Update main branch with latest changes

.github/workflows/update_static.yml

@@ -0,0 +1,30 @@
+name: Update Static Files
+
+on:
+  schedule:
+    - cron: '0 */6 * * *'  # Runs every 6 hours
+  workflow_dispatch:  # Allows manual triggering
+
+jobs:
+  update_static:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+    - name: Generate static files
+      env:
+        OPENWEATHERMAP_API_KEY: ${{ secrets.OPENWEATHERMAP_API_KEY || '' }}
+      run: |
+        python generate_static.py
+    - name: Deploy to GitHub Pages
+      uses: peaceiris/actions-gh-pages@v3
+      with:
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        publish_dir: ./build

README.md

@@ -23,12 +23,20 @@ This Weather Monitoring System is a Python-based application that fetches real-t
 - Web dashboard for real-time weather visualization
 - Machine learning-based weather prediction for the next 24 hours
 
-    ### Web Dashboard
+   ### Web Dashboard
     The web dashboard provides a user-friendly interface to view current weather data, forecasts, and predictions for all monitored cities.
 
-    ### Machine Learning Weather Prediction
+   ### Machine Learning Weather Prediction
     Trained machine learning models for 24-hour weather prediction are stored in the `models/` directory.
 
+   ### Hosted Dashboard
+
+   You can view a static version of the weather dashboard online:
+
+   https://aryanbv.github.io/weather_monitoring_system/
+
+   Note: This static version is updated periodically and may not reflect real-time data. For the most up-to-date information, please run the application locally as described in the Usage section.
+
 ### Weather Monitoring System
 
 To view the real-time weather dashboard:

app.py

@@ -26,18 +26,25 @@ def dashboard():
                 predictor.load_model()
             except FileNotFoundError:
                 historical_data = db_handler.get_historical_weather_data(city)
-                predictor.train_model(historical_data)
-
+                if historical_data:
+                    predictor.train_model(historical_data)
+                else:
+                    continue  # Skip prediction if no historical data
+
             next_day = datetime.now() + timedelta(days=1)
-            prediction = predictor.predict(
-                next_day.hour,
-                next_day.weekday(),
-                next_day.month,
-                latest_data[city]['humidity'],
-                latest_data[city]['wind_speed'],
-                latest_data[city]['weather_condition']
-            )
-            predictions[city] = round(prediction, 1)
+            try:
+                prediction = predictor.predict(
+                    next_day.hour,
+                    next_day.weekday(),
+                    next_day.month,
+                    latest_data[city]['humidity'],
+                    latest_data[city]['wind_speed'],
+                    latest_data[city]['weather_condition']
+                )
+                predictions[city] = round(prediction, 1)
+            except ValueError as e:
+                print(f"Prediction error for {city}: {str(e)}")
+                predictions[city] = "N/A"
 
     return render_template('dashboard.html', latest_data=latest_data, predictions=predictions)
 

src/ml/weather_predictor.py

@@ -11,14 +11,17 @@ def __init__(self, city):
         self.model = None
         self.le = LabelEncoder()
         self.model_path = f'models/{city}_weather_model.joblib'
+        self.le_path = f'models/{city}_label_encoder.joblib'
+        self.is_fitted = False
 
     def prepare_data(self, data):
         df = pd.DataFrame(data)
         df['timestamp'] = pd.to_datetime(df['timestamp'])
         df['hour'] = df['timestamp'].dt.hour
         df['day_of_week'] = df['timestamp'].dt.dayofweek
         df['month'] = df['timestamp'].dt.month
-        df['weather_condition'] = self.le.fit_transform(df['weather_condition'])
+        self.le.fit(df['weather_condition'])
+        df['weather_condition'] = self.le.transform(df['weather_condition'])
         return df
 
     def train_model(self, data):
@@ -29,21 +32,33 @@ def train_model(self, data):
         self.model = RandomForestRegressor(n_estimators=100, random_state=42)
         self.model.fit(X_train, y_train)
         self.save_model()
+        self.is_fitted = True
 
     def predict(self, hour, day_of_week, month, humidity, wind_speed, weather_condition):
-        if self.model is None:
+        if not self.is_fitted:
             self.load_model()
-        weather_condition_encoded = self.le.transform([weather_condition])[0]
+        try:
+            weather_condition_encoded = self.le.transform([weather_condition])[0]
+        except ValueError:
+            # If the weather condition is not in the encoder, use a default value
+            weather_condition_encoded = -1
+
+        if self.model is None:
+            raise ValueError("Model not trained or loaded. Please train the model first.")
+
         prediction = self.model.predict([[hour, day_of_week, month, humidity, wind_speed, weather_condition_encoded]])
         return prediction[0]
 
     def save_model(self):
         if not os.path.exists('models'):
             os.makedirs('models')
         joblib.dump(self.model, self.model_path)
+        joblib.dump(self.le, self.le_path)
 
     def load_model(self):
-        if os.path.exists(self.model_path):
+        if os.path.exists(self.model_path) and os.path.exists(self.le_path):
             self.model = joblib.load(self.model_path)
+            self.le = joblib.load(self.le_path)
+            self.is_fitted = True
         else:
             raise FileNotFoundError(f"No trained model found for {self.city}")

update_github.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+
+# Update main branch
+git checkout main
+git add .
+git commit -m "Update main branch with latest changes"
+git push origin main
+
+# Update gh-pages branch
+git checkout gh-pages
+git merge main
+python generate_static.py
+git add .
+git commit -m "Update static files for GitHub Pages"
+git push origin gh-pages
+
+# Switch back to main branch
+git checkout main
+
+echo "GitHub repository and Pages site updated successfully!"