wavetrainer 0.0.30__tar.gz → 0.0.32__tar.gz

{wavetrainer-0.0.30/wavetrainer.egg-info → wavetrainer-0.0.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.30
+Version: 0.0.32
 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-0.0.30 → wavetrainer-0.0.32}/setup.py

@@ -23,7 +23,7 @@ def install_requires() -> typing.List[str]:
 
 setup(
     name='wavetrainer',
-    version='0.0.30',
+    version='0.0.32',
     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-0.0.30 → wavetrainer-0.0.32}/wavetrainer/__init__.py

@@ -2,5 +2,5 @@
 
 from .create import create
 
-__VERSION__ = "0.0.30"
+__VERSION__ = "0.0.32"
 __all__ = ("create",)

{wavetrainer-0.0.30 → wavetrainer-0.0.32}/wavetrainer/reducer/combined_reducer.py

@@ -18,6 +18,7 @@ from .unseen_reducer import UnseenReducer
 
 _COMBINED_REDUCER_FILE = "combined_reducer.json"
 _REDUCERS_KEY = "reducers"
+_REMOVED_COLUMNS_FILE = "combined_reducer_removed_columns.json"
 
 
 class CombinedReducer(Reducer):
@@ -35,6 +36,7 @@ class CombinedReducer(Reducer):
             CorrelationReducer(),
             SmartCorrelationReducer(),
         ]
+        self._folder = None
 
     @classmethod
     def name(cls) -> str:
@@ -67,6 +69,7 @@ class CombinedReducer(Reducer):
                     self._reducers.append(SmartCorrelationReducer())
         for reducer in self._reducers:
             reducer.load(folder)
+        self._folder = folder
 
     def save(self, folder: str, trial: optuna.Trial | optuna.trial.FrozenTrial) -> None:
         with open(
@@ -89,8 +92,19 @@ class CombinedReducer(Reducer):
         eval_x: pd.DataFrame | None = None,
         eval_y: pd.Series | pd.DataFrame | None = None,
     ) -> Self:
+        removed_columns_dict = {}
         for reducer in self._reducers:
+            before_columns = set(df.columns.values)
             df = reducer.fit_transform(df)
+            after_columns = set(df.columns.values)
+            removed_columns = before_columns.difference(after_columns)
+            if removed_columns:
+                removed_columns_dict[reducer.name()] = list(removed_columns)
+        if self._folder is not None:
+            with open(
+                os.path.join(self._folder, _REMOVED_COLUMNS_FILE), encoding="utf8"
+            ) as handle:
+                json.dump(removed_columns_dict, handle)
         return self
 
     def transform(self, df: pd.DataFrame) -> pd.DataFrame:

{wavetrainer-0.0.30 → wavetrainer-0.0.32}/wavetrainer/trainer.py

@@ -37,6 +37,7 @@ _TEST_SIZE_KEY = "test_size"
 _VALIDATION_SIZE_KEY = "validation_size"
 _IDX_USR_ATTR_KEY = "idx"
 _DT_COLUMN_KEY = "dt_column"
+_BAD_OUTPUT = -1000.0
 
 
 def _assign_bin(timestamp, bins: list[datetime.datetime]) -> int:
@@ -209,6 +210,7 @@ class Trainer(Fit):
                 folder = os.path.join(
                     self._folder, str(y_series.name), split_idx.isoformat()
                 )
+                new_folder = os.path.exists(folder)
                 os.makedirs(folder, exist_ok=True)
                 trial_file = os.path.join(folder, _TRIAL_FILENAME)
                 if os.path.exists(trial_file):
@@ -234,8 +236,10 @@ class Trainer(Fit):
                     x_train = windower.fit_transform(x_train)
                     y_train = y_train[-len(x_train) :]
                     if len(y_train.unique()) <= 1:
+                        if new_folder:
+                            os.removedirs(folder)
                         logging.warning("Y train only contains 1 unique datapoint.")
-                        return -1.0
+                        return _BAD_OUTPUT
 
                     # Perform common reductions
                     reducer = CombinedReducer()
@@ -297,7 +301,9 @@ class Trainer(Fit):
                     return output
                 except WavetrainException as exc:
                     logging.warning(str(exc))
-                    return -1.0
+                    if new_folder:
+                        os.removedirs(folder)
+                    return _BAD_OUTPUT
 
             start_validation_index = (
                 dt_index.to_list()[-int(len(dt_index) * self._validation_size) - 1]
@@ -339,6 +345,18 @@ class Trainer(Fit):
                     if self._max_train_timeout is None
                     else self._max_train_timeout.total_seconds(),
                 )
+            while (
+                study.best_trial.value is None or study.best_trial.value == _BAD_OUTPUT
+            ):
+                logging.info("Performing extra train")
+                study.optimize(
+                    test_objective,
+                    n_trials=1,
+                    show_progress_bar=True,
+                    timeout=None
+                    if self._max_train_timeout is None
+                    else self._max_train_timeout.total_seconds(),
+                )
 
             train_len = len(df[dt_index < start_test_index])
             test_len = len(
@@ -372,7 +390,7 @@ class Trainer(Fit):
 
                 test_df = df.iloc[: train_len + count + test_len]
                 test_series = y_series.iloc[: train_len + count + test_len]
-                if len(test_df) <= 2:
+                if len(test_df) <= 3:
                     continue
 
                 if test_idx < start_validation_index:

{wavetrainer-0.0.30 → wavetrainer-0.0.32/wavetrainer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: wavetrainer
-Version: 0.0.30
+Version: 0.0.32
 Summary: A library for automatically finding the optimal model within feature and hyperparameter space.
 Home-page: https://github.com/8W9aG/wavetrainer
 Author: Will Sackfield