Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
import pydeck as pdk
from datetime import datetime, timedelta
import plotly.express as px

# Set page config
st.set_page_config(layout="wide", page_title="NYC Map Visualization")

# Generate mock data
def generate_mock_data():
    # Food truck locations around NYC
    np.random.seed(42)
    n_trucks = 100
    
    # Roughly NYC bounds
    nyc_bounds = {
        "lat": (40.4774, 40.9176),
        "lon": (-74.2591, -73.7004)
    }
    
    food_trucks = pd.DataFrame({
        "lat": np.random.uniform(nyc_bounds["lat"][0], nyc_bounds["lat"][1], n_trucks),
        "lon": np.random.uniform(nyc_bounds["lon"][0], nyc_bounds["lon"][1], n_trucks),
        "name": [f"Food Truck #{i}" for i in range(n_trucks)],
        "rating": np.random.uniform(3.0, 5.0, n_trucks),
        "cuisine": np.random.choice(["Hot Dogs", "Tacos", "Halal", "Ice Cream", "Pizza"], n_trucks),
        "borough": np.random.choice(["Manhattan", "Brooklyn", "Queens", "Bronx", "Staten Island"], n_trucks)
    })
    
    # Generate pedestrian activity heatmap data
    n_points = 1000
    pedestrian_data = pd.DataFrame({
        "lat": np.random.uniform(nyc_bounds["lat"][0], nyc_bounds["lat"][1], n_points),
        "lon": np.random.uniform(nyc_bounds["lon"][0], nyc_bounds["lon"][1], n_points),
        "weight": np.random.exponential(1, n_points)
    })
    
    return food_trucks, pedestrian_data

# Initialize session state
if 'food_trucks' not in st.session_state:
    st.session_state.food_trucks, st.session_state.pedestrian_data = generate_mock_data()

# Sidebar controls
st.sidebar.title("Map Controls")

# Layer toggles
st.sidebar.subheader("Layers")
show_trucks = st.sidebar.checkbox("Show Food Trucks", True)
show_heatmap = st.sidebar.checkbox("Show Pedestrian Heatmap", True)

# Borough filter
boroughs = st.sidebar.multiselect(
    "Filter Boroughs",
    ["Manhattan", "Brooklyn", "Queens", "Bronx", "Staten Island"],
    ["Manhattan", "Brooklyn", "Queens", "Bronx", "Staten Island"]
)

# Map style
map_style = st.sidebar.selectbox(
    "Map Style",
    ["mapbox://styles/mapbox/streets-v11", "mapbox://styles/mapbox/satellite-v9"]
)

# Heatmap settings
st.sidebar.subheader("Heatmap Settings")
radius = st.sidebar.slider("Heatmap Radius", 50, 300, 100)
intensity = st.sidebar.slider("Heatmap Intensity", 0.1, 2.0, 1.0)

# Main content
st.title("NYC Food Trucks & Pedestrian Activity")

# Filter data based on borough selection
filtered_trucks = st.session_state.food_trucks[
    st.session_state.food_trucks['borough'].isin(boroughs)
]

# Create map layers
layers = []

if show_heatmap:
    heatmap_layer = pdk.Layer(
        "HeatmapLayer",
        data=st.session_state.pedestrian_data,
        opacity=0.9,
        get_position=["lon", "lat"],
        get_weight="weight",
        radius_pixels=radius,
        intensity=intensity,
        threshold=0.05,
    )
    layers.append(heatmap_layer)

if show_trucks:
    truck_layer = pdk.Layer(
        "ScatterplotLayer",
        data=filtered_trucks,
        get_position=["lon", "lat"],
        get_color=[255, 0, 0, 160],
        get_radius=50,
        pickable=True,
    )
    layers.append(truck_layer)

# Create the map view
view_state = pdk.ViewState(
    latitude=40.7128,
    longitude=-74.0060,
    zoom=11,
    pitch=0,
)

# Render the map
r = pdk.Deck(
    layers=layers,
    initial_view_state=view_state,
    map_style=map_style,
    tooltip={
        "html": "<b>Food Truck:</b> {name}<br/>"
                "<b>Cuisine:</b> {cuisine}<br/>"
                "<b>Rating:</b> {rating:.1f}⭐<br/>"
                "<b>Borough:</b> {borough}",
        "style": {
            "backgroundColor": "white",
            "color": "black"
        }
    }
)

st.pydeck_chart(r)

# Stats Panel
col1, col2, col3 = st.columns(3)

with col1:
    st.metric(
        "Total Food Trucks",
        len(filtered_trucks)
    )

with col2:
    avg_rating = filtered_trucks['rating'].mean()
    st.metric(
        "Average Rating",
        f"{avg_rating:.2f}⭐"
    )

with col3:
    top_cuisine = filtered_trucks['cuisine'].mode().iloc[0]
    st.metric(
        "Most Popular Cuisine",
        top_cuisine
    )

# Show cuisine distribution
fig = px.pie(
    filtered_trucks, 
    names='cuisine', 
    title='Cuisine Distribution'
)
st.plotly_chart(fig, use_container_width=True)

# Show borough distribution
fig = px.bar(
    filtered_trucks['borough'].value_counts().reset_index(),
    x='index',
    y='borough',
    title='Food Trucks by Borough',
    labels={'index': 'Borough', 'borough': 'Count'}
)
st.plotly_chart(fig, use_container_width=True)