wavetrainer 0.0.41__tar.gz → 0.0.43__tar.gz

{wavetrainer-0.0.41/wavetrainer.egg-info → wavetrainer-0.0.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.41
+Version: 0.0.43
 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-0.0.41 → wavetrainer-0.0.43}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.41',
+    version='0.0.43',
     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-0.0.41 → wavetrainer-0.0.43}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.41"
+__VERSION__ = "0.0.43"
 __all__ = ("create",)

{wavetrainer-0.0.41 → wavetrainer-0.0.43}/wavetrainer/model/xgboost/xgboost_model.py

@@ -107,7 +107,11 @@ class XGBoostModel(Model):
     @property
     def feature_importances(self) -> dict[str, float]:
         bst = self._provide_xgboost()
-        return bst.get_booster().get_score(importance_type="weight")  # type: ignore
+        try:
+            return bst.get_booster().get_score(importance_type="weight")  # type: ignore
+        except XGBoostError as exc:
+            print(str(exc))
+            return {}
 
     def provide_estimator(self):
         return self._provide_xgboost()

{wavetrainer-0.0.41 → wavetrainer-0.0.43}/wavetrainer/selector/selector.py

@@ -1,6 +1,6 @@
 """The selector class."""
 
-# pylint: disable=too-many-locals
+# pylint: disable=too-many-locals,line-too-long
 import functools
 import json
 import logging
@@ -59,12 +59,12 @@ class Selector(Params, Fit):
             raise ValueError("y is not a series.")
         if len(df.columns) <= 1:
             return self
-        n_features_to_select = max(1, int(len(df.columns) * self._feature_ratio))
-        steps = int((len(df.columns) - n_features_to_select) / self._steps)
+        print(
+            f"Performing feature selection with {self._steps} steps and a total ratio of {self._feature_ratio}"
+        )
         current_features = df.columns.values.tolist()
-        self._model.fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y)
 
-        def set_current_features():
+        def set_current_features(required_features: int):
             nonlocal current_features
             feature_importances = self._model.feature_importances
             if not feature_importances:
@@ -80,24 +80,27 @@ class Selector(Params, Fit):
             )
             if not current_features:
                 current_features = [list(feature_importances.keys())[0]]
+            current_features = current_features[:required_features]
 
-        for i in range(steps):
+        n_features = len(current_features)
+        for i in range(self._steps):
             print(
                 f"Recursive Feature Elimination Step {i}, current features: {len(current_features)}"
             )
             ratio_diff = 1.0 - self._feature_ratio
-            ratio_step = ratio_diff / float(steps)
+            ratio_step = ratio_diff / float(self._steps)
             current_ratio = 1.0 - (ratio_step * i)
             n_features = max(1, int(len(df.columns) * current_ratio))
             if n_features >= len(current_features):
                 continue
-            set_current_features()
+
+            self._model.fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y)
+            set_current_features(n_features)
             print(f"Reduced features to {len(current_features)}")
             df = df[current_features]
             if eval_x is not None:
                 eval_x = eval_x[current_features]
-            self._model.fit(df, y=y, w=w, eval_x=eval_x, eval_y=eval_y)
-        set_current_features()
+
         self._selector = current_features
 
         return self

{wavetrainer-0.0.41 → wavetrainer-0.0.43}/wavetrainer/trainer.py

@@ -281,13 +281,14 @@ class Trainer(Fit):
                     x_test = selector.transform(x_test)
                     print(f"Selection took {time.time() - start_selector}")
                     start_train = time.time()
-                    x_pred = model.fit_transform(
+                    model.fit(
                         x_train,
                         y=y_train,
                         w=w,
                         eval_x=x_test if not no_evaluation else None,
                         eval_y=y_test if not no_evaluation else None,
                     )
+                    y_pred = model.transform(x_test)
                     print(f"Training took {time.time() - start_train}")
 
                     # Calibrate
@@ -295,13 +296,12 @@ class Trainer(Fit):
                     calibrator = CalibratorRouter(model)
                     calibrator.set_options(trial, x)
                     calibrator.fit(
-                        x_pred if calibrator.predictions_as_x(y_train) else x_train,
-                        y=y_train,
+                        y_pred if calibrator.predictions_as_x(y_test) else x_test,
+                        y=y_test,
                     )
                     print(f"Calibrating took {time.time() - start_calibrate}")
 
                     # Output
-                    y_pred = model.transform(x_test)
                     cal_pred = calibrator.transform(
                         y_pred if calibrator.predictions_as_x(y_test) else x_test
                     )
@@ -441,6 +441,8 @@ class Trainer(Fit):
                         if self._max_train_timeout is None
                         else self._max_train_timeout.total_seconds(),
                     )
+                else:
+                    break
 
                 _fit(study.best_trial, test_df, test_series, True, test_idx, True)
                 last_processed_dt = test_idx

{wavetrainer-0.0.41 → wavetrainer-0.0.43/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.41
+Version: 0.0.43
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield