wavetrainer 0.0.31__tar.gz → 0.0.33__tar.gz

{wavetrainer-0.0.31/wavetrainer.egg-info → wavetrainer-0.0.33}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.31
+Version: 0.0.33
 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-0.0.31 → wavetrainer-0.0.33}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.31',
+    version='0.0.33',
     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-0.0.31 → wavetrainer-0.0.33}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.31"
+__VERSION__ = "0.0.33"
 __all__ = ("create",)

{wavetrainer-0.0.31 → wavetrainer-0.0.33}/wavetrainer/model/catboost_model.py

@@ -162,6 +162,7 @@ class CatboostModel(Model):
             raise ValueError("y is null.")
         self._model_type = determine_model_type(y)
         catboost = self._provide_catboost()
+        logging.info("Fitting catboost model with depth %d", self._depth)
 
         train_pool = Pool(
             df,

{wavetrainer-0.0.31 → wavetrainer-0.0.33}/wavetrainer/reducer/combined_reducer.py

@@ -18,6 +18,7 @@ from .unseen_reducer import UnseenReducer
 
 _COMBINED_REDUCER_FILE = "combined_reducer.json"
 _REDUCERS_KEY = "reducers"
+_REMOVED_COLUMNS_FILE = "combined_reducer_removed_columns.json"
 
 
 class CombinedReducer(Reducer):
@@ -35,6 +36,7 @@ class CombinedReducer(Reducer):
             CorrelationReducer(),
             SmartCorrelationReducer(),
         ]
+        self._folder = None
 
     @classmethod
     def name(cls) -> str:
@@ -67,6 +69,7 @@ class CombinedReducer(Reducer):
                     self._reducers.append(SmartCorrelationReducer())
         for reducer in self._reducers:
             reducer.load(folder)
+        self._folder = folder
 
     def save(self, folder: str, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
         with open(
@@ -89,17 +92,19 @@ class CombinedReducer(Reducer):
         eval_x: pd.DataFrame | None = None,
         eval_y: pd.Series | pd.DataFrame | None = None,
     ) -> Self:
+        removed_columns_dict = {}
         for reducer in self._reducers:
             before_columns = set(df.columns.values)
             df = reducer.fit_transform(df)
             after_columns = set(df.columns.values)
             removed_columns = before_columns.difference(after_columns)
             if removed_columns:
-                logging.info(
-                    "Removed columns %s using %s",
-                    ",".join(removed_columns),
-                    reducer.name(),
-                )
+                removed_columns_dict[reducer.name()] = list(removed_columns)
+        if self._folder is not None:
+            with open(
+                os.path.join(self._folder, _REMOVED_COLUMNS_FILE), encoding="utf8"
+            ) as handle:
+                json.dump(removed_columns_dict, handle)
         return self
 
     def transform(self, df: pd.DataFrame) -> pd.DataFrame:

{wavetrainer-0.0.31 → wavetrainer-0.0.33}/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-0.0.33/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-0.0.31 → wavetrainer-0.0.33}/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-0.0.31 → wavetrainer-0.0.33}/wavetrainer/trainer.py

@@ -37,7 +37,7 @@ _TEST_SIZE_KEY = "test_size"
 _VALIDATION_SIZE_KEY = "validation_size"
 _IDX_USR_ATTR_KEY = "idx"
 _DT_COLUMN_KEY = "dt_column"
-_BAD_OUTPUT = -1.0
+_BAD_OUTPUT = -1000.0
 
 
 def _assign_bin(timestamp, bins: list[datetime.datetime]) -> int:
@@ -345,7 +345,10 @@ class Trainer(Fit):
                     if self._max_train_timeout is None
                     else self._max_train_timeout.total_seconds(),
                 )
-            while study.best_trial.value is None or study.best_trial.value != _BAD_OUTPUT:
+            while (
+                study.best_trial.value is None or study.best_trial.value == _BAD_OUTPUT
+            ):
+                logging.info("Performing extra train")
                 study.optimize(
                     test_objective,
                     n_trials=1,
@@ -387,7 +390,7 @@ class Trainer(Fit):
 
                 test_df = df.iloc[: train_len + count + test_len]
                 test_series = y_series.iloc[: train_len + count + test_len]
-                if len(test_df) <= 2:
+                if len(test_df) <= 3:
                     continue
 
                 if test_idx < start_validation_index:

{wavetrainer-0.0.31 → wavetrainer-0.0.33/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.31
+Version: 0.0.33
 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-0.0.31 → wavetrainer-0.0.33}/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