Initial Dashboard Deployment

.gitignore

@@ -0,0 +1,21 @@
+# Python Cache
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Databases and Downloaded Archives
+*.db
+*.db.wal
+*.zip
+
+# Jupyter Notebook Checkpoints 
+.ipynb_checkpoints/
+
+# Virtual Environments
+venv/
+env/
+.env
+
+# OS Generated Files
+.DS_Store
+Thumbs.db

Dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.11-slim
+
+# System deps for GDAL/geopandas
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libgdal-dev \
+    gdal-bin \
+    libgeos-dev \
+    libproj-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Install Python deps
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY data_pipeline.py .
+COPY dashboard_helpers.py .
+COPY app.ipynb .
+
+# Pre-download databases so it's baked into the image
+RUN python -c "import leafmap; \
+    leafmap.download_file( \
+        'https://opengeos.org/data/duckdb/nyc_data.db.zip', \
+        unzip=True, \
+        overwrite=True \
+    )"
+RUN python data_pipeline.py
+
+# Expose the port HF Spaces expects
+EXPOSE 7860
+
+# Launch Solara
+CMD ["solara", "run", "app.py", "--host=0.0.0.0", "--port=7860"]

README.md

@@ -1,12 +1,51 @@
 ---
-title: Nyc Mobility Solara Dashboard
-emoji: 🦀
+title: NYC Taxi Mobility Equity Dashboard_Solara
 colorFrom: blue
-colorTo: indigo
+colorTo: green
 sdk: docker
-pinned: false
+pinned: true
 license: mit
-short_description: The NYC Mobility Dashboard powered by Solara
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# NYC Mobility Equity Dashboard
+_Debayan Mandal_
+
+An interactive Solara dashboard analyzing whether **FHV** and
+**Yellow Taxi** services are equitably distributed across NYC neighborhoods
+relative to demographic baselines.
+
+## Features
+
+- **Pickup & Drop-off choropleth maps** for FHV and Yellow Taxi by month
+- **Diverging demographic maps** showing deviation from citywide population baselines
+- **Top-10 stats tables** split by service and direction
+- **Month dropdown** to explore Jan–Mar 2025 data
+
+## Data Sources
+
+- [NYC TLC Trip Record Data](https://www.nyc.gov/site/tlc/about/tlc-trip-record-data.page) (parquet via CloudFront)
+- [NYC Taxi Zones](https://data.source.coop/cholmes/nyc-taxi-zones/) (Source Cooperative)
+- [NYC Census Blocks](https://opengeos.org/data/duckdb/nyc_data.db.zip) (OpenGeos)
+
+## Architecture
+
+| File | Purpose |
+|------|---------|
+| `data_pipeline.py` | DuckDB setup, spatial joins, trip ingestion, relative risk |
+| `dashboard_helpers.py` | Reusable map and stats-table builder functions |
+| `app.py` | Main Solara application and UI component script |
+| `Dockerfile` | Container setup for Hugging Face Spaces deployment |
+
+## Local Development
+
+To run this dashboard locally, you must first build the pre-computed DuckDB database, and then launch the Solara server.
+
+```bash
+# 1. Install dependencies
+pip install -r requirements.txt
+
+# 2. Run the pipeline to fetch data and generate processed_dashboard.db
+python data_pipeline.py
+
+# 3. Launch the hot-reloading Solara development server
+solara run app.py

app.py

@@ -0,0 +1,80 @@
+import solara
+import duckdb
+from dashboard_helpers import build_trip_map, build_demo_map, build_stats
+
+# 1. Connect to our pre-baked database in read-only mode
+con = duckdb.connect('processed_dashboard.db', read_only=True)
+con.install_extension('spatial')
+con.load_extension('spatial')
+
+# 2. Grab baselines
+baseline_df = con.sql("SELECT * FROM city_baselines").df()
+baseline_white = float(baseline_df["baseline_white_pct"].iloc[0]) / 100.0
+baseline_black = float(baseline_df["baseline_black_pct"].iloc[0]) / 100.0
+
+# 3. Define our Reactive State
+selected_month = solara.reactive("Feb2025")
+
+# 4. Build Reusable Components
+@solara.component
+def TaxiMap(service, metric, cmap, title):
+    month = selected_month.value
+    m = build_trip_map(con, service, month, metric, cmap, title)
+    
+    with solara.Card(title=f"{title} ({month})"):
+        solara.display(m)
+
+@solara.component
+def ServiceStatsCard(service, cmap_pu, cmap_do):
+    month = selected_month.value
+    pu_head, pu_table = build_stats(con, service, month, 'pu', cmap_pu, 'Pickups')
+    do_head, do_table = build_stats(con, service, month, 'do', cmap_do, 'Drop-offs')
+    with solara.Card():
+        solara.Markdown(f"### {service} Top 10 Destinations ({month})", style={"text-align": "center"})
+        with solara.Row():
+            with solara.Column():
+                solara.display(pu_head)
+                solara.display(pu_table)
+            with solara.Column():
+                solara.display(do_head)
+                solara.display(do_table)
+
+@solara.component
+def DemographicMap(column, baseline_val, title):
+    m = build_demo_map(con, column, baseline_val, title)
+    with solara.Card(title=title):
+        solara.display(m)
+
+# 5. Build the Main Page Layout
+@solara.component
+def Page():
+    solara.Title("NYC Taxi Mobility Equity Dashboard")
+    
+    with solara.Column():
+        with solara.Column(align="center"):
+            # Header
+            solara.Markdown("# NYC Taxi Mobility Equity Dashboard", style={"text-align": "center"})
+            solara.Markdown(
+                "<div style='text-align: center;'>This interactive dashboard analyzes whether <b>FHV</b> and <b>Yellow Taxi</b> services are over- or under-represented  in areas with different demographic compositions relative to the NYC baseline.</div>"
+            )
+            # UI Control
+            solara.Select(label="Select Month", value=selected_month, values=['Jan2025', 'Feb2025', 'Mar2025'])
+        
+        # Grid Layout
+        with solara.GridFixed(columns=2):
+            # Row 1: Pickups
+            TaxiMap('FHV', 'pu', 'Blues', 'FHV Pickups')
+            TaxiMap('Yellow', 'pu', 'Blues', 'Yellow Pickups')
+            
+            # Row 2: Drop-offs
+            TaxiMap('FHV', 'do', 'Greens', 'FHV Drop-offs')
+            TaxiMap('Yellow', 'do', 'Greens', 'Yellow Drop-offs')
+            
+            # Row 3: Demographics
+            DemographicMap('white_pct', baseline_white * 100, f'White Pop. Deviation ({baseline_white*100:.1f}%)')
+            DemographicMap('black_pct', baseline_black * 100, f'Black Pop. Deviation ({baseline_black*100:.1f}%)')
+    
+    with solara.Column(align="center"):
+        with solara.GridFixed(columns=2):
+            ServiceStatsCard('FHV', 'Blues', 'YlOrBr')
+            ServiceStatsCard('Yellow', 'Greens', 'YlOrBr')

dashboard_helpers.py

@@ -0,0 +1,74 @@
+import geopandas as gpd
+import ipywidgets as widgets
+import leafmap
+
+# Trip-volume choropleth
+def build_trip_map(con, service, month, metric, cmap, legend_prefix):
+    if metric == "pu":
+        table, col = "trip_counts_pu", "trips_pu"
+    else:
+        table, col = "trip_counts_do", "trips_do"
+
+    df = con.sql(f"""
+        SELECT tz.zone, t.{col} AS trips,
+               ST_AsText(ST_Transform(tz.geometry, 'EPSG:26918', 'OGC:CRS84')) AS geometry
+        FROM {table} AS t
+        JOIN taxi_zones_utm AS tz ON t.LocationID = tz.LocationID
+        WHERE t.service = '{service}' AND t.month = '{month}'
+    """).df()
+
+    gdf = gpd.GeoDataFrame(
+        df, geometry=gpd.GeoSeries.from_wkt(df["geometry"]), crs="EPSG:4326"
+    )
+    m = leafmap.Map(center=[40.7, -73.9], zoom=10, draw_control=False)
+    m.layout.height = "400px"
+    m.add_basemap("CartoDB.DarkMatter")
+    m.add_data(
+        gdf, column="trips", cmap=cmap,
+        legend_title=f"{legend_prefix} ({month})",
+    )
+    return m
+
+# Demographic baseline choropleth
+def build_demo_map(con, column, baseline_val, legend_title):
+    df = con.sql(f"""
+        SELECT zd.TaxiZone AS zone,
+               ROUND(zd.{column} - {baseline_val}, 1) AS deviation,
+               ST_AsText(ST_Transform(tz.geometry, 'EPSG:26918', 'OGC:CRS84')) AS geometry
+        FROM zone_demographics AS zd
+        JOIN taxi_zones_utm AS tz ON zd.LocationID = tz.LocationID
+        WHERE zd.TotalPop > 0
+    """).df()
+
+    gdf = gpd.GeoDataFrame(
+        df, geometry=gpd.GeoSeries.from_wkt(df["geometry"]), crs="EPSG:4326"
+    )
+    m = leafmap.Map(center=[40.7, -73.9], zoom=10, draw_control=False)
+    m.layout.height = "400px"
+    m.add_basemap("CartoDB.DarkMatter")
+    m.add_data(
+        gdf, column="deviation", cmap="RdYlBu",
+        legend_title=legend_title,
+    )
+    return m
+
+# Top-10 stats table
+def build_stats(con, service, month, metric, cmap, label):
+    if metric == "pu":
+        table, col, alias = "trip_counts_pu", "trips_pu", "Pickups"
+    else:
+        table, col, alias = "trip_counts_do", "trips_do", "Dropoffs"
+
+    df = con.sql(f"""
+        SELECT tz.zone AS Neighborhood, t.{col} AS {alias}
+        FROM {table} t
+        JOIN taxi_zones_utm tz ON t.LocationID = tz.LocationID
+        WHERE t.service = '{service}' AND t.month = '{month}'
+        ORDER BY t.{col} DESC LIMIT 10
+    """).df()
+
+    header = widgets.HTML(
+        f"<h3 style='text-align:center;'>{service} Top 10 {label} ({month})</h3>"
+    )
+    styled = df.style.background_gradient(cmap=cmap, subset=[alias]).hide(axis="index")
+    return header, styled

data_pipeline.py

@@ -0,0 +1,132 @@
+import os
+import pathlib
+import duckdb
+import pandas as pd
+import leafmap
+
+# DuckDB connection & extensions
+con = duckdb.connect('processed_dashboard.db')
+con.install_extension("httpfs")
+con.load_extension("httpfs")
+con.install_extension("spatial")
+con.load_extension("spatial")
+
+# Taxi-zone geometry
+TAXI_ZONES_URL = (
+    "https://data.source.coop/cholmes/nyc-taxi-zones/taxi_zones.parquet"
+)
+con.sql(f"CREATE OR REPLACE VIEW taxi_zones AS SELECT * FROM '{TAXI_ZONES_URL}'")
+
+# NYC census blocks 
+DB_PATH = pathlib.Path("nyc_data.db")
+if not DB_PATH.exists():
+    leafmap.download_file(
+        "https://opengeos.org/data/duckdb/nyc_data.db.zip",
+        unzip=True,
+        overwrite=True,
+    )
+con.execute("ATTACH 'nyc_data.db' AS nyc_data (READ_ONLY)")
+
+
+# Compute demographics
+con.sql("""
+    CREATE OR REPLACE TABLE taxi_zones_utm AS
+    SELECT * EXCLUDE (geometry),
+        ST_GeomFromWKB(ST_AsWKB(ST_Transform(geometry, 'EPSG:2263', 'EPSG:26918'))) AS geometry
+    FROM taxi_zones
+""")
+
+con.sql("""
+    CREATE OR REPLACE TABLE zone_demographics AS
+    SELECT
+        tz.LocationID,
+        tz.zone     AS TaxiZone,
+        tz.borough  AS Borough,
+        SUM(cb.popn_total) AS TotalPop,
+        SUM(cb.popn_white) AS WhitePop,
+        SUM(cb.popn_black) AS BlackPop,
+        100.0 * SUM(cb.popn_white) / SUM(cb.popn_total) AS white_pct,
+        100.0 * SUM(cb.popn_black) / SUM(cb.popn_total) AS black_pct
+    FROM nyc_data.nyc_census_blocks AS cb
+    JOIN taxi_zones_utm AS tz ON ST_Intersects(tz.geometry, cb.geom)
+    GROUP BY tz.LocationID, tz.zone, tz.borough
+""")
+
+baseline_df = con.sql("""
+    SELECT
+        ROUND(100.0 * SUM(popn_white) / SUM(popn_total), 2) AS baseline_white_pct,
+        ROUND(100.0 * SUM(popn_black) / SUM(popn_total), 2) AS baseline_black_pct
+    FROM nyc_data.nyc_census_blocks
+""").df()
+con.sql("CREATE OR REPLACE TABLE city_baselines AS SELECT * FROM baseline_df")
+
+baseline_white: float = float(baseline_df["baseline_white_pct"].iloc[0]) / 100.0
+baseline_black: float = float(baseline_df["baseline_black_pct"].iloc[0]) / 100.0
+
+# Trip data ingestion
+_pu_field = {"FHV": "PUlocationID", "Yellow": "PULocationID"}
+_do_field = {"FHV": "DOlocationID", "Yellow": "DOLocationID"}
+
+TRIP_URLS = {
+    "FHV_Jan2025":    "https://d37ci6vzurychx.cloudfront.net/trip-data/fhv_tripdata_2025-01.parquet",
+    "FHV_Feb2025":    "https://d37ci6vzurychx.cloudfront.net/trip-data/fhv_tripdata_2025-02.parquet",
+    "FHV_Mar2025":    "https://d37ci6vzurychx.cloudfront.net/trip-data/fhv_tripdata_2025-03.parquet",
+    "Yellow_Jan2025": "https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2025-01.parquet",
+    "Yellow_Feb2025": "https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2025-02.parquet",
+    "Yellow_Mar2025": "https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2025-03.parquet",
+}
+
+con.execute(
+    "CREATE OR REPLACE TABLE trip_counts_pu "
+    "(service VARCHAR, month VARCHAR, LocationID INTEGER, trips_pu BIGINT)"
+)
+con.execute(
+    "CREATE OR REPLACE TABLE trip_counts_do "
+    "(service VARCHAR, month VARCHAR, LocationID INTEGER, trips_do BIGINT)"
+)
+
+for key, url in TRIP_URLS.items():
+    service, month = key.split("_")
+    pu, do = _pu_field[service], _do_field[service]
+    con.sql(
+        f"INSERT INTO trip_counts_pu "
+        f"SELECT '{service}', '{month}', CAST({pu} AS INTEGER), COUNT(*) "
+        f"FROM '{url}' "
+        f"WHERE {pu} IS NOT NULL AND CAST({pu} AS INTEGER) NOT IN (0, 264, 265) "
+        f"GROUP BY {pu}"
+    )
+    con.sql(
+        f"INSERT INTO trip_counts_do "
+        f"SELECT '{service}', '{month}', CAST({do} AS INTEGER), COUNT(*) "
+        f"FROM '{url}' "
+        f"WHERE {do} IS NOT NULL AND CAST({do} AS INTEGER) NOT IN (0, 264, 265) "
+        f"GROUP BY {do}"
+    )
+
+# Representative ratio summary
+bw = baseline_white * 100
+bb = baseline_black * 100
+
+rr_pu_df = con.sql(f"""
+    SELECT tp.service, tp.month,
+        SUM(tp.trips_pu * zd.white_pct) * 1.0 / SUM(tp.trips_pu) / {bw} AS RR_white_PU,
+        SUM(tp.trips_pu * zd.black_pct) * 1.0 / SUM(tp.trips_pu) / {bb} AS RR_black_PU
+    FROM trip_counts_pu AS tp
+    JOIN zone_demographics AS zd ON tp.LocationID = zd.LocationID
+    WHERE zd.TotalPop > 0
+    GROUP BY tp.service, tp.month
+""").df()
+
+rr_do_df = con.sql(f"""
+    SELECT td.service, td.month,
+        SUM(td.trips_do * zd.white_pct) * 1.0 / SUM(td.trips_do) / {bw} AS RR_white_DO,
+        SUM(td.trips_do * zd.black_pct) * 1.0 / SUM(td.trips_do) / {bb} AS RR_black_DO
+    FROM trip_counts_do AS td
+    JOIN zone_demographics AS zd ON td.LocationID = zd.LocationID
+    WHERE zd.TotalPop > 0
+    GROUP BY td.service, td.month
+""").df()
+
+rr_combined: pd.DataFrame = pd.merge(
+    rr_pu_df, rr_do_df, on=["service", "month"], how="outer"
+)

requirements.txt

@@ -0,0 +1,9 @@
+solara>=1.32.0
+duckdb>=1.0.0
+pandas>=2.0.0
+geopandas>=0.14.0
+leafmap>=0.36.0
+ipywidgets>=8.0.0
+shapely>=2.0.0
+pyproj>=3.6.0
+mapclassify>=2.5.0