openstef 3.4.43__py3-none-any.whl → 3.4.45__py3-none-any.whl

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

@@ -28,6 +28,11 @@ from openstef.feature_engineering.weather_features import (
     add_humidity_features,
 )
 
+from openstef.feature_engineering.cyclic_features import (
+    add_seasonal_cyclic_features,
+    add_time_cyclic_features,
+)
+
 
 def apply_features(
     data: pd.DataFrame,
@@ -113,5 +118,11 @@ def apply_features(
     # Add solar features; when pj is unavailable a default location is used.
     data = add_additional_solar_features(data, pj, feature_names)
 
+    # Adds cyclical features to capture seasonal and periodic patterns in time-based data.
+    data = add_seasonal_cyclic_features(data)
+
+    # Adds polar time features (sine and cosine) to capture periodic patterns based on the timestamp index.
+    data = add_time_cyclic_features(data)
+
     # Return dataframe including all requested features
     return data

openstef/feature_engineering/cyclic_features.py

@@ -0,0 +1,102 @@
+# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
+#
+# SPDX-License-Identifier: MPL-2.0
+
+# Module for adding temporal cyclic features to time-based data for capturing seasonality and periodic patterns.
+# Features include yearly, weekly, and monthly seasonality, as well as time-of-day periodicity.
+
+
+import numpy as np
+import pandas as pd
+
+import structlog
+import logging
+
+from openstef.settings import Settings
+
+structlog.configure(
+    wrapper_class=structlog.make_filtering_bound_logger(
+        logging.getLevelName(Settings.log_level)
+    )
+)
+logger = structlog.get_logger(__name__)
+
+
+NUM_SECONDS_IN_A_DAY = 24 * 60 * 60
+
+
+def add_time_cyclic_features(
+    data: pd.DataFrame,
+) -> pd.DataFrame:
+    """Adds time of the day features cyclically encoded using sine and cosine to the input data.
+
+    Args:
+        data: Dataframe indexed by datetime.
+
+    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):
+        raise ValueError("Index should be a pandas DatetimeIndex")
+
+    # Make a copy of the DataFrame to avoid modifying the original
+    data = data.copy()
+
+    second_of_the_day = (
+        data.index.second + data.index.minute * 60 + data.index.hour * 60 * 60
+    )
+    period_of_the_day = 2 * np.pi * second_of_the_day / NUM_SECONDS_IN_A_DAY
+
+    data["time0fday_sine"] = np.sin(period_of_the_day)
+    data["time0fday_cosine"] = np.cos(period_of_the_day)
+
+    return data
+
+
+def add_seasonal_cyclic_features(
+    data: pd.DataFrame, compute_features: list = None
+) -> pd.DataFrame:
+    """Adds cyclical features to capture seasonal and periodic patterns in time-based data.
+
+    Args:
+    - data (pd.DataFrame): DataFrame with a DatetimeIndex.
+    - compute_features (list): Optional. List of features to compute. Options are:
+      ['season', 'dayofweek', 'month']. Default is all features.
+
+    Returns:
+    - pd.DataFrame: DataFrame with added cyclical features.
+
+    Example:
+    >>> 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):
+        raise ValueError("The DataFrame index must be a DatetimeIndex.")
+
+    # Make a copy of the DataFrame to avoid modifying the original
+    data = data.copy()
+
+    # Default to all features if none specified
+    compute_features = compute_features or ["season", "dayofweek", "month"]
+
+    days_in_year = 365.25  # Account for leap years
+
+    # Add seasonality features (day of year)
+    if "season" in compute_features:
+        data["season_sine"] = np.sin(2 * np.pi * data.index.dayofyear / days_in_year)
+        data["season_cosine"] = np.cos(2 * np.pi * data.index.dayofyear / days_in_year)
+
+    # Add weekly features (day of the week)
+    if "dayofweek" in compute_features:
+        data["day0fweek_sine"] = np.sin(2 * np.pi * data.index.day_of_week / 7)
+        data["day0fweek_cosine"] = np.cos(2 * np.pi * data.index.day_of_week / 7)
+
+    # Add monthly features (month of the year)
+    if "month" in compute_features:
+        data["month_sine"] = np.sin(2 * np.pi * data.index.month / 12)
+        data["month_cosine"] = np.cos(2 * np.pi * data.index.month / 12)
+
+    return data

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-3.4.43.dist-info → openstef-3.4.45.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.43
+Version: 3.4.45
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.43.dist-info → openstef-3.4.45.dist-info}/RECORD

@@ -15,11 +15,12 @@ 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=AgIFnfud55vj0UUWJYwrMTjUzFCBxpV5ACaUK21-ZUo,4451
+openstef/feature_engineering/apply_features.py,sha256=9scyEpUZcSWQrhMXV4c7iT1KvmHDk1J_KSZ_qI63lfY,4866
 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/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
@@ -82,15 +83,15 @@ 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-3.4.43.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
-openstef-3.4.43.dist-info/METADATA,sha256=L2J9ATvIMBE06--ITAksEWnqGYNZr5T-oODgLroNZFw,8068
-openstef-3.4.43.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-openstef-3.4.43.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
-openstef-3.4.43.dist-info/RECORD,,
+openstef-3.4.45.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
+openstef-3.4.45.dist-info/METADATA,sha256=nszNfTz9kFGVZyiXyRL18H4_6WtSIlZDvLuAAleM5wM,8068
+openstef-3.4.45.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+openstef-3.4.45.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
+openstef-3.4.45.dist-info/RECORD,,