Update app.py

app.py

@@ -1,21 +1,6 @@
 # app.py
-# Mutual Fund Churn Explorer - Gradio app (full, fixed version)
-# - Option B style: infer AMC->AMC transfers when one sells and another buys the same security
-# - Interactive: node/company color, shape, edge color/thickness
-# - Select company -> shows buyers/sellers; select AMC -> shows inferred transfers
-# - Supports optional CSV upload to replace built-in sample dataset
-#
-# Usage:
-#   pip install -r requirements.txt
-#   python app.py
-#
-# requirements.txt (example)
-# gradio>=3.0
-# networkx>=2.6
-# plotly>=5.0
-# numpy
-# pandas
-# kaleido  # optional if you want to export static images
+# Fixed Mutual Fund Churn Explorer - Gradio app
+# Fixes ValueError: numpy.float64 passed to layout.width by coercing to int and enforcing minimums.
 
 import gradio as gr
 import pandas as pd
@@ -26,7 +11,7 @@ from collections import defaultdict
 import io
 
 # ---------------------------
-# Sample dataset (editable)
+# Default sample data
 # ---------------------------
 DEFAULT_AMCS = [
     "SBI MF", "ICICI Pru MF", "HDFC MF", "Nippon India MF", "Kotak MF",
@@ -39,7 +24,6 @@ DEFAULT_COMPANIES = [
     "Pearl Global", "Hindalco", "Tata Elxsi", "Cummins India", "Vedanta"
 ]
 
-# Best-effort sample mappings (you can replace by uploading CSV)
 SAMPLE_BUY = {
     "SBI MF": ["Bajaj Finance", "AU Small Finance Bank"],
     "ICICI Pru MF": ["HDFC Bank"],
@@ -77,13 +61,9 @@ SAMPLE_FRESH_BUY = {
 }
 
 # ---------------------------
-# Utilities: build maps from CSV or defaults
+# CSV -> maps utility
 # ---------------------------
 def maps_from_dataframe(df, amc_col="AMC", company_col="Company", action_col="Action"):
-    """
-    Expected actions (case-insensitive): buy, sell, complete_exit, fresh_buy
-    Returns: (amcs, companies, buy_map, sell_map, complete_exit_map, fresh_buy_map)
-    """
     amcs = sorted(df[amc_col].dropna().unique().tolist())
     companies = sorted(df[company_col].dropna().unique().tolist())
 
@@ -105,18 +85,12 @@ def maps_from_dataframe(df, amc_col="AMC", company_col="Company", action_col="Ac
         elif act in ("fresh_buy", "fresh", "new"):
             fresh_buy[a].append(c)
         else:
-            # try to infer from words
             if "sell" in act:
                 sell_map[a].append(c)
-            elif "buy" in act:
-                buy_map[a].append(c)
             elif "exit" in act:
                 complete_exit[a].append(c)
             else:
-                # default to buy if unclear
                 buy_map[a].append(c)
-
-    # ensure dict -> normal dict
     return amcs, companies, dict(buy_map), dict(sell_map), dict(complete_exit), dict(fresh_buy)
 
 def sanitize_map(m, companies_list):
@@ -125,7 +99,6 @@ def sanitize_map(m, companies_list):
         out[k] = [v for v in vals if v in companies_list]
     return out
 
-# default dataset packaging function
 def load_default_dataset():
     AMCS = DEFAULT_AMCS.copy()
     COMPANIES = DEFAULT_COMPANIES.copy()
@@ -136,7 +109,7 @@ def load_default_dataset():
     return AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY
 
 # ---------------------------
-# Inference: AMC->AMC transfers
+# Infer transfers AMC->AMC
 # ---------------------------
 def infer_amc_transfers(buy_map, sell_map):
     transfers = defaultdict(int)
@@ -153,7 +126,6 @@ def infer_amc_transfers(buy_map, sell_map):
         buyers = company_to_buyers.get(c, [])
         for s in sellers:
             for b in buyers:
-                # infer s -> b transfer for this company
                 transfers[(s,b)] += 1
     edge_list = []
     for (s,b), w in transfers.items():
@@ -165,33 +137,33 @@ def infer_amc_transfers(buy_map, sell_map):
 # ---------------------------
 def build_graph(AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY, include_transfers=True):
     G = nx.DiGraph()
-    # add nodes
     for a in AMCS:
         G.add_node(a, type="amc", label=a)
     for c in COMPANIES:
         G.add_node(c, type="company", label=c)
-    # add AMC->company edges
-    def add_edge(a, c, action, weight=1):
+
+    def add_edge(a,c,action,weight=1):
         if not G.has_node(a) or not G.has_node(c):
             return
         if G.has_edge(a,c):
             G[a][c]["weight"] += weight
             G[a][c]["actions"].append(action)
         else:
-            G.add_edge(a, c, weight=weight, actions=[action])
+            G.add_edge(a,c, weight=weight, actions=[action])
+
     for a, comps in BUY_MAP.items():
         for c in comps:
-            add_edge(a, c, "buy", weight=1)
+            add_edge(a,c,"buy",1)
     for a, comps in SELL_MAP.items():
         for c in comps:
-            add_edge(a, c, "sell", weight=1)
+            add_edge(a,c,"sell",1)
     for a, comps in COMPLETE_EXIT.items():
         for c in comps:
-            add_edge(a, c, "complete_exit", weight=3)
+            add_edge(a,c,"complete_exit",3)
     for a, comps in FRESH_BUY.items():
         for c in comps:
-            add_edge(a, c, "fresh_buy", weight=3)
-    # inferred transfers (AMC->AMC)
+            add_edge(a,c,"fresh_buy",3)
+
     if include_transfers:
         transfers = infer_amc_transfers(BUY_MAP, SELL_MAP)
         for s,b,attrs in transfers:
@@ -201,11 +173,11 @@ def build_graph(AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY, in
                 G[s][b]["weight"] += attrs.get("weight",1)
                 G[s][b]["actions"].append("transfer")
             else:
-                G.add_edge(s, b, weight=attrs.get("weight",1), actions=["transfer"])
+                G.add_edge(s,b, weight=attrs.get("weight",1), actions=["transfer"])
     return G
 
 # ---------------------------
-# Plotly visualization
+# Plotly visualizer (coerce width/height -> int with minimums)
 # ---------------------------
 def graph_to_plotly(G,
                     node_color_amc="#9EC5FF",
@@ -219,9 +191,22 @@ def graph_to_plotly(G,
                     show_labels=True,
                     width=1400,
                     height=900):
-    # position: spring layout with fixed seed for reproducibility
+    # ensure width/height are native ints and sensible
+    try:
+        width = int(float(width))
+    except Exception:
+        width = 1400
+    try:
+        height = int(float(height))
+    except Exception:
+        height = 900
+    if width < 600:
+        width = 600
+    if height < 360:
+        height = 360
+
     pos = nx.spring_layout(G, seed=42, k=1.4)
-    # nodes
+
     node_x = []
     node_y = []
     node_text = []
@@ -248,41 +233,39 @@ def graph_to_plotly(G,
         hoverinfo='text'
     )
 
-    # edges - draw each edge as a separate trace for styling
     edge_traces = []
     for u, v, attrs in G.edges(data=True):
         x0, y0 = pos[u]
         x1, y1 = pos[v]
         actions = attrs.get("actions", [])
-        weight = attrs.get("weight", 1)
-        # priority styling
+        weight = float(attrs.get("weight", 1.0))
         if "complete_exit" in actions:
             color = edge_color_sell
             dash = "solid"
-            width = max(edge_thickness_base * 3.5, 3)
+            width_px = max(float(edge_thickness_base) * 3.5, 3.0)
         elif "fresh_buy" in actions:
             color = edge_color_buy
             dash = "solid"
-            width = max(edge_thickness_base * 3.5, 3)
+            width_px = max(float(edge_thickness_base) * 3.5, 3.0)
         elif "transfer" in actions:
             color = edge_color_transfer
             dash = "dash"
-            width = max(edge_thickness_base * (1 + np.log1p(weight)), 1.5)
+            width_px = max(float(edge_thickness_base) * (1.0 + np.log1p(weight)), 1.5)
         elif "sell" in actions:
             color = edge_color_sell
             dash = "dot"
-            width = max(edge_thickness_base * (1 + np.log1p(weight)), 1)
-        else:  # buy or default
+            width_px = max(float(edge_thickness_base) * (1.0 + np.log1p(weight)), 1.0)
+        else:
             color = edge_color_buy
             dash = "solid"
-            width = max(edge_thickness_base * (1 + np.log1p(weight)), 1)
+            width_px = max(float(edge_thickness_base) * (1.0 + np.log1p(weight)), 1.0)
 
         edge_traces.append(
             go.Scatter(
                 x=[x0, x1, None],
                 y=[y0, y1, None],
                 mode='lines',
-                line=dict(width=width, color=color, dash=dash),
+                line=dict(width=float(width_px), color=color, dash=dash),
                 hoverinfo='text',
                 text=", ".join(actions)
             )
@@ -346,29 +329,21 @@ def amc_transfer_summary(amc_name, BUY_MAP, SELL_MAP):
     fig.update_layout(title_text=f"Inferred transfers from {amc_name}", height=360, width=700)
     return fig, df
 
-# loop detection in inferred AMC->AMC graph (simple cycles up to length n)
 def detect_loops(G, max_length=6):
-    # extract only nodes that are AMCs
     amc_nodes = [n for n,d in G.nodes(data=True) if d['type']=='amc']
-    loops = []
-    # Work on a directed graph of only amc nodes with transfer edges
     H = nx.DiGraph()
     for u,v,d in G.edges(data=True):
         if u in amc_nodes and v in amc_nodes and "transfer" in d.get("actions",[]):
             H.add_edge(u,v, weight=d.get("weight",1))
-    # use simple cycle detection (may find many cycles)
     try:
         cycles = list(nx.simple_cycles(H))
     except Exception:
         cycles = []
-    # filter by max_length
-    for c in cycles:
-        if 2 <= len(c) <= max_length:
-            loops.append(c)
+    loops = [c for c in cycles if 2 <= len(c) <= max_length]
     return loops
 
 # ---------------------------
-# Gradio interface
+# Build initial dataset + graph
 # ---------------------------
 def build_initial_graph_and_data():
     AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY = load_default_dataset()
@@ -376,14 +351,15 @@ def build_initial_graph_and_data():
     fig = graph_to_plotly(G)
     return (AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY, G, fig)
 
-# Prepare initial data
 (AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY, G_initial, initial_fig) = build_initial_graph_and_data()
 
+# ---------------------------
+# Gradio UI
+# ---------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("# Mutual Fund Churn Explorer (inferred AMC→AMC transfers)")
+    gr.Markdown("# Mutual Fund Churn Explorer (fixed layout issue)")
     with gr.Row():
         with gr.Column(scale=3):
-            gr.Markdown("## Controls")
             csv_uploader = gr.File(label="Upload CSV (optional). Columns: AMC,Company,Action", file_types=['.csv'])
             node_color_company = gr.ColorPicker(value="#FFCF9E", label="Company node color")
             node_color_amc = gr.ColorPicker(value="#9EC5FF", label="AMC node color")
@@ -398,18 +374,15 @@ with gr.Blocks() as demo:
             gr.Markdown("## Inspect")
             company_selector = gr.Dropdown(choices=COMPANIES, label="Select Company (show buyers/sellers)")
             amc_selector = gr.Dropdown(choices=AMCS, label="Select AMC (inferred transfers)")
-
         with gr.Column(scale=7):
             network_plot = gr.Plot(value=initial_fig, label="Network graph (drag to zoom)")
 
-    # outputs
     company_plot = gr.Plot(label="Company trade summary")
     company_table = gr.Dataframe(headers=["Role","AMC"], interactive=False, label="Trades (company)")
     amc_plot = gr.Plot(label="AMC inferred transfers")
     amc_table = gr.Dataframe(headers=["security","buyer_amc"], interactive=False, label="Inferred transfers (AMC)")
     loops_text = gr.Markdown()
 
-    # function to load CSV if provided and build maps
     def load_dataset_from_csv(file_obj):
         if file_obj is None:
             return AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY
@@ -418,8 +391,6 @@ with gr.Blocks() as demo:
             if isinstance(raw, bytes):
                 raw = raw.decode('utf-8', errors='ignore')
             df = pd.read_csv(io.StringIO(raw))
-            # expect columns: AMC, Company, Action
-            # normalize column names
             cols = [c.strip().lower() for c in df.columns]
             col_map = {}
             for c in df.columns:
@@ -432,21 +403,16 @@ with gr.Blocks() as demo:
             df = df.rename(columns=col_map)
             required = {"AMC","Company","Action"}
             if not required.issubset(set(df.columns)):
-                # can't parse - fallback to default
                 return AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY
             amcs, companies, buy_map, sell_map, complete_exit, fresh_buy = maps_from_dataframe(df, "AMC", "Company", "Action")
-            # sanitize - ensure company nodes exist
             return amcs, companies, buy_map, sell_map, complete_exit, fresh_buy
         except Exception as e:
             print("CSV load error:", e)
             return AMCS, COMPANIES, BUY_MAP, SELL_MAP, COMPLETE_EXIT, FRESH_BUY
 
-    # callback to rebuild network
     def on_update(csv_file, node_color_company_val, node_color_amc_val, node_shape_company_val, node_shape_amc_val,
                   edge_color_buy_val, edge_color_sell_val, edge_color_transfer_val, edge_thickness_val, include_transfers_val):
-        # load dataset (possibly replaced by CSV)
         amcs, companies, buy_map, sell_map, complete_exit, fresh_buy = load_dataset_from_csv(csv_file)
-        # ensure inputs for dropdowns updated - but here we just create fig
         G = build_graph(amcs, companies, buy_map, sell_map, complete_exit, fresh_buy, include_transfers=include_transfers_val)
         fig = graph_to_plotly(G,
                               node_color_amc=node_color_amc_val,
@@ -458,7 +424,6 @@ with gr.Blocks() as demo:
                               edge_color_transfer=edge_color_transfer_val,
                               edge_thickness_base=edge_thickness_val,
                               show_labels=True)
-        # detect loops and prepare a small markdown summary
         loops = detect_loops(G, max_length=6)
         if loops:
             loops_md = "### Detected AMC transfer loops (inferred):\n"
@@ -466,7 +431,6 @@ with gr.Blocks() as demo:
                 loops_md += f"- Loop {i}: " + " → ".join(loop) + "\n"
         else:
             loops_md = "No small transfer loops detected (based on current inferred transfer edges)."
-        # return fig and loops text plus update choices for dropdowns (we will update lists client-side)
         return fig, loops_md, companies, amcs
 
     update_btn.click(on_update,
@@ -474,7 +438,6 @@ with gr.Blocks() as demo:
                              edge_color_buy, edge_color_sell, edge_color_transfer, edge_thickness, include_transfers_chk],
                      outputs=[network_plot, loops_text, company_selector, amc_selector])
 
-    # company select callback
     def on_company_sel(company_name, csv_file):
         amcs, companies, buy_map, sell_map, complete_exit, fresh_buy = load_dataset_from_csv(csv_file)
         fig, df = company_trade_summary(company_name, buy_map, sell_map, fresh_buy, complete_exit)
@@ -484,7 +447,6 @@ with gr.Blocks() as demo:
 
     company_selector.change(on_company_sel, inputs=[company_selector, csv_uploader], outputs=[company_plot, company_table])
 
-    # amc select callback
     def on_amc_sel(amc_name, csv_file):
         amcs, companies, buy_map, sell_map, complete_exit, fresh_buy = load_dataset_from_csv(csv_file)
         fig, df = amc_transfer_summary(amc_name, buy_map, sell_map)