Update app.py

app.py

@@ -29,6 +29,7 @@ logger.info(f"Standardized Column Names: {data.columns.tolist()}")
 data = data.apply(lambda col: col.str.strip() if col.dtype == "object" else col)
 data.rename(columns={
     "company": "Company",
+    "valuation": "Valuation",
     "date_joined": "Date_Joined",
     "country": "Country",
     "city": "City",
@@ -36,6 +37,10 @@ data.rename(columns={
     "select_investors": "Select_Investors"
 }, inplace=True)
 
+# Convert valuation to numeric for proportional node sizing
+data["Valuation"] = pd.to_numeric(
+    data["Valuation"].replace({"\$": "", ",": ""}, regex=True), errors="coerce"
+)
 logger.info("Data cleaned and columns renamed.")
 
 # Build investor-company mapping
@@ -55,15 +60,17 @@ investor_company_mapping = build_investor_company_mapping(data)
 logger.info("Investor to company mapping created.")
 
 # Filter investors by country, industry, and investor selection
-def filter_investors(selected_country, selected_industry, selected_investor):
+def filter_investors(selected_country, selected_industry, selected_investors):
     filtered_data = data.copy()
     if selected_country != "All":
         filtered_data = filtered_data[filtered_data["Country"] == selected_country]
     if selected_industry != "All":
         filtered_data = filtered_data[filtered_data["Industry"] == selected_industry]
-    if selected_investor != "All":
+    if selected_investors != ["All"]:
         filtered_data = filtered_data[
-            filtered_data["Select_Investors"].str.contains(selected_investor, na=False)
+            filtered_data["Select_Investors"].apply(
+                lambda x: any(inv in x for inv in selected_investors) if pd.notnull(x) else False
+            )
         ]
 
     investor_company_mapping_filtered = build_investor_company_mapping(filtered_data)
@@ -95,36 +102,48 @@ def generate_graph(investors, filtered_data):
     edge_trace = go.Scatter(
         x=edge_x,
         y=edge_y,
-        line=dict(width=1, color='#888'),
-        hoverinfo='none',
-        mode='lines'
+        line=dict(width=1, color="#888"),
+        hoverinfo="none",
+        mode="lines"
     )
 
     node_x = []
     node_y = []
     node_text = []
     node_color = []
+    node_size = []
+
+    # Color palette for investors (color blind friendly)
+    investor_colors = [
+        "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7"
+    ]
+
+    investor_color_map = {investor: investor_colors[i % len(investor_colors)] for i, investor in enumerate(investors)}
 
     for node in G.nodes():
         x, y = pos[node]
         node_x.append(x)
         node_y.append(y)
+
         if node in investors:
             node_text.append(node)  # Label investors
-            node_color.append(20)  # Fixed color for investors
+            node_color.append(investor_color_map[node])  # Assign distinct colors to investors
+            node_size.append(20)  # Fixed size for investor nodes
         else:
+            valuation = filtered_data.loc[filtered_data["Company"] == node, "Valuation"].sum()
             node_text.append("")  # Hide company labels by default
-            node_color.append(10)
+            node_color.append("lightgreen")  # Light green for companies
+            node_size.append(max(10, valuation / 100))  # Size proportional to valuation
 
     node_trace = go.Scatter(
         x=node_x,
         y=node_y,
         text=node_text,
-        mode='markers',
-        hoverinfo='text',
+        mode="markers",
+        hoverinfo="text",
         marker=dict(
             showscale=False,
-            size=15,
+            size=node_size,
             color=node_color,
         )
     )
@@ -135,15 +154,15 @@ def generate_graph(investors, filtered_data):
         title="Venture Networks",
         titlefont_size=20,
         margin=dict(l=20, r=20, t=50, b=20),
-        hovermode='closest',
+        hovermode="closest",
         width=1200,
         height=800
     )
     return fig
 
 # Gradio app
-def app(selected_country, selected_industry, selected_investor):
-    investors, filtered_data = filter_investors(selected_country, selected_industry, selected_investor)
+def app(selected_country, selected_industry, selected_investors):
+    investors, filtered_data = filter_investors(selected_country, selected_industry, selected_investors)
     graph = generate_graph(investors, filtered_data)
     return investors, graph
 
@@ -157,7 +176,7 @@ def main():
         with gr.Row():
             country_filter = gr.Dropdown(choices=country_list, label="Country", value="All")
             industry_filter = gr.Dropdown(choices=industry_list, label="Industry", value="All")
-            investor_filter = gr.Dropdown(choices=investor_list, label="Investor", value="All")
+            investor_filter = gr.CheckboxGroup(choices=investor_list, label="Investors", value=["All"])
 
         investor_output = gr.Textbox(label="Filtered Investors")
         graph_output = gr.Plot(label="Network Graph")