Add geo map

app.py

@@ -1,7 +1,11 @@
 import streamlit as st
 import pandas as pd
 import plotly.express as px
+import folium
+from folium.plugins import HeatMap, MarkerCluster
+from streamlit_folium import st_folium
 
+@st.cache_data
 def load_and_preprocess_data(file_path):
     # Read the data
     df = pd.read_csv(file_path)
@@ -99,41 +103,90 @@ def get_top_violations(df, age_group):
     
     return violations_df.head()
 
+@st.cache_data
+def create_map(df, selected_year):
+    filtered_df = df[df['Year'] == selected_year]
+    
+    if len(filtered_df) > 1000:
+        filtered_df = filtered_df.sample(n=1000, random_state=42)
+    
+    m = folium.Map(
+        location=[33.4255, -111.9400],
+        zoom_start=12,
+        control_scale=True,
+        tiles='CartoDB positron'
+    )
+    
+    marker_cluster = MarkerCluster().add_to(m)
+        
+    for _, row in filtered_df.iterrows():
+        folium.Marker(
+            location=[row['Latitude'], row['Longitude']],
+            popup=f"Accident at {row['Longitude']}, {row['Latitude']}<br>Date: {row['DateTime']}<br>Severity: {row['Injuryseverity']}",
+            icon=folium.Icon(color='red')
+        ).add_to(marker_cluster)
+    
+    heat_data = filtered_df[['Latitude', 'Longitude']].values.tolist()
+    HeatMap(heat_data, radius=15, max_zoom=13, min_opacity=0.3).add_to(m)
+    
+    return m
+
 def main():
     st.title('Traffic Crash Analysis')
     
     # Load data
     df = load_and_preprocess_data('1.08_Crash_Data_Report_(detail).csv')
     
-    # Create simple dropdown for age groups
-    age_groups = ['All Ages', '16-25', '26-35', '36-45', '46-55', '56-65', '65+']
-    selected_age = st.selectbox('Select Age Group:', age_groups)
-    
-    # Create and display chart
-    fig = create_severity_violation_chart(df, selected_age)
-    st.plotly_chart(fig, use_container_width=True)
+    # Create tabs for different visualizations
+    tab1, tab2 = st.tabs(["Crash Statistics", "Crash Map"])
     
-    # Display statistics
-    if selected_age == 'All Ages':
-        total_incidents = len(df)
-    else:
-        total_incidents = len(df[
-            (df['Age_Group_Drv1'] == selected_age) | 
-            (df['Age_Group_Drv2'] == selected_age)
-        ])
-    
-    # Create two columns for statistics
-    col1, col2 = st.columns(2)
-    
-    with col1:
-        st.markdown(f"### Total Incidents")
-        st.markdown(f"**{total_incidents:,}** incidents for {selected_age}")
-    
-    # Display top violations table
-    with col2:
-        st.markdown("### Top Violations")
-        top_violations = get_top_violations(df, selected_age)
-        st.table(top_violations)
+    with tab1:
+        # Age group selection
+        age_groups = ['All Ages', '16-25', '26-35', '36-45', '46-55', '56-65', '65+']
+        selected_age = st.selectbox('Select Age Group:', age_groups)
+        
+        # Create and display chart
+        fig = create_severity_violation_chart(df, selected_age)
+        st.plotly_chart(fig, use_container_width=True)
+        
+        # Display statistics
+        if selected_age == 'All Ages':
+            total_incidents = len(df)
+        else:
+            total_incidents = len(df[
+                (df['Age_Group_Drv1'] == selected_age) | 
+                (df['Age_Group_Drv2'] == selected_age)
+            ])
+        
+        # Create two columns for statistics
+        col1, col2 = st.columns(2)
+        
+        with col1:
+            st.markdown(f"### Total Incidents")
+            st.markdown(f"**{total_incidents:,}** incidents for {selected_age}")
+        
+        with col2:
+            st.markdown("### Top Violations")
+            top_violations = get_top_violations(df, selected_age)
+            st.table(top_violations)
+    
+    with tab2:
+        # Year selection for map
+        years = sorted(df['Year'].unique())
+        selected_year = st.selectbox('Select Year:', years)
+        
+        # Create and display map
+        st.markdown("### Crash Location Map")
+        map_placeholder = st.empty()
+        with map_placeholder:
+            m = create_map(df, selected_year)
+            map_data = st_folium(
+                m,
+                width=800,
+                height=600,
+                key=f"map_{selected_year}",
+                returned_objects=["null_drawing"]
+            )
 
 if __name__ == "__main__":
     main()