app.py

import gradio as gr
import pandas as pd
import plotly.graph_objects as go
import numpy as np

def plot_real_estate_correlation(state):
    # Read the CSV file
    df = pd.read_csv('https://files.zillowstatic.com/research/public_csvs/zhvi/Zip_zhvi_uc_sfrcondo_tier_0.33_0.67_sm_sa_month.csv')

    # Filter for the given state
    df = df[df['State'] == state.upper()]

    # Extract the list of ZIP codes and price data
    zip_codes = df['RegionName'].unique()
    price_data = df.iloc[:, 7:]  # Assuming price data starts from the 8th column

    # Drop rows with missing data to avoid issues in correlation calculation
    price_data = price_data.dropna(axis=1, how='all')

    # Calculate the correlation matrix for ZIP codes
    corr_matrix = price_data.T.corr()

    # Prepare the grid data for 3D plot
    x_data, y_data = np.meshgrid(zip_codes, zip_codes)
    z_data = corr_matrix.values

    # Create the 3D surface plot
    fig = go.Figure(data=[go.Surface(z=z_data, x=x_data, y=y_data)])

    # Update plot layout
    fig.update_layout(
        title=f'3D Correlation Matrix of Housing Prices in {state}',
        scene=dict(
            xaxis_title='ZIP Code',
            yaxis_title='ZIP Code',
            zaxis_title='Correlation',
        ),
        autosize=True
    )

    return fig

iface = gr.Interface(fn=plot_real_estate_correlation,
                     inputs=[gr.components.Textbox(label="State (e.g., 'NJ' for New Jersey)")],
                     outputs=gr.Plot())

iface.launch(share=False, debug=True)