Update app.py

app.py

@@ -9,23 +9,23 @@ def plot_zip_code_correlation(zip_codes_str, start_date, end_date):
     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.")
 
-    # Convert input string to list of zip codes
-    zip_codes = [z.strip() for z in zip_codes_str.split(",")]
+    # Process ZIP codes (ensure 5-digit format)
+    zip_codes = [z.strip().zfill(5) for z in zip_codes_str.split(",")]
 
-    # Read the CSV file
+    # Load data
     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 ZIP codes
-    df = df[df['RegionName'].astype(str).isin(zip_codes)]
+    # Ensure ZIP codes in dataframe are strings with leading zeros
+    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.")
 
-    # Extract valid date columns within the selected date range
+    # Extract date columns within the selected range
     date_columns = []
     for col in df.columns[7:]:
         try:
@@ -38,35 +38,34 @@ def plot_zip_code_correlation(zip_codes_str, start_date, end_date):
     if not date_columns:
         raise ValueError("No data available within the selected date range.")
 
-    # Initialize price matrix
+    # Build price matrix
     price_matrix = []
-    zip_list = []
+    valid_zip_list = []
 
     for zip_code in zip_codes:
-        df_zip = df[df['RegionName'].astype(str) == zip_code]
+        df_zip = df[df['RegionName'] == zip_code]
         if not df_zip.empty:
             prices = df_zip.loc[:, date_columns].values.flatten()
             if not np.isnan(prices).all():
                 price_matrix.append(prices)
-                zip_list.append(zip_code)
+                valid_zip_list.append(zip_code)
 
     if len(price_matrix) < 2:
-        raise ValueError("Not enough data for correlation calculation.")
+        raise ValueError(f"Not enough data for correlation calculation. Ensure at least two valid ZIP codes with overlapping data between {start_date} and {end_date}.")
 
-    price_matrix_df = pd.DataFrame(price_matrix, index=zip_list, columns=date_columns)
+    price_matrix_df = pd.DataFrame(price_matrix, index=valid_zip_list, columns=date_columns)
     price_matrix_df = price_matrix_df.T.dropna()
 
     # Calculate correlation matrix
     corr_matrix = price_matrix_df.corr()
 
-    # Prepare 3D plot data
+    # Prepare 3D plot
     z_data = corr_matrix.values
-    x_data, y_data = np.meshgrid(zip_list, zip_list)
+    x_data, y_data = np.meshgrid(valid_zip_list, valid_zip_list)
 
-    # Plot
     fig = go.Figure(data=[go.Surface(z=z_data, x=x_data, y=y_data)])
     fig.update_layout(
-        title=f'3D Correlation Matrix ({start_date} to {end_date})',
+        title=f'3D Correlation Matrix of Housing Prices ({start_date} to {end_date})',
         scene=dict(
             xaxis_title='ZIP Code',
             yaxis_title='ZIP Code',
@@ -80,12 +79,12 @@ def plot_zip_code_correlation(zip_codes_str, start_date, end_date):
 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="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="ZIP Code 3D Correlation Matrix with Date Range"
+    title="3D ZIP Code Housing Price Correlation Matrix"
 )
 
 iface.launch(share=False, debug=True)