update covid search

pages/1_🗺️_COVID_Navigator.py

@@ -2,6 +2,27 @@ import streamlit as st
 import duckdb
 import pandas as pd
 from st_aggrid import AgGrid, GridOptionsBuilder, GridUpdateMode
+from st_link_analysis import st_link_analysis, NodeStyle, EdgeStyle
+from graph_builder import StLinkBuilder
+
+# Node styles configuration
+NODE_STYLES = [
+    NodeStyle("EVENT", "#FF7F3E", "name", "description"),
+    NodeStyle("PERSON", "#4CAF50", "name", "person"),
+    NodeStyle("NAME", "#2A629A", "created_at", "badge"),
+    NodeStyle("ORGANIZATION", "#9C27B0", "name", "business"),
+    NodeStyle("LOCATION", "#2196F3", "name", "place"),
+    NodeStyle("THEME", "#FFC107", "name", "sell"),
+    NodeStyle("COUNT", "#795548", "name", "inventory"),
+    NodeStyle("AMOUNT", "#607D8B", "name", "wallet"),
+]
+
+# Edge styles configuration
+EDGE_STYLES = [
+    EdgeStyle("MENTIONED_IN", caption="label", directed=True),
+    EdgeStyle("LOCATED_IN", caption="label", directed=True),
+    EdgeStyle("CATEGORIZED_AS", caption="label", directed=True)
+]
 
 # Constants for raw data categories
 GDELT_CATEGORIES = {
@@ -28,7 +49,7 @@ def initialize_db():
     """)
     return con
 
-def fetch_data(con, source_filter=None, themes_filter=None, 
+def fetch_data(con, source_filter=None,
                start_date=None, end_date=None, limit=50, include_all_columns=False):
     """Fetch filtered data from the database"""
     if include_all_columns:
@@ -97,6 +118,24 @@ def render_data_grid(df):
             return selected[0]
     return None
 
+def render_graph(record):
+    """
+    Render a graph visualization for the selected record.
+    Uses StLinkBuilder to convert the record into graph format and then
+    displays the graph using st_link_analysis.
+    """
+    st.subheader(f"Event Graph: {record.get('GKGRECORDID', 'Unknown')}")
+    stlink_builder = StLinkBuilder()
+    # Convert the record (a Series) into a DataFrame with one row
+    record_df = pd.DataFrame([record])
+    graph_data = stlink_builder.build_graph(record_df)
+    return st_link_analysis(
+        elements=graph_data,
+        layout="fcose", # Column configuration for data grid - cose, fcose, breadthfirst, cola
+        node_styles=NODE_STYLES,
+        edge_styles=EDGE_STYLES
+    )
+
 def render_raw_data(record):
     """Render raw GDELT data in expandable sections."""
     st.header("Full Record Details")
@@ -160,15 +199,19 @@ def main():
                 # Find the full record in the original DataFrame using the selected ID
                 selected_id = selected_row['ID']
                 full_record = df_full[df_full['GKGRECORDID'] == selected_id].iloc[0]
-                
+
+                # Display the graph and raw data below the grid
+                render_graph(full_record)
+
                 # Display the raw data below the grid
                 render_raw_data(full_record)
             else:
                 st.info("Select a record above to view its complete details.")
+
         else:
             st.warning("No matching records found.")
 
     # Close database connection
     con.close()
 
-main()
+main()

pages/2_🔍_COVID_Event_Graph.py

@@ -142,7 +142,7 @@ def main():
                 start_date = st.text_input("Start date (YYYYMMDD)", "20200314")
                 end_date = st.text_input("End date (YYYYMMDD)", "20200315")
                 limit = st.slider("Number of results to display", 10, 500, 100)
-
+            
             # Fetch initial data view
             df_initial = fetch_data(
                 con=con,
@@ -162,19 +162,19 @@ def main():
                 limit=limit,
                 include_all_columns=True
             )
-            
+
             # Create a DataFrame for the grid with only the key columns
             grid_df = df_initial[['GKGRECORDID', 'DATE', 'SourceCommonName', 'tone', 'DocumentIdentifier', 'SourceCollectionIdentifier']].copy()
             grid_df.columns = ['ID', 'Date', 'Source', 'Tone', 'Doc ID', 'Source Collection ID']
             
             # Render the interactive data grid at the top
             selected_row = render_data_grid(grid_df)
-            
+
             if selected_row:
                 # Find the full record in the original DataFrame using the selected ID
                 selected_id = selected_row['ID']
                 full_record = df_full[df_full['GKGRECORDID'] == selected_id].iloc[0]
-                
+
                 # Display the graph and raw data below the grid
                 render_graph(full_record)
             else: