (3, 4)})
+    True
+
+    """
+    if isinstance(matching, dict):
+        matching = matching_dict_to_set(matching)
+    # If the given set is not a matching, then it is not a maximal matching.
+    edges = set()
+    nodes = set()
+    for edge in matching:
+        if len(edge) != 2:
+            raise nx.NetworkXError(f"matching has non-2-tuple edge {edge}")
+        u, v = edge
+        if u not in G or v not in G:
+            raise nx.NetworkXError(f"matching contains edge {edge} with node not in G")
+        if u == v:
+            return False
+        if not G.has_edge(u, v):
+            return False
+        if u in nodes or v in nodes:
+            return False
+        nodes.update(edge)
+        edges.add(edge)
+        edges.add((v, u))
+    # A matching is maximal if adding any new edge from G to it
+    # causes the resulting set to match some node twice.
+    # Be careful to check for adding selfloops
+    for u, v in G.edges:
+        if (u, v) not in edges:
+            # could add edge (u, v) to edges and have a bigger matching
+            if u not in nodes and v not in nodes and u != v:
+                return False
+    return True
+
+
+@nx._dispatchable
+def is_perfect_matching(G, matching):
+    """Return True if ``matching`` is a perfect matching for ``G``
+
+    A *perfect matching* in a graph is a matching in which exactly one edge
+    is incident upon each vertex.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    matching : dict or set
+        A dictionary or set representing a matching. If a dictionary, it
+        must have ``matching[u] == v`` and ``matching[v] == u`` for each
+        edge ``(u, v)`` in the matching. If a set, it must have elements
+        of the form ``(u, v)``, where ``(u, v)`` is an edge in the
+        matching.
+
+    Returns
+    -------
+    bool
+        Whether the given set or dictionary represents a valid perfect
+        matching in the graph.
+
+    Examples
+    --------
+    >>> G = nx.Graph([(1, 2), (1, 3), (2, 3), (2, 4), (3, 5), (4, 5), (4, 6)])
+    >>> my_match = {1: 2, 3: 5, 4: 6}
+    >>> nx.is_perfect_matching(G, my_match)
+    True
+
+    """
+    if isinstance(matching, dict):
+        matching = matching_dict_to_set(matching)
+
+    nodes = set()
+    for edge in matching:
+        if len(edge) != 2:
+            raise nx.NetworkXError(f"matching has non-2-tuple edge {edge}")
+        u, v = edge
+        if u not in G or v not in G:
+            raise nx.NetworkXError(f"matching contains edge {edge} with node not in G")
+        if u == v:
+            return False
+        if not G.has_edge(u, v):
+            return False
+        if u in nodes or v in nodes:
+            return False
+        nodes.update(edge)
+    return len(nodes) == len(G)
+
+
+@not_implemented_for("multigraph")
+@not_implemented_for("directed")
+@nx._dispatchable(edge_attrs="weight")
+def min_weight_matching(G, weight="weight"):
+    """Computing a minimum-weight maximal matching of G.
+
+    Use the maximum-weight algorithm with edge weights subtracted
+    from the maximum weight of all edges.
+
+    A matching is a subset of edges in which no node occurs more than once.
+    The weight of a matching is the sum of the weights of its edges.
+    A maximal matching cannot add more edges and still be a matching.
+    The cardinality of a matching is the number of matched edges.
+
+    This method replaces the edge weights with 1 plus the maximum edge weight
+    minus the original edge weight.
+
+    new_weight = (max_weight + 1) - edge_weight
+
+    then runs :func:`max_weight_matching` with the new weights.
+    The max weight matching with these new weights corresponds
+    to the min weight matching using the original weights.
+    Adding 1 to the max edge weight keeps all edge weights positive
+    and as integers if they started as integers.
+
+    You might worry that adding 1 to each weight would make the algorithm
+    favor matchings with more edges. But we use the parameter
+    `maxcardinality=True` in `max_weight_matching` to ensure that the
+    number of edges in the competing matchings are the same and thus
+    the optimum does not change due to changes in the number of edges.
+
+    Read the documentation of `max_weight_matching` for more information.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+      Undirected graph
+
+    weight: string, optional (default='weight')
+       Edge data key corresponding to the edge weight.
+       If key not found, uses 1 as weight.
+
+    Returns
+    -------
+    matching : set
+        A minimal weight matching of the graph.
+
+    See Also
+    --------
+    max_weight_matching
+    """
+    if len(G.edges) == 0:
+        return max_weight_matching(G, maxcardinality=True, weight=weight)
+    G_edges = G.edges(data=weight, default=1)
+    max_weight = 1 + max(w for _, _, w in G_edges)
+    InvG = nx.Graph()
+    edges = ((u, v, max_weight - w) for u, v, w in G_edges)
+    InvG.add_weighted_edges_from(edges, weight=weight)
+    return max_weight_matching(InvG, maxcardinality=True, weight=weight)
+
+
+@not_implemented_for("multigraph")
+@not_implemented_for("directed")
+@nx._dispatchable(edge_attrs="weight")
+def max_weight_matching(G, maxcardinality=False, weight="weight"):
+    """Compute a maximum-weighted matching of G.
+
+    A matching is a subset of edges in which no node occurs more than once.
+    The weight of a matching is the sum of the weights of its edges.
+    A maximal matching cannot add more edges and still be a matching.
+    The cardinality of a matching is the number of matched edges.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+      Undirected graph
+
+    maxcardinality: bool, optional (default=False)
+       If maxcardinality is True, compute the maximum-cardinality matching
+       with maximum weight among all maximum-cardinality matchings.
+
+    weight: string, optional (default='weight')
+       Edge data key corresponding to the edge weight.
+       If key not found, uses 1 as weight.
+
+
+    Returns
+    -------
+    matching : set
+        A maximal matching of the graph.
+
+     Examples
+    --------
+    >>> G = nx.Graph()
+    >>> edges = [(1, 2, 6), (1, 3, 2), (2, 3, 1), (2, 4, 7), (3, 5, 9), (4, 5, 3)]
+    >>> G.add_weighted_edges_from(edges)
+    >>> sorted(nx.max_weight_matching(G))
+    [(2, 4), (5, 3)]
+
+    Notes
+    -----
+    If G has edges with weight attributes the edge data are used as
+    weight values else the weights are assumed to be 1.
+
+    This function takes time O(number_of_nodes ** 3).
+
+    If all edge weights are integers, the algorithm uses only integer
+    computations.  If floating point weights are used, the algorithm
+    could return a slightly suboptimal matching due to numeric
+    precision errors.
+
+    This method is based on the "blossom" method for finding augmenting
+    paths and the "primal-dual" method for finding a matching of maximum
+    weight, both methods invented by Jack Edmonds [1]_.
+
+    Bipartite graphs can also be matched using the functions present in
+    :mod:`networkx.algorithms.bipartite.matching`.
+
+    References
+    ----------
+    .. [1] "Efficient Algorithms for Finding Maximum Matching in Graphs",
+       Zvi Galil, ACM Computing Surveys, 1986.
+    """
+    #
+    # The algorithm is taken from "Efficient Algorithms for Finding Maximum
+    # Matching in Graphs" by Zvi Galil, ACM Computing Surveys, 1986.
+    # It is based on the "blossom" method for finding augmenting paths and
+    # the "primal-dual" method for finding a matching of maximum weight, both
+    # methods invented by Jack Edmonds.
+    #
+    # A C program for maximum weight matching by Ed Rothberg was used
+    # extensively to validate this new code.
+    #
+    # Many terms used in the code comments are explained in the paper
+    # by Galil. You will probably need the paper to make sense of this code.
+    #
+
+    class NoNode:
+        """Dummy value which is different from any node."""
+
+    class Blossom:
+        """Representation of a non-trivial blossom or sub-blossom."""
+
+        __slots__ = ["childs", "edges", "mybestedges"]
+
+        # b.childs is an ordered list of b's sub-blossoms, starting with
+        # the base and going round the blossom.
+
+        # b.edges is the list of b's connecting edges, such that
+        # b.edges[i] = (v, w) where v is a vertex in b.childs[i]
+        # and w is a vertex in b.childs[wrap(i+1)].
+
+        # If b is a top-level S-blossom,
+        # b.mybestedges is a list of least-slack edges to neighboring
+        # S-blossoms, or None if no such list has been computed yet.
+        # This is used for efficient computation of delta3.
+
+        # Generate the blossom's leaf vertices.
+        def leaves(self):
+            stack = [*self.childs]
+            while stack:
+                t = stack.pop()
+                if isinstance(t, Blossom):
+                    stack.extend(t.childs)
+                else:
+                    yield t
+
+    # Get a list of vertices.
+    gnodes = list(G)
+    if not gnodes:
+        return set()  # don't bother with empty graphs
+
+    # Find the maximum edge weight.
+    maxweight = 0
+    allinteger = True
+    for i, j, d in G.edges(data=True):
+        wt = d.get(weight, 1)
+        if i != j and wt > maxweight:
+            maxweight = wt
+        allinteger = allinteger and (str(type(wt)).split("'")[1] in ("int", "long"))
+
+    # If v is a matched vertex, mate[v] is its partner vertex.
+    # If v is a single vertex, v does not occur as a key in mate.
+    # Initially all vertices are single; updated during augmentation.
+    mate = {}
+
+    # If b is a top-level blossom,
+    # label.get(b) is None if b is unlabeled (free),
+    #                 1 if b is an S-blossom,
+    #                 2 if b is a T-blossom.
+    # The label of a vertex is found by looking at the label of its top-level
+    # containing blossom.
+    # If v is a vertex inside a T-blossom, label[v] is 2 iff v is reachable
+    # from an S-vertex outside the blossom.
+    # Labels are assigned during a stage and reset after each augmentation.
+    label = {}
+
+    # If b is a labeled top-level blossom,
+    # labeledge[b] = (v, w) is the edge through which b obtained its label
+    # such that w is a vertex in b, or None if b's base vertex is single.
+    # If w is a vertex inside a T-blossom and label[w] == 2,
+    # labeledge[w] = (v, w) is an edge through which w is reachable from
+    # outside the blossom.
+    labeledge = {}
+
+    # If v is a vertex, inblossom[v] is the top-level blossom to which v
+    # belongs.
+    # If v is a top-level vertex, inblossom[v] == v since v is itself
+    # a (trivial) top-level blossom.
+    # Initially all vertices are top-level trivial blossoms.
+    inblossom = dict(zip(gnodes, gnodes))
+
+    # If b is a sub-blossom,
+    # blossomparent[b] is its immediate parent (sub-)blossom.
+    # If b is a top-level blossom, blossomparent[b] is None.
+    blossomparent = dict(zip(gnodes, repeat(None)))
+
+    # If b is a (sub-)blossom,
+    # blossombase[b] is its base VERTEX (i.e. recursive sub-blossom).
+    blossombase = dict(zip(gnodes, gnodes))
+
+    # If w is a free vertex (or an unreached vertex inside a T-blossom),
+    # bestedge[w] = (v, w) is the least-slack edge from an S-vertex,
+    # or None if there is no such edge.
+    # If b is a (possibly trivial) top-level S-blossom,
+    # bestedge[b] = (v, w) is the least-slack edge to a different S-blossom
+    # (v inside b), or None if there is no such edge.
+    # This is used for efficient computation of delta2 and delta3.
+    bestedge = {}
+
+    # If v is a vertex,
+    # dualvar[v] = 2 * u(v) where u(v) is the v's variable in the dual
+    # optimization problem (if all edge weights are integers, multiplication
+    # by two ensures that all values remain integers throughout the algorithm).
+    # Initially, u(v) = maxweight / 2.
+    dualvar = dict(zip(gnodes, repeat(maxweight)))
+
+    # If b is a non-trivial blossom,
+    # blossomdual[b] = z(b) where z(b) is b's variable in the dual
+    # optimization problem.
+    blossomdual = {}
+
+    # If (v, w) in allowedge or (w, v) in allowedg, then the edge
+    # (v, w) is known to have zero slack in the optimization problem;
+    # otherwise the edge may or may not have zero slack.
+    allowedge = {}
+
+    # Queue of newly discovered S-vertices.
+    queue = []
+
+    # Return 2 * slack of edge (v, w) (does not work inside blossoms).
+    def slack(v, w):
+        return dualvar[v] + dualvar[w] - 2 * G[v][w].get(weight, 1)
+
+    # Assign label t to the top-level blossom containing vertex w,
+    # coming through an edge from vertex v.
+    def assignLabel(w, t, v):
+        b = inblossom[w]
+        assert label.get(w) is None and label.get(b) is None
+        label[w] = label[b] = t
+        if v is not None:
+            labeledge[w] = labeledge[b] = (v, w)
+        else:
+            labeledge[w] = labeledge[b] = None
+        bestedge[w] = bestedge[b] = None
+        if t == 1:
+            # b became an S-vertex/blossom; add it(s vertices) to the queue.
+            if isinstance(b, Blossom):
+                queue.extend(b.leaves())
+            else:
+                queue.append(b)
+        elif t == 2:
+            # b became a T-vertex/blossom; assign label S to its mate.
+            # (If b is a non-trivial blossom, its base is the only vertex
+            # with an external mate.)
+            base = blossombase[b]
+            assignLabel(mate[base], 1, base)
+
+    # Trace back from vertices v and w to discover either a new blossom
+    # or an augmenting path. Return the base vertex of the new blossom,
+    # or NoNode if an augmenting path was found.
+    def scanBlossom(v, w):
+        # Trace back from v and w, placing breadcrumbs as we go.
+        path = []
+        base = NoNode
+        while v is not NoNode:
+            # Look for a breadcrumb in v's blossom or put a new breadcrumb.
+            b = inblossom[v]
+            if label[b] & 4:
+                base = blossombase[b]
+                break
+            assert label[b] == 1
+            path.append(b)
+            label[b] = 5
+            # Trace one step back.
+            if labeledge[b] is None:
+                # The base of blossom b is single; stop tracing this path.
+                assert blossombase[b] not in mate
+                v = NoNode
+            else:
+                assert labeledge[b][0] == mate[blossombase[b]]
+                v = labeledge[b][0]
+                b = inblossom[v]
+                assert label[b] == 2
+                # b is a T-blossom; trace one more step back.
+                v = labeledge[b][0]
+            # Swap v and w so that we alternate between both paths.
+            if w is not NoNode:
+                v, w = w, v
+        # Remove breadcrumbs.
+        for b in path:
+            label[b] = 1
+        # Return base vertex, if we found one.
+        return base
+
+    # Construct a new blossom with given base, through S-vertices v and w.
+    # Label the new blossom as S; set its dual variable to zero;
+    # relabel its T-vertices to S and add them to the queue.
+    def addBlossom(base, v, w):
+        bb = inblossom[base]
+        bv = inblossom[v]
+        bw = inblossom[w]
+        # Create blossom.
+        b = Blossom()
+        blossombase[b] = base
+        blossomparent[b] = None
+        blossomparent[bb] = b
+        # Make list of sub-blossoms and their interconnecting edge endpoints.
+        b.childs = path = []
+        b.edges = edgs = [(v, w)]
+        # Trace back from v to base.
+        while bv != bb:
+            # Add bv to the new blossom.
+            blossomparent[bv] = b
+            path.append(bv)
+            edgs.append(labeledge[bv])
+            assert label[bv] == 2 or (
+                label[bv] == 1 and labeledge[bv][0] == mate[blossombase[bv]]
+            )
+            # Trace one step back.
+            v = labeledge[bv][0]
+            bv = inblossom[v]
+        # Add base sub-blossom; reverse lists.
+        path.append(bb)
+        path.reverse()
+        edgs.reverse()
+        # Trace back from w to base.
+        while bw != bb:
+            # Add bw to the new blossom.
+            blossomparent[bw] = b
+            path.append(bw)
+            edgs.append((labeledge[bw][1], labeledge[bw][0]))
+            assert label[bw] == 2 or (
+                label[bw] == 1 and labeledge[bw][0] == mate[blossombase[bw]]
+            )
+            # Trace one step back.
+            w = labeledge[bw][0]
+            bw = inblossom[w]
+        # Set label to S.
+        assert label[bb] == 1
+        label[b] = 1
+        labeledge[b] = labeledge[bb]
+        # Set dual variable to zero.
+        blossomdual[b] = 0
+        # Relabel vertices.
+        for v in b.leaves():
+            if label[inblossom[v]] == 2:
+                # This T-vertex now turns into an S-vertex because it becomes
+                # part of an S-blossom; add it to the queue.
+                queue.append(v)
+            inblossom[v] = b
+        # Compute b.mybestedges.
+        bestedgeto = {}
+        for bv in path:
+            if isinstance(bv, Blossom):
+                if bv.mybestedges is not None:
+                    # Walk this subblossom's least-slack edges.
+                    nblist = bv.mybestedges
+                    # The sub-blossom won't need this data again.
+                    bv.mybestedges = None
+                else:
+                    # This subblossom does not have a list of least-slack
+                    # edges; get the information from the vertices.
+                    nblist = [
+                        (v, w) for v in bv.leaves() for w in G.neighbors(v) if v != w
+                    ]
+            else:
+                nblist = [(bv, w) for w in G.neighbors(bv) if bv != w]
+            for k in nblist:
+                (i, j) = k
+                if inblossom[j] == b:
+                    i, j = j, i
+                bj = inblossom[j]
+                if (
+                    bj != b
+                    and label.get(bj) == 1
+                    and ((bj not in bestedgeto) or slack(i, j) < slack(*bestedgeto[bj]))
+                ):
+                    bestedgeto[bj] = k
+            # Forget about least-slack edge of the subblossom.
+            bestedge[bv] = None
+        b.mybestedges = list(bestedgeto.values())
+        # Select bestedge[b].
+        mybestedge = None
+        bestedge[b] = None
+        for k in b.mybestedges:
+            kslack = slack(*k)
+            if mybestedge is None or kslack < mybestslack:
+                mybestedge = k
+                mybestslack = kslack
+        bestedge[b] = mybestedge
+
+    # Expand the given top-level blossom.
+    def expandBlossom(b, endstage):
+        # This is an obnoxiously complicated recursive function for the sake of
+        # a stack-transformation.  So, we hack around the complexity by using
+        # a trampoline pattern.  By yielding the arguments to each recursive
+        # call, we keep the actual callstack flat.
+
+        def _recurse(b, endstage):
+            # Convert sub-blossoms into top-level blossoms.
+            for s in b.childs:
+                blossomparent[s] = None
+                if isinstance(s, Blossom):
+                    if endstage and blossomdual[s] == 0:
+                        # Recursively expand this sub-blossom.
+                        yield s
+                    else:
+                        for v in s.leaves():
+                            inblossom[v] = s
+                else:
+                    inblossom[s] = s
+            # If we expand a T-blossom during a stage, its sub-blossoms must be
+            # relabeled.
+            if (not endstage) and label.get(b) == 2:
+                # Start at the sub-blossom through which the expanding
+                # blossom obtained its label, and relabel sub-blossoms untili
+                # we reach the base.
+                # Figure out through which sub-blossom the expanding blossom
+                # obtained its label initially.
+                entrychild = inblossom[labeledge[b][1]]
+                # Decide in which direction we will go round the blossom.
+                j = b.childs.index(entrychild)
+                if j & 1:
+                    # Start index is odd; go forward and wrap.
+                    j -= len(b.childs)
+                    jstep = 1
+                else:
+                    # Start index is even; go backward.
+                    jstep = -1
+                # Move along the blossom until we get to the base.
+                v, w = labeledge[b]
+                while j != 0:
+                    # Relabel the T-sub-blossom.
+                    if jstep == 1:
+                        p, q = b.edges[j]
+                    else:
+                        q, p = b.edges[j - 1]
+                    label[w] = None
+                    label[q] = None
+                    assignLabel(w, 2, v)
+                    # Step to the next S-sub-blossom and note its forward edge.
+                    allowedge[(p, q)] = allowedge[(q, p)] = True
+                    j += jstep
+                    if jstep == 1:
+                        v, w = b.edges[j]
+                    else:
+                        w, v = b.edges[j - 1]
+                    # Step to the next T-sub-blossom.
+                    allowedge[(v, w)] = allowedge[(w, v)] = True
+                    j += jstep
+                # Relabel the base T-sub-blossom WITHOUT stepping through to
+                # its mate (so don't call assignLabel).
+                bw = b.childs[j]
+                label[w] = label[bw] = 2
+                labeledge[w] = labeledge[bw] = (v, w)
+                bestedge[bw] = None
+                # Continue along the blossom until we get back to entrychild.
+                j += jstep
+                while b.childs[j] != entrychild:
+                    # Examine the vertices of the sub-blossom to see whether
+                    # it is reachable from a neighboring S-vertex outside the
+                    # expanding blossom.
+                    bv = b.childs[j]
+                    if label.get(bv) == 1:
+                        # This sub-blossom just got label S through one of its
+                        # neighbors; leave it be.
+                        j += jstep
+                        continue
+                    if isinstance(bv, Blossom):
+                        for v in bv.leaves():
+                            if label.get(v):
+                                break
+                    else:
+                        v = bv
+                    # If the sub-blossom contains a reachable vertex, assign
+                    # label T to the sub-blossom.
+                    if label.get(v):
+                        assert label[v] == 2
+                        assert inblossom[v] == bv
+                        label[v] = None
+                        label[mate[blossombase[bv]]] = None
+                        assignLabel(v, 2, labeledge[v][0])
+                    j += jstep
+            # Remove the expanded blossom entirely.
+            label.pop(b, None)
+            labeledge.pop(b, None)
+            bestedge.pop(b, None)
+            del blossomparent[b]
+            del blossombase[b]
+            del blossomdual[b]
+
+        # Now, we apply the trampoline pattern.  We simulate a recursive
+        # callstack by maintaining a stack of generators, each yielding a
+        # sequence of function arguments.  We grow the stack by appending a call
+        # to _recurse on each argument tuple, and shrink the stack whenever a
+        # generator is exhausted.
+        stack = [_recurse(b, endstage)]
+        while stack:
+            top = stack[-1]
+            for s in top:
+                stack.append(_recurse(s, endstage))
+                break
+            else:
+                stack.pop()
+
+    # Swap matched/unmatched edges over an alternating path through blossom b
+    # between vertex v and the base vertex. Keep blossom bookkeeping
+    # consistent.
+    def augmentBlossom(b, v):
+        # This is an obnoxiously complicated recursive function for the sake of
+        # a stack-transformation.  So, we hack around the complexity by using
+        # a trampoline pattern.  By yielding the arguments to each recursive
+        # call, we keep the actual callstack flat.
+
+        def _recurse(b, v):
+            # Bubble up through the blossom tree from vertex v to an immediate
+            # sub-blossom of b.
+            t = v
+            while blossomparent[t] != b:
+                t = blossomparent[t]
+            # Recursively deal with the first sub-blossom.
+            if isinstance(t, Blossom):
+                yield (t, v)
+            # Decide in which direction we will go round the blossom.
+            i = j = b.childs.index(t)
+            if i & 1:
+                # Start index is odd; go forward and wrap.
+                j -= len(b.childs)
+                jstep = 1
+            else:
+                # Start index is even; go backward.
+                jstep = -1
+            # Move along the blossom until we get to the base.
+            while j != 0:
+                # Step to the next sub-blossom and augment it recursively.
+                j += jstep
+                t = b.childs[j]
+                if jstep == 1:
+                    w, x = b.edges[j]
+                else:
+                    x, w = b.edges[j - 1]
+                if isinstance(t, Blossom):
+                    yield (t, w)
+                # Step to the next sub-blossom and augment it recursively.
+                j += jstep
+                t = b.childs[j]
+                if isinstance(t, Blossom):
+                    yield (t, x)
+                # Match the edge connecting those sub-blossoms.
+                mate[w] = x
+                mate[x] = w
+            # Rotate the list of sub-blossoms to put the new base at the front.
+            b.childs = b.childs[i:] + b.childs[:i]
+            b.edges = b.edges[i:] + b.edges[:i]
+            blossombase[b] = blossombase[b.childs[0]]
+            assert blossombase[b] == v
+
+        # Now, we apply the trampoline pattern.  We simulate a recursive
+        # callstack by maintaining a stack of generators, each yielding a
+        # sequence of function arguments.  We grow the stack by appending a call
+        # to _recurse on each argument tuple, and shrink the stack whenever a
+        # generator is exhausted.
+        stack = [_recurse(b, v)]
+        while stack:
+            top = stack[-1]
+            for args in top:
+                stack.append(_recurse(*args))
+                break
+            else:
+                stack.pop()
+
+    # Swap matched/unmatched edges over an alternating path between two
+    # single vertices. The augmenting path runs through S-vertices v and w.
+    def augmentMatching(v, w):
+        for s, j in ((v, w), (w, v)):
+            # Match vertex s to vertex j. Then trace back from s
+            # until we find a single vertex, swapping matched and unmatched
+            # edges as we go.
+            while 1:
+                bs = inblossom[s]
+                assert label[bs] == 1
+                assert (labeledge[bs] is None and blossombase[bs] not in mate) or (
+                    labeledge[bs][0] == mate[blossombase[bs]]
+                )
+                # Augment through the S-blossom from s to base.
+                if isinstance(bs, Blossom):
+                    augmentBlossom(bs, s)
+                # Update mate[s]
+                mate[s] = j
+                # Trace one step back.
+                if labeledge[bs] is None:
+                    # Reached single vertex; stop.
+                    break
+                t = labeledge[bs][0]
+                bt = inblossom[t]
+                assert label[bt] == 2
+                # Trace one more step back.
+                s, j = labeledge[bt]
+                # Augment through the T-blossom from j to base.
+                assert blossombase[bt] == t
+                if isinstance(bt, Blossom):
+                    augmentBlossom(bt, j)
+                # Update mate[j]
+                mate[j] = s
+
+    # Verify that the optimum solution has been reached.
+    def verifyOptimum():
+        if maxcardinality:
+            # Vertices may have negative dual;
+            # find a constant non-negative number to add to all vertex duals.
+            vdualoffset = max(0, -min(dualvar.values()))
+        else:
+            vdualoffset = 0
+        # 0. all dual variables are non-negative
+        assert min(dualvar.values()) + vdualoffset >= 0
+        assert len(blossomdual) == 0 or min(blossomdual.values()) >= 0
+        # 0. all edges have non-negative slack and
+        # 1. all matched edges have zero slack;
+        for i, j, d in G.edges(data=True):
+            wt = d.get(weight, 1)
+            if i == j:
+                continue  # ignore self-loops
+            s = dualvar[i] + dualvar[j] - 2 * wt
+            iblossoms = [i]
+            jblossoms = [j]
+            while blossomparent[iblossoms[-1]] is not None:
+                iblossoms.append(blossomparent[iblossoms[-1]])
+            while blossomparent[jblossoms[-1]] is not None:
+                jblossoms.append(blossomparent[jblossoms[-1]])
+            iblossoms.reverse()
+            jblossoms.reverse()
+            for bi, bj in zip(iblossoms, jblossoms):
+                if bi != bj:
+                    break
+                s += 2 * blossomdual[bi]
+            assert s >= 0
+            if mate.get(i) == j or mate.get(j) == i:
+                assert mate[i] == j and mate[j] == i
+                assert s == 0
+        # 2. all single vertices have zero dual value;
+        for v in gnodes:
+            assert (v in mate) or dualvar[v] + vdualoffset == 0
+        # 3. all blossoms with positive dual value are full.
+        for b in blossomdual:
+            if blossomdual[b] > 0:
+                assert len(b.edges) % 2 == 1
+                for i, j in b.edges[1::2]:
+                    assert mate[i] == j and mate[j] == i
+        # Ok.
+
+    # Main loop: continue until no further improvement is possible.
+    while 1:
+        # Each iteration of this loop is a "stage".
+        # A stage finds an augmenting path and uses that to improve
+        # the matching.
+
+        # Remove labels from top-level blossoms/vertices.
+        label.clear()
+        labeledge.clear()
+
+        # Forget all about least-slack edges.
+        bestedge.clear()
+        for b in blossomdual:
+            b.mybestedges = None
+
+        # Loss of labeling means that we can not be sure that currently
+        # allowable edges remain allowable throughout this stage.
+        allowedge.clear()
+
+        # Make queue empty.
+        queue[:] = []
+
+        # Label single blossoms/vertices with S and put them in the queue.
+        for v in gnodes:
+            if (v not in mate) and label.get(inblossom[v]) is None:
+                assignLabel(v, 1, None)
+
+        # Loop until we succeed in augmenting the matching.
+        augmented = 0
+        while 1:
+            # Each iteration of this loop is a "substage".
+            # A substage tries to find an augmenting path;
+            # if found, the path is used to improve the matching and
+            # the stage ends. If there is no augmenting path, the
+            # primal-dual method is used to pump some slack out of
+            # the dual variables.
+
+            # Continue labeling until all vertices which are reachable
+            # through an alternating path have got a label.
+            while queue and not augmented:
+                # Take an S vertex from the queue.
+                v = queue.pop()
+                assert label[inblossom[v]] == 1
+
+                # Scan its neighbors:
+                for w in G.neighbors(v):
+                    if w == v:
+                        continue  # ignore self-loops
+                    # w is a neighbor to v
+                    bv = inblossom[v]
+                    bw = inblossom[w]
+                    if bv == bw:
+                        # this edge is internal to a blossom; ignore it
+                        continue
+                    if (v, w) not in allowedge:
+                        kslack = slack(v, w)
+                        if kslack <= 0:
+                            # edge k has zero slack => it is allowable
+                            allowedge[(v, w)] = allowedge[(w, v)] = True
+                    if (v, w) in allowedge:
+                        if label.get(bw) is None:
+                            # (C1) w is a free vertex;
+                            # label w with T and label its mate with S (R12).
+                            assignLabel(w, 2, v)
+                        elif label.get(bw) == 1:
+                            # (C2) w is an S-vertex (not in the same blossom);
+                            # follow back-links to discover either an
+                            # augmenting path or a new blossom.
+                            base = scanBlossom(v, w)
+                            if base is not NoNode:
+                                # Found a new blossom; add it to the blossom
+                                # bookkeeping and turn it into an S-blossom.
+                                addBlossom(base, v, w)
+                            else:
+                                # Found an augmenting path; augment the
+                                # matching and end this stage.
+                                augmentMatching(v, w)
+                                augmented = 1
+                                break
+                        elif label.get(w) is None:
+                            # w is inside a T-blossom, but w itself has not
+                            # yet been reached from outside the blossom;
+                            # mark it as reached (we need this to relabel
+                            # during T-blossom expansion).
+                            assert label[bw] == 2
+                            label[w] = 2
+                            labeledge[w] = (v, w)
+                    elif label.get(bw) == 1:
+                        # keep track of the least-slack non-allowable edge to
+                        # a different S-blossom.
+                        if bestedge.get(bv) is None or kslack < slack(*bestedge[bv]):
+                            bestedge[bv] = (v, w)
+                    elif label.get(w) is None:
+                        # w is a free vertex (or an unreached vertex inside
+                        # a T-blossom) but we can not reach it yet;
+                        # keep track of the least-slack edge that reaches w.
+                        if bestedge.get(w) is None or kslack < slack(*bestedge[w]):
+                            bestedge[w] = (v, w)
+
+            if augmented:
+                break
+
+            # There is no augmenting path under these constraints;
+            # compute delta and reduce slack in the optimization problem.
+            # (Note that our vertex dual variables, edge slacks and delta's
+            # are pre-multiplied by two.)
+            deltatype = -1
+            delta = deltaedge = deltablossom = None
+
+            # Compute delta1: the minimum value of any vertex dual.
+            if not maxcardinality:
+                deltatype = 1
+                delta = min(dualvar.values())
+
+            # Compute delta2: the minimum slack on any edge between
+            # an S-vertex and a free vertex.
+            for v in G.nodes():
+                if label.get(inblossom[v]) is None and bestedge.get(v) is not None:
+                    d = slack(*bestedge[v])
+                    if deltatype == -1 or d < delta:
+                        delta = d
+                        deltatype = 2
+                        deltaedge = bestedge[v]
+
+            # Compute delta3: half the minimum slack on any edge between
+            # a pair of S-blossoms.
+            for b in blossomparent:
+                if (
+                    blossomparent[b] is None
+                    and label.get(b) == 1
+                    and bestedge.get(b) is not None
+                ):
+                    kslack = slack(*bestedge[b])
+                    if allinteger:
+                        assert (kslack % 2) == 0
+                        d = kslack // 2
+                    else:
+                        d = kslack / 2.0
+                    if deltatype == -1 or d < delta:
+                        delta = d
+                        deltatype = 3
+                        deltaedge = bestedge[b]
+
+            # Compute delta4: minimum z variable of any T-blossom.
+            for b in blossomdual:
+                if (
+                    blossomparent[b] is None
+                    and label.get(b) == 2
+                    and (deltatype == -1 or blossomdual[b] < delta)
+                ):
+                    delta = blossomdual[b]
+                    deltatype = 4
+                    deltablossom = b
+
+            if deltatype == -1:
+                # No further improvement possible; max-cardinality optimum
+                # reached. Do a final delta update to make the optimum
+                # verifiable.
+                assert maxcardinality
+                deltatype = 1
+                delta = max(0, min(dualvar.values()))
+
+            # Update dual variables according to delta.
+            for v in gnodes:
+                if label.get(inblossom[v]) == 1:
+                    # S-vertex: 2*u = 2*u - 2*delta
+                    dualvar[v] -= delta
+                elif label.get(inblossom[v]) == 2:
+                    # T-vertex: 2*u = 2*u + 2*delta
+                    dualvar[v] += delta
+            for b in blossomdual:
+                if blossomparent[b] is None:
+                    if label.get(b) == 1:
+                        # top-level S-blossom: z = z + 2*delta
+                        blossomdual[b] += delta
+                    elif label.get(b) == 2:
+                        # top-level T-blossom: z = z - 2*delta
+                        blossomdual[b] -= delta
+
+            # Take action at the point where minimum delta occurred.
+            if deltatype == 1:
+                # No further improvement possible; optimum reached.
+                break
+            elif deltatype == 2:
+                # Use the least-slack edge to continue the search.
+                (v, w) = deltaedge
+                assert label[inblossom[v]] == 1
+                allowedge[(v, w)] = allowedge[(w, v)] = True
+                queue.append(v)
+            elif deltatype == 3:
+                # Use the least-slack edge to continue the search.
+                (v, w) = deltaedge
+                allowedge[(v, w)] = allowedge[(w, v)] = True
+                assert label[inblossom[v]] == 1
+                queue.append(v)
+            elif deltatype == 4:
+                # Expand the least-z blossom.
+                expandBlossom(deltablossom, False)
+
+            # End of a this substage.
+
+        # Paranoia check that the matching is symmetric.
+        for v in mate:
+            assert mate[mate[v]] == v
+
+        # Stop when no more augmenting path can be found.
+        if not augmented:
+            break
+
+        # End of a stage; expand all S-blossoms which have zero dual.
+        for b in list(blossomdual.keys()):
+            if b not in blossomdual:
+                continue  # already expanded
+            if blossomparent[b] is None and label.get(b) == 1 and blossomdual[b] == 0:
+                expandBlossom(b, True)
+
+    # Verify that we reached the optimum solution (only for integer weights).
+    if allinteger:
+        verifyOptimum()
+
+    return matching_dict_to_set(mate)

pythonProject/.venv/Lib/site-packages/networkx/algorithms/mis.py

@@ -0,0 +1,77 @@
+"""
+Algorithm to find a maximal (not maximum) independent set.
+
+"""
+import networkx as nx
+from networkx.utils import not_implemented_for, py_random_state
+
+__all__ = ["maximal_independent_set"]
+
+
+@not_implemented_for("directed")
+@py_random_state(2)
+@nx._dispatchable
+def maximal_independent_set(G, nodes=None, seed=None):
+    """Returns a random maximal independent set guaranteed to contain
+    a given set of nodes.
+
+    An independent set is a set of nodes such that the subgraph
+    of G induced by these nodes contains no edges. A maximal
+    independent set is an independent set such that it is not possible
+    to add a new node and still get an independent set.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    nodes : list or iterable
+       Nodes that must be part of the independent set. This set of nodes
+       must be independent.
+
+    seed : integer, random_state, or None (default)
+        Indicator of random number generation state.
+        See :ref:`Randomness<randomness>`.
+
+    Returns
+    -------
+    indep_nodes : list
+       List of nodes that are part of a maximal independent set.
+
+    Raises
+    ------
+    NetworkXUnfeasible
+       If the nodes in the provided list are not part of the graph or
+       do not form an independent set, an exception is raised.
+
+    NetworkXNotImplemented
+        If `G` is directed.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(5)
+    >>> nx.maximal_independent_set(G)  # doctest: +SKIP
+    [4, 0, 2]
+    >>> nx.maximal_independent_set(G, [1])  # doctest: +SKIP
+    [1, 3]
+
+    Notes
+    -----
+    This algorithm does not solve the maximum independent set problem.
+
+    """
+    if not nodes:
+        nodes = {seed.choice(list(G))}
+    else:
+        nodes = set(nodes)
+    if not nodes.issubset(G):
+        raise nx.NetworkXUnfeasible(f"{nodes} is not a subset of the nodes of G")
+    neighbors = set.union(*[set(G.adj[v]) for v in nodes])
+    if set.intersection(neighbors, nodes):
+        raise nx.NetworkXUnfeasible(f"{nodes} is not an independent set of G")
+    indep_nodes = list(nodes)
+    available_nodes = set(G.nodes()).difference(neighbors.union(nodes))
+    while available_nodes:
+        node = seed.choice(list(available_nodes))
+        indep_nodes.append(node)
+        available_nodes.difference_update(list(G.adj[node]) + [node])
+    return indep_nodes

pythonProject/.venv/Lib/site-packages/networkx/algorithms/moral.py

@@ -0,0 +1,59 @@
+r"""Function for computing the moral graph of a directed graph."""
+
+import itertools
+
+import networkx as nx
+from networkx.utils import not_implemented_for
+
+__all__ = ["moral_graph"]
+
+
+@not_implemented_for("undirected")
+@nx._dispatchable(returns_graph=True)
+def moral_graph(G):
+    r"""Return the Moral Graph
+
+    Returns the moralized graph of a given directed graph.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+        Directed graph
+
+    Returns
+    -------
+    H : NetworkX graph
+        The undirected moralized graph of G
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If `G` is undirected.
+
+    Examples
+    --------
+    >>> G = nx.DiGraph([(1, 2), (2, 3), (2, 5), (3, 4), (4, 3)])
+    >>> G_moral = nx.moral_graph(G)
+    >>> G_moral.edges()
+    EdgeView([(1, 2), (2, 3), (2, 5), (2, 4), (3, 4)])
+
+    Notes
+    -----
+    A moral graph is an undirected graph H = (V, E) generated from a
+    directed Graph, where if a node has more than one parent node, edges
+    between these parent nodes are inserted and all directed edges become
+    undirected.
+
+    https://en.wikipedia.org/wiki/Moral_graph
+
+    References
+    ----------
+    .. [1] Wray L. Buntine. 1995. Chain graphs for learning.
+           In Proceedings of the Eleventh conference on Uncertainty
+           in artificial intelligence (UAI'95)
+    """
+    H = G.to_undirected()
+    for preds in G.pred.values():
+        predecessors_combinations = itertools.combinations(preds, r=2)
+        H.add_edges_from(predecessors_combinations)
+    return H

pythonProject/.venv/Lib/site-packages/networkx/algorithms/node_classification.py

@@ -0,0 +1,218 @@
+""" This module provides the functions for node classification problem.
+
+The functions in this module are not imported
+into the top level `networkx` namespace.
+You can access these functions by importing
+the `networkx.algorithms.node_classification` modules,
+then accessing the functions as attributes of `node_classification`.
+For example:
+
+  >>> from networkx.algorithms import node_classification
+  >>> G = nx.path_graph(4)
+  >>> G.edges()
+  EdgeView([(0, 1), (1, 2), (2, 3)])
+  >>> G.nodes[0]["label"] = "A"
+  >>> G.nodes[3]["label"] = "B"
+  >>> node_classification.harmonic_function(G)
+  ['A', 'A', 'B', 'B']
+
+References
+----------
+Zhu, X., Ghahramani, Z., & Lafferty, J. (2003, August).
+Semi-supervised learning using gaussian fields and harmonic functions.
+In ICML (Vol. 3, pp. 912-919).
+"""
+import networkx as nx
+
+__all__ = ["harmonic_function", "local_and_global_consistency"]
+
+
+@nx.utils.not_implemented_for("directed")
+@nx._dispatchable(node_attrs="label_name")
+def harmonic_function(G, max_iter=30, label_name="label"):
+    """Node classification by Harmonic function
+
+    Function for computing Harmonic function algorithm by Zhu et al.
+
+    Parameters
+    ----------
+    G : NetworkX Graph
+    max_iter : int
+        maximum number of iterations allowed
+    label_name : string
+        name of target labels to predict
+
+    Returns
+    -------
+    predicted : list
+        List of length ``len(G)`` with the predicted labels for each node.
+
+    Raises
+    ------
+    NetworkXError
+        If no nodes in `G` have attribute `label_name`.
+
+    Examples
+    --------
+    >>> from networkx.algorithms import node_classification
+    >>> G = nx.path_graph(4)
+    >>> G.nodes[0]["label"] = "A"
+    >>> G.nodes[3]["label"] = "B"
+    >>> G.nodes(data=True)
+    NodeDataView({0: {'label': 'A'}, 1: {}, 2: {}, 3: {'label': 'B'}})
+    >>> G.edges()
+    EdgeView([(0, 1), (1, 2), (2, 3)])
+    >>> predicted = node_classification.harmonic_function(G)
+    >>> predicted
+    ['A', 'A', 'B', 'B']
+
+    References
+    ----------
+    Zhu, X., Ghahramani, Z., & Lafferty, J. (2003, August).
+    Semi-supervised learning using gaussian fields and harmonic functions.
+    In ICML (Vol. 3, pp. 912-919).
+    """
+    import numpy as np
+    import scipy as sp
+
+    X = nx.to_scipy_sparse_array(G)  # adjacency matrix
+    labels, label_dict = _get_label_info(G, label_name)
+
+    if labels.shape[0] == 0:
+        raise nx.NetworkXError(
+            f"No node on the input graph is labeled by '{label_name}'."
+        )
+
+    n_samples = X.shape[0]
+    n_classes = label_dict.shape[0]
+    F = np.zeros((n_samples, n_classes))
+
+    # Build propagation matrix
+    degrees = X.sum(axis=0)
+    degrees[degrees == 0] = 1  # Avoid division by 0
+    # TODO: csr_array
+    D = sp.sparse.csr_array(sp.sparse.diags((1.0 / degrees), offsets=0))
+    P = (D @ X).tolil()
+    P[labels[:, 0]] = 0  # labels[:, 0] indicates IDs of labeled nodes
+    # Build base matrix
+    B = np.zeros((n_samples, n_classes))
+    B[labels[:, 0], labels[:, 1]] = 1
+
+    for _ in range(max_iter):
+        F = (P @ F) + B
+
+    return label_dict[np.argmax(F, axis=1)].tolist()
+
+
+@nx.utils.not_implemented_for("directed")
+@nx._dispatchable(node_attrs="label_name")
+def local_and_global_consistency(G, alpha=0.99, max_iter=30, label_name="label"):
+    """Node classification by Local and Global Consistency
+
+    Function for computing Local and global consistency algorithm by Zhou et al.
+
+    Parameters
+    ----------
+    G : NetworkX Graph
+    alpha : float
+        Clamping factor
+    max_iter : int
+        Maximum number of iterations allowed
+    label_name : string
+        Name of target labels to predict
+
+    Returns
+    -------
+    predicted : list
+        List of length ``len(G)`` with the predicted labels for each node.
+
+    Raises
+    ------
+    NetworkXError
+        If no nodes in `G` have attribute `label_name`.
+
+    Examples
+    --------
+    >>> from networkx.algorithms import node_classification
+    >>> G = nx.path_graph(4)
+    >>> G.nodes[0]["label"] = "A"
+    >>> G.nodes[3]["label"] = "B"
+    >>> G.nodes(data=True)
+    NodeDataView({0: {'label': 'A'}, 1: {}, 2: {}, 3: {'label': 'B'}})
+    >>> G.edges()
+    EdgeView([(0, 1), (1, 2), (2, 3)])
+    >>> predicted = node_classification.local_and_global_consistency(G)
+    >>> predicted
+    ['A', 'A', 'B', 'B']
+
+    References
+    ----------
+    Zhou, D., Bousquet, O., Lal, T. N., Weston, J., & Schölkopf, B. (2004).
+    Learning with local and global consistency.
+    Advances in neural information processing systems, 16(16), 321-328.
+    """
+    import numpy as np
+    import scipy as sp
+
+    X = nx.to_scipy_sparse_array(G)  # adjacency matrix
+    labels, label_dict = _get_label_info(G, label_name)
+
+    if labels.shape[0] == 0:
+        raise nx.NetworkXError(
+            f"No node on the input graph is labeled by '{label_name}'."
+        )
+
+    n_samples = X.shape[0]
+    n_classes = label_dict.shape[0]
+    F = np.zeros((n_samples, n_classes))
+
+    # Build propagation matrix
+    degrees = X.sum(axis=0)
+    degrees[degrees == 0] = 1  # Avoid division by 0
+    # TODO: csr_array
+    D2 = np.sqrt(sp.sparse.csr_array(sp.sparse.diags((1.0 / degrees), offsets=0)))
+    P = alpha * ((D2 @ X) @ D2)
+    # Build base matrix
+    B = np.zeros((n_samples, n_classes))
+    B[labels[:, 0], labels[:, 1]] = 1 - alpha
+
+    for _ in range(max_iter):
+        F = (P @ F) + B
+
+    return label_dict[np.argmax(F, axis=1)].tolist()
+
+
+def _get_label_info(G, label_name):
+    """Get and return information of labels from the input graph
+
+    Parameters
+    ----------
+    G : Network X graph
+    label_name : string
+        Name of the target label
+
+    Returns
+    -------
+    labels : numpy array, shape = [n_labeled_samples, 2]
+        Array of pairs of labeled node ID and label ID
+    label_dict : numpy array, shape = [n_classes]
+        Array of labels
+        i-th element contains the label corresponding label ID `i`
+    """
+    import numpy as np
+
+    labels = []
+    label_to_id = {}
+    lid = 0
+    for i, n in enumerate(G.nodes(data=True)):
+        if label_name in n[1]:
+            label = n[1][label_name]
+            if label not in label_to_id:
+                label_to_id[label] = lid
+                lid += 1
+            labels.append([i, label_to_id[label]])
+    labels = np.array(labels)
+    label_dict = np.array(
+        [label for label, _ in sorted(label_to_id.items(), key=lambda x: x[1])]
+    )
+    return (labels, label_dict)