File size: 2,415 Bytes
68f4690 615dbda 68f4690 615dbda 7ed2a2c 615dbda 7ed2a2c 615dbda 7ed2a2c 68f4690 7ed2a2c 68f4690 7ed2a2c 68f4690 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
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 filter only columns that are date strings
zip_codes = df['RegionName'].unique()
# Extract columns that are valid date strings only
date_columns = []
for col in df.columns[7:]:
try:
# Try to parse column names as dates
pd.to_datetime(col)
date_columns.append(col)
except:
continue
# Initialize a DataFrame to hold price data for correlation calculation
price_matrix = []
# Loop through each ZIP code in the state
for zip_code in zip_codes:
df_zip = df[df['RegionName'] == zip_code]
# Extract only the columns with valid date data (price values)
prices = df_zip.loc[:, date_columns].values.flatten()
# Append prices to the matrix if there are no missing values
if not np.isnan(prices).all():
price_matrix.append(prices)
# Convert to DataFrame for easier manipulation
price_matrix_df = pd.DataFrame(price_matrix, index=zip_codes, columns=date_columns)
# Transpose to align for correlation calculation (each column = ZIP code)
price_matrix_df = price_matrix_df.T.dropna()
# Calculate the correlation matrix for ZIP codes
corr_matrix = price_matrix_df.corr()
# Prepare the grid data for 3D plot
z_data = corr_matrix.values
x_data, y_data = np.meshgrid(zip_codes, zip_codes)
# 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) |