wavetrainer 0.0.20__tar.gz → 0.0.22__tar.gz

{wavetrainer-0.0.20/wavetrainer.egg-info → wavetrainer-0.0.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.20
+Version: 0.0.22
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield
@@ -22,6 +22,7 @@ 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
 
 # wavetrainer
 
@@ -50,6 +51,7 @@ Python 3.11.6:
 - [venn-abers](https://github.com/ip200/venn-abers)
 - [mapie](https://mapie.readthedocs.io/en/stable/)
 - [pytz](https://pythonhosted.org/pytz/)
+- [torch](https://pytorch.org/)
 
 ## Raison D'être :thought_balloon:
 

{wavetrainer-0.0.20 → wavetrainer-0.0.22}/README.md

@@ -25,6 +25,7 @@ Python 3.11.6:
 - [venn-abers](https://github.com/ip200/venn-abers)
 - [mapie](https://mapie.readthedocs.io/en/stable/)
 - [pytz](https://pythonhosted.org/pytz/)
+- [torch](https://pytorch.org/)
 
 ## Raison D'être :thought_balloon:
 

wavetrainer-0.0.20/wavetrainer.egg-info/requires.txt → wavetrainer-0.0.22/requirements.txt

@@ -9,3 +9,4 @@ catboost>=1.2.7
 venn-abers>=1.4.6
 mapie>=0.9.2
 pytz>=2025.1
+torch>=2.6.0

{wavetrainer-0.0.20 → wavetrainer-0.0.22}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.20',
+    version='0.0.22',
     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-0.0.20 → wavetrainer-0.0.22}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.20"
+__VERSION__ = "0.0.22"
 __all__ = ("create",)

{wavetrainer-0.0.20 → wavetrainer-0.0.22}/wavetrainer/model/catboost_model.py

@@ -7,6 +7,7 @@ from typing import Any, Self
 
 import optuna
 import pandas as pd
+import torch
 from catboost import CatBoost, Pool  # type: ignore
 
 from ..model_type import ModelType, determine_model_type
@@ -189,6 +190,8 @@ class CatboostModel(Model):
                         boosting_type=self._boosting_type,
                         early_stopping_rounds=self._early_stopping_rounds,
                         metric_period=100,
+                        task_type="GPU" if torch.cuda.is_available() else "CPU",
+                        devices="0" if torch.cuda.is_available() else None,
                     )
                 case ModelType.REGRESSION:
                     catboost = CatBoostRegressorWrapper(
@@ -199,6 +202,8 @@ class CatboostModel(Model):
                         boosting_type=self._boosting_type,
                         early_stopping_rounds=self._early_stopping_rounds,
                         metric_period=100,
+                        task_type="GPU" if torch.cuda.is_available() else "CPU",
+                        devices="0" if torch.cuda.is_available() else None,
                     )
                 case ModelType.BINNED_BINARY:
                     catboost = CatBoostClassifierWrapper(
@@ -209,6 +214,8 @@ class CatboostModel(Model):
                         boosting_type=self._boosting_type,
                         early_stopping_rounds=self._early_stopping_rounds,
                         metric_period=100,
+                        task_type="GPU" if torch.cuda.is_available() else "CPU",
+                        devices="0" if torch.cuda.is_available() else None,
                     )
                 case ModelType.MULTI_CLASSIFICATION:
                     catboost = CatBoostClassifierWrapper(
@@ -219,6 +226,8 @@ class CatboostModel(Model):
                         boosting_type=self._boosting_type,
                         early_stopping_rounds=self._early_stopping_rounds,
                         metric_period=100,
+                        task_type="GPU" if torch.cuda.is_available() else "CPU",
+                        devices="0" if torch.cuda.is_available() else None,
                     )
             self._catboost = catboost
         if catboost is None:

{wavetrainer-0.0.20 → wavetrainer-0.0.22/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.20
+Version: 0.0.22
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield
@@ -22,6 +22,7 @@ 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
 
 # wavetrainer
 
@@ -50,6 +51,7 @@ Python 3.11.6:
 - [venn-abers](https://github.com/ip200/venn-abers)
 - [mapie](https://mapie.readthedocs.io/en/stable/)
 - [pytz](https://pythonhosted.org/pytz/)
+- [torch](https://pytorch.org/)
 
 ## Raison D'être :thought_balloon:
 

wavetrainer-0.0.20/requirements.txt → wavetrainer-0.0.22/wavetrainer.egg-info/requires.txt

@@ -8,4 +8,5 @@ scipy>=1.15.2
 catboost>=1.2.7
 venn-abers>=1.4.6
 mapie>=0.9.2
-pytz>=2025.1
+pytz>=2025.1
+torch>=2.6.0

{wavetrainer-0.0.20 → wavetrainer-0.0.22}/wavetrainer/trainer.py

@@ -323,11 +323,6 @@ class Trainer(Fit):
             for count, test_idx in tqdm.tqdm(
                 enumerate(dt_index[dt_index >= start_test_index])
             ):
-                if (
-                    last_processed_dt is not None
-                    and test_idx < last_processed_dt + self._walkforward_timedelta
-                ):
-                    continue
                 test_dt = test_idx.to_pydatetime()
                 found = False
                 for trial in study.trials:
@@ -340,6 +335,11 @@ class Trainer(Fit):
                 if found:
                     last_processed_dt = test_dt
                     continue
+                if (
+                    last_processed_dt is not None
+                    and test_idx < last_processed_dt + self._walkforward_timedelta
+                ):
+                    continue
 
                 test_df = df.iloc[: train_len + count + test_len]
                 test_series = y_series.iloc[: train_len + count + test_len]