openstef 3.4.44__tar.gz → 3.4.45__tar.gz

{openstef-3.4.44 → openstef-3.4.45}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.44
+Version: 3.4.45
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.44 → openstef-3.4.45}/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-3.4.44 → openstef-3.4.45}/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 → openstef-3.4.45}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.44
+Version: 3.4.45
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.44 → openstef-3.4.45}/setup.py

@@ -29,7 +29,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.44",
+    version="3.4.45",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),