Code Editor for app.py

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

st.title("New York Vehicle Weights Over Time")

# Load and prepare data
@st.cache_data
def load_data():
    # Using NY DMV vehicle dataset
    url = "https://corsproxy.io/?https://data.ny.gov/api/views/eagh-ukzt/rows.csv"
    # NOTE: Using corsproxy.io because we're in a WASM environment. If running locally,
    # you can remove the corsproxy.io prefix.
    
    try:
        df = pd.read_csv(url)
        # Clean and process the data
        df['year'] = pd.to_datetime(df['Vehicle Year'], format='%Y')
        df['weight'] = df['Maximum Gross Weight']
        return df
    except Exception as e:
        st.error(f"Error loading data: {str(e)}")
        return pd.DataFrame()

# Load the data
df = load_data()

if not df.empty:
    # Add filters
    st.sidebar.header("Filters")
    
    # Year range filter
    year_range = st.sidebar.slider(
        "Select Year Range",
        min_value=df['year'].dt.year.min(),
        max_value=df['year'].dt.year.max(),
        value=(df['year'].dt.year.min(), df['year'].dt.year.max())
    )
    
    # Filter data based on selection
    mask = (df['year'].dt.year >= year_range[0]) & (df['year'].dt.year <= year_range[1])
    filtered_df = df[mask]
    
    # Create visualization
    st.subheader("Average Vehicle Weight by Year")
    fig = px.line(
        filtered_df.groupby(df['year'].dt.year)['weight'].mean().reset_index(),
        x='year',
        y='weight',
        title='Average Vehicle Weight Over Time'
    )
    st.plotly_chart(fig)
    
    # Show summary statistics
    st.subheader("Summary Statistics")
    stats = filtered_df.groupby(filtered_df['year'].dt.year)['weight'].agg(['mean', 'min', 'max', 'count']).round(2)
    stats.columns = ['Average Weight', 'Minimum Weight', 'Maximum Weight', 'Number of Vehicles']
    st.dataframe(stats)
    
    # Show raw data
    if st.checkbox("Show Raw Data"):
        st.subheader("Raw Data")
        st.dataframe(filtered_df[['year', 'weight']].sort_values('year'))
else:
    st.warning("Unable to load data. Please try again later.")