Update app.py

app.py

@@ -5,11 +5,13 @@ from sklearn.model_selection import train_test_split
 from sklearn.metrics import mean_squared_error
 import gradio as gr
 import os
+import json
+import datetime
 
 # API Endpoints
 WEATHER_API = "https://api.open-meteo.com/v1/forecast"
 ELECTRICITY_PRICE_API = "https://www.elprisetjustnu.se/api/v1/prices"
-ENERGY_PRODUCTION_API = "https://transparency.entsoe.eu/api"
+ENERGY_CHARTS_API = "https://energy-charts.info/api/public_power"
 
 # Fetch weather data
 def fetch_weather_data():
@@ -26,16 +28,28 @@ def fetch_weather_data():
 
 # Fetch electricity price data
 def fetch_electricity_prices():
-    response = requests.get(ELECTRICITY_PRICE_API + "/json/sv")
+    today = datetime.datetime.now().strftime('%Y/%m-%d')
+    url = f"{ELECTRICITY_PRICE_API}/{today}_SE3.json"  # Replace 'SE3' with the desired price category
+    response = requests.get(url)
     response.raise_for_status()
     return pd.DataFrame(response.json())
 
-# Fetch energy production prices
+# Fetch energy production data using Energy-Charts API
 def fetch_energy_production_data():
-    # Placeholder for actual API parameters
-    response = requests.get(ENERGY_PRODUCTION_API, params={})
+    params = {
+        "country": "se",  # Sweden country code
+        "start": "2023-01-01",
+        "end": "2023-12-31"
+    }
+    response = requests.get(ENERGY_CHARTS_API, params=params)
     response.raise_for_status()
-    return pd.DataFrame(response.json())
+    data = response.json()
+    production_data = {
+        "unix_seconds": data["unix_seconds"],
+        "production": {ptype["name"]: ptype["data"] for ptype in data["production_types"]}
+    }
+    production_df = pd.DataFrame(production_data)
+    return production_df
 
 # Prepare the dataset
 def prepare_dataset(weather_data, electricity_data, energy_data):
@@ -64,6 +78,28 @@ def predict_price(features):
     prediction = model.predict(pd.DataFrame([features]))
     return prediction[0]
 
+# Update predictions and save to file
+def update_predictions():
+    # Fetch the latest data
+    weather_data = fetch_weather_data()
+    electricity_data = fetch_electricity_prices()
+    energy_data = fetch_energy_production_data()
+
+    # Prepare dataset
+    dataset = prepare_dataset(weather_data, electricity_data, energy_data)
+
+    # Load the model
+    model = xgb.XGBRegressor()
+    model.load_model("electricity_price_model.json")
+
+    # Generate predictions
+    predictions = model.predict(dataset.drop("price", axis=1))
+
+    # Save predictions to file
+    predictions_output = dataset.copy()
+    predictions_output["predicted_price"] = predictions
+    predictions_output.to_json("predictions.json", orient="records")
+
 # Gradio Interface
 def gradio_interface():
     def wrapper(temp, precip, wind_speed, humidity, energy_price, electricity_price):
@@ -95,16 +131,19 @@ def gradio_interface():
     interface.launch()
 
 if __name__ == "__main__":
-    # Fetch data
-    weather_data = fetch_weather_data()
-    electricity_data = fetch_electricity_prices()
-    energy_data = fetch_energy_production_data()
-
-    # Prepare dataset and train the model
-    dataset = prepare_dataset(weather_data, electricity_data, energy_data)
-    rmse = train_model(dataset)
-    print(f"Model trained with RMSE: {rmse}")
-
-    # Launch Gradio interface
-    gradio_interface()
-
+    import sys
+    if len(sys.argv) > 1 and sys.argv[1] == "update":
+        update_predictions()
+    else:
+        # Fetch data
+        weather_data = fetch_weather_data()
+        electricity_data = fetch_electricity_prices()
+        energy_data = fetch_energy_production_data()
+
+        # Prepare dataset and train the model
+        dataset = prepare_dataset(weather_data, electricity_data, energy_data)
+        rmse = train_model(dataset)
+        print(f"Model trained with RMSE: {rmse}")
+
+        # Launch Gradio interface
+        gradio_interface()