openstef 3.4.44__py3-none-any.whl → 3.4.46__py3-none-any.whl

openstef/data/NL_terrestrial_radiation.csv.license

@@ -0,0 +1,3 @@
+SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com>
+
+SPDX-License-Identifier: MPL-2.0

openstef/data_classes/prediction_job.py

@@ -79,6 +79,9 @@ class PredictionJobDataClass(BaseModel):
     """Minimum length (in rows) of the forecast input for making a regular forecast."""
     flatliner_threshold_minutes: int = 1440
     """Number of minutes that the load has to be constant to detect a flatliner. """
+    data_balancing_ratio: Optional[float] = None
+    """If data balancing is enabled, the data will be balanced with data from 1 year 
+    ago in the future."""
     depends_on: Optional[list[Union[int, str]]]
     """Link to another prediction job on which this prediction job might depend."""
     sid: Optional[str]

openstef/feature_engineering/apply_features.py

@@ -31,6 +31,7 @@ from openstef.feature_engineering.weather_features import (
 from openstef.feature_engineering.cyclic_features import (
     add_seasonal_cyclic_features,
     add_time_cyclic_features,
+    add_daylight_terrestrial_feature,
 )
 
 
@@ -124,5 +125,8 @@ def apply_features(
     # Adds polar time features (sine and cosine) to capture periodic patterns based on the timestamp index.
     data = add_time_cyclic_features(data)
 
+    # Adds daylight terrestrial feature
+    data = add_daylight_terrestrial_feature(data)
+
     # Return dataframe including all requested features
     return data

openstef/feature_engineering/cyclic_features.py

@@ -13,6 +13,8 @@ import structlog
 import logging
 
 from openstef.settings import Settings
+from openstef import PROJECT_ROOT
+
 
 structlog.configure(
     wrapper_class=structlog.make_filtering_bound_logger(
@@ -21,10 +23,65 @@ structlog.configure(
 )
 logger = structlog.get_logger(__name__)
 
-
+TERRESTRIAL_RADIATION_CSV_PATH: str = (
+    PROJECT_ROOT / "openstef" / "data" / "NL_terrestrial_radiation.csv"
+)
 NUM_SECONDS_IN_A_DAY = 24 * 60 * 60
 
 
+def add_daylight_terrestrial_feature(
+    data: pd.DataFrame,
+    path_to_terrestrial_radiation_csv: str = TERRESTRIAL_RADIATION_CSV_PATH,
+) -> pd.DataFrame:
+    """Add daylight terrestrial radiation feature to the input dataset. This function processes terrestrial radiation
+    data and aligns it with the time indices of the input dataset. The terrestrial radiation data is normalized,
+    interpolated, and merged with the main dataset to provide a feature representing terrestrial radiation.
+
+    Args:
+        data (pd.DataFrame):
+            The input dataset containing a time-indexed DataFrame.
+        path_to_terrestrial_radiation_csv (str):
+            File path to the CSV file containing terrestrial radiation data. The CSV file
+            should have a time-based index.
+
+    Returns:
+        pd.DataFrame:
+            The input dataset with an added column for the terrestrial radiation feature.
+
+    Notes:
+        - The function assumes the input data and the terrestrial radiation data share
+          the same time zone and frequency alignment.
+        - The terrestrial radiation values are normalized using z-score normalization.
+
+    """
+    # Load the terrestrial radiation data
+    terrestrial_radiation = pd.read_csv(path_to_terrestrial_radiation_csv, index_col=0)
+    terrestrial_radiation.index = pd.to_datetime(terrestrial_radiation.index)
+
+    # Align the index with the input data's year
+    year_diff = data.index.min().year - terrestrial_radiation.index.min().year
+    terrestrial_radiation.index += pd.DateOffset(years=year_diff)
+
+    # Resample to 15-minute intervals, and interpolate missing values
+    terrestrial_radiation = terrestrial_radiation.resample("15min").mean().interpolate()
+
+    # Normalize the terrestrial radiation values using z-score normalization
+    terrestrial_radiation = (
+        terrestrial_radiation - terrestrial_radiation.mean(axis=0)
+    ) / terrestrial_radiation.std(axis=0)
+    terrestrial_radiation.columns = ["daylight_continuous"]
+
+    # Make a copy of the DataFrame to avoid modifying the original
+    data = data.copy()
+
+    # Merge the terrestrial radiation data with the input dataset
+    data = data.merge(
+        terrestrial_radiation, left_index=True, right_index=True, how="left"
+    )
+
+    return data
+
+
 def add_time_cyclic_features(
     data: pd.DataFrame,
 ) -> pd.DataFrame:
@@ -35,6 +92,7 @@ def add_time_cyclic_features(
 
     Returns:
         DataFrame that is the same as input dataframe with extra columns for the added time of the day features.
+
     """
     # Ensure the index is a DatetimeIndex
     if not isinstance(data.index, pd.DatetimeIndex):
@@ -71,6 +129,7 @@ def add_seasonal_cyclic_features(
     >>> data = pd.DataFrame(index=pd.date_range(start='2023-01-01', periods=365, freq='D'))
     >>> data_with_features = add_cyclical_features(data)
     >>> print(data_with_features.head())
+
     """
     # Ensure the index is a DatetimeIndex
     if not isinstance(data.index, pd.DatetimeIndex):

openstef/tasks/train_model.py

@@ -22,6 +22,8 @@ Example:
 from datetime import datetime, timedelta
 from pathlib import Path
 
+import pandas as pd
+
 from openstef.data_classes.prediction_job import PredictionJobDataClass
 from openstef.enums import ModelType, PipelineType
 from openstef.exceptions import (
@@ -114,10 +116,16 @@ def train_model_task(
         return
 
     # Define start and end of the training input data
+    training_period_days_to_fetch = (
+        TRAINING_PERIOD_DAYS
+        if pj.data_balancing_ratio is None
+        else int(pj.data_balancing_ratio * TRAINING_PERIOD_DAYS)
+    )
+
     if datetime_end is None:
         datetime_end = datetime.utcnow()
     if datetime_start is None:
-        datetime_start = datetime_end - timedelta(days=TRAINING_PERIOD_DAYS)
+        datetime_start = datetime_end - timedelta(days=training_period_days_to_fetch)
 
     # Get training input data from database
     input_data = context.database.get_model_input(
@@ -127,6 +135,29 @@ def train_model_task(
         datetime_end=datetime_end,
     )
 
+    # If data balancing is enabled, fetch data from 1 year ago and combine it with the
+    # current data
+    if pj.data_balancing_ratio is not None:
+        # Because the data is from the past, we can use the data from the "future"
+        balanced_datetime_start = datetime_end - timedelta(days=365)
+        balanced_datetime_end = balanced_datetime_start + timedelta(
+            days=training_period_days_to_fetch
+        )
+
+        balanced_input_data = context.database.get_model_input(
+            pid=pj["id"],
+            location=[pj["lat"], pj["lon"]],
+            datetime_start=balanced_datetime_start,
+            datetime_end=balanced_datetime_end,
+        )
+
+        input_data = pd.concat(
+            [
+                balanced_input_data,
+                input_data,
+            ]
+        )
+
     context.perf_meter.checkpoint("Retrieved timeseries input")
 
     # Excecute the model training pipeline

{openstef-3.4.44.dist-info → openstef-3.4.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.44
+Version: 3.4.46
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.44.dist-info → openstef-3.4.46.dist-info}/RECORD

@@ -4,6 +4,8 @@ openstef/app_settings.py,sha256=EJTDtimctFQQ-3f7ZcOQaRYohpZk3JD6aZBWPFYM2_A,582
 openstef/enums.py,sha256=Wmoag2p7G2cvENA1qt8FcVbAgo-MswXKxmq7vkxHaxs,2680
 openstef/exceptions.py,sha256=U4u2LTcdT6cmzpipT2Jh7kq9nCjT_-6gntn8yjuhGU0,1993
 openstef/settings.py,sha256=nSgkBqFxuqB3w7Rwo60i8j37c5ngDbt6vpjHS6QtJXQ,354
+openstef/data/NL_terrestrial_radiation.csv,sha256=A4kbW56GDzWi4tWUwY2C-4PiOvcKJCwkWQQtdg4ekPE,820246
+openstef/data/NL_terrestrial_radiation.csv.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
 openstef/data/dutch_holidays.csv,sha256=Cg8EYjXp1O0lcFOkIOmrS5HaOArrxZwOXsZ9pVkIcKI,49847
 openstef/data/dutch_holidays.csv.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
 openstef/data/pv_single_coefs.csv,sha256=jadIEYdHvl1lnV_06X_FASkJZ6C3Hecs5xZnH1gPMvI,24779
@@ -15,12 +17,12 @@ openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_model_card.md.license,sha25
 openstef/data_classes/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/data_classes/data_prep.py,sha256=gRSL7UiHvZis8m8z7VoTCZc0Ccffhef5_hmSyApnqK0,3417
 openstef/data_classes/model_specifications.py,sha256=Uod1W3QzhRqVLb6zvXwxh9wRL3EHCzSvX0oDNd28cFk,1197
-openstef/data_classes/prediction_job.py,sha256=oVgk6rTC8IYYIGpEuaZHPi01l7gomQQ--BHlixj0Eb0,5496
+openstef/data_classes/prediction_job.py,sha256=_o5_9HYv6ERTIWlcMpUE-mWwe7dRpaiP83dgNpqpa5Y,5657
 openstef/data_classes/split_function.py,sha256=ljQIQQu1t1Y_CVWGAy25jrM6wG9odIVVQVimrT1n-1s,3358
 openstef/feature_engineering/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
-openstef/feature_engineering/apply_features.py,sha256=9scyEpUZcSWQrhMXV4c7iT1KvmHDk1J_KSZ_qI63lfY,4866
+openstef/feature_engineering/apply_features.py,sha256=S9HSsooDPcSSyEw9kixEhjjk3MAkAfyK1VhZKg5R0gA,4995
 openstef/feature_engineering/bidding_zone_to_country_mapping.py,sha256=u9aabjFDImydkO6_cXiaQxBT4gb5zy0gGTg2EoIUO_Y,2106
-openstef/feature_engineering/cyclic_features.py,sha256=gmU49D40yR9-Fh9ajiv3SyIWVLQcnibvQ4fFnpvAOj4,3527
+openstef/feature_engineering/cyclic_features.py,sha256=0Z3wZeF_qrkmEcOq91gtdSMZucAq99kUoBuFDV0SHqk,5962
 openstef/feature_engineering/data_preparation.py,sha256=htca9LBO3ZN1D-iX4vXf0UN1fw_rRO7y6N3AuYVMpfk,5628
 openstef/feature_engineering/feature_adder.py,sha256=aSqDl_gUrB3H2TD3cNvU5JniY_KOb4u4a2A6J7zB2BQ,6835
 openstef/feature_engineering/feature_applicator.py,sha256=DR7jayrEMlra4BFL1Ps5WV2fxbkQ6VaOTa5RIKM-YNk,7447
@@ -83,15 +85,15 @@ openstef/tasks/create_solar_forecast.py,sha256=cZiIoCVHlLlDrsWeH3ZX4zfcMMrgGgqkG
 openstef/tasks/create_wind_forecast.py,sha256=RhshkmNSyFWx4Y6yQn02GzHjWTREbN5A5GAeWv0JpcE,2907
 openstef/tasks/optimize_hyperparameters.py,sha256=meiOn5S4yBrk5ANCFwcBCfTZIhm-b1rdh9TFh7KFr3E,4754
 openstef/tasks/split_forecast.py,sha256=AF_AwFcD6BqOrfvNLhIm_8gb7SpyKxEx60mymoxohPg,9323
-openstef/tasks/train_model.py,sha256=x1YlLC71l_9AD1r_IwvzKVA4ZTnMv6VMfKYvrPp6gpU,7471
+openstef/tasks/train_model.py,sha256=o8QVPReJ71BZVCOL6Rs3PFD9Zg4LT16dPcbf87xnXpA,8494
 openstef/tasks/utils/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/tasks/utils/dependencies.py,sha256=Jy9dtV_G7lTEa5Cdy--wvMxJuAb0adb3R0X4QDjVteM,3077
 openstef/tasks/utils/predictionjobloop.py,sha256=Ysy3zF5lzPMz_asYDKeF5m0qgVT3tCtwSPihqMjnI5Q,9580
 openstef/tasks/utils/taskcontext.py,sha256=L9K14ycwgVxbIVUjH2DIn_QWbnu-OfxcGtQ1K9T6sus,5630
 openstef/validation/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/validation/validation.py,sha256=HVgreHvcZvPazfwC3NNE8_3lsMsZEd_42osCAg1_6W4,11128
-openstef-3.4.44.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
-openstef-3.4.44.dist-info/METADATA,sha256=7Vc97wXZdf6BQiksF8TuMg3hpRVw6HY2xZ7mJT2JGoM,8068
-openstef-3.4.44.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-openstef-3.4.44.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
-openstef-3.4.44.dist-info/RECORD,,
+openstef-3.4.46.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
+openstef-3.4.46.dist-info/METADATA,sha256=UJAm_jF1JSm4lcXL2tPkwR7XBaEleozpBF6iJnI8D4U,8068
+openstef-3.4.46.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+openstef-3.4.46.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
+openstef-3.4.46.dist-info/RECORD,,