[DEP] Move impute to legacy (#1823)

* impute to legacy

* remove imputer API

* remove Theta

* fix import

aeon/classification/hybrid/_hivecote_v2.py

@@ -4,7 +4,7 @@
 representations, using the weighted probabilistic CAWPE as an ensemble controller.
 """
 
-__maintainer__ = []
+__maintainer__ = ["MatthewMiddlehurst", "TonyBagnall"]
 __all__ = ["HIVECOTEV2"]
 
 from datetime import datetime

aeon/forecasting/model_selection/_tune.py

@@ -386,68 +386,6 @@ class ForecastingGridSearchCV(BaseGridSearch):
     n_best_scores_: list of float
         The scores of n_best_forecasters_ sorted from best to worst
         score of forecasters
-
-    Examples
-    --------
-    >>> from aeon.datasets import load_shampoo_sales
-    >>> from aeon.forecasting.model_selection import (
-    ...     ExpandingWindowSplitter,
-    ...     ForecastingGridSearchCV,
-    ...     ExpandingWindowSplitter)
-    >>> from aeon.forecasting.naive import NaiveForecaster
-    >>> y = load_shampoo_sales()
-    >>> fh = [1,2,3]
-    >>> cv = ExpandingWindowSplitter(fh=fh)
-    >>> forecaster = NaiveForecaster()
-    >>> param_grid = {"strategy" : ["last", "mean", "drift"]}
-    >>> gscv = ForecastingGridSearchCV(
-    ...     forecaster=forecaster,
-    ...     param_grid=param_grid,
-    ...     cv=cv,
-    ...     n_jobs=-1)
-    >>> gscv.fit(y)
-    ForecastingGridSearchCV(...)
-    >>> y_pred = gscv.predict(fh)
-
-        Advanced model meta-tuning (model selection) with multiple forecasters
-        together with hyper-parametertuning at same time using sklearn notation:
-    >>> from aeon.datasets import load_shampoo_sales
-    >>> from aeon.forecasting.exp_smoothing import ExponentialSmoothing
-    >>> from aeon.forecasting.naive import NaiveForecaster
-    >>> from aeon.forecasting.model_selection import ExpandingWindowSplitter
-    >>> from aeon.forecasting.model_selection import ForecastingGridSearchCV
-    >>> from aeon.forecasting.compose import TransformedTargetForecaster
-    >>> from aeon.forecasting.theta import ThetaForecaster
-    >>> from aeon.transformations.impute import Imputer
-    >>> y = load_shampoo_sales()
-    >>> pipe = TransformedTargetForecaster(steps=[
-    ...     ("imputer", Imputer()),
-    ...     ("forecaster", NaiveForecaster())])
-    >>> cv = ExpandingWindowSplitter(
-    ...     initial_window=24,
-    ...     step_length=12,
-    ...     fh=[1,2,3])
-    >>> gscv = ForecastingGridSearchCV(
-    ...     forecaster=pipe,
-    ...     param_grid=[{
-    ...         "forecaster": [NaiveForecaster(sp=12)],
-    ...         "forecaster__strategy": ["drift", "last", "mean"],
-    ...     },
-    ...     {
-    ...         "imputer__method": ["mean", "drift"],
-    ...         "forecaster": [ThetaForecaster(sp=12)],
-    ...     },
-    ...     {
-    ...         "imputer__method": ["mean", "median"],
-    ...         "forecaster": [ExponentialSmoothing(sp=12)],
-    ...         "forecaster__trend": ["add", "mul"],
-    ...     },
-    ...     ],
-    ...     cv=cv,
-    ...     n_jobs=-1)  # doctest: +SKIP
-    >>> gscv.fit(y)  # doctest: +SKIP
-    ForecastingGridSearchCV(...)
-    >>> y_pred = gscv.predict(fh=[1,2,3])  # doctest: +SKIP
     """
 
     def __init__(

aeon/transformations/_legacy/compose.py

@@ -869,7 +869,7 @@ def get_test_params(cls, parameter_set="default"):
         -------
         params : dict or list of dict
         """
-        from aeon.transformations.impute import Imputer
+        from aeon.transformations._legacy.impute import Imputer
 
         # test with 2 simple detrend transformations with selected_transformer
         params1 = {

aeon/transformations/impute.py → aeon/transformations/_legacy/impute.py

@@ -5,20 +5,13 @@
 
 
 import numpy as np
-from deprecated.sphinx import deprecated
 from sklearn.utils import check_random_state
 
 from aeon.forecasting.base import ForecastingHorizon
 from aeon.forecasting.trend import PolynomialTrendForecaster
 from aeon.transformations.base import BaseTransformer
 
 
-# TODO: remove in v0.11.0
-@deprecated(
-    version="0.10.0",
-    reason="Imputer will be removed in version 0.11.0.",
-    category=FutureWarning,
-)
 class Imputer(BaseTransformer):
     """Missing value imputation.
 
@@ -70,19 +63,6 @@ class Imputer(BaseTransformer):
         method="forecaster" is set, otherwise forecaster is ignored.
     random_state : int/float/str, optional
         Value to set random.seed() if method="random", default None
-
-    Examples
-    --------
-    >>> from aeon.transformations.impute import Imputer
-    >>> from aeon.datasets import load_airline
-    >>> from aeon.forecasting.model_selection import temporal_train_test_split
-    >>> y = load_airline()
-    >>> y_train, y_test = temporal_train_test_split(y)
-    >>> transformer = Imputer(method="drift")
-    >>> transformer.fit(y_train)
-    Imputer(...)
-    >>> y_test.iloc[3] = np.nan
-    >>> y_hat = transformer.transform(y_test)
     """
 
     _tags = {

aeon/transformations/_legacy/lag.py

@@ -384,7 +384,7 @@ def _fit(self, X, y=None):
         self: reference to self
         """
         from aeon.transformations._legacy.compose import FeatureUnion, YtoX
-        from aeon.transformations.impute import Imputer
+        from aeon.transformations._legacy.impute import Imputer
 
         impute_method = self.impute_method
         lags = self._lags

aeon/transformations/tests/test_compose.py

@@ -19,13 +19,13 @@
     OptionalPassthrough,
     TransformerPipeline,
 )
+from aeon.transformations._legacy.impute import Imputer
 from aeon.transformations._legacy.subset import _ColumnSelect
 from aeon.transformations._legacy.summarize import SummaryTransformer
 from aeon.transformations._legacy.theta import (
     _ThetaLinesTransformer as ThetaLinesTransformer,
 )
 from aeon.transformations.collection.pad import PaddingTransformer
-from aeon.transformations.impute import Imputer
 
 
 def test_dunder_mul():

docs/api_reference/transformations.rst

@@ -229,18 +229,6 @@ Segmentation
     RandomIntervalSegmenter
     SlidingWindowSegmenter
 
-Missing value imputation
-~~~~~~~~~~~~~~~~~~~~~~~~
-
-.. currentmodule:: aeon.transformations.impute
-
-.. autosummary::
-    :toctree: auto_generated/
-    :template: class.rst
-
-    Imputer
-
-
 Window-based series transforms
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~