wavetrainer 0.0.5__tar.gz → 0.0.7__tar.gz

{wavetrainer-0.0.5/wavetrainer.egg-info → wavetrainer-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.5
+Version: 0.0.7
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield
@@ -21,7 +21,6 @@ Requires-Dist: scipy>=1.15.2
 Requires-Dist: catboost>=1.2.7
 Requires-Dist: venn-abers>=1.4.6
 Requires-Dist: mapie>=0.9.2
-Requires-Dist: shapiq>=1.2.2
 
 # wavetrainer
 
@@ -49,7 +48,6 @@ Python 3.11.6:
 - [catboost](https://catboost.ai/)
 - [venn-abers](https://github.com/ip200/venn-abers)
 - [mapie](https://mapie.readthedocs.io/en/stable/)
-- [shapiq](https://github.com/mmschlk/shapiq)
 
 ## Raison D'être :thought_balloon:
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/README.md

@@ -24,7 +24,6 @@ Python 3.11.6:
 - [catboost](https://catboost.ai/)
 - [venn-abers](https://github.com/ip200/venn-abers)
 - [mapie](https://mapie.readthedocs.io/en/stable/)
-- [shapiq](https://github.com/mmschlk/shapiq)
 
 ## Raison D'être :thought_balloon:
 

wavetrainer-0.0.5/wavetrainer.egg-info/requires.txt → wavetrainer-0.0.7/requirements.txt

@@ -7,5 +7,4 @@ numpy>=1.26.4
 scipy>=1.15.2
 catboost>=1.2.7
 venn-abers>=1.4.6
-mapie>=0.9.2
-shapiq>=1.2.2
+mapie>=0.9.2

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.5',
+    version='0.0.7',
     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-0.0.7/tests/model/catboost_kwargs_test.py

@@ -0,0 +1,28 @@
+"""Tests for the catboost kwargs handler class."""
+import unittest
+
+import pandas as pd
+
+from wavetrainer.model.catboost_kwargs import handle_fit_kwargs
+
+
+class TestCatboostKwargs(unittest.TestCase):
+
+    def test_handle_fit_kwargs(self):
+        x_train = pd.DataFrame(data={
+            "thing": [0.0, 1.0, 2.0, 3.0, 4.0],
+        })
+        x_train["thing"] = x_train["thing"].astype('category')
+        y_train = pd.Series(data=[1.0, 2.0, 3.0, 4.0])
+        x_test = pd.DataFrame(data={
+            "thing": [0.0, 1.0, 2.0, 3.0, 4.0],
+        })
+        x_test["thing"] = x_test["thing"].astype('category')
+        y_test = pd.Series(data=[1.0, 2.0, 3.0, 4.0])
+        args, _ = handle_fit_kwargs(
+            x_train,
+            y_train,
+            eval_set=(x_test, y_test),
+            cat_features=x_train.select_dtypes(include="category").columns.tolist(),
+        )
+        assert len(args) == 2

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/tests/trainer_test.py

@@ -20,10 +20,11 @@ class TestTrainer(unittest.TestCase):
                 data={
                     "column1": x_data,
                     "column2": [(x * random.random()) + random.random() for x in x_data],
-                    "column3": [(x / random.random()) - random.random() for x in x_data],
+                    "column3": [int(((x / random.random()) - random.random()) * 1000.0) for x in x_data],
                 },
                 index=x_index,
             )
+            df["column3"] = df["column3"].astype('category')
             y = pd.DataFrame(
                 data={
                     "y": [x % 2 == 0 for x in x_data],

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.5"
+__VERSION__ = "0.0.7"
 __all__ = ("create",)

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/calibrator/calibrator_router.py

@@ -24,6 +24,8 @@ _CALIBRATORS = {
 class CalibratorRouter(Calibrator):
     """A router that routes to a different calibrator class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _calibrator: Calibrator | None
 
     def __init__(self, model: Model):
@@ -66,7 +68,10 @@ class CalibratorRouter(Calibrator):
         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:
+        # pylint: disable=no-else-return
         calibrator: Calibrator | None = None
         if determine_model_type(df) == ModelType.REGRESSION:
             calibrator = MAPIECalibrator(self._model)

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/calibrator/mapie_calibrator.py

@@ -1,11 +1,13 @@
 """A calibrator that implements MAPIE."""
 
+import logging
 import os
 from typing import Self
 
 import joblib  # type: ignore
 import optuna
 import pandas as pd
+import sklearn  # type: ignore
 from mapie.regression import MapieRegressor  # type: ignore
 
 from ..model.model import PROBABILITY_COLUMN_PREFIX, Model
@@ -17,6 +19,8 @@ _CALIBRATOR_FILENAME = "mapie.joblib"
 class MAPIECalibrator(Calibrator):
     """A class that uses MAPIE as a calibrator."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     def __init__(self, model: Model):
         super().__init__(model)
         self._mapie = MapieRegressor(model.estimator, method="plus")
@@ -39,27 +43,34 @@ class MAPIECalibrator(Calibrator):
         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:
         mapie = self._mapie
         if mapie is None:
             raise ValueError("mapie is null")
         if y is None:
             raise ValueError("y is null")
+        if len(df) <= 5:
+            return self
         mapie.fit(df.to_numpy(), y.to_numpy())
         return self
 
     def transform(self, df: pd.DataFrame) -> pd.DataFrame:
-        alpha = []
-        for potential_alpha in [0.05, 0.32]:
-            if len(df) > int(1.0 / potential_alpha):
-                alpha.append(potential_alpha)
-        if alpha:
-            _, y_pis = self._mapie.predict(df, alpha=alpha)
-            for i in range(y_pis.shape[1]):
-                if i >= len(alpha):
-                    continue
-                for ii in range(y_pis.shape[2]):
-                    alpha_val = alpha[i]
-                    values = y_pis[:, i, ii].flatten().tolist()
-                    df[f"{PROBABILITY_COLUMN_PREFIX}{alpha_val}_{ii == 1}"] = values
+        try:
+            alpha = []
+            for potential_alpha in [0.05, 0.32]:
+                if len(df) > int(1.0 / potential_alpha) + 1:
+                    alpha.append(potential_alpha)
+            if alpha:
+                _, y_pis = self._mapie.predict(df, alpha=alpha)
+                for i in range(y_pis.shape[1]):
+                    if i >= len(alpha):
+                        continue
+                    for ii in range(y_pis.shape[2]):
+                        alpha_val = alpha[i]
+                        values = y_pis[:, i, ii].flatten().tolist()
+                        df[f"{PROBABILITY_COLUMN_PREFIX}{alpha_val}_{ii == 1}"] = values
+        except sklearn.exceptions.NotFittedError as exc:  # type: ignore
+            logging.warning(str(exc))
         return df

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/calibrator/vennabers_calibrator.py

@@ -17,6 +17,8 @@ _CALIBRATOR_FILENAME = "vennabers.joblib"
 class VennabersCalibrator(Calibrator):
     """A class that uses venn abers as a calibrator."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     def __init__(self, model: Model):
         super().__init__(model)
         self._vennabers = VennAbers()
@@ -39,6 +41,8 @@ class VennabersCalibrator(Calibrator):
         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:
         vennabers = self._vennabers
         if vennabers is None:

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/fit.py

@@ -8,11 +8,15 @@ import pandas as pd
 class Fit:
     """The prototype fit class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     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:
         """Fit the dataframe."""
         raise NotImplementedError("fit not implemented in parent class.")
@@ -25,6 +29,9 @@ class 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,
     ) -> pd.DataFrame:
         """Fit and then trasnfrom the dataframe."""
-        return self.fit(df, y=y).transform(df)
+        return self.fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y).transform(df)

wavetrainer-0.0.7/wavetrainer/model/catboost_classifier_wrap.py

@@ -0,0 +1,15 @@
+"""A wrapper for catboost classifier to handle some edge cases."""
+
+# pylint: disable=duplicate-code
+
+from catboost import CatBoostClassifier  # type: ignore
+
+from .catboost_kwargs import handle_fit_kwargs
+
+
+class CatBoostClassifierWrapper(CatBoostClassifier):
+    """A wrapper for the catboost classifier."""
+
+    def fit(self, *args, **kwargs):
+        args, kwargs = handle_fit_kwargs(*args, **kwargs)
+        return super().fit(*args, **kwargs)

wavetrainer-0.0.7/wavetrainer/model/catboost_kwargs.py

@@ -0,0 +1,50 @@
+"""A list of constant catboost kwargs."""
+
+from typing import Any
+
+import numpy as np
+from catboost import Pool  # type: ignore
+
+ORIGINAL_X_ARG_KEY = "original_x"
+EVAL_SET_ARG_KEY = "eval_set"
+CAT_FEATURES_ARG_KEY = "cat_features"
+
+
+def handle_fit_kwargs(*args, **kwargs) -> tuple[tuple[Any, ...], dict[str, Any]]:
+    """Handles keyword args coming into a catboost fit method."""
+    if ORIGINAL_X_ARG_KEY in kwargs:
+        df = kwargs[ORIGINAL_X_ARG_KEY]
+        eval_x, eval_y = kwargs[EVAL_SET_ARG_KEY]
+        cat_features = kwargs[CAT_FEATURES_ARG_KEY]
+        args_list = list(args)
+        fit_x = args_list[0]
+        fix_x_cp = fit_x.copy()
+
+        # Stupid code to ensure eval is feature equivalent to train data
+        included_columns = []
+        for i in range(fix_x_cp.shape[1]):
+            arr_col_values = fix_x_cp[:, i]
+            for col in df.columns:
+                if col in included_columns:
+                    continue
+                df_col_values = df[col].values
+                if np.allclose(df_col_values, arr_col_values, equal_nan=True):
+                    included_columns.append(col)
+                    break
+        # We also need to update cat_features or catboost will yell at us
+        cat_features = list(
+            set(list(kwargs.get(CAT_FEATURES_ARG_KEY, []))) & set(included_columns)
+        )
+        args_list[0] = df[included_columns]
+        args = tuple(args_list)
+
+        eval_x = eval_x[included_columns]
+        kwargs[EVAL_SET_ARG_KEY] = Pool(
+            eval_x,
+            label=eval_y,
+            cat_features=cat_features,
+        )
+        kwargs[CAT_FEATURES_ARG_KEY] = cat_features
+
+        del kwargs[ORIGINAL_X_ARG_KEY]
+    return args, kwargs

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/model/catboost_model.py

@@ -6,10 +6,13 @@ from typing import Any, Self
 
 import optuna
 import pandas as pd
-from catboost import CatBoostClassifier  # type: ignore
-from catboost import CatBoost, CatBoostRegressor, Pool
+from catboost import CatBoost, Pool  # type: ignore
 
 from ..model_type import ModelType, determine_model_type
+from .catboost_classifier_wrap import CatBoostClassifierWrapper
+from .catboost_kwargs import (CAT_FEATURES_ARG_KEY, EVAL_SET_ARG_KEY,
+                              ORIGINAL_X_ARG_KEY)
+from .catboost_regressor_wrap import CatBoostRegressorWrapper
 from .model import PREDICTION_COLUMN, PROBABILITY_COLUMN_PREFIX, Model
 
 _MODEL_FILENAME = "model.cbm"
@@ -25,6 +28,8 @@ _MODEL_TYPE_KEY = "model_type"
 class CatboostModel(Model):
     """A class that uses Catboost as a model."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _catboost: CatBoost | None
     _iterations: None | int
     _learning_rate: None | float
@@ -51,10 +56,21 @@ class CatboostModel(Model):
     def estimator(self) -> Any:
         return self._provide_catboost()
 
-    def pre_fit(self, y: pd.Series | pd.DataFrame | None):
+    def pre_fit(
+        self,
+        df: pd.DataFrame,
+        y: pd.Series | pd.DataFrame | None,
+        eval_x: pd.DataFrame | None = None,
+        eval_y: pd.Series | pd.DataFrame | None = None,
+    ):
         if y is None:
             raise ValueError("y is null.")
         self._model_type = determine_model_type(y)
+        return {
+            EVAL_SET_ARG_KEY: (eval_x, eval_y),
+            CAT_FEATURES_ARG_KEY: df.select_dtypes(include="category").columns.tolist(),
+            ORIGINAL_X_ARG_KEY: df,
+        }
 
     def set_options(self, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
         self._iterations = trial.suggest_int(_ITERATIONS_KEY, 100, 10000)
@@ -102,6 +118,8 @@ class CatboostModel(Model):
         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:
         if y is None:
             raise ValueError("y is null.")
@@ -113,11 +131,16 @@ class CatboostModel(Model):
             label=y,
             weight=w,
         )
+        eval_pool = Pool(
+            eval_x,
+            label=eval_y,
+        )
         catboost.fit(
             train_pool,
             early_stopping_rounds=100,
             verbose=False,
             metric_period=100,
+            eval_set=eval_pool,
         )
         return self
 
@@ -142,7 +165,7 @@ class CatboostModel(Model):
         if catboost is None:
             match self._model_type:
                 case ModelType.BINARY:
-                    catboost = CatBoostClassifier(
+                    catboost = CatBoostClassifierWrapper(
                         iterations=self._iterations,
                         learning_rate=self._learning_rate,
                         depth=self._depth,
@@ -152,7 +175,7 @@ class CatboostModel(Model):
                         metric_period=100,
                     )
                 case ModelType.REGRESSION:
-                    catboost = CatBoostRegressor(
+                    catboost = CatBoostRegressorWrapper(
                         iterations=self._iterations,
                         learning_rate=self._learning_rate,
                         depth=self._depth,
@@ -162,7 +185,7 @@ class CatboostModel(Model):
                         metric_period=100,
                     )
                 case ModelType.BINNED_BINARY:
-                    catboost = CatBoostClassifier(
+                    catboost = CatBoostClassifierWrapper(
                         iterations=self._iterations,
                         learning_rate=self._learning_rate,
                         depth=self._depth,
@@ -172,7 +195,7 @@ class CatboostModel(Model):
                         metric_period=100,
                     )
                 case ModelType.MULTI_CLASSIFICATION:
-                    catboost = CatBoostClassifier(
+                    catboost = CatBoostClassifierWrapper(
                         iterations=self._iterations,
                         learning_rate=self._learning_rate,
                         depth=self._depth,

wavetrainer-0.0.7/wavetrainer/model/catboost_regressor_wrap.py

@@ -0,0 +1,13 @@
+"""A wrapper for catboost regressor to handle some edge cases."""
+
+from catboost import CatBoostRegressor  # type: ignore
+
+from .catboost_kwargs import handle_fit_kwargs
+
+
+class CatBoostRegressorWrapper(CatBoostRegressor):
+    """A wrapper for the catboost regressor."""
+
+    def fit(self, *args, **kwargs):
+        args, kwargs = handle_fit_kwargs(*args, **kwargs)
+        return super().fit(*args, **kwargs)

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/model/model.py

@@ -24,6 +24,12 @@ class Model(Params, Fit):
         """The estimator backing the model."""
         raise NotImplementedError("estimator not implemented in parent class.")
 
-    def pre_fit(self, y: pd.Series | pd.DataFrame | None) -> None:
+    def pre_fit(
+        self,
+        df: pd.DataFrame,
+        y: pd.Series | pd.DataFrame | None,
+        eval_x: pd.DataFrame | None = None,
+        eval_y: pd.Series | pd.DataFrame | None = None,
+    ) -> dict[str, Any]:
         """A call to make sure the model is prepared for the target type."""
         raise NotImplementedError("pre_fit not implemented in parent class.")

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/model/model_router.py

@@ -20,6 +20,8 @@ _MODELS = {
 class ModelRouter(Model):
     """A router that routes to a different weights class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _model: Model | None
 
     def __init__(self) -> None:
@@ -37,11 +39,17 @@ class ModelRouter(Model):
             raise ValueError("model is null")
         return model.estimator
 
-    def pre_fit(self, y: pd.Series | pd.DataFrame | None):
+    def pre_fit(
+        self,
+        df: pd.DataFrame,
+        y: pd.Series | pd.DataFrame | None,
+        eval_x: pd.DataFrame | None = None,
+        eval_y: pd.Series | pd.DataFrame | None = None,
+    ) -> dict[str, Any]:
         model = self._model
         if model is None:
             raise ValueError("model is null")
-        model.pre_fit(y)
+        return model.pre_fit(df, y=y, eval_x=eval_x, eval_y=eval_y)
 
     def set_options(self, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
         self._model = _MODELS[
@@ -76,11 +84,13 @@ class ModelRouter(Model):
         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:
         model = self._model
         if model is None:
             raise ValueError("model is null")
-        model.fit(df, y=y, w=w)
+        model.fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y)
         return self
 
     def transform(self, df: pd.DataFrame) -> pd.DataFrame:

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/reducer/base_selector_reducer.py

@@ -15,6 +15,8 @@ from .reducer import Reducer
 class BaseSelectorReducer(Reducer):
     """A class that uses the base selector from the feature engine."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     def __init__(self, base_selector: BaseSelector, file_name: str) -> None:
         super().__init__()
         self._base_selector = base_selector
@@ -40,6 +42,8 @@ class BaseSelectorReducer(Reducer):
         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:
         try:
             self._base_selector.fit(df)  # type: ignore

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/reducer/combined_reducer.py

@@ -20,6 +20,8 @@ _REDUCERS_KEY = "reducers"
 class CombinedReducer(Reducer):
     """A reducer that combines a series of reducers."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     def __init__(self):
         super().__init__()
         self._reducers = [
@@ -73,6 +75,8 @@ class CombinedReducer(Reducer):
         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:
         for reducer in self._reducers:
             df = reducer.fit_transform(df)

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/reducer/nonnumeric_reducer.py

@@ -11,6 +11,8 @@ from .reducer import Reducer
 class NonNumericReducer(Reducer):
     """A class that removes non numeric columns from a dataframe."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     @classmethod
     def name(cls) -> str:
         return "nonnumeric"
@@ -29,6 +31,8 @@ class NonNumericReducer(Reducer):
         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:
         return self
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/selector/selector.py

@@ -7,6 +7,7 @@ from typing import Self
 import joblib  # type: ignore
 import optuna
 import pandas as pd
+import sklearn  # type: ignore
 from sklearn.feature_selection import RFE  # type: ignore
 
 from ..fit import Fit
@@ -19,6 +20,8 @@ _SELECTOR_FILE = "selector.joblib"
 class Selector(Params, Fit):
     """The selector class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _selector: RFE | None
 
     def __init__(self, model: Model):
@@ -43,8 +46,11 @@ class Selector(Params, Fit):
         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._model.pre_fit(y)
+        sklearn.set_config(enable_metadata_routing=False)
+        model_kwargs = self._model.pre_fit(df, y=y, eval_x=eval_x, eval_y=eval_y)
         if not isinstance(y, pd.Series):
             raise ValueError("y is not a series.")
         n_features_to_select = max(1, int(len(df.columns) * self._feature_ratio))
@@ -57,7 +63,7 @@ class Selector(Params, Fit):
             ),
         )
         try:
-            self._selector.fit(df, y=y, sample_weight=w)
+            self._selector.fit(df, y=y, sample_weight=w, **model_kwargs)
         except ValueError as exc:
             # Catch issues with 1 feature as a reduction target.
             logging.warning(str(exc))

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/trainer.py

@@ -11,7 +11,7 @@ from typing import Self
 import optuna
 import pandas as pd
 import tqdm
-from sklearn.metrics import f1_score, mean_absolute_error  # type: ignore
+from sklearn.metrics import f1_score, r2_score  # type: ignore
 
 from .calibrator.calibrator_router import CalibratorRouter
 from .exceptions import WavetrainException
@@ -158,6 +158,8 @@ class Trainer(Fit):
         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:
         """Perform a train on the data to fit to the targets."""
         if y is None:
@@ -217,10 +219,12 @@ class Trainer(Fit):
                     # Train
                     selector = Selector(model)
                     selector.set_options(trial)
-                    selector.fit(x_train, y=y_train, w=w)
+                    selector.fit(x_train, y=y_train, w=w, eval_x=x_test, eval_y=y_test)
                     x_train = selector.transform(x_train)
                     x_test = selector.transform(x_test)
-                    x_pred = model.fit_transform(x_train, y=y_train)
+                    x_pred = model.fit_transform(
+                        x_train, y=y_train, w=w, eval_x=x_test, eval_y=y_test
+                    )
 
                     # Calibrate
                     calibrator = CalibratorRouter(model)
@@ -243,8 +247,8 @@ class Trainer(Fit):
                     y_pred = model.transform(x_test)
                     y_pred = calibrator.transform(y_pred)
                     if determine_model_type(y_series) == ModelType.REGRESSION:
-                        return mean_absolute_error(y_test, y_pred[[PREDICTION_COLUMN]])
-                    return f1_score(y_test, y_pred[[PREDICTION_COLUMN]])
+                        return float(r2_score(y_test, y_pred[[PREDICTION_COLUMN]]))
+                    return float(f1_score(y_test, y_pred[[PREDICTION_COLUMN]]))
                 except WavetrainException as exc:
                     logging.warning(str(exc))
                     return -1.0

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/class_weights.py

@@ -14,6 +14,8 @@ from .weights import WEIGHTS_COLUMN, Weights
 class ClassWeights(Weights):
     """Class weight class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _class_weights: dict[Any, float]
 
     def __init__(self) -> None:
@@ -39,6 +41,8 @@ class ClassWeights(Weights):
         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:
         if not isinstance(y, pd.Series):
             raise ValueError("y is not a series.")

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/combined_weights.py

@@ -13,6 +13,8 @@ from .weights_router import WeightsRouter
 class CombinedWeights(Weights):
     """A weights class that combines multiple weights."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     def __init__(self) -> None:
         super().__init__()
         self._weights = [WeightsRouter(), ClassWeights()]
@@ -38,6 +40,8 @@ class CombinedWeights(Weights):
         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:
         for weights in self._weights:
             weights.fit(df, y=y)

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/exponential_weights.py

@@ -12,6 +12,8 @@ from .weights import WEIGHTS_COLUMN, Weights
 class ExponentialWeights(Weights):
     """Exponential weight class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     @classmethod
     def name(cls) -> str:
         """The name of the weight class."""
@@ -31,6 +33,8 @@ class ExponentialWeights(Weights):
         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:
         return self
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/linear_weights.py

@@ -12,7 +12,7 @@ from .weights import WEIGHTS_COLUMN, Weights
 class LinearWeights(Weights):
     """Linear weight class."""
 
-    # pylint: disable=duplicate-code
+    # pylint: disable=duplicate-code,too-many-positional-arguments,too-many-arguments
 
     @classmethod
     def name(cls) -> str:
@@ -33,6 +33,8 @@ class LinearWeights(Weights):
         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:
         return self
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/noop_weights.py

@@ -12,7 +12,7 @@ from .weights import WEIGHTS_COLUMN, Weights
 class NoopWeights(Weights):
     """Noop weight class."""
 
-    # pylint: disable=duplicate-code
+    # pylint: disable=duplicate-code,too-many-positional-arguments,too-many-arguments
 
     @classmethod
     def name(cls) -> str:
@@ -33,6 +33,8 @@ class NoopWeights(Weights):
         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:
         return self
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/sigmoid_weights.py

@@ -13,7 +13,7 @@ from .weights import WEIGHTS_COLUMN, Weights
 class SigmoidWeights(Weights):
     """Sigmoid weight class."""
 
-    # pylint: disable=duplicate-code
+    # pylint: disable=duplicate-code,too-many-positional-arguments,too-many-arguments
 
     @classmethod
     def name(cls) -> str:
@@ -34,6 +34,8 @@ class SigmoidWeights(Weights):
         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:
         return self
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/weights/weights_router.py

@@ -26,6 +26,8 @@ _WEIGHTS = {
 class WeightsRouter(Weights):
     """A router that routes to a different weights class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _weights: Weights | None
 
     def __init__(self) -> None:
@@ -71,6 +73,8 @@ class WeightsRouter(Weights):
         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:
         return self
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer/windower/windower.py

@@ -18,6 +18,8 @@ _LOOKBACK_KEY = "lookback"
 class Windower(Params, Fit):
     """The windower class."""
 
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
     _lookback_ratio: float | None
 
     def __init__(self, dt_column: str | None):
@@ -48,6 +50,8 @@ class Windower(Params, Fit):
         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:
         lookback_ratio = self._lookback_ratio
         if lookback_ratio is None:

{wavetrainer-0.0.5 → wavetrainer-0.0.7/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.5
+Version: 0.0.7
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield
@@ -21,7 +21,6 @@ Requires-Dist: scipy>=1.15.2
 Requires-Dist: catboost>=1.2.7
 Requires-Dist: venn-abers>=1.4.6
 Requires-Dist: mapie>=0.9.2
-Requires-Dist: shapiq>=1.2.2
 
 # wavetrainer
 
@@ -49,7 +48,6 @@ Python 3.11.6:
 - [catboost](https://catboost.ai/)
 - [venn-abers](https://github.com/ip200/venn-abers)
 - [mapie](https://mapie.readthedocs.io/en/stable/)
-- [shapiq](https://github.com/mmschlk/shapiq)
 
 ## Raison D'être :thought_balloon:
 

{wavetrainer-0.0.5 → wavetrainer-0.0.7}/wavetrainer.egg-info/SOURCES.txt

@@ -5,6 +5,8 @@ requirements.txt
 setup.py
 tests/__init__.py
 tests/trainer_test.py
+tests/model/__init__.py
+tests/model/catboost_kwargs_test.py
 wavetrainer/__init__.py
 wavetrainer/create.py
 wavetrainer/exceptions.py
@@ -24,7 +26,10 @@ wavetrainer/calibrator/calibrator_router.py
 wavetrainer/calibrator/mapie_calibrator.py
 wavetrainer/calibrator/vennabers_calibrator.py
 wavetrainer/model/__init__.py
+wavetrainer/model/catboost_classifier_wrap.py
+wavetrainer/model/catboost_kwargs.py
 wavetrainer/model/catboost_model.py
+wavetrainer/model/catboost_regressor_wrap.py
 wavetrainer/model/model.py
 wavetrainer/model/model_router.py
 wavetrainer/reducer/__init__.py

wavetrainer-0.0.5/requirements.txt → wavetrainer-0.0.7/wavetrainer.egg-info/requires.txt

@@ -8,4 +8,3 @@ scipy>=1.15.2
 catboost>=1.2.7
 venn-abers>=1.4.6
 mapie>=0.9.2
-shapiq>=1.2.2