Update app.py

app.py

@@ -3,7 +3,16 @@ import pandas as pd
 import plotly.graph_objects as go
 import numpy as np
 
-def plot_zip_code_correlation(zip_codes_str):
+def plot_zip_code_correlation(zip_codes_str, start_date, end_date):
+    # Validate dates
+    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.")
+
     # Convert input string to list of zip codes
     zip_codes = [z.strip() for z in zip_codes_str.split(",")]
 
@@ -16,16 +25,20 @@ def plot_zip_code_correlation(zip_codes_str):
     if df.empty:
         raise ValueError("No data found for the provided ZIP codes.")
 
-    # Extract columns that are valid date strings only
+    # Extract valid date columns within the selected date range
     date_columns = []
     for col in df.columns[7:]:
         try:
-            pd.to_datetime(col)
-            date_columns.append(col)
+            date = pd.to_datetime(col)
+            if start_date <= str(date.date()) <= end_date:
+                date_columns.append(col)
         except:
             continue
 
-    # Initialize a DataFrame to hold price data for correlation calculation
+    if not date_columns:
+        raise ValueError("No data available within the selected date range.")
+
+    # Initialize price matrix
     price_matrix = []
     zip_list = []
 
@@ -37,25 +50,23 @@ def plot_zip_code_correlation(zip_codes_str):
                 price_matrix.append(prices)
                 zip_list.append(zip_code)
 
-    # Check if there is enough data
     if len(price_matrix) < 2:
         raise ValueError("Not enough data for correlation calculation.")
 
     price_matrix_df = pd.DataFrame(price_matrix, index=zip_list, columns=date_columns)
     price_matrix_df = price_matrix_df.T.dropna()
 
-    # Calculate correlation
+    # Calculate correlation matrix
     corr_matrix = price_matrix_df.corr()
 
-    # Prepare data for 3D plot
+    # Prepare 3D plot data
     z_data = corr_matrix.values
     x_data, y_data = np.meshgrid(zip_list, zip_list)
 
-    # Create the 3D surface plot
+    # Plot
     fig = go.Figure(data=[go.Surface(z=z_data, x=x_data, y=y_data)])
-
     fig.update_layout(
-        title='3D Correlation Matrix of Housing Prices for Selected ZIP Codes',
+        title=f'3D Correlation Matrix ({start_date} to {end_date})',
         scene=dict(
             xaxis_title='ZIP Code',
             yaxis_title='ZIP Code',
@@ -68,9 +79,13 @@ def plot_zip_code_correlation(zip_codes_str):
 
 iface = gr.Interface(
     fn=plot_zip_code_correlation,
-    inputs=gr.Textbox(label="Enter comma-separated ZIP codes (e.g., 07001, 07002, 07003)"),
+    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="ZIP Code 3D Correlation Matrix"
+    title="ZIP Code 3D Correlation Matrix with Date Range"
 )
 
-iface.launch(debug=True)
+iface.launch(share=False, debug=True)