app.py

import streamlit as st
import pandas as pd
import plotly.express as px
import altair as alt
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)
    
    # 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()

@st.cache_data
def create_map(df, selected_year):
    filtered_df = df[df['Year'] == selected_year]
        
    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 create_injuries_fatalities_chart(crash_data, unit_type):

    # 5th visualization title
    st.header("5. Total Injuries and Fatalities by Month")
    
    # Filter rows where we have valid data for all necessary columns
    crash_data = crash_data[['DateTime', 'Totalinjuries', 'Totalfatalities', 'Unittype_One', 'Unittype_Two']].dropna()

    # Convert "DateTime" to datetime type
    crash_data['DateTime'] = pd.to_datetime(crash_data['DateTime'], errors='coerce')
    crash_data['Month'] = crash_data['DateTime'].dt.month_name()

    # sort months in order
    month_order = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December']
    crash_data['Month'] = pd.Categorical(crash_data['Month'], categories=month_order, ordered=True)

    # Dropdown for Unit Type selection
    # Dropdown for Unit Type selection
    # st.sidebar.selectbox("Select Unit Type", options=['Total'] + crash_data['Unittype_One'].dropna().unique().tolist())  # previous location of dropdown in sidebar
    # unit_type = st.selectbox("Select Unit Type", options=['Total'] + crash_data['Unittype_One'].dropna().unique().tolist())
    # unit_type_pairs = set()
    # for _, row in crash_data[['Unittype_One', 'Unittype_Two']].dropna().iterrows():
    #     if row['Unittype_One'] != 'Driverless' or row['Unittype_Two'] != 'Driverless':
    #         pair = ' vs '.join(sorted([row['Unittype_One'], row['Unittype_Two']]))
    #         unit_type_pairs.add(pair)
    # # unit_type_pairs = list(unit_type_pairs) # modified as below to sort the dropdown options in alphabetical order
    # unit_type_pairs = sorted(list(unit_type_pairs))
    # unit_type = st.selectbox("Select Unit Type Pair", options=['Total'] + unit_type_pairs)

    # Filter data based on the selected unit type
    if unit_type == 'Total':
        filtered_data = crash_data
    else:
        unit_one, unit_two = unit_type.split(' vs ')
        filtered_data = crash_data[((crash_data['Unittype_One'] == unit_one) & (crash_data['Unittype_Two'] == unit_two)) |
                                   ((crash_data['Unittype_One'] == unit_two) & (crash_data['Unittype_Two'] == unit_one))]

    # Group data by month and calculate total injuries and fatalities
    monthly_sum = filtered_data.groupby('Month').agg({'Totalinjuries': 'sum', 'Totalfatalities': 'sum'}).reset_index()

    # Reshape the data for easier plotting
    injuries = monthly_sum[['Month', 'Totalinjuries']].rename(columns={'Totalinjuries': 'Value'})
    injuries['Measure'] = 'Total Injuries'

    fatalities = monthly_sum[['Month', 'Totalfatalities']].rename(columns={'Totalfatalities': 'Value'})
    fatalities['Measure'] = 'Total Fatalities'

    combined_data = pd.concat([injuries, fatalities])

    # Originally tried to use bar chart but switched to line chart for better trend visualization
    # alt.Chart(monthly_sum).mark_bar().encode(
    #     x=alt.X('Month', sort=month_order, title='Month'),
    #     y=alt.Y('Totalinjuries', title='Total Injuries', axis=alt.Axis(titleColor='blue', labelColor='blue', tickColor='blue')),
    #     color=alt.value('blue'),
    #     tooltip=['Month', 'Totalinjuries']
    # ).properties(
    #     title='Total Injuries and Fatalities by Month',
    #     width=300,
    #     height=300
    # ) + alt.Chart(monthly_sum).mark_bar().encode(
    #     x=alt.X('Month', sort=month_order, title='Month'),
    #     y=alt.Y('Totalfatalities', title='Total Fatalities', axis=alt.Axis(titleColor='red', labelColor='red', tickColor='red')),
    #     color=alt.value('red'),
    #     tooltip=['Month', 'Totalfatalities']
    # )

    # Tried to figure out how to plot a legend using altair
    # line_chart = alt.Chart(monthly_sum).mark_line(point=True).encode(
    #     x=alt.X('Month', sort=month_order, title='Month'),
    #     y=alt.Y('Totalinjuries', title='Total Injuries & Fatalities', axis=alt.Axis(titleColor='black')),
    #     color=alt.value('blue'),
    #     tooltip=['Month', 'Totalinjuries']
    # ).properties(
    #     title=f'Total Injuries and Fatalities by Month for Unit Type Pair: {unit_type}',
    #     width=600,
    #     height=400
    # ) + alt.Chart(monthly_sum).mark_line(point=True).encode(
    #     x=alt.X('Month', sort=month_order, title='Month'),
    #     y=alt.Y('Totalfatalities', axis=alt.Axis(titleColor='red')),
    #     color=alt.value('red'),
    #     tooltip=['Month', 'Totalfatalities']
    # ).configure_legend(
    #     titleFontSize=14,
    #     labelFontSize=12,
    #     titleColor='black',
    #     labelColor='black'
    # )
    
    # Plot line chart
    line_chart = alt.Chart(combined_data).mark_line(point=True).encode(
        x=alt.X('Month:N', sort=month_order, title='Month'),
        y=alt.Y('Value:Q', title='Total Injuries & Fatalities'),
        color=alt.Color('Measure:N', title='', scale=alt.Scale(domain=['Total Injuries', 'Total Fatalities'], range=['blue', 'red'])),
        tooltip=['Month', 'Measure:N', 'Value:Q']
    ).properties(
        title=f'Total Injuries and Fatalities by Month for Unit Type Pair: {unit_type}',
        width=600,
        height=400
    )

    # # Combine the charts (trying to make legend)
    # combined_chart = alt.layer(line_chart_injuries, line_chart_fatalities).properties(
    #     title=f'Total Injuries and Fatalities by Month for Unit Type Pair: {unit_type}',
    #     width=600,
    #     height=400
    # ).configure_legend(
    #     titleFontSize=14,
    #     labelFontSize=12,
    #     titleColor='black',
    #     labelColor='black'
    # )
    
    return line_chart

def create_crash_trend_chart(df, weather=None):
    if weather and weather != 'All Conditions':
        df = df[df['Weather'] == weather]
    
    # Group data by year and count unique Incident IDs
    trend_data = df.groupby('Year')['Incidentid'].nunique().reset_index()
    trend_data.columns = ['Year', 'Crash Count']
    
    # Create line graph
    fig = px.line(
        trend_data,
        x='Year',
        y='Crash Count',
        title=f'Crash Trend Over Time ({weather})',
        labels={'Year': 'Year', 'Crash Count': 'Number of Unique Crashes'},
        markers=True,
        height=600
    )
    
    fig.update_traces(line=dict(width=2), marker=dict(size=8))
    fig.update_layout(legend_title_text='Trend')
    
    return fig

def main():
    st.title('Traffic Crash Analysis')
    
    # Load data
    df = load_and_preprocess_data('1.08_Crash_Data_Report_(detail).csv')

    if 'Weather' not in df.columns:
        df['Weather'] = 'Unknown'
    
    # Create tabs for different visualizations
    tab1, tab2, tab3, tab4, tab5 = st.tabs(["Crash Statistics", "Crash Map", "Crash Trend", "Crash Injuries/Fatalities","Distribution by Category"])
    
    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"]
            )
    
    with tab3:
        # Weather condition filter
        weather = ['All Conditions'] + sorted(df['Weather'].unique())
        selected_weather = st.selectbox('Select Weather Condition:', weather)
        
        # Create and display line graph
        st.markdown("### Crash Trend Over Time")
        trend_fig = create_crash_trend_chart(df, selected_weather)
        st.plotly_chart(trend_fig, use_container_width=True)

    with tab4:
        # Dropdown for Unit Type selection
        unit_type_pairs = set()
        for _, row in df[['Unittype_One', 'Unittype_Two']].dropna().iterrows():
            if row['Unittype_One'] != 'Driverless' or row['Unittype_Two'] != 'Driverless':
                pair = ' vs '.join(sorted([row['Unittype_One'], row['Unittype_Two']]))
                unit_type_pairs.add(pair)
        unit_type_pairs = sorted(list(unit_type_pairs))
        unit_type = st.selectbox("Select Unit Type Pair", options=['Total'] + unit_type_pairs)
    
        # Create 5th Visualization: Injuries and fatalities chart
        injuries_fatalities_chart = create_injuries_fatalities_chart(df, unit_type)
        st.altair_chart(injuries_fatalities_chart, use_container_width=True)
        st.markdown("#### TODO: add write-up for this 5th chart.")
        
    with tab5:
        # Dropdown for category selection
        categories = [
            'Collisionmanner',
            'Lightcondition',
            'Weather',
            'SurfaceCondition',
            'AlcoholUse_Drv1',
            'Gender_Drv1',
        ]
        selected_category = st.selectbox("Select Category:", categories)

        # Dropdown for year selection
        years = ['All Years'] + sorted(df['Year'].dropna().unique().astype(int).tolist())
        selected_year = st.selectbox("Select Year:", years)

        # Generate and display the distribution chart
        st.markdown(f"### Distribution of Incidents by {selected_category}")
        distribution_chart = create_category_distribution_chart(df, selected_category, selected_year)
        st.plotly_chart(distribution_chart, use_container_width=True)


if __name__ == "__main__":
    main()