wavetrainer 0.0.52__tar.gz → 0.1.0__tar.gz

{wavetrainer-0.0.52/wavetrainer.egg-info → wavetrainer-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.52
+Version: 0.1.0
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield
@@ -20,7 +20,6 @@ Requires-Dist: numpy>=1.26.4
 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: pytz>=2025.1
 Requires-Dist: torch>=2.6.0
 Requires-Dist: tabpfn>=2.0.6
@@ -53,7 +52,6 @@ Python 3.11.6:
 - [scipy](https://scipy.org/)
 - [catboost](https://catboost.ai/)
 - [venn-abers](https://github.com/ip200/venn-abers)
-- [mapie](https://mapie.readthedocs.io/en/stable/)
 - [pytz](https://pythonhosted.org/pytz/)
 - [torch](https://pytorch.org/)
 - [tabpfn](https://github.com/PriorLabs/TabPFN)

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/README.md

@@ -23,7 +23,6 @@ Python 3.11.6:
 - [scipy](https://scipy.org/)
 - [catboost](https://catboost.ai/)
 - [venn-abers](https://github.com/ip200/venn-abers)
-- [mapie](https://mapie.readthedocs.io/en/stable/)
 - [pytz](https://pythonhosted.org/pytz/)
 - [torch](https://pytorch.org/)
 - [tabpfn](https://github.com/PriorLabs/TabPFN)

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/requirements.txt

@@ -7,7 +7,6 @@ numpy>=1.26.4
 scipy>=1.15.2
 catboost>=1.2.7
 venn-abers>=1.4.6
-mapie>=0.9.2
 pytz>=2025.1
 torch>=2.6.0
 tabpfn>=2.0.6

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.52',
+    version='0.1.0',
     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-0.0.52 → wavetrainer-0.1.0}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.52"
+__VERSION__ = "0.1.0"
 __all__ = ("create",)

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/wavetrainer/calibrator/calibrator_router.py

@@ -1,6 +1,7 @@
 """A calibrator class that routes to other calibrators."""
 
 import json
+import logging
 import os
 from typing import Self
 
@@ -10,14 +11,12 @@ import pandas as pd
 from ..model.model import Model
 from ..model_type import ModelType, determine_model_type
 from .calibrator import Calibrator
-from .mapie_calibrator import MAPIECalibrator
 from .vennabers_calibrator import VennabersCalibrator
 
 _CALIBRATOR_ROUTER_FILE = "calibrator_router.json"
 _CALIBRATOR_KEY = "calibrator"
 _CALIBRATORS = {
     VennabersCalibrator.name(): VennabersCalibrator,
-    MAPIECalibrator.name(): MAPIECalibrator,
 }
 
 
@@ -40,10 +39,6 @@ class CalibratorRouter(Calibrator):
         calibrator = self._calibrator
         if calibrator is not None:
             return calibrator.predictions_as_x(None)
-        if y is None:
-            raise ValueError("y is null")
-        if determine_model_type(y) == ModelType.REGRESSION:
-            return False
         return True
 
     def set_options(
@@ -55,9 +50,11 @@ class CalibratorRouter(Calibrator):
         calibrator.set_options(trial, df)
 
     def load(self, folder: str) -> None:
-        with open(
-            os.path.join(folder, _CALIBRATOR_ROUTER_FILE), encoding="utf8"
-        ) as handle:
+        file_path = os.path.join(folder, _CALIBRATOR_ROUTER_FILE)
+        if not os.path.exists(file_path):
+            logging.warning("file %s does not exist", file_path)
+            return
+        with open(file_path, encoding="utf8") as handle:
             params = json.load(handle)
             calibrator = _CALIBRATORS[params[_CALIBRATOR_KEY]](self._model)
         calibrator.load(folder)
@@ -66,7 +63,8 @@ class CalibratorRouter(Calibrator):
     def save(self, folder: str, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
         calibrator = self._calibrator
         if calibrator is None:
-            raise ValueError("calibrator is null.")
+            logging.warning("calibrator is null")
+            return
         calibrator.save(folder, trial)
         with open(
             os.path.join(folder, _CALIBRATOR_ROUTER_FILE), "w", encoding="utf8"
@@ -91,7 +89,7 @@ class CalibratorRouter(Calibrator):
         if y is None:
             raise ValueError("y is null")
         if determine_model_type(y) == ModelType.REGRESSION:
-            calibrator = MAPIECalibrator(self._model)
+            return self
         else:
             calibrator = VennabersCalibrator(self._model)
         calibrator.fit(df, y=y, w=w)
@@ -101,5 +99,6 @@ class CalibratorRouter(Calibrator):
     def transform(self, df: pd.DataFrame) -> pd.DataFrame:
         calibrator = self._calibrator
         if calibrator is None:
-            raise ValueError("calibrator is null.")
+            logging.warning("calibrator is null")
+            return df
         return calibrator.transform(df)

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/wavetrainer/model/xgboost/xgboost_model.py

@@ -275,6 +275,8 @@ class XGBoostModel(Model):
         if eval_x is not None and eval_y is not None and self._best_iteration is None:
             eval_x = _convert_categoricals(eval_x)
             evals = [(eval_x, eval_y), (df, y)]
+        if w is not None:
+            w = w.fillna(0.0).clip(lower=0.00001)
         xgboost.fit(  # type: ignore
             df,
             y,

{wavetrainer-0.0.52 → wavetrainer-0.1.0/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.52
+Version: 0.1.0
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield
@@ -20,7 +20,6 @@ Requires-Dist: numpy>=1.26.4
 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: pytz>=2025.1
 Requires-Dist: torch>=2.6.0
 Requires-Dist: tabpfn>=2.0.6
@@ -53,7 +52,6 @@ Python 3.11.6:
 - [scipy](https://scipy.org/)
 - [catboost](https://catboost.ai/)
 - [venn-abers](https://github.com/ip200/venn-abers)
-- [mapie](https://mapie.readthedocs.io/en/stable/)
 - [pytz](https://pythonhosted.org/pytz/)
 - [torch](https://pytorch.org/)
 - [tabpfn](https://github.com/PriorLabs/TabPFN)

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/wavetrainer.egg-info/SOURCES.txt

@@ -23,7 +23,6 @@ wavetrainer.egg-info/top_level.txt
 wavetrainer/calibrator/__init__.py
 wavetrainer/calibrator/calibrator.py
 wavetrainer/calibrator/calibrator_router.py
-wavetrainer/calibrator/mapie_calibrator.py
 wavetrainer/calibrator/vennabers_calibrator.py
 wavetrainer/model/__init__.py
 wavetrainer/model/model.py

{wavetrainer-0.0.52 → wavetrainer-0.1.0}/wavetrainer.egg-info/requires.txt

@@ -7,7 +7,6 @@ numpy>=1.26.4
 scipy>=1.15.2
 catboost>=1.2.7
 venn-abers>=1.4.6
-mapie>=0.9.2
 pytz>=2025.1
 torch>=2.6.0
 tabpfn>=2.0.6

wavetrainer-0.0.52/wavetrainer/calibrator/mapie_calibrator.py

@@ -1,80 +0,0 @@
-"""A calibrator that implements MAPIE."""
-
-import os
-from typing import Self
-
-import joblib  # type: ignore
-import optuna
-import pandas as pd
-from mapie.regression import MapieRegressor  # type: ignore
-
-from ..model.model import PROBABILITY_COLUMN_PREFIX, Model
-from .calibrator import Calibrator
-
-_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.create_estimator(), method="plus", cv=5)
-
-    @classmethod
-    def name(cls) -> str:
-        return "mapie"
-
-    def predictions_as_x(self, y: pd.Series | pd.DataFrame | None = None) -> bool:
-        return False
-
-    def set_options(
-        self, trial: optuna.Trial | optuna.trial.FrozenTrial, df: pd.DataFrame
-    ) -> None:
-        pass
-
-    def load(self, folder: str) -> None:
-        self._mapie = joblib.load(os.path.join(folder, _CALIBRATOR_FILENAME))
-
-    def save(self, folder: str, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
-        joblib.dump(self._mapie, os.path.join(folder, _CALIBRATOR_FILENAME))
-
-    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:
-        mapie = self._mapie
-        if mapie is None:
-            raise ValueError("mapie is null")
-        if y is None:
-            raise ValueError("y is null")
-        mapie.fit(self._model.convert_df(df), y)
-        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) + 1
-                and len(df) > int(1.0 / (1.0 - potential_alpha)) + 1
-            ):
-                alpha.append(potential_alpha)
-        ret_df = pd.DataFrame(index=df.index)
-        if alpha:
-            _, y_pis = self._mapie.predict(
-                self._model.convert_df(df), alpha=alpha, allow_infinite_bounds=True
-            )
-            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()
-                    ret_df[f"{PROBABILITY_COLUMN_PREFIX}{alpha_val}_{ii == 1}"] = values
-        return ret_df