app.py

import streamlit as st
import pandas as pd
import plotly.express as px

def load_and_preprocess_data(file_path):
    # Read the data
    df = pd.read_csv(file_path)
    
    # Basic preprocessing
    df = df.drop(['X', 'Y'], axis=1)
    df.dropna(subset=['Incidentid', 'DateTime', 'Year', 'Latitude', 'Longitude'], inplace=True)

    # Convert Year to int 
    df['Year'] = df['Year'].astype(int)

    # Fill missing values
    numeric = ['Age_Drv1', 'Age_Drv2']
    for col in numeric:
        df[col].fillna(df[col].median(), inplace=True)
        
    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
    bins = [15, 25, 35, 45, 55, 65, 90]
    labels = ['16-25', '26-35', '36-45', '46-55', '56-65', '65+']
    
    df['Age_Group_Drv1'] = pd.cut(df['Age_Drv1'], bins=bins, labels=labels)
    df['Age_Group_Drv2'] = pd.cut(df['Age_Drv2'], bins=bins, labels=labels)
    
    return df

def create_severity_violation_chart(df, age_group=None):
    # Apply age group filter if selected
    if age_group != 'All Ages':
        df = df[(df['Age_Group_Drv1'] == age_group) | (df['Age_Group_Drv2'] == age_group)]
    
    # Combine violations from both drivers
    violations_1 = df.groupby(['Violation1_Drv1', 'Injuryseverity']).size().reset_index(name='count')
    violations_2 = df.groupby(['Violation1_Drv2', 'Injuryseverity']).size().reset_index(name='count')
    
    violations_1.columns = ['Violation', 'Severity', 'count']
    violations_2.columns = ['Violation', 'Severity', 'count']
    
    violations = pd.concat([violations_1, violations_2])
    violations = violations.groupby(['Violation', 'Severity'])['count'].sum().reset_index()
    
    # Create visualization
    fig = px.bar(
        violations,
        x='Violation',
        y='count',
        color='Severity',
        title=f'Crash Severity Distribution by Violation Type - {age_group}',
        labels={'count': 'Number of Incidents', 'Violation': 'Violation Type'},
        height=600
    )
    
    fig.update_layout(
        xaxis_tickangle=-45,
        legend_title='Severity Level',
        barmode='stack'
    )
    
    return fig

def get_top_violations(df, age_group):
    if age_group == 'All Ages':
        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'] == age_group) | 
            (df['Age_Group_Drv2'] == age_group)
        ]
        violations = pd.concat([
            filtered_df['Violation1_Drv1'].value_counts(),
            filtered_df['Violation1_Drv2'].value_counts()
        ]).groupby(level=0).sum()
    
    # Convert to DataFrame and format
    violations_df = violations.reset_index()
    violations_df.columns = ['Violation Type', 'Count']
    violations_df['Percentage'] = (violations_df['Count'] / violations_df['Count'].sum() * 100).round(2)
    violations_df['Percentage'] = violations_df['Percentage'].map('{:.2f}%'.format)
    
    return violations_df.head()

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)
    
    # 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)

if __name__ == "__main__":
    main()