Update app.py

app.py

@@ -10,10 +10,19 @@ def plot_real_estate_correlation(state):
     # Filter for the given state
     df = df[df['State'] == state.upper()]
 
-    # Extract the list of ZIP codes and dates
+    # Extract the list of ZIP codes and filter only columns that are date strings
     zip_codes = df['RegionName'].unique()
-    dates = pd.to_datetime(df.columns[7:])  # Assuming price data starts from the 8th column
-
+    
+    # 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 = []
 
@@ -21,15 +30,15 @@ def plot_real_estate_correlation(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
+        # 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)
+    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()