idk3

app.py

@@ -45,15 +45,15 @@ NUMERIC_COLS = ['NUMBER OF PERSONS INJURED', 'NUMBER OF PERSONS KILLED',
                 'NUMBER OF CYCLIST INJURED', 'NUMBER OF CYCLIST KILLED',
                 'NUMBER OF MOTORIST INJURED', 'NUMBER OF MOTORIST KILLED']
 
-# Get unique values for dropdowns
-boroughs = ['All'] + sorted([b for b in df['BOROUGH'].dropna().unique() if str(b) != 'nan'])
-years = ['All'] + sorted([int(y) for y in df['CRASH_YEAR'].unique()])
-months = ['All'] + sorted(df['CRASH_MONTH'].unique())
+# Get unique values for dropdowns - convert to native Python types
+boroughs = ['All'] + sorted([str(b) for b in df['BOROUGH'].dropna().unique() if str(b) != 'nan'])
+years = ['All'] + [int(y) for y in sorted(df['CRASH_YEAR'].unique())]
+months = ['All'] + [int(m) for m in sorted(df['CRASH_MONTH'].unique())]
 vehicles = ['All'] + sorted(VALID_VEHICLE_TYPES + ['OTHER'])
-person_types = ['All'] + sorted([s for s in df['PERSON_TYPE'].dropna().unique() if str(s) != 'nan'])
-injury_types = ['All'] + sorted([t for t in df['PERSON_INJURY'].dropna().unique() if str(t) != 'nan'])
-genders = ['All'] + sorted([g for g in df['PERSON_SEX'].dropna().unique() if str(g) != 'nan'])
-safety_equip = ['All'] + sorted([s for s in df['SAFETY_EQUIPMENT'].dropna().unique() 
+person_types = ['All'] + sorted([str(s) for s in df['PERSON_TYPE'].dropna().unique() if str(s) != 'nan'])
+injury_types = ['All'] + sorted([str(t) for t in df['PERSON_INJURY'].dropna().unique() if str(t) != 'nan'])
+genders = ['All'] + sorted([str(g) for g in df['PERSON_SEX'].dropna().unique() if str(g) != 'nan'])
+safety_equip = ['All'] + sorted([str(s) for s in df['SAFETY_EQUIPMENT'].dropna().unique() 
                                   if str(s) not in ['nan', 'NOT APPLICABLE', 'NOT REPORTED', 'DOES NOT APPLY']][:15])
 
 
@@ -160,12 +160,15 @@ def generate_report(borough, year, month, dow_list, hour_min, hour_max, vehicle,
     if borough != 'All':
         filtered_df = filtered_df[filtered_df['BOROUGH'] == borough]
     if year != 'All':
-        filtered_df = filtered_df[filtered_df['CRASH_YEAR'] == year]
+        filtered_df = filtered_df[filtered_df['CRASH_YEAR'] == int(year)]
     if month != 'All':
-        filtered_df = filtered_df[filtered_df['CRASH_MONTH'] == month]
-    if dow_list:
-        filtered_df = filtered_df[filtered_df['CRASH_DAYOFWEEK'].isin(dow_list)]
-    filtered_df = filtered_df[(filtered_df['CRASH_HOUR'] >= hour_min) & (filtered_df['CRASH_HOUR'] <= hour_max)]
+        filtered_df = filtered_df[filtered_df['CRASH_MONTH'] == int(month)]
+    if dow_list and len(dow_list) > 0:
+        # Convert to list of ints if needed
+        dow_ints = [int(d) if isinstance(d, str) else d for d in dow_list]
+        filtered_df = filtered_df[filtered_df['CRASH_DAYOFWEEK'].isin(dow_ints)]
+    filtered_df = filtered_df[(filtered_df['CRASH_HOUR'] >= int(hour_min)) & 
+                              (filtered_df['CRASH_HOUR'] <= int(hour_max))]
     if vehicle != 'All':
         filtered_df = filtered_df[filtered_df['VEHICLE TYPE CODE 1'] == vehicle]
     if person_type != 'All':
@@ -185,19 +188,19 @@ def generate_report(borough, year, month, dow_list, hour_min, hour_max, vehicle,
     
     # Summary Statistics
     total_records = len(filtered_df)
-    total_injuries = filtered_df['NUMBER OF PERSONS INJURED'].sum()
-    total_fatalities = filtered_df['NUMBER OF PERSONS KILLED'].sum()
+    total_injuries = int(filtered_df['NUMBER OF PERSONS INJURED'].sum())
+    total_fatalities = int(filtered_df['NUMBER OF PERSONS KILLED'].sum())
     injury_rate = (total_injuries / total_records * 100) if total_records > 0 else 0
     
     summary_text = f"""
-    📊 **Summary Statistics**
-    - **Total Records:** {total_records:,}
-    - **Total Injuries:** {int(total_injuries):,} ({injury_rate:.2f}%)
-    - **Total Fatalities:** {int(total_fatalities):,}
-    - **Pedestrian Injuries:** {int(filtered_df['NUMBER OF PEDESTRIANS INJURED'].sum()):,}
-    - **Cyclist Injuries:** {int(filtered_df['NUMBER OF CYCLIST INJURED'].sum()):,}
-    - **Motorist Injuries:** {int(filtered_df['NUMBER OF MOTORIST INJURED'].sum()):,}
-    - **Unique Crashes:** {len(filtered_df['COLLISION_ID'].unique()):,}
+📊 **Summary Statistics**
+- **Total Records:** {total_records:,}
+- **Total Injuries:** {total_injuries:,} ({injury_rate:.2f}%)
+- **Total Fatalities:** {total_fatalities:,}
+- **Pedestrian Injuries:** {int(filtered_df['NUMBER OF PEDESTRIANS INJURED'].sum()):,}
+- **Cyclist Injuries:** {int(filtered_df['NUMBER OF CYCLIST INJURED'].sum()):,}
+- **Motorist Injuries:** {int(filtered_df['NUMBER OF MOTORIST INJURED'].sum()):,}
+- **Unique Crashes:** {len(filtered_df['COLLISION_ID'].unique()):,}
     """
     
     # Chart 1: Trend Analysis
@@ -223,10 +226,10 @@ def generate_report(borough, year, month, dow_list, hour_min, hour_max, vehicle,
     
     # Chart 3: Categorical Analysis
     if c3_y == 'count':
-        chart3_data = filtered_df[c3_x].value_counts().head(c3_top)
+        chart3_data = filtered_df[c3_x].value_counts().head(int(c3_top))
         y_label = 'Number of Records'
     else:
-        chart3_data = filtered_df.groupby(c3_x)[c3_y].sum().sort_values(ascending=False).head(c3_top)
+        chart3_data = filtered_df.groupby(c3_x)[c3_y].sum().sort_values(ascending=False).head(int(c3_top))
         y_label = c3_y
     
     fig3 = px.bar(x=chart3_data.index, y=chart3_data.values,
@@ -273,6 +276,7 @@ def generate_report(borough, year, month, dow_list, hour_min, hour_max, vehicle,
         fig6 = go.Figure()
         fig6.add_annotation(text="No secondary factors", xref="paper", yref="paper",
                            x=0.5, y=0.5, showarrow=False)
+        fig6.update_layout(height=400)
     
     # Chart 7: Injury Rate Comparison
     compare_data = filtered_df.groupby(compare_cat).agg({
@@ -308,6 +312,7 @@ def generate_report(borough, year, month, dow_list, hour_min, hour_max, vehicle,
                           title='Day × Hour Heatmap', template='plotly_white', height=500)
     else:
         fig8 = go.Figure()
+        fig8.update_layout(height=500)
     
     return summary_text, fig1, fig2, fig3, fig4, fig5, fig6, fig7, fig8
 
@@ -331,7 +336,7 @@ with gr.Blocks(title="NYC Motor Vehicle Crashes Dashboard") as demo:
             month = gr.Dropdown(choices=months, value='All', label="Month")
             dow = gr.CheckboxGroup(choices=[('Mon', 0), ('Tue', 1), ('Wed', 2), ('Thu', 3), 
                                             ('Fri', 4), ('Sat', 5), ('Sun', 6)],
-                                  label="Day of Week")
+                                  label="Day of Week", type="value")
             hour_min = gr.Slider(minimum=0, maximum=23, value=0, step=1, label="Hour Min")
             hour_max = gr.Slider(minimum=0, maximum=23, value=23, step=1, label="Hour Max")
             vehicle = gr.Dropdown(choices=vehicles, value='All', label="Vehicle Type 1")