Update app.py

app.py

@@ -10,19 +10,36 @@ def plot_real_estate_correlation(state):
     # Filter for the given state
     df = df[df['State'] == state.upper()]
 
-    # Extract the list of ZIP codes and price data
+    # Extract the list of ZIP codes and dates
     zip_codes = df['RegionName'].unique()
-    price_data = df.iloc[:, 7:]  # Assuming price data starts from the 8th column
+    dates = pd.to_datetime(df.columns[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')
+    # 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 date data (price values)
+        prices = df_zip.iloc[0, 7:].values  # Extract price values starting from the 8th column
+
+        # 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)
+
+    # 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_data.T.corr()
+    corr_matrix = price_matrix_df.corr()
 
     # Prepare the grid data for 3D plot
-    x_data, y_data = np.meshgrid(zip_codes, zip_codes)
     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)])