| import gradio as gr |
| import pandas as pd |
| import plotly.graph_objects as go |
| import numpy as np |
| from datetime import datetime |
|
|
| |
| df_sample = pd.read_csv('https://files.zillowstatic.com/research/public_csvs/zhvi/Zip_zhvi_uc_sfrcondo_tier_0.33_0.67_sm_sa_month.csv', nrows=1) |
| latest_data_date_str = df_sample.columns[-1] |
|
|
| def plot_zip_code_correlation(zip_codes_str, start_date, end_date): |
| start_year = pd.to_datetime(start_date).year |
| end_year = pd.to_datetime(end_date).year |
| if start_year < 2000 or end_year < 2000: |
| raise ValueError("Please select dates no earlier than the year 2000.") |
| if start_year > end_year: |
| raise ValueError("Start date must be before end date.") |
|
|
| zip_codes = [z.strip().zfill(5) for z in zip_codes_str.split(",")] |
| 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') |
| df['RegionName'] = df['RegionName'].astype(str).str.zfill(5) |
| df = df[df['RegionName'].isin(zip_codes)] |
| if df.empty: |
| raise ValueError("No data found for the provided ZIP codes.") |
|
|
| date_columns = [col for col in df.columns[7:] if start_date <= col <= end_date] |
| if not date_columns: |
| raise ValueError("No data available within the selected date range.") |
|
|
| price_matrix = [] |
| valid_zip_list = [] |
| for zip_code in zip_codes: |
| df_zip = df[df['RegionName'] == zip_code] |
| if not df_zip.empty: |
| prices = df_zip[date_columns].values.flatten() |
| if not np.isnan(prices).all(): |
| price_matrix.append(prices) |
| valid_zip_list.append(zip_code) |
|
|
| if len(price_matrix) < 2: |
| raise ValueError("Not enough data for correlation calculation.") |
|
|
| price_matrix_df = pd.DataFrame(price_matrix, index=valid_zip_list, columns=date_columns).T.dropna() |
| corr_matrix = price_matrix_df.corr() |
| z_data = corr_matrix.values |
| x_data, y_data = np.meshgrid(valid_zip_list, valid_zip_list) |
|
|
| fig = go.Figure(data=[go.Surface(z=z_data, x=x_data, y=y_data)]) |
| fig.update_layout( |
| title=f'3D Correlation Matrix of Housing Prices ({start_date} to {end_date})', |
| scene=dict(xaxis_title='ZIP Code', yaxis_title='ZIP Code', zaxis_title='Correlation'), |
| autosize=True |
| ) |
| return fig |
|
|
| iface = gr.Interface( |
| fn=plot_zip_code_correlation, |
| inputs=[ |
| gr.Textbox(label="Enter comma-separated ZIP codes (e.g., 07001,07002,07003)"), |
| gr.Textbox(label="Start Date (YYYY-MM-DD) - No earlier than 2000"), |
| gr.Textbox(label="End Date (YYYY-MM-DD) - No earlier than 2000") |
| ], |
| outputs=gr.Plot(), |
| title="3D ZIP Code Housing Price Correlation Matrix", |
| description=f""" |
| ## US Real Estate Zip ZHVI Price Movement Correlation Matrix Gen |
| |
| Track housing price correlations by ZIP code to make informed decisions as a property owner or buyer. |
| **Data up to {latest_data_date_str}**. Enter ZIP codes below. |
| |
| [Contact a real estate broker](https://micheled.com) |
| """ |
| ) |
|
|
| iface.launch(share=False, debug=True) |
