openstef 3.4.42__tar.gz → 3.4.43__tar.gz

{openstef-3.4.42 → openstef-3.4.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.42
+Version: 3.4.43
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.42 → openstef-3.4.43}/openstef/data_classes/prediction_job.py

@@ -9,7 +9,7 @@ from pydantic.v1 import BaseModel
 from openstef.data_classes.data_prep import DataPrepDataClass
 from openstef.data_classes.model_specifications import ModelSpecificationDataClass
 from openstef.data_classes.split_function import SplitFuncDataClass
-from openstef.enums import PipelineType
+from openstef.enums import PipelineType, BiddingZone
 
 
 class PredictionJobDataClass(BaseModel):
@@ -54,6 +54,8 @@ class PredictionJobDataClass(BaseModel):
     lon: Optional[float] = 5.291266
     """Longitude of the forecasted location in degrees. Used for fetching weather data in tasks, calculating derrived features and component splitting."""
     name: str
+    """Bidding zone is used to determine the electricity price. It is also used to determine the holidays that should be used. Currently only ENTSO-E bidding zones are supported."""
+    electricity_bidding_zone: Optional[BiddingZone] = BiddingZone.NL
     """Name of the forecast, e.g. the location name."""
     train_components: Optional[bool]
     """Whether splitting the forecasts in wind, solar, rest is desired."""

openstef-3.4.43/openstef/enums.py

@@ -0,0 +1,132 @@
+# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
+#
+# SPDX-License-Identifier: MPL-2.0
+from enum import Enum
+
+
+class BiddingZone(Enum):
+    DE_50HZ = "DE_50HZ"
+    AL = "AL"
+    DE_AMPRION = "DE_AMPRION"
+    AT = "AT"
+    BY = "BY"
+    BE = "BE"
+    BA = "BA"
+    BG = "BG"
+    CZ_DE_SK = "CZ_DE_SK"
+    HR = "HR"
+    CWE = "CWE"
+    CY = "CY"
+    CZ = "CZ"
+    DE_AT_LU = "DE_AT_LU"
+    DE_LU = "DE_LU"
+    DK = "DK"
+    DK_1 = "DK_1"
+    DK_1_NO_1 = "DK_1_NO_1"
+    DK_2 = "DK_2"
+    DK_CA = "DK_CA"
+    EE = "EE"
+    FI = "FI"
+    MK = "MK"
+    FR = "FR"
+    DE = "DE"
+    GR = "GR"
+    HU = "HU"
+    IS = "IS"
+    IE_SEM = "IE_SEM"
+    IE = "IE"
+    IT = "IT"
+    IT_SACO_AC = "IT_SACO_AC"
+    IT_CALA = "IT_CALA"
+    IT_SACO_DC = "IT_SACO_DC"
+    IT_BRNN = "IT_BRNN"
+    IT_CNOR = "IT_CNOR"
+    IT_CSUD = "IT_CSUD"
+    IT_FOGN = "IT_FOGN"
+    IT_GR = "IT_GR"
+    IT_MACRO_NORTH = "IT_MACRO_NORTH"
+    IT_MACRO_SOUTH = "IT_MACRO_SOUTH"
+    IT_MALTA = "IT_MALTA"
+    IT_NORD = "IT_NORD"
+    IT_NORD_AT = "IT_NORD_AT"
+    IT_NORD_CH = "IT_NORD_CH"
+    IT_NORD_FR = "IT_NORD_FR"
+    IT_NORD_SI = "IT_NORD_SI"
+    IT_PRGP = "IT_PRGP"
+    IT_ROSN = "IT_ROSN"
+    IT_SARD = "IT_SARD"
+    IT_SICI = "IT_SICI"
+    IT_SUD = "IT_SUD"
+    RU_KGD = "RU_KGD"
+    LV = "LV"
+    LT = "LT"
+    LU = "LU"
+    LU_BZN = "LU_BZN"
+    MT = "MT"
+    ME = "ME"
+    GB = "GB"
+    GE = "GE"
+    GB_IFA = "GB_IFA"
+    GB_IFA2 = "GB_IFA2"
+    GB_ELECLINK = "GB_ELECLINK"
+    UK = "UK"
+    NL = "NL"
+    NO_1 = "NO_1"
+    NO_1A = "NO_1A"
+    NO_2 = "NO_2"
+    NO_2_NSL = "NO_2_NSL"
+    NO_2A = "NO_2A"
+    NO_3 = "NO_3"
+    NO_4 = "NO_4"
+    NO_5 = "NO_5"
+    NO = "NO"
+    PL_CZ = "PL_CZ"
+    PL = "PL"
+    PT = "PT"
+    MD = "MD"
+    RO = "RO"
+    RU = "RU"
+    SE_1 = "SE_1"
+    SE_2 = "SE_2"
+    SE_3 = "SE_3"
+    SE_4 = "SE_4"
+    RS = "RS"
+    SK = "SK"
+    SI = "SI"
+    GB_NIR = "GB_NIR"
+    ES = "ES"
+    SE = "SE"
+    CH = "CH"
+    DE_TENNET = "DE_TENNET"
+    DE_TRANSNET = "DE_TRANSNET"
+    TR = "TR"
+    UA = "UA"
+    UA_DOBTPP = "UA_DOBTPP"
+    UA_BEI = "UA_BEI"
+    UA_IPS = "UA_IPS"
+    XK = "XK"
+    DE_AMP_LU = "DE_AMP_LU"
+
+
+class ModelType(Enum):
+    XGB = "xgb"
+    XGB_QUANTILE = "xgb_quantile"
+    XGB_MULTIOUTPUT_QUANTILE = "xgb_multioutput_quantile"
+    LGB = "lgb"
+    LINEAR = "linear"
+    LINEAR_QUANTILE = "linear_quantile"
+    ARIMA = "arima"
+    FLATLINER = "flatliner"
+
+
+class ForecastType(Enum):
+    DEMAND = "demand"
+    WIND = "wind"
+    SOLAR = "solar"
+    BASECASE = "basecase"
+
+
+class PipelineType(Enum):
+    FORECAST = "forecast"
+    TRAIN = "train"
+    HYPER_PARMATERS = "hyper_parameters"

{openstef-3.4.42 → openstef-3.4.43}/openstef/feature_engineering/apply_features.py

@@ -14,10 +14,14 @@ Examples of features that are added:
 import pandas as pd
 
 from openstef.data_classes.prediction_job import PredictionJobDataClass
+from openstef.enums import BiddingZone
 from openstef.feature_engineering.holiday_features import (
     generate_holiday_feature_functions,
 )
 from openstef.feature_engineering.lag_features import generate_lag_feature_functions
+from openstef.feature_engineering.bidding_zone_to_country_mapping import (
+    BIDDING_ZONE_TO_COUNTRY_CODE_MAPPING,
+)
 from openstef.feature_engineering.weather_features import (
     add_additional_solar_features,
     add_additional_wind_features,
@@ -58,6 +62,7 @@ def apply_features(
 
         import pandas as pd
         import numpy as np
+        from geopy.geocoders import Nominatim
         index = pd.date_range(start = "2017-01-01 09:00:00",
         freq = '15T', periods = 200)
         data = pd.DataFrame(index = index,
@@ -66,6 +71,9 @@ def apply_features(
                             np.random.uniform(0.7,1.7, 200)))
 
     """
+    if pj is None:
+        pj = {"electricity_bidding_zone": BiddingZone.NL}
+
     # Get lag feature functions
     feature_functions = generate_lag_feature_functions(feature_names, horizon)
 
@@ -80,8 +88,14 @@ def apply_features(
         }
     )
 
+    # Get country code from bidding zone if available
+    electricity_bidding_zone = pj.get("electricity_bidding_zone", BiddingZone.NL)
+    country_code = BIDDING_ZONE_TO_COUNTRY_CODE_MAPPING[electricity_bidding_zone.name]
+
     # Get holiday feature functions
-    feature_functions.update(generate_holiday_feature_functions())
+    feature_functions.update(
+        generate_holiday_feature_functions(country_code=country_code)
+    )
 
     # Add the features to the dataframe using previously defined feature functions
     for key, featfunc in feature_functions.items():

openstef-3.4.43/openstef/feature_engineering/bidding_zone_to_country_mapping.py

@@ -0,0 +1,106 @@
+# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
+#
+# SPDX-License-Identifier: MPL-2.0
+BIDDING_ZONE_TO_COUNTRY_CODE_MAPPING = {
+    "DE_50HZ": "DE",
+    "AL": "AL",
+    "DE_AMPRION": "DE",
+    "AT": "AT",
+    "BY": "BY",
+    "BE": "BE",
+    "BA": "BA",
+    "BG": "BG",
+    "CZ_DE_SK": "CZ",
+    "HR": "HR",
+    "CWE": "CWE",
+    "CY": "CY",
+    "CZ": "CZ",
+    "DE_AT_LU": "DE",
+    "DE_LU": "DE",
+    "DK": "DK",
+    "DK_1": "DK",
+    "DK_1_NO_1": "DK",
+    "DK_2": "DK",
+    "DK_CA": "DK",
+    "EE": "EE",
+    "FI": "FI",
+    "MK": "MK",
+    "FR": "FR",
+    "DE": "DE",
+    "GR": "GR",
+    "HU": "HU",
+    "IS": "IS",
+    "IE_SEM": "IE",
+    "IE": "IE",
+    "IT": "IT",
+    "IT_SACO_AC": "IT",
+    "IT_CALA": "IT",
+    "IT_SACO_DC": "IT",
+    "IT_BRNN": "IT",
+    "IT_CNOR": "IT",
+    "IT_CSUD": "IT",
+    "IT_FOGN": "IT",
+    "IT_GR": "IT",
+    "IT_MACRO_NORTH": "IT",
+    "IT_MACRO_SOUTH": "IT",
+    "IT_MALTA": "IT",
+    "IT_NORD": "IT",
+    "IT_NORD_AT": "IT",
+    "IT_NORD_CH": "IT",
+    "IT_NORD_FR": "IT",
+    "IT_NORD_SI": "IT",
+    "IT_PRGP": "IT",
+    "IT_ROSN": "IT",
+    "IT_SARD": "IT",
+    "IT_SICI": "IT",
+    "IT_SUD": "IT",
+    "RU_KGD": "RU",
+    "LV": "LV",
+    "LT": "LT",
+    "LU": "LU",
+    "LU_BZN": "LU",
+    "MT": "MT",
+    "ME": "ME",
+    "GB": "GB",
+    "GE": "GE",
+    "GB_IFA": "GB",
+    "GB_IFA2": "GB",
+    "GB_ELECLINK": "GB",
+    "UK": "UK",
+    "NL": "NL",
+    "NO_1": "NO",
+    "NO_1A": "NO",
+    "NO_2": "NO",
+    "NO_2_NSL": "NO",
+    "NO_2A": "NO",
+    "NO_3": "NO",
+    "NO_4": "NO",
+    "NO_5": "NO",
+    "NO": "NO",
+    "PL_CZ": "PL",
+    "PL": "PL",
+    "PT": "PT",
+    "MD": "MD",
+    "RO": "RO",
+    "RU": "RU",
+    "SE_1": "SE",
+    "SE_2": "SE",
+    "SE_3": "SE",
+    "SE_4": "SE",
+    "RS": "RS",
+    "SK": "SK",
+    "SI": "SI",
+    "GB_NIR": "GB",
+    "ES": "ES",
+    "SE": "SE",
+    "CH": "CH",
+    "DE_TENNET": "DE",
+    "DE_TRANSNET": "DE",
+    "TR": "TR",
+    "UA": "UA",
+    "UA_DOBTPP": "UA",
+    "UA_BEI": "UA",
+    "UA_IPS": "UA",
+    "XK": "XK",
+    "DE_AMP_LU": "DE",
+}

{openstef-3.4.42 → openstef-3.4.43}/openstef/feature_engineering/holiday_features.py

@@ -14,7 +14,7 @@ HOLIDAY_CSV_PATH: str = PROJECT_ROOT / "openstef" / "data" / "dutch_holidays.csv
 
 
 def generate_holiday_feature_functions(
-    country: str = "NL",
+    country_code: str = "NL",
     years: list = None,
     path_to_school_holidays_csv: str = HOLIDAY_CSV_PATH,
 ) -> dict:
@@ -69,7 +69,7 @@ def generate_holiday_feature_functions(
             now.year + 1,
         ]
 
-    country_holidays = holidays.country_holidays(country, years=years)
+    country_holidays = holidays.country_holidays(country_code, years=years)
 
     # Make holiday function dict
     holiday_functions = {}
@@ -96,7 +96,7 @@ def generate_holiday_feature_functions(
 
         # Check for bridge day
         holiday_functions, bridge_days = check_for_bridge_day(
-            date, holiday_name, country, years, holiday_functions, bridge_days
+            date, holiday_name, country_code, years, holiday_functions, bridge_days
         )
 
     # Add feature function that includes all bridgedays
@@ -104,33 +104,42 @@ def generate_holiday_feature_functions(
         {"is_bridgeday": lambda x: np.isin(x.index.date, np.array(list(bridge_days)))}
     )
 
-    # Manully generated csv including all dutch schoolholidays for different regions
-    df_holidays = pd.read_csv(path_to_school_holidays_csv, index_col=None)
-    df_holidays["datum"] = pd.to_datetime(df_holidays.datum).apply(lambda x: x.date())
-
-    # Add check function that includes all holidays of the provided csv
-    holiday_functions.update(
-        {"is_schoolholiday": lambda x: np.isin(x.index.date, df_holidays.datum.values)}
-    )
-
-    # Loop over list of holidays names
-    for holiday_name in list(set(df_holidays.name)):
-        # Define function explicitely to mitigate 'late binding' problem
-        def make_holiday_func(holidayname=holiday_name):
-            return lambda x: np.isin(
-                x.index.date, df_holidays.datum[df_holidays.name == holidayname].values
-            )
+    # Add school holidays if country is NL
+    if country_code == "NL":
+        # Manully generated csv including all dutch schoolholidays for different regions
+        df_holidays = pd.read_csv(path_to_school_holidays_csv, index_col=None)
+        df_holidays["datum"] = pd.to_datetime(df_holidays.datum).apply(
+            lambda x: x.date()
+        )
 
-        # Create lag function for each holiday
+        # Add check function that includes all holidays of the provided csv
         holiday_functions.update(
             {
-                "is_"
-                + holiday_name.replace(" ", "_").lower(): make_holiday_func(
-                    holidayname=holiday_name
+                "is_schoolholiday": lambda x: np.isin(
+                    x.index.date, df_holidays.datum.values
                 )
             }
         )
 
+        # Loop over list of holidays names
+        for holiday_name in list(set(df_holidays.name)):
+            # Define function explicitely to mitigate 'late binding' problem
+            def make_holiday_func(holidayname=holiday_name):
+                return lambda x: np.isin(
+                    x.index.date,
+                    df_holidays.datum[df_holidays.name == holidayname].values,
+                )
+
+            # Create lag function for each holiday
+            holiday_functions.update(
+                {
+                    "is_"
+                    + holiday_name.replace(" ", "_").lower(): make_holiday_func(
+                        holidayname=holiday_name
+                    )
+                }
+            )
+
     return holiday_functions
 
 

{openstef-3.4.42 → openstef-3.4.43}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.42
+Version: 3.4.43
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.42 → openstef-3.4.43}/openstef.egg-info/SOURCES.txt

@@ -29,6 +29,7 @@ openstef/data_classes/prediction_job.py
 openstef/data_classes/split_function.py
 openstef/feature_engineering/__init__.py
 openstef/feature_engineering/apply_features.py
+openstef/feature_engineering/bidding_zone_to_country_mapping.py
 openstef/feature_engineering/data_preparation.py
 openstef/feature_engineering/feature_adder.py
 openstef/feature_engineering/feature_applicator.py

{openstef-3.4.42 → openstef-3.4.43}/setup.py

@@ -29,7 +29,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.42",
+    version="3.4.43",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),

openstef-3.4.42/openstef/enums.py

@@ -1,28 +0,0 @@
-# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
-#
-# SPDX-License-Identifier: MPL-2.0
-from enum import Enum
-
-
-class ModelType(Enum):
-    XGB = "xgb"
-    XGB_QUANTILE = "xgb_quantile"
-    XGB_MULTIOUTPUT_QUANTILE = "xgb_multioutput_quantile"
-    LGB = "lgb"
-    LINEAR = "linear"
-    LINEAR_QUANTILE = "linear_quantile"
-    ARIMA = "arima"
-    FLATLINER = "flatliner"
-
-
-class ForecastType(Enum):
-    DEMAND = "demand"
-    WIND = "wind"
-    SOLAR = "solar"
-    BASECASE = "basecase"
-
-
-class PipelineType(Enum):
-    FORECAST = "forecast"
-    TRAIN = "train"
-    HYPER_PARMATERS = "hyper_parameters"