Update app.py

app.py

@@ -8,7 +8,7 @@ import os
 from datetime import datetime
 
 # Load the trained model for image-based fog classification
-learn = load_learner('fog_classifier.pkl')
+learn = load_learner('afog_classifier.pkl')
 labels = learn.dls.vocab
 
 # Use environment variables for API keys
@@ -29,14 +29,14 @@ def get_weather_data(location):
     current_data = current_response.json()
 
     current_weather = {
-        'temperature': current_data['main']['temp'],
-        'feels_like': current_data['main']['feels_like'],
-        'description': current_data['weather'][0]['description'],
-        'wind_speed': current_data['wind']['speed'],
-        'pressure': current_data['main']['pressure'],
-        'humidity': current_data['main']['humidity'],
-        'visibility': current_data['visibility'] / 1000,
-        'dew_point': current_data['main']['temp'] - ((100 - current_data['main']['humidity']) / 5.0)
+        'temperature': current_data['main'].get('temp', 0),
+        'feels_like': current_data['main'].get('feels_like', 0),
+        'description': current_data['weather'][0].get('description', ''),
+        'wind_speed': current_data['wind'].get('speed', 0),
+        'pressure': current_data['main'].get('pressure', 0),
+        'humidity': current_data['main'].get('humidity', 0),
+        'visibility': current_data.get('visibility', 10000) / 1000,
+        'dew_point': current_data['main'].get('temp', 0) - ((100 - current_data['main'].get('humidity', 0)) / 5.0)
     }
     return current_weather
 
@@ -53,20 +53,20 @@ def train_fog_model():
 # Function to predict fog based on weather data
 def predict_fog(model, feature_columns, weather_data):
     new_data = pd.DataFrame({
-        'Temperature': [weather_data['temperature']],
-        'Feels like': [weather_data['feels_like']],
-        'Wind speed': [weather_data['wind_speed']],
-        'Pressure': [weather_data['pressure']],
-        'Humidity': [weather_data['humidity']],
-        'Dew point': [weather_data['dew_point']],
-        'Visibility': [weather_data['visibility']]
+        'Temperature': [weather_data.get('temperature', 0)],
+        'Feels like': [weather_data.get('feels_like', 0)],
+        'Wind speed': [weather_data.get('wind_speed', 0)],
+        'Pressure': [weather_data.get('pressure', 0)],
+        'Humidity': [weather_data.get('humidity', 0)],
+        'Dew point': [weather_data.get('dew_point', 0)],
+        'Visibility': [weather_data.get('visibility', 10)]
     })
 
     for col in feature_columns:
         if col.startswith('Description_'):
             new_data[col] = 0
 
-    description_column = f"Description_{weather_data['description'].replace(' ', '_')}"
+    description_column = f"Description_{weather_data.get('description', '').replace(' ', '_')}"
     if description_column in feature_columns:
         new_data[description_column] = 1
 
@@ -83,9 +83,9 @@ def get_5day_forecast(location):
     for entry in forecast_data['list']:
         forecast_list.append({
             'date': entry['dt_txt'],
-            'temperature': entry['main']['temp'],
-            'humidity': entry['main']['humidity'],
-            'description': entry['weather'][0]['description']
+            'temperature': entry['main'].get('temp', 0),
+            'humidity': entry['main'].get('humidity', 0),
+            'description': entry['weather'][0].get('description', '')
         })
     return forecast_list
 
@@ -99,14 +99,14 @@ def predict_current_weather(location):
         fog_prediction = predict_fog(fog_model, feature_columns, current_weather)
 
         result = f"Current weather in {location}:\n"
-        result += f"Temperature: {current_weather['temperature']}°C\n"
-        result += f"Feels like: {current_weather['feels_like']}°C\n"
-        result += f"Description: {current_weather['description']}\n"
-        result += f"Wind speed: {current_weather['wind_speed']} m/s\n"
-        result += f"Pressure: {current_weather['pressure']} hPa\n"
-        result += f"Humidity: {current_weather['humidity']}%\n"
-        result += f"Dew point: {current_weather['dew_point']}°C\n"
-        result += f"Visibility: {current_weather['visibility']} km\n"
+        result += f"Temperature: {current_weather.get('temperature', 0)}°C\n"
+        result += f"Feels like: {current_weather.get('feels_like', 0)}°C\n"
+        result += f"Description: {current_weather.get('description', '')}\n"
+        result += f"Wind speed: {current_weather.get('wind_speed', 0)} m/s\n"
+        result += f"Pressure: {current_weather.get('pressure', 0)} hPa\n"
+        result += f"Humidity: {current_weather.get('humidity', 0)}%\n"
+        result += f"Dew point: {current_weather.get('dew_point', 0)}°C\n"
+        result += f"Visibility: {current_weather.get('visibility', 10)} km\n"
         result += f"\nFog Prediction: {fog_prediction}"
 
         return result
@@ -171,18 +171,18 @@ def integrated_prediction(image, location):
     formatted_forecast = format_5day_forecast(forecast_list)
 
     # Determine transmission power based on current and future fog predictions
-    transmission_power = determine_transmission_power(image_prediction, weather_prediction, current_weather['humidity'])
+    transmission_power = determine_transmission_power(image_prediction, weather_prediction, current_weather.get('humidity', 0))
 
     # Check fog predictions for the next 5 days
     fog_days = []
     for entry in forecast_list:
         date = entry['date'].split()[0]
         weather_data = {
-            'temperature': entry['temperature'],
-            'humidity': entry['humidity'],
-            'description': entry['description'],
+            'temperature': entry.get('temperature', 0),
+            'humidity': entry.get('humidity', 0),
+            'description': entry.get('description', ''),
             'visibility': 10,  # Assuming visibility is 10 km for simplicity
-            'dew_point': entry['temperature'] - ((100 - entry['humidity']) / 5.0)
+            'dew_point': entry.get('temperature', 0) - ((100 - entry.get('humidity', 0)) / 5.0)
         }
         fog_prediction = predict_fog(fog_model, feature_columns, weather_data)
         if fog_prediction == "Foggy weather":