openstef 3.3.13__tar.gz → 3.3.15__tar.gz

{openstef-3.3.13 → openstef-3.3.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.3.13
+Version: 3.3.15
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -30,7 +30,7 @@ Requires-Dist: scikit-learn~=1.3
 Requires-Dist: scipy~=1.10
 Requires-Dist: statsmodels~=0.13.5
 Requires-Dist: structlog~=23.1
-Requires-Dist: xgboost~=2.0
+Requires-Dist: xgboost~=1.7
 Provides-Extra: proloaf
 Requires-Dist: proloaf==0.2.0; extra == "proloaf"
 Requires-Dist: torch==1.10.0; extra == "proloaf"

openstef-3.3.15/openstef/preprocessing/preprocessing.py

@@ -0,0 +1,42 @@
+# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
+#
+# SPDX-License-Identifier: MPL-2.0
+
+import numpy as np
+import pandas as pd
+
+
+def replace_repeated_values_with_nan(
+    df: pd.DataFrame, threshold: int, column_name: str
+) -> pd.DataFrame:
+    """Replace sequentially repeated values with NaN.
+
+    Args:
+        df: Data with potential repeating values.
+        threshold: The minimum number of squentially repeated values needed to trigger the replacement with NaN.
+        column_name: Column name of input dataframe with repeating values.
+
+    Returns:
+        DataFrame, similar to df, with the desired values set to NaN.
+
+    """
+    data = df.copy()
+
+    # Add a boolean column to mark sequential duplicates
+    data["temp_is_duplicate"] = data[column_name].eq(data[column_name].shift(1))
+
+    # Create an unique identifier for each sequence with the same value, so we can easily remove the correct sequences
+    data["temp_repeated_group"] = (~data["temp_is_duplicate"]).cumsum()
+
+    # Create mask of sequences larger than or equal to the threshold value
+    mask = (
+        data.groupby("temp_repeated_group")[column_name].transform("count") >= threshold
+    )
+
+    # Replace the masked values with NaN
+    data.loc[mask, column_name] = np.nan
+
+    # Drop temporary columns
+    data = data.drop(["temp_is_duplicate", "temp_repeated_group"], axis=1)
+
+    return data

{openstef-3.3.13 → openstef-3.3.15}/openstef/validation/validation.py

@@ -62,7 +62,7 @@ def validate(
 
     # Drop 'false' measurements. e.g. where load appears to be constant.
     data = replace_repeated_values_with_nan(
-        data, max_length=flatliner_threshold_repetitions, column_name=data.columns[0]
+        data, threshold=flatliner_threshold_repetitions, column_name=data.columns[0]
     )
     num_repeated_values = len(data) - len(data.iloc[:, 0].dropna())
     if num_repeated_values > 0:

{openstef-3.3.13 → openstef-3.3.15}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.3.13
+Version: 3.3.15
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -30,7 +30,7 @@ Requires-Dist: scikit-learn~=1.3
 Requires-Dist: scipy~=1.10
 Requires-Dist: statsmodels~=0.13.5
 Requires-Dist: structlog~=23.1
-Requires-Dist: xgboost~=2.0
+Requires-Dist: xgboost~=1.7
 Provides-Extra: proloaf
 Requires-Dist: proloaf==0.2.0; extra == "proloaf"
 Requires-Dist: torch==1.10.0; extra == "proloaf"

{openstef-3.3.13 → openstef-3.3.15}/openstef.egg-info/requires.txt

@@ -13,7 +13,7 @@ scikit-learn~=1.3
 scipy~=1.10
 statsmodels~=0.13.5
 structlog~=23.1
-xgboost~=2.0
+xgboost~=1.7
 
 [proloaf]
 proloaf==0.2.0

{openstef-3.3.13 → openstef-3.3.15}/setup.py

@@ -29,7 +29,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.3.13",
+    version="3.3.15",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),

openstef-3.3.13/openstef/preprocessing/preprocessing.py

@@ -1,27 +0,0 @@
-# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
-#
-# SPDX-License-Identifier: MPL-2.0
-
-import numpy as np
-import pandas as pd
-
-
-def replace_repeated_values_with_nan(
-    df: pd.DataFrame, max_length: int, column_name: str
-) -> pd.DataFrame:
-    """Replace sequentially repeated values with NaN.
-
-    Args:
-        df: Data with potential repeating values.
-        max_length: Maximum length of sequence. Above are set to NaN.
-        column_name: Column name of input dataframe with repeating values.
-
-    Returns:
-        DataFrame, similar to df, with the desired values set to NaN.
-
-    """
-    data = df.copy(deep=True)
-    sequentials = data[column_name].diff().ne(0).cumsum()
-    grouped_sequentials_over_max = sequentials.groupby(sequentials).head(max_length)
-    data.loc[~data.index.isin(grouped_sequentials_over_max.index), column_name] = np.nan
-    return data