Update src/streamlit_app.py

src/streamlit_app.py

@@ -333,41 +333,69 @@ def generate_entity_csv(df):
     return csv_buffer
 # -----------------------------------
 # --- Existing App Functionality (HTML) ---
-
 def generate_html_report(df, text_input, elapsed_time, df_topic_data):
     """
-    Generates a full HTML report containing all analysis results and
-    visualizations, with CSS media queries for mobile responsiveness.
+    Generates a full HTML report containing all analysis results and visualizations.
+    (Content omitted for brevity but assumed to be here).
     """
-    # 1. Generate Visualizations (Plotly HTML generation code remains the same, 
-    # ensuring bubble chart to_html includes config={'responsive': True})
-    # ... (Plotly generation code for treemap_html, pie_html, bar_category_html, bar_freq_html, network_html) ...
-    
+    # 1. Generate Visualizations (Plotly HTML)
+    # 1a. Treemap
+    fig_treemap = px.treemap(
+        df,
+        path=[px.Constant("All Entities"), 'category', 'label', 'text'],
+        values='score',
+        color='category',
+        title="Entity Distribution by Category and Label",
+        color_discrete_sequence=px.colors.qualitative.Dark24
+    )
+    fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25))
+    treemap_html = fig_treemap.to_html(full_html=False, include_plotlyjs='cdn')
+    # 1b. Pie Chart
+    grouped_counts = df['category'].value_counts().reset_index()
+    grouped_counts.columns = ['Category', 'Count']
+    # Changed color_discrete_sequence from sequential.RdBu (which has reds) to sequential.Cividis
+    fig_pie = px.pie(grouped_counts, values='Count', names='Category',title='Distribution of Entities by Category',color_discrete_sequence=px.colors.sequential.Cividis)
+    fig_pie.update_layout(margin=dict(t=50, b=10))
+    pie_html = fig_pie.to_html(full_html=False, include_plotlyjs='cdn')
+    # 1c. Bar Chart (Category Count)
+    fig_bar_category = px.bar(grouped_counts, x='Category', y='Count',color='Category', title='Total Entities per Category',color_discrete_sequence=px.colors.qualitative.Pastel)
+    fig_bar_category.update_layout(xaxis={'categoryorder': 'total descending'},margin=dict(t=50, b=100))
+    bar_category_html = fig_bar_category.to_html(full_html=False,include_plotlyjs='cdn')
+    # 1d. Bar Chart (Most Frequent Entities)
+    word_counts = df['text'].value_counts().reset_index()
+    word_counts.columns = ['Entity', 'Count']
+    repeating_entities = word_counts[word_counts['Count'] > 1].head(10)
+    bar_freq_html = '<p>No entities appear more than once in the text for visualization.</p>'
+    if not repeating_entities.empty:
+        # Changed color_discrete_sequence from sequential.Plasma (which has pink/magenta) to sequential.Viridis
+        fig_bar_freq = px.bar(repeating_entities, x='Entity', y='Count',color='Entity', title='Top 10 Most Frequent Entities',color_discrete_sequence=px.colors.sequential.Viridis)
+        fig_bar_freq.update_layout(xaxis={'categoryorder': 'total descending'},margin=dict(t=50, b=100))
+        bar_freq_html = fig_bar_freq.to_html(full_html=False, include_plotlyjs='cdn')
+    # 1e. Network Graph HTML
+    network_fig = generate_network_graph(df, text_input)
+    network_html = network_fig.to_html(full_html=False, include_plotlyjs='cdn')
     # 1f. Topic Charts HTML
     topic_charts_html = '<h3>Topic Word Weights (Bubble Chart)</h3>'
     if df_topic_data is not None and not df_topic_data.empty:
         bubble_figure = create_topic_word_bubbles(df_topic_data)
         if bubble_figure:
-            # IMPORTANT: Ensure config={'responsive': True} is here to make the plot resize
+            
             topic_charts_html += f'<div class="chart-box">{bubble_figure.to_html(full_html=False, include_plotlyjs="cdn", config={"responsive": True})}</div>'
         else:
             topic_charts_html += '<p style="color: red;">Error: Topic modeling data was available but visualization failed.</p>'
     else:
-        topic_charts_html += '<div class="chart-box" style="text-align: center; padding: 50px; background-color: #fff; border: 1px dashed #888888;">'
+        topic_charts_html += '<div class="chart-box" style="text-align: center; padding: 50px; background-color: #fff; border: 1px dashed #888888;">' # Changed border color
         topic_charts_html += '<p><strong>Topic Modeling requires more unique input.</strong></p>'
         topic_charts_html += '<p>Please enter text containing at least two unique entities to generate the Topic Bubble Chart.</p>'
         topic_charts_html += '</div>'
-
     # 2. Get Highlighted Text
     highlighted_text_html = highlight_entities(text_input, df).replace("div style", "div class='highlighted-text' style")
-    
     # 3. Entity Tables (Pandas to HTML)
     entity_table_html = df[['text', 'label', 'score', 'start', 'end', 'category']].to_html(
         classes='table table-striped',
         index=False
     )
-    
-    # 4. Construct the Final HTML with Mobile CSS Fixes
+    # 4. Construct the Final HTML
     html_content = f"""<!DOCTYPE html><html lang="en"><head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
@@ -450,12 +478,11 @@ white-space: pre-wrap; margin-bottom: 20px; }}
     </div></body></html>
     """
     return html_content
- 
-     
 
 
 
     
+    
 # --- Page Configuration and Styling (No Sidebar) ---
 st.set_page_config(layout="wide", page_title="NER & Topic Report App")
 
@@ -802,4 +829,6 @@ if st.session_state.show_results:
             file_name="extracted_entities.csv",
             mime="text/csv",
             type="secondary"
-        )
+        )
+
+