app.py

import pandas as pd
import geopandas as gpd
import gradio as gr
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np

# ========================
# Data Loading
# ========================

# Load the health and demographic data
conus_data = pd.read_csv("conus27.csv")
# Load the county shapefile
county_geojson = gpd.read_file("county.geojson")
# Load the county embeddings
county_embeddings = pd.read_csv("county_embeddings.csv")
# Load the unemployment data
county_unemployment = pd.read_csv("county_unemployment.csv")
# Load the poverty data
zcta_poverty = pd.read_csv("zcta_poverty.csv")
# Load the ZCTA shapefile
zcta_geojson = gpd.read_file("zcta.geojson")

# Merge unemployment data with county_geojson
county_unemployment_melted = county_unemployment.melt(id_vars=['place'], 
                                                      var_name='date',
                                                      value_name='unemployment_rate')
county_unemployment_melted['place'] = county_unemployment_melted['place'].astype(str)


county_geojson_unemployment = county_geojson.merge(county_unemployment_melted, left_on='place', right_on='place', how='left')

# Prepare poverty data
zcta_poverty_melted = zcta_poverty.melt(id_vars=['place'], var_name='year', value_name='poverty_rate')


zcta_poverty_melted['place'] = zcta_poverty_melted['place'].astype(str)


zcta_geojson['place'] = zcta_geojson['place'].astype(str)

zcta_geojson_poverty = zcta_geojson.merge(zcta_poverty_melted, left_on='place', right_on='place', how='left')


# List of health metrics available
health_metrics = [col for col in conus_data.columns if col.startswith('Percent_Person_')]
# Simplify metric names
simplified_metrics = [col.replace('Percent_Person_', '') for col in health_metrics]
metric_mapping = dict(zip(simplified_metrics, health_metrics))

# ========================
# Utility Functions
# ========================

def plot_health_metric(metric):
    """
    Plots the geographical distribution of a selected health metric.
    """
    metric_full_name = metric_mapping[metric]
    fig, ax = plt.subplots(1, 1, figsize=(12, 8))
    gdf_health.plot(
        column=metric_full_name,
        cmap='OrRd',
        markersize=50,
        legend=True,
        legend_kwds={'label': f"{metric} (%)"},
        ax=ax,
        alpha=0.7,
        edgecolor='k'
    )
    ax.set_title(f'Geographical Distribution of {metric}', fontsize=15)
    ax.axis('off')
    plt.tight_layout()
    return fig

def plot_correlation_matrix(selected_metrics):
    """
    Plots the correlation matrix for selected health metrics.
    """
    selected_columns = [metric_mapping[metric] for metric in selected_metrics]
    corr = conus_data[selected_columns].corr()
    fig, ax = plt.subplots(figsize=(10, 8))
    sns.heatmap(corr, annot=True, cmap='coolwarm', square=True, ax=ax)
    ax.set_title('Correlation Matrix of Selected Health Metrics', fontsize=15)
    plt.tight_layout()
    return fig

def plot_unemployment_map(date):
    """
    Plots the unemployment rate map for a selected date.
    """
    date = str(date)
    data = county_geojson_unemployment[county_geojson_unemployment['date'] == date]
    fig, ax = plt.subplots(1, 1, figsize=(12, 8))
    data.plot(
        column='unemployment_rate',
        cmap='Blues',
        linewidth=0.8,
        ax=ax,
        edgecolor='0.8',
        legend=True,
        missing_kwds={"color": "lightgrey", "label": "Missing values"},
    )
    ax.set_title(f'Unemployment Rate by County ({date})', fontsize=15)
    ax.axis('off')
    plt.tight_layout()
    return fig

def plot_poverty_map(year):
    """
    Plots the poverty rate map for a selected year.
    """
    year = str(year)
    data = zcta_geojson_poverty[zcta_geojson_poverty['year'] == year]
    fig, ax = plt.subplots(1, 1, figsize=(12, 8))
    data.plot(
        column='poverty_rate',
        cmap='Reds',
        linewidth=0.8,
        ax=ax,
        edgecolor='0.8',
        legend=True,
        missing_kwds={"color": "lightgrey", "label": "Missing values"},
    )
    ax.set_title(f'Poverty Rate by ZCTA ({year})', fontsize=15)
    ax.axis('off')
    plt.tight_layout()
    return fig

def summarize_health_metrics(metric):
    """
    Generates summary statistics for a selected health metric.
    """
    metric_full_name = metric_mapping[metric]
    summary = conus_data[metric_full_name].describe().to_frame().reset_index()
    summary.columns = ['Statistic', 'Value']
    return summary

# ========================
# Gradio Interface Functions
# ========================

def health_metric_interface(metric):
    fig = plot_health_metric(metric)
    summary = summarize_health_metrics(metric)
    return fig, summary

def correlation_interface(metrics):
    fig = plot_correlation_matrix(metrics)
    return fig

def unemployment_interface(date):
    fig = plot_unemployment_map(date)
    return fig

def poverty_interface(year):
    fig = plot_poverty_map(year)
    return fig

# ========================
# Gradio App Setup
# ========================

with gr.Blocks(title="US Population Health Dashboard") as demo:
    gr.Markdown("# US Population Health Dashboard")
    gr.Markdown("Explore health metrics, socioeconomic data, and their geospatial distributions across the United States.")

    with gr.Tab("Health Metrics Map"):
        gr.Markdown("### Geographical Distribution of Health Metrics")
        health_metric = gr.Dropdown(label="Select a Health Metric", choices=simplified_metrics, value=simplified_metrics[0])
        health_plot = gr.Plot()
        health_summary = gr.Dataframe(headers=["Statistic", "Value"])
        health_metric.change(health_metric_interface, inputs=health_metric, outputs=[health_plot, health_summary])

    with gr.Tab("Health Metrics Correlation"):
        gr.Markdown("### Correlation Matrix of Health Metrics")
        correlation_metrics = gr.CheckboxGroup(label="Select Health Metrics", choices=simplified_metrics, value=simplified_metrics[:5])
        correlation_plot = gr.Plot()
        correlation_metrics.change(correlation_interface, inputs=correlation_metrics, outputs=correlation_plot)

    with gr.Tab("Unemployment Rate Map"):
        gr.Markdown("### Geographical Distribution of Unemployment Rates")
        dates = county_unemployment_melted['date'].unique().tolist()
        unemployment_date = gr.Slider(label="Select a Date", minimum=min(dates), maximum=max(dates), step=1, value=dates[0])
        unemployment_plot = gr.Plot()
        unemployment_date.change(unemployment_interface, inputs=unemployment_date, outputs=unemployment_plot)

    with gr.Tab("Poverty Rate Map"):
        gr.Markdown("### Geographical Distribution of Poverty Rates")
        years = zcta_poverty_melted['year'].unique().astype(int).tolist()
        poverty_year = gr.Slider(label="Select a Year", minimum=min(years), maximum=max(years), step=1, value=years[0])
        poverty_plot = gr.Plot()
        poverty_year.change(poverty_interface, inputs=poverty_year, outputs=poverty_plot)

# ========================
# Launch the App
# ========================

if __name__ == "__main__":
    demo.launch()