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 folium
from streamlit_folium import folium_static
import random

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

# Generate mock data
@st.cache_data
def generate_mock_data():
    # Food truck locations (Manhattan-centered coordinates)
    n_trucks = 100
    trucks_df = pd.DataFrame({
        'latitude': np.random.normal(40.7589, 0.02, n_trucks),
        'longitude': np.random.normal(-73.9851, 0.02, n_trucks),
        'name': [f'Food Truck #{i}' for i in range(n_trucks)],
        'type': np.random.choice(['Hot Dogs', 'Tacos', 'Halal', 'Ice Cream', 'Coffee'], n_trucks),
        'rating': np.random.uniform(3.0, 5.0, n_trucks),
        'last_active': [datetime.now() - timedelta(minutes=random.randint(0, 360)) for _ in range(n_trucks)]
    })
    
    # Pedestrian activity (grid points)
    lat_range = np.linspace(40.7, 40.8, 50)
    lon_range = np.linspace(-74.02, -73.95, 50)
    grid_points = []
    for lat in lat_range:
        for lon in lon_range:
            grid_points.append({
                'latitude': lat,
                'longitude': lon,
                'activity': np.random.exponential(100)
            })
    pedestrian_df = pd.DataFrame(grid_points)
    
    return trucks_df, pedestrian_df

# Load data
trucks_df, pedestrian_df = generate_mock_data()

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

# Time filter
time_range = st.sidebar.slider(
    "Time Window (minutes ago)",
    min_value=0,
    max_value=360,
    value=(0, 360)
)

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

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

# Heatmap settings
if show_heatmap:
    st.sidebar.subheader("Heatmap Settings")
    heatmap_radius = st.sidebar.slider("Radius", 10, 100, 50)
    heatmap_intensity = st.sidebar.slider("Intensity", 0.1, 2.0, 1.0)

# Main content
st.title("NYC Interactive Map")

# Filter data based on time range
filtered_trucks = trucks_df[
    (trucks_df['last_active'] >= datetime.now() - timedelta(minutes=time_range[1])) &
    (trucks_df['last_active'] <= datetime.now() - timedelta(minutes=time_range[0]))
]

# Create layers
layers = []

if show_trucks:
    trucks_layer = pdk.Layer(
        "ScatterplotLayer",
        filtered_trucks,
        get_position=["longitude", "latitude"],
        get_radius=50,
        get_fill_color=[255, 0, 0, 140],
        pickable=True
    )
    layers.append(trucks_layer)

if show_heatmap:
    heatmap_layer = pdk.Layer(
        "HeatmapLayer",
        pedestrian_df,
        get_position=["longitude", "latitude"],
        get_weight="activity",
        radiusPixels=heatmap_radius,
        intensity=heatmap_intensity
    )
    layers.append(heatmap_layer)

# Create the map
view_state = pdk.ViewState(
    latitude=40.7589,
    longitude=-73.9851,
    zoom=12,
    pitch=0
)

r = pdk.Deck(
    layers=layers,
    initial_view_state=view_state,
    map_style=map_style,
    tooltip={
        "html": "<b>Food Truck:</b> {name}<br/>"
                "<b>Type:</b> {type}<br/>"
                "<b>Rating:</b> {rating:.1f}⭐<br/>"
                "<b>Last Active:</b> {last_active}",
        "style": {
            "backgroundColor": "steelblue",
            "color": "white"
        }
    }
)

# Create two columns
col1, col2 = st.columns([3, 1])

with col1:
    st.pydeck_chart(r)

with col2:
    st.subheader("Statistics")
    
    # Active trucks
    st.metric(
        "Active Food Trucks",
        len(filtered_trucks),
        f"{len(filtered_trucks) - len(trucks_df)}"
    )
    
    # Average rating
    avg_rating = filtered_trucks['rating'].mean()
    st.metric(
        "Average Rating",
        f"{avg_rating:.1f}⭐"
    )
    
    # Most common type
    most_common = filtered_trucks['type'].mode().iloc[0]
    st.metric(
        "Most Popular Type",
        most_common
    )
    
    # Pedestrian activity
    if show_heatmap:
        total_activity = pedestrian_df['activity'].sum()
        st.metric(
            "Total Pedestrian Activity",
            f"{total_activity:,.0f}"
        )