Implemented Non Autorgressive Quantile Regression

src/data/preprocessing.py

@@ -9,11 +9,24 @@ import pytz
 
 history_data_path = "../../data/history-quarter-hour-data.csv"
 forecast_data_path = "../../data/load_forecast.csv"
+pv_forecast_data_path = "../../data/pv_gen_forecast.csv"
+wind_forecast_data_path = "../../data/wind_gen_forecast.csv"
 
 class DataConfig:
-    NRV_HISTORY: bool = True
-    LOAD_FORECAST: bool = True
-    LOAD_HISTORY: bool = False
+    def __init__(self):
+        self.NRV_HISTORY: bool = True
+
+        ### LOAD ###
+        self.LOAD_FORECAST: bool = True
+        self.LOAD_HISTORY: bool = False
+
+        ### PV ###
+        self.PV_FORECAST: bool = False
+        self.PV_HISTORY: bool = False
+
+        ### WIND ###
+        self.WIND_FORECAST: bool = False
+        self.WIND_HISTORY: bool = False
 
 class DataProcessor:
     def __init__(self, data_config: DataConfig):
@@ -26,8 +39,12 @@ class DataProcessor:
 
         self.history_features = self.get_nrv_history()
         self.future_features = self.get_load_forecast()
+        self.pv_forecast = self.get_pv_forecast()
+        self.wind_forecast = self.get_wind_forecast()
 
         self.all_features = self.history_features.merge(self.future_features, on='datetime', how='left')
+        self.all_features = self.all_features.merge(self.pv_forecast, on='datetime', how='left')
+        self.all_features = self.all_features.merge(self.wind_forecast, on='datetime', how='left')
 
         self.data_config = data_config
 
@@ -69,6 +86,31 @@ class DataProcessor:
         df.sort_values(by="datetime", inplace=True)
         return df
     
+    def get_pv_forecast(self):
+        df = pd.read_csv(pv_forecast_data_path, delimiter=';')
+
+        df = df.rename(columns={'dayahead11hforecast': 'pv_forecast', 'Datetime': 'datetime'})
+        df = df[['datetime', 'pv_forecast']]
+
+        df = df.groupby('datetime').mean().reset_index()
+        df['datetime'] = pd.to_datetime(df['datetime'], utc=True)
+        df.sort_values(by="datetime", inplace=True)
+        return df
+
+    def get_wind_forecast(self):
+        df = pd.read_csv(wind_forecast_data_path, delimiter=';')
+
+        df = df.rename(columns={'dayaheadforecast': 'wind_forecast', 'datetime': 'datetime'})
+        df = df[['datetime', 'wind_forecast']]
+
+        # remove nan rows
+        df = df[~df['wind_forecast'].isnull()]
+
+        df = df.groupby('datetime').mean().reset_index()
+        df['datetime'] = pd.to_datetime(df['datetime'], utc=True)
+        df.sort_values(by="datetime", inplace=True)
+        return df
+    
     def set_batch_size(self, batch_size: int):
         self.batch_size = batch_size