wavetrainer 0.0.14__tar.gz → 0.0.16__tar.gz

{wavetrainer-0.0.14/wavetrainer.egg-info → wavetrainer-0.0.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.14
+Version: 0.0.16
 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-0.0.14 → wavetrainer-0.0.16}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.14',
+    version='0.0.16',
     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-0.0.14 → wavetrainer-0.0.16}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.14"
+__VERSION__ = "0.0.16"
 __all__ = ("create",)

{wavetrainer-0.0.14 → wavetrainer-0.0.16}/wavetrainer/reducer/combined_reducer.py

@@ -1,6 +1,7 @@
 """A reducer that combines all the other reducers."""
 
 import json
+import logging
 import os
 from typing import Self
 
@@ -12,6 +13,7 @@ from .correlation_reducer import CorrelationReducer
 from .duplicate_reducer import DuplicateReducer
 from .nonnumeric_reducer import NonNumericReducer
 from .reducer import Reducer
+from .unseen_reducer import UnseenReducer
 
 _COMBINED_REDUCER_FILE = "combined_reducer.json"
 _REDUCERS_KEY = "reducers"
@@ -25,6 +27,7 @@ class CombinedReducer(Reducer):
     def __init__(self):
         super().__init__()
         self._reducers = [
+            UnseenReducer(),
             ConstantReducer(),
             DuplicateReducer(),
             NonNumericReducer(),
@@ -54,6 +57,8 @@ class CombinedReducer(Reducer):
                     self._reducers.append(CorrelationReducer())
                 elif reducer_name == NonNumericReducer.name():
                     self._reducers.append(NonNumericReducer())
+                elif reducer_name == UnseenReducer.name():
+                    self._reducers.append(UnseenReducer())
         for reducer in self._reducers:
             reducer.load(folder)
 
@@ -84,5 +89,9 @@ class CombinedReducer(Reducer):
 
     def transform(self, df: pd.DataFrame) -> pd.DataFrame:
         for reducer in self._reducers:
-            df = reducer.transform(df)
+            try:
+                df = reducer.transform(df)
+            except ValueError as exc:
+                logging.warning("Failed to reduce %s", reducer.name())
+                raise exc
         return df

wavetrainer-0.0.16/wavetrainer/reducer/unseen_reducer.py

@@ -0,0 +1,58 @@
+"""A reducer that removes unseen columns."""
+
+import json
+import os
+from typing import Self
+
+import optuna
+import pandas as pd
+
+from .reducer import Reducer
+
+_UNSEEN_REDUCER_FILE = "unseen_reducer.json"
+
+
+class UnseenReducer(Reducer):
+    """A class that removes unseen columns from a dataframe."""
+
+    # pylint: disable=too-many-positional-arguments,too-many-arguments
+
+    def __init__(self):
+        super().__init__()
+        self._seen_features = set()
+
+    @classmethod
+    def name(cls) -> str:
+        return "unseen"
+
+    def set_options(self, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
+        pass
+
+    def load(self, folder: str) -> None:
+        with open(
+            os.path.join(folder, _UNSEEN_REDUCER_FILE), encoding="utf8"
+        ) as handle:
+            self._seen_features = set(json.load(handle))
+
+    def save(self, folder: str) -> None:
+        with open(
+            os.path.join(folder, _UNSEEN_REDUCER_FILE), "w", encoding="utf8"
+        ) as handle:
+            json.dump(
+                list(self._seen_features),
+                handle,
+            )
+
+    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._seen_features = df.columns.values.tolist()
+        return self
+
+    def transform(self, df: pd.DataFrame) -> pd.DataFrame:
+        return df[list(self._seen_features)]

{wavetrainer-0.0.14 → wavetrainer-0.0.16}/wavetrainer/selector/selector.py

@@ -20,7 +20,7 @@ _SELECTOR_FILE = "selector.joblib"
 class Selector(Params, Fit):
     """The selector class."""
 
-    # pylint: disable=too-many-positional-arguments,too-many-arguments
+    # pylint: disable=too-many-positional-arguments,too-many-arguments,consider-using-enumerate
 
     _selector: RFE | None
 
@@ -66,6 +66,14 @@ class Selector(Params, Fit):
         )
         try:
             self._selector.fit(df, y=y, sample_weight=w, **model_kwargs)
+            importances = self._model.estimator.feature_importances_
+            try:
+                importances_len = len(importances)
+                columns = self._selector.get_feature_names_out()
+                for i in range(importances_len):
+                    logging.info("Feature %s: %f", columns[i], importances[i])
+            except TypeError:
+                pass
         except ValueError as exc:
             # Catch issues with 1 feature as a reduction target.
             logging.warning(str(exc))

{wavetrainer-0.0.14 → wavetrainer-0.0.16}/wavetrainer/trainer.py

@@ -317,7 +317,7 @@ class Trainer(Fit):
 
             last_processed_dt = None
             for count, test_idx in tqdm.tqdm(
-                enumerate(test_dt_index[test_dt_index >= start_test_index])
+                enumerate(dt_index[dt_index >= start_test_index])
             ):
                 if (
                     last_processed_dt is not None

{wavetrainer-0.0.14 → wavetrainer-0.0.16/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.14
+Version: 0.0.16
 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-0.0.14 → wavetrainer-0.0.16}/wavetrainer.egg-info/SOURCES.txt

@@ -40,6 +40,7 @@ wavetrainer/reducer/correlation_reducer.py
 wavetrainer/reducer/duplicate_reducer.py
 wavetrainer/reducer/nonnumeric_reducer.py
 wavetrainer/reducer/reducer.py
+wavetrainer/reducer/unseen_reducer.py
 wavetrainer/selector/__init__.py
 wavetrainer/selector/selector.py
 wavetrainer/weights/__init__.py