Update app.py

app.py

@@ -113,25 +113,32 @@ def forecast_solar_energy(historical_data):
 # Read and preprocess CSV data for prediction
 def preprocess_csv_for_prediction(csv_file):
     try:
-        # Load the data from CSV file
-        data = pd.read_csv(csv_file.name)  # Corrected from Solar_Irradiance.csv to use the file input
+        # Load the dataset from CSV
+        data = pd.read_csv(csv_file.name)
 
-        # Ensure that the CSV has 7 columns (features) and at least 43 rows (timesteps)
-        if data.shape[1] != 7:
-            return "Error: CSV should have exactly 7 columns corresponding to the 7 features"
+        # Validate column names
+        expected_columns = ['Month', 'Hour', 'Irradiance(W/m^2)', 'Latitude', 'Longitude', 
+                            'Panel_Capacity(W)', 'Panel_Efficiency', 'Wind_Speed(km/h)', 
+                            'Cloud_Cover(%)', 'temperature (°f)']
+        if list(data.columns) != expected_columns:
+            return f"Error: Expected columns {expected_columns}, but got {list(data.columns)}"
 
-        # Check if there are enough rows (43 days of data)
+        # Ensure there are at least 43 rows for prediction
         if data.shape[0] < 43:
-            return "Error: CSV should have at least 43 rows of data"
+            return "Error: CSV must have at least 43 rows of data for prediction"
 
-        # Select the last 43 rows of data
-        last_43_days = data.tail(43)
+        # Select the relevant columns for the LSTM model
+        relevant_columns = ['Irradiance(W/m^2)', 'Panel_Efficiency', 'Wind_Speed(km/h)', 
+                            'Cloud_Cover(%)', 'temperature (°f)']
+        last_43_days = data.tail(43)[relevant_columns]
 
-        # Convert the data to a numpy array (we expect 43 days, 7 features)
-        data_array = last_43_days.values.astype(np.float32)
+        # Handle missing values (replace NaNs with 0)
+        if last_43_days.isnull().any().any():
+            last_43_days.fillna(0, inplace=True)
 
-        # Reshape the data to match the input shape (1, 43, 7)
-        sequence = np.reshape(data_array, (1, 43, 7))
+        # Convert to numpy array and reshape for LSTM input
+        data_array = last_43_days.values.astype(np.float32)
+        sequence = np.reshape(data_array, (1, 43, len(relevant_columns)))
 
         return sequence
     except Exception as e:
@@ -140,13 +147,13 @@ def preprocess_csv_for_prediction(csv_file):
 
 # Function to process image and forecast energy using CSV file
 # Function to process image and forecast energy using CSV file
-def process_image_and_forecast(image, min_area, pixel_area, clip_limit, tile_size, panel_type,
+def process_image_and_forecast(image, min_area, pixel_area, clip_limit, tile_size, panel_type, 
                                 panel_length, panel_width, irradiance, electricity_rate, historical_data_csv):
     try:
+        # Process the uploaded image
         if image is None:
             return None, "Error: No image provided."
 
-        # Process image
         preprocessed = preprocess_image(image, clip_limit, tile_size)
         roof_contour = find_roof_contour(preprocessed, min_area)
         roof_area = calculate_roof_area(roof_contour, pixel_area)
@@ -155,25 +162,24 @@ def process_image_and_forecast(image, min_area, pixel_area, clip_limit, tile_siz
         num_panels, total_energy_kwh, total_cost_inr = calculate_panels_and_energy(
             roof_area, panel_length, panel_width, panel_type, irradiance
         )
-
         yearly_savings = estimate_savings(total_energy_kwh, electricity_rate)
 
-        # Forecast energy from CSV data
+        # Forecast energy using the CSV data
         forecast_text = ""
         if historical_data_csv:
-            # Preprocess and predict from CSV data
             sequence = preprocess_csv_for_prediction(historical_data_csv)
-            if isinstance(sequence, str):  # If an error message is returned
+            if isinstance(sequence, str):  # Handle errors during preprocessing
                 return image, sequence
 
+            # Predict energy output
             predicted_energy = model.predict(sequence)
             forecast_text = f"Predicted Energy Output for Next Day: {predicted_energy[0][0]:.2f} kWh"
 
-        # Draw the roof contour if found
+        # Draw the roof contour on the image
         if roof_contour is not None:
             cv2.drawContours(image, [roof_contour], -1, (0, 255, 0), 2)
 
-        # Return results as text
+        # Compile results
         result_text = (
             f"Roof Area: {roof_area:.2f} sq.m | Panels: {num_panels} | "
             f"Energy Output: {total_energy_kwh:.2f} kWh | Cost: ₹{total_cost_inr:.2f} | "
@@ -185,6 +191,7 @@ def process_image_and_forecast(image, min_area, pixel_area, clip_limit, tile_siz
         return image, f"Error: {str(e)}"
 
 
+
 # Gradio Interface
 interface = gr.Interface(
     fn=process_image_and_forecast,