add Retrieval Distribution stats

app.py

@@ -213,6 +213,34 @@ st.markdown("""
         margin: 10px 0;
         border-left: 4px solid #007bff;
     }
+    
+    .retrieval-distribution-container {
+        background-color: #ffffff;
+        padding: 25px;
+        border-radius: 10px;
+        margin: 20px 0;
+        border: 2px solid #e0e0e0;
+        box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1), 0 2px 4px rgba(0, 0, 0, 0.06);
+    }
+    
+    .metric-label {
+        font-size: 0.9rem;
+        color: #555;
+        margin-bottom: 5px;
+        text-align: center;
+    }
+    
+    .metric-value {
+        font-size: 1.8rem;
+        font-weight: bold;
+        color: #000000;
+        text-align: center;
+    }
+    
+    .metric-container {
+        text-align: center;
+        padding: 10px;
+    }
 </style>
 """, unsafe_allow_html=True)
 
@@ -284,6 +312,7 @@ def extract_chunk_statistics(sources: List[Any]) -> Dict[str, Any]:
     sources_list = []
     years = []
     filenames = []
+    districts = []
     
     for doc in sources:
         metadata = getattr(doc, 'metadata', {})
@@ -310,45 +339,67 @@ def extract_chunk_statistics(sources: List[Any]) -> Dict[str, Any]:
         # Extract filename
         filename = metadata.get('filename', 'Unknown')
         filenames.append(filename)
+        
+        # Extract district
+        district = metadata.get('district', 'Unknown')
+        if district and district != 'Unknown':
+            districts.append(district)
+        else:
+            districts.append('Unknown')
     
     # Count occurrences
     source_counts = Counter(sources_list)
     year_counts = Counter(years)
     filename_counts = Counter(filenames)
+    district_counts = Counter(districts)
     
     return {
         'total_chunks': len(sources),
         'unique_sources': len(source_counts),
         'unique_years': len([y for y in year_counts.keys() if y != 'Unknown']),
         'unique_filenames': len(filename_counts),
+        'unique_districts': len([d for d in district_counts.keys() if d != 'Unknown']),
         'source_distribution': dict(source_counts),
         'year_distribution': dict(year_counts),
         'filename_distribution': dict(filename_counts),
+        'district_distribution': dict(district_counts),
         'sources': sources_list,
         'years': years,
-        'filenames': filenames
+        'filenames': filenames,
+        'districts': districts
     }
 
-def display_chunk_statistics_charts(stats: Dict[str, Any], title: str = "Retrieved Chunks Statistics"):
+def display_chunk_statistics_charts(stats: Dict[str, Any], title: str = "Retrieval Statistics"):
     """Display statistics as interactive charts for 10+ results."""
     if not stats or stats.get('total_chunks', 0) == 0:
         return
     
-    st.subheader(f"📊 {title}")
-    
-    # Summary metrics
-    col1, col2, col3, col4 = st.columns(4)
-    with col1:
-        st.metric("Total Chunks", stats['total_chunks'])
-    with col2:
-        st.metric("Unique Sources", stats['unique_sources'])
-    with col3:
-        st.metric("Unique Years", stats['unique_years'])
-    with col4:
-        st.metric("Unique Files", stats['unique_filenames'])
+    # Wrap everything in one styled container - open it
+    st.markdown(f"""
+    <div class="retrieval-distribution-container">
+        <h3 style="margin-top: 0;">📊 {title}</h3>
+        <div style="display: flex; justify-content: space-around; align-items: center; padding: 15px 0; border-bottom: 1px solid #e0e0e0; margin-bottom: 20px;">
+            <div class="metric-container">
+                <div class="metric-label">Total Chunks</div>
+                <div class="metric-value">{stats['total_chunks']}</div>
+            </div>
+            <div class="metric-container">
+                <div class="metric-label">Unique Sources</div>
+                <div class="metric-value">{stats['unique_sources']}</div>
+            </div>
+            <div class="metric-container">
+                <div class="metric-label">Unique Years</div>
+                <div class="metric-value">{stats['unique_years']}</div>
+            </div>
+            <div class="metric-container">
+                <div class="metric-label">Unique Files</div>
+                <div class="metric-value">{stats['unique_filenames']}</div>
+            </div>
+        </div>
+    """, unsafe_allow_html=True)
     
-    # Charts side by side
-    col1, col2 = st.columns(2)
+    # Charts - three columns to include Districts
+    col1, col2, col3 = st.columns(3)
     
     with col1:
         # Source distribution chart
@@ -397,12 +448,43 @@ def display_chunk_statistics_charts(stats: Dict[str, Any], title: str = "Retriev
                 st.plotly_chart(fig_year, use_container_width=True)
             else:
                 st.info("No valid years found in the results")
+    
+    with col3:
+        # District distribution chart
+        if stats.get('district_distribution'):
+            district_dist_filtered = {k: v for k, v in stats['district_distribution'].items() if k != 'Unknown'}
+            if district_dist_filtered:
+                district_df = pd.DataFrame(
+                    list(district_dist_filtered.items()),
+                    columns=['District', 'Count']
+                )
+                district_df = district_df.sort_values('Count', ascending=False)
+                
+                fig_district = px.bar(
+                    district_df,
+                    x='Count',
+                    y='District',
+                    orientation='h',
+                    title='Distribution by District',
+                    color='Count',
+                    color_continuous_scale='blues'
+                )
+                fig_district.update_layout(height=400, showlegend=False)
+                st.plotly_chart(fig_district, use_container_width=True)
+            else:
+                st.info("No valid districts found in the results")
+    
+    # Close the container
+    st.markdown('</div>', unsafe_allow_html=True)
 
-def display_chunk_statistics_table(stats: Dict[str, Any], title: str = "Retrieved Chunks Statistics"):
+def display_chunk_statistics_table(stats: Dict[str, Any], title: str = "Retrieval Distribution"):
     """Display statistics as tables for smaller results with fixed alignment."""
     if not stats or stats.get('total_chunks', 0) == 0:
         return
     
+    # Wrap in styled container
+    st.markdown('<div class="retrieval-distribution-container">', unsafe_allow_html=True)
+    
     st.subheader(f"📊 {title}")
     
     # Create a container with fixed height for alignment
@@ -413,18 +495,20 @@ def display_chunk_statistics_table(stats: Dict[str, Any], title: str = "Retrieve
         col1, col2, col3, col4 = st.columns(4)
         
         with col1:
-            st.markdown("**📈 Summary**")
-            summary_data = {
-                "Metric": ["Total", "Sources", "Years", "Files"],
-                "Count": [
-                    stats['total_chunks'],
-                    stats['unique_sources'],
-                    stats['unique_years'],
-                    stats['unique_filenames']
-                ]
-            }
-            summary_df = pd.DataFrame(summary_data)
-            st.dataframe(summary_df, hide_index=True, use_container_width=True)
+            st.markdown("**🏘️ Districts**")
+            if stats.get('district_distribution'):
+                district_dist_filtered = {k: v for k, v in stats['district_distribution'].items() if k != 'Unknown'}
+                if district_dist_filtered:
+                    district_data = {
+                        "District": list(district_dist_filtered.keys()),
+                        "Count": list(district_dist_filtered.values())
+                    }
+                    district_df = pd.DataFrame(district_data).sort_values('Count', ascending=False)
+                    st.dataframe(district_df, hide_index=True, use_container_width=True)
+                else:
+                    st.write("No district data")
+            else:
+                st.write("No district data")
         
         with col2:
             st.markdown("**📂 Sources**")
@@ -472,6 +556,9 @@ def display_chunk_statistics_table(stats: Dict[str, Any], title: str = "Retrieve
                 st.dataframe(file_df, hide_index=True, use_container_width=True)
             else:
                 st.write("No file data")
+    
+    # Close container
+    st.markdown('</div>', unsafe_allow_html=True)
 
 @st.cache_data
 def load_filter_options():
@@ -545,11 +632,13 @@ def main():
                 help="Choose specific reports to search. When enabled, all other filters are ignored."
             )
         st.markdown('</div>', unsafe_allow_html=True)
+
+        st.markdown('---')
         
         # Determine if filename filter is active
         filename_mode = len(selected_filenames) > 0
         # Sources filter
-        st.markdown('<div class="filter-section">', unsafe_allow_html=True)
+        # st.markdown('<div class="filter-section">', unsafe_allow_html=True)
         st.markdown('<div class="filter-title">📊 Sources</div>', unsafe_allow_html=True)
         selected_sources = st.multiselect(
             "Select sources:",
@@ -562,7 +651,7 @@ def main():
         st.markdown('</div>', unsafe_allow_html=True)
         
         # Years filter
-        st.markdown('<div class="filter-section">', unsafe_allow_html=True)
+        # st.markdown('<div class="filter-section">', unsafe_allow_html=True)
         st.markdown('<div class="filter-title">📅 Years</div>', unsafe_allow_html=True)
         selected_years = st.multiselect(
             "Select years:",
@@ -575,7 +664,7 @@ def main():
         st.markdown('</div>', unsafe_allow_html=True)
         
         # Districts filter
-        st.markdown('<div class="filter-section">', unsafe_allow_html=True)
+        # st.markdown('<div class="filter-section">', unsafe_allow_html=True)
         st.markdown('<div class="filter-title">🏘️ Districts</div>', unsafe_allow_html=True)
         selected_districts = st.multiselect(
             "Select districts:",
@@ -820,9 +909,12 @@ def main():
                 
                 # Show charts for 10+ results, tables for fewer
                 if len(sources) >= 10:
-                    display_chunk_statistics_charts(stats, "Retrieved Documents Statistics")
+                    display_chunk_statistics_charts(stats, "Retrieval Statistics")
+                    # Also show tables below charts for detailed view
+                    st.markdown("---")
+                    display_chunk_statistics_table(stats, "Retrieval Distribution")
                 else:
-                    display_chunk_statistics_table(stats, "Retrieved Documents Statistics")
+                    display_chunk_statistics_table(stats, "Retrieval Distribution")
                 
                 st.markdown("---")
                 st.markdown("### 📄 Document Details")