Create app.py

app.py

@@ -0,0 +1,148 @@
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+import numpy as np
+
+def load_and_preprocess_data(file_path):
+    # Read the data
+    df = pd.read_csv(file_path)
+    
+    # Drop redundant columns
+    df = df.drop(['X', 'Y'], axis=1)
+    
+    # Handle missing values
+    df.dropna(subset=['Incidentid', 'DateTime', 'Year', 'Latitude', 'Longitude'], inplace=True)
+    
+    # Fill numeric values
+    numeric = ['Age_Drv1', 'Age_Drv2']
+    for col in numeric:
+        df[col].fillna(df[col].median(), inplace=True)
+    
+    # Fill categorical values
+    categorical = [
+        'Gender_Drv1', 'Violation1_Drv1', 'AlcoholUse_Drv1', 'DrugUse_Drv1',
+        'Gender_Drv2', 'Violation1_Drv2', 'AlcoholUse_Drv2', 'DrugUse_Drv2',
+        'Unittype_Two', 'Traveldirection_Two', 'Unitaction_Two', 'CrossStreet'
+    ]
+    for col in categorical:
+        df[col].fillna('Unknown', inplace=True)
+    
+    # Remove invalid ages
+    df = df[
+        (df['Age_Drv1'] <= 90) & 
+        (df['Age_Drv2'] <= 90) & 
+        (df['Age_Drv1'] >= 16) & 
+        (df['Age_Drv2'] >= 16)
+    ]
+    
+    # Create age groups for both drivers
+    df['Age_Group_Drv1'] = pd.cut(
+        df['Age_Drv1'],
+        bins=[15, 25, 35, 45, 55, 65, 90],
+        labels=['16-25', '26-35', '36-45', '46-55', '56-65', '65+']
+    )
+    
+    df['Age_Group_Drv2'] = pd.cut(
+        df['Age_Drv2'],
+        bins=[15, 25, 35, 45, 55, 65, 90],
+        labels=['16-25', '26-35', '36-45', '46-55', '56-65', '65+']
+    )
+    
+    return df
+
+def create_severity_violation_chart(df, selected_age_group=None):
+    # Filter by age group if selected
+    if selected_age_group:
+        df = df[
+            (df['Age_Group_Drv1'] == selected_age_group) | 
+            (df['Age_Group_Drv2'] == selected_age_group)
+        ]
+    
+    # Create violation categories for both drivers
+    violations_drv1 = df.groupby(['Violation1_Drv1', 'Injuryseverity']).size().reset_index(name='count')
+    violations_drv2 = df.groupby(['Violation1_Drv2', 'Injuryseverity']).size().reset_index(name='count')
+    
+    # Combine violations from both drivers
+    violations_drv1.columns = ['Violation', 'Severity', 'count']
+    violations_drv2.columns = ['Violation', 'Severity', 'count']
+    violations_combined = pd.concat([violations_drv1, violations_drv2])
+    
+    # Aggregate the combined violations
+    violations_agg = violations_combined.groupby(['Violation', 'Severity'])['count'].sum().reset_index()
+    
+    # Create the stacked bar chart
+    fig = px.bar(
+        violations_agg,
+        x='Violation',
+        y='count',
+        color='Severity',
+        title=f'Distribution of Crash Severity by Violation Type {selected_age_group if selected_age_group else ""}',
+        labels={'count': 'Number of Incidents', 'Violation': 'Violation Type'},
+        height=600
+    )
+    
+    # Customize the layout
+    fig.update_layout(
+        xaxis_tickangle=-45,
+        legend_title='Severity',
+        barmode='stack',
+        showlegend=True
+    )
+    
+    return fig
+
+def main():
+    st.title('Traffic Crash Analysis Dashboard')
+    
+    # Load data
+    df = load_and_preprocess_data('1.08_Crash_Data_Report_(detail).csv')
+    
+    # Create age group selector
+    st.sidebar.header('Filters')
+    age_groups = ['All'] + list(df['Age_Group_Drv1'].unique())
+    selected_age_group = st.sidebar.selectbox('Select Age Group', age_groups)
+    
+    # Create and display the chart
+    if selected_age_group == 'All':
+        fig = create_severity_violation_chart(df)
+    else:
+        fig = create_severity_violation_chart(df, selected_age_group)
+    
+    st.plotly_chart(fig, use_container_width=True)
+    
+    # Add additional insights
+    st.subheader('Analysis Insights')
+    
+    # Calculate and display some statistics
+    if selected_age_group == 'All':
+        total_crashes = len(df)
+    else:
+        total_crashes = len(df[
+            (df['Age_Group_Drv1'] == selected_age_group) | 
+            (df['Age_Group_Drv2'] == selected_age_group)
+        ])
+    
+    st.write(f"Total number of crashes: {total_crashes:,}")
+    
+    # Show top violations
+    st.subheader('Top Violations')
+    if selected_age_group == 'All':
+        violations = pd.concat([
+            df['Violation1_Drv1'].value_counts(),
+            df['Violation1_Drv2'].value_counts()
+        ]).groupby(level=0).sum()
+    else:
+        filtered_df = df[
+            (df['Age_Group_Drv1'] == selected_age_group) | 
+            (df['Age_Group_Drv2'] == selected_age_group)
+        ]
+        violations = pd.concat([
+            filtered_df['Violation1_Drv1'].value_counts(),
+            filtered_df['Violation1_Drv2'].value_counts()
+        ]).groupby(level=0).sum()
+    
+    st.write(violations.head())
+
+if __name__ == "__main__":
+    main()