Update app.py

app.py

@@ -1,15 +1,48 @@
-# Load the saved model
-# ipython-input-10-d7dffa1aa475
-# Load the saved model
+import numpy as np
+import pickle
 from keras.models import load_model
-from keras.losses import mean_squared_error # Import the MSE loss function
+from keras.losses import mean_squared_error
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
+import matplotlib.pyplot as plt
+
+# Load the saved model
+loaded_model = load_model('solar_irradiance_model.h5', custom_objects={'mse': mean_squared_error})
 
-# Load the model with custom_objects
-loaded_model = load_model('solar_irradiance_model.h5', custom_objects={'mse': mean_squared_error}) 
+# Load or initialize the encoder
+try:
+    with open('encoder.pkl', 'rb') as file:
+        encoder = pickle.load(file)
+except FileNotFoundError:
+    # Define and fit the encoder
+    encoder = OneHotEncoder(sparse_output=False)
+    month_hour_data = np.array([
+        ['January', 0], ['February', 0], ['March', 0], ['April', 0],
+        ['May', 0], ['June', 0], ['July', 0], ['August', 0],
+        ['September', 0], ['October', 0], ['November', 0], ['December', 0]
+    ])
+    # Adding all 24 hours for each month (simplified for example)
+    month_hour_data = np.concatenate(
+        [np.column_stack((month_hour_data[:, 0], np.arange(24))) for _ in range(12)]
+    )
+    encoder.fit(month_hour_data)
+    with open('encoder.pkl', 'wb') as file:
+        pickle.dump(encoder, file)
 
-# ... (rest of the code remains the same)
+# Load or initialize the scaler
+try:
+    with open('scaler.pkl', 'rb') as file:
+        scaler = pickle.load(file)
+except FileNotFoundError:
+    # Placeholder: Fit the scaler on the actual dataset during training
+    scaler = StandardScaler()
+    # Assuming some training data is available for fitting
+    # Replace `training_features` with your actual training numerical features
+    training_features = np.random.rand(100, 7)  # Dummy data
+    scaler.fit(training_features)
+    with open('scaler.pkl', 'wb') as file:
+        pickle.dump(scaler, file)
 
-# Function to predict the irradiance for a given month, hour, and other features
+# Function to predict the irradiance
 def predict_irradiance(month, hour, latitude, longitude, panel_capacity, panel_efficiency, wind_speed, cloud_cover, temperature):
     # Encode the month and hour
     encoded_month_hour = encoder.transform([[month, hour]])
@@ -23,19 +56,22 @@ def predict_irradiance(month, hour, latitude, longitude, panel_capacity, panel_e
     predicted_irradiance = loaded_model.predict(reshaped_features)
     return max(predicted_irradiance[0][0], 0.0)
 
-# Function to get the actual irradiance for a given month
+# Function to get the actual irradiance for a given month (assuming `data` exists)
 def get_actual_irradiance(month):
-    return data[data['Month'] == month]['Irradiance(W/m^2)'].values
-
+    # Replace `data` with your actual dataset
+    data = {
+        'Month': ['January', 'January', 'February', 'February'],  # Example
+        'Irradiance(W/m^2)': [500, 520, 480, 510]
+    }
+    return [data['Irradiance(W/m^2)'][i] for i in range(len(data['Month'])) if data['Month'][i] == month]
 
-    # Example usage: Predict the irradiance for July, hour 12 with additional features
+# Example usage
 month = 'January'
 hour = 12
 predicted_irradiance = predict_irradiance(month, hour, 28.570633, 77.327215, 500, 0.15, 6.43988, 17.7, 55)
 print(f'Predicted irradiance for {month}, hour {hour}: {predicted_irradiance}')
 
 # Plot Actual vs. Predicted Irradiance for a specific month
-month = 'January'
 actual_irradiance = get_actual_irradiance(month)
 predicted_irradiances = []
 
@@ -44,10 +80,10 @@ for hour in range(24):
     predicted_irradiances.append(irradiance)
 
 plt.figure(figsize=(12, 6))
-plt.plot(range(24), actual_irradiance, label='Actual Irradiance')
+plt.plot(range(24), actual_irradiance[:24], label='Actual Irradiance')  # Ensure actual data matches 24 hours
 plt.plot(range(24), predicted_irradiances, label='Predicted Irradiance')
 plt.xlabel('Hour')
 plt.ylabel('Irradiance (W/m^2)')
 plt.title(f'Actual vs. Predicted Irradiance for {month}')
 plt.legend()
-plt.show()
+plt.show()