wavetrainer 0.0.32__tar.gz → 0.0.34__tar.gz

{wavetrainer-0.0.32/wavetrainer.egg-info → wavetrainer-0.0.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.32
+Version: 0.0.34
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield

{wavetrainer-0.0.32 → wavetrainer-0.0.34}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.32',
+    version='0.0.34',
     description='A library for automatically finding the optimal model within feature and hyperparameter space.',
     long_description=long_description,
     long_description_content_type='text/markdown',

{wavetrainer-0.0.32 → wavetrainer-0.0.34}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.32"
+__VERSION__ = "0.0.34"
 __all__ = ("create",)

{wavetrainer-0.0.32 → wavetrainer-0.0.34}/wavetrainer/model/catboost_model.py

@@ -216,6 +216,7 @@ class CatboostModel(Model):
             iterations = (
                 best_iteration if best_iteration is not None else self._iterations
             )
+            logging.info("Creating catboost model with depth %d", self._depth)
             match self._model_type:
                 case ModelType.BINARY:
                     catboost = CatBoostClassifierWrapper(

{wavetrainer-0.0.32 → wavetrainer-0.0.34}/wavetrainer/reducer/correlation_reducer.py

@@ -1,10 +1,15 @@
 """A reducer that removes correlation features."""
 
+# pylint: disable=too-many-arguments,too-many-positional-arguments
+from typing import Self
+
 import optuna
 import pandas as pd
 from feature_engine.selection import DropCorrelatedFeatures
 
 from .base_selector_reducer import BaseSelectorReducer
+from .non_categorical_numeric_columns import \
+    find_non_categorical_numeric_columns
 
 _CORRELATION_REDUCER_FILENAME = "correlation_reducer.joblib"
 _CORRELATION_REDUCER_THRESHOLD = "correlation_reducer_threshold"
@@ -34,3 +39,14 @@ class CorrelationReducer(BaseSelectorReducer):
         self._correlation_selector.threshold = trial.suggest_float(
             _CORRELATION_REDUCER_THRESHOLD, 0.1, 0.9
         )
+
+    def fit(
+        self,
+        df: pd.DataFrame,
+        y: pd.Series | pd.DataFrame | None = None,
+        w: pd.Series | None = None,
+        eval_x: pd.DataFrame | None = None,
+        eval_y: pd.Series | pd.DataFrame | None = None,
+    ) -> Self:
+        self._correlation_selector.variables = find_non_categorical_numeric_columns(df)
+        return super().fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y)

wavetrainer-0.0.34/wavetrainer/reducer/non_categorical_numeric_columns.py

@@ -0,0 +1,19 @@
+"""A helper function for retrieving numeric columns without categoricals."""
+
+import numpy as np
+import pandas as pd
+
+
+def find_non_categorical_numeric_columns(df: pd.DataFrame) -> list[str]:
+    """
+    Finds numeric columns in a Pandas DataFrame that are not categorical.
+
+    Args:
+        df (pd.DataFrame): The input DataFrame.
+
+    Returns:
+        list: A list of column names that are numeric and not categorical.
+    """
+    numeric_cols = set(df.select_dtypes(include=np.number).columns.tolist())
+    categorical_cols = set(df.select_dtypes(include="category").columns.tolist())
+    return list(numeric_cols.difference(categorical_cols))

{wavetrainer-0.0.32 → wavetrainer-0.0.34}/wavetrainer/reducer/smart_correlation_reducer.py

@@ -1,10 +1,15 @@
 """A reducer that removes correlation features via further heuristics."""
 
+# pylint: disable=too-many-arguments,too-many-positional-arguments
+from typing import Self
+
 import optuna
 import pandas as pd
 from feature_engine.selection import SmartCorrelatedSelection
 
 from .base_selector_reducer import BaseSelectorReducer
+from .non_categorical_numeric_columns import \
+    find_non_categorical_numeric_columns
 
 _SMART_CORRELATION_REDUCER_FILENAME = "smart_correlation_reducer.joblib"
 _SMART_CORRELATION_REDUCER_THRESHOLD = "smart_correlation_reducer_threshold"
@@ -30,3 +35,14 @@ class SmartCorrelationReducer(BaseSelectorReducer):
         self._correlation_selector.threshold = trial.suggest_float(
             _SMART_CORRELATION_REDUCER_THRESHOLD, 0.1, 0.9
         )
+
+    def fit(
+        self,
+        df: pd.DataFrame,
+        y: pd.Series | pd.DataFrame | None = None,
+        w: pd.Series | None = None,
+        eval_x: pd.DataFrame | None = None,
+        eval_y: pd.Series | pd.DataFrame | None = None,
+    ) -> Self:
+        self._correlation_selector.variables = find_non_categorical_numeric_columns(df)
+        return super().fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y)

{wavetrainer-0.0.32 → wavetrainer-0.0.34/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.32
+Version: 0.0.34
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield

{wavetrainer-0.0.32 → wavetrainer-0.0.34}/wavetrainer.egg-info/SOURCES.txt

@@ -39,6 +39,7 @@ wavetrainer/reducer/combined_reducer.py
 wavetrainer/reducer/constant_reducer.py
 wavetrainer/reducer/correlation_reducer.py
 wavetrainer/reducer/duplicate_reducer.py
+wavetrainer/reducer/non_categorical_numeric_columns.py
 wavetrainer/reducer/nonnumeric_reducer.py
 wavetrainer/reducer/reducer.py
 wavetrainer/reducer/smart_correlation_reducer.py