File size: 14,572 Bytes
7885a28 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 |
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import warnings
import numpy as np
from ..base import BaseEstimator, RegressorMixin, _fit_context, clone
from ..exceptions import NotFittedError
from ..linear_model import LinearRegression
from ..preprocessing import FunctionTransformer
from ..utils import Bunch, _safe_indexing, check_array
from ..utils._metadata_requests import (
MetadataRouter,
MethodMapping,
_routing_enabled,
process_routing,
)
from ..utils._param_validation import HasMethods
from ..utils._tags import get_tags
from ..utils.validation import check_is_fitted
__all__ = ["TransformedTargetRegressor"]
class TransformedTargetRegressor(RegressorMixin, BaseEstimator):
"""Meta-estimator to regress on a transformed target.
Useful for applying a non-linear transformation to the target `y` in
regression problems. This transformation can be given as a Transformer
such as the :class:`~sklearn.preprocessing.QuantileTransformer` or as a
function and its inverse such as `np.log` and `np.exp`.
The computation during :meth:`fit` is::
regressor.fit(X, func(y))
or::
regressor.fit(X, transformer.transform(y))
The computation during :meth:`predict` is::
inverse_func(regressor.predict(X))
or::
transformer.inverse_transform(regressor.predict(X))
Read more in the :ref:`User Guide <transformed_target_regressor>`.
.. versionadded:: 0.20
Parameters
----------
regressor : object, default=None
Regressor object such as derived from
:class:`~sklearn.base.RegressorMixin`. This regressor will
automatically be cloned each time prior to fitting. If `regressor is
None`, :class:`~sklearn.linear_model.LinearRegression` is created and used.
transformer : object, default=None
Estimator object such as derived from
:class:`~sklearn.base.TransformerMixin`. Cannot be set at the same time
as `func` and `inverse_func`. If `transformer is None` as well as
`func` and `inverse_func`, the transformer will be an identity
transformer. Note that the transformer will be cloned during fitting.
Also, the transformer is restricting `y` to be a numpy array.
func : function, default=None
Function to apply to `y` before passing to :meth:`fit`. Cannot be set
at the same time as `transformer`. If `func is None`, the function used will be
the identity function. If `func` is set, `inverse_func` also needs to be
provided. The function needs to return a 2-dimensional array.
inverse_func : function, default=None
Function to apply to the prediction of the regressor. Cannot be set at
the same time as `transformer`. The inverse function is used to return
predictions to the same space of the original training labels. If
`inverse_func` is set, `func` also needs to be provided. The inverse
function needs to return a 2-dimensional array.
check_inverse : bool, default=True
Whether to check that `transform` followed by `inverse_transform`
or `func` followed by `inverse_func` leads to the original targets.
Attributes
----------
regressor_ : object
Fitted regressor.
transformer_ : object
Transformer used in :meth:`fit` and :meth:`predict`.
n_features_in_ : int
Number of features seen during :term:`fit`. Only defined if the
underlying regressor exposes such an attribute when fit.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
See Also
--------
sklearn.preprocessing.FunctionTransformer : Construct a transformer from an
arbitrary callable.
Notes
-----
Internally, the target `y` is always converted into a 2-dimensional array
to be used by scikit-learn transformers. At the time of prediction, the
output will be reshaped to a have the same number of dimensions as `y`.
Examples
--------
>>> import numpy as np
>>> from sklearn.linear_model import LinearRegression
>>> from sklearn.compose import TransformedTargetRegressor
>>> tt = TransformedTargetRegressor(regressor=LinearRegression(),
... func=np.log, inverse_func=np.exp)
>>> X = np.arange(4).reshape(-1, 1)
>>> y = np.exp(2 * X).ravel()
>>> tt.fit(X, y)
TransformedTargetRegressor(...)
>>> tt.score(X, y)
1.0
>>> tt.regressor_.coef_
array([2.])
For a more detailed example use case refer to
:ref:`sphx_glr_auto_examples_compose_plot_transformed_target.py`.
"""
_parameter_constraints: dict = {
"regressor": [HasMethods(["fit", "predict"]), None],
"transformer": [HasMethods("transform"), None],
"func": [callable, None],
"inverse_func": [callable, None],
"check_inverse": ["boolean"],
}
def __init__(
self,
regressor=None,
*,
transformer=None,
func=None,
inverse_func=None,
check_inverse=True,
):
self.regressor = regressor
self.transformer = transformer
self.func = func
self.inverse_func = inverse_func
self.check_inverse = check_inverse
def _fit_transformer(self, y):
"""Check transformer and fit transformer.
Create the default transformer, fit it and make additional inverse
check on a subset (optional).
"""
if self.transformer is not None and (
self.func is not None or self.inverse_func is not None
):
raise ValueError(
"'transformer' and functions 'func'/'inverse_func' cannot both be set."
)
elif self.transformer is not None:
self.transformer_ = clone(self.transformer)
else:
if (self.func is not None and self.inverse_func is None) or (
self.func is None and self.inverse_func is not None
):
lacking_param, existing_param = (
("func", "inverse_func")
if self.func is None
else ("inverse_func", "func")
)
raise ValueError(
f"When '{existing_param}' is provided, '{lacking_param}' must also"
f" be provided. If {lacking_param} is supposed to be the default,"
" you need to explicitly pass it the identity function."
)
self.transformer_ = FunctionTransformer(
func=self.func,
inverse_func=self.inverse_func,
validate=True,
check_inverse=self.check_inverse,
)
# We are transforming the target here and not the features, so we set the
# output of FunctionTransformer() to be a numpy array (default) and to not
# depend on the global configuration:
self.transformer_.set_output(transform="default")
# XXX: sample_weight is not currently passed to the
# transformer. However, if transformer starts using sample_weight, the
# code should be modified accordingly. At the time to consider the
# sample_prop feature, it is also a good use case to be considered.
self.transformer_.fit(y)
if self.check_inverse:
idx_selected = slice(None, None, max(1, y.shape[0] // 10))
y_sel = _safe_indexing(y, idx_selected)
y_sel_t = self.transformer_.transform(y_sel)
if not np.allclose(y_sel, self.transformer_.inverse_transform(y_sel_t)):
warnings.warn(
(
"The provided functions or transformer are"
" not strictly inverse of each other. If"
" you are sure you want to proceed regardless"
", set 'check_inverse=False'"
),
UserWarning,
)
@_fit_context(
# TransformedTargetRegressor.regressor/transformer are not validated yet.
prefer_skip_nested_validation=False
)
def fit(self, X, y, **fit_params):
"""Fit the model according to the given training data.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Training vector, where `n_samples` is the number of samples and
`n_features` is the number of features.
y : array-like of shape (n_samples,)
Target values.
**fit_params : dict
- If `enable_metadata_routing=False` (default): Parameters directly passed
to the `fit` method of the underlying regressor.
- If `enable_metadata_routing=True`: Parameters safely routed to the `fit`
method of the underlying regressor.
.. versionchanged:: 1.6
See :ref:`Metadata Routing User Guide <metadata_routing>` for
more details.
Returns
-------
self : object
Fitted estimator.
"""
if y is None:
raise ValueError(
f"This {self.__class__.__name__} estimator "
"requires y to be passed, but the target y is None."
)
y = check_array(
y,
input_name="y",
accept_sparse=False,
ensure_all_finite=True,
ensure_2d=False,
dtype="numeric",
allow_nd=True,
)
# store the number of dimension of the target to predict an array of
# similar shape at predict
self._training_dim = y.ndim
# transformers are designed to modify X which is 2d dimensional, we
# need to modify y accordingly.
if y.ndim == 1:
y_2d = y.reshape(-1, 1)
else:
y_2d = y
self._fit_transformer(y_2d)
# transform y and convert back to 1d array if needed
y_trans = self.transformer_.transform(y_2d)
# FIXME: a FunctionTransformer can return a 1D array even when validate
# is set to True. Therefore, we need to check the number of dimension
# first.
if y_trans.ndim == 2 and y_trans.shape[1] == 1:
y_trans = y_trans.squeeze(axis=1)
self.regressor_ = self._get_regressor(get_clone=True)
if _routing_enabled():
routed_params = process_routing(self, "fit", **fit_params)
else:
routed_params = Bunch(regressor=Bunch(fit=fit_params))
self.regressor_.fit(X, y_trans, **routed_params.regressor.fit)
if hasattr(self.regressor_, "feature_names_in_"):
self.feature_names_in_ = self.regressor_.feature_names_in_
return self
def predict(self, X, **predict_params):
"""Predict using the base regressor, applying inverse.
The regressor is used to predict and the `inverse_func` or
`inverse_transform` is applied before returning the prediction.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Samples.
**predict_params : dict of str -> object
- If `enable_metadata_routing=False` (default): Parameters directly passed
to the `predict` method of the underlying regressor.
- If `enable_metadata_routing=True`: Parameters safely routed to the
`predict` method of the underlying regressor.
.. versionchanged:: 1.6
See :ref:`Metadata Routing User Guide <metadata_routing>`
for more details.
Returns
-------
y_hat : ndarray of shape (n_samples,)
Predicted values.
"""
check_is_fitted(self)
if _routing_enabled():
routed_params = process_routing(self, "predict", **predict_params)
else:
routed_params = Bunch(regressor=Bunch(predict=predict_params))
pred = self.regressor_.predict(X, **routed_params.regressor.predict)
if pred.ndim == 1:
pred_trans = self.transformer_.inverse_transform(pred.reshape(-1, 1))
else:
pred_trans = self.transformer_.inverse_transform(pred)
if (
self._training_dim == 1
and pred_trans.ndim == 2
and pred_trans.shape[1] == 1
):
pred_trans = pred_trans.squeeze(axis=1)
return pred_trans
def __sklearn_tags__(self):
regressor = self._get_regressor()
tags = super().__sklearn_tags__()
tags.regressor_tags.poor_score = True
tags.input_tags.sparse = get_tags(regressor).input_tags.sparse
tags.target_tags.multi_output = get_tags(regressor).target_tags.multi_output
return tags
@property
def n_features_in_(self):
"""Number of features seen during :term:`fit`."""
# For consistency with other estimators we raise a AttributeError so
# that hasattr() returns False the estimator isn't fitted.
try:
check_is_fitted(self)
except NotFittedError as nfe:
raise AttributeError(
"{} object has no n_features_in_ attribute.".format(
self.__class__.__name__
)
) from nfe
return self.regressor_.n_features_in_
def get_metadata_routing(self):
"""Get metadata routing of this object.
Please check :ref:`User Guide <metadata_routing>` on how the routing
mechanism works.
.. versionadded:: 1.6
Returns
-------
routing : MetadataRouter
A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
routing information.
"""
router = MetadataRouter(owner=self.__class__.__name__).add(
regressor=self._get_regressor(),
method_mapping=MethodMapping()
.add(caller="fit", callee="fit")
.add(caller="predict", callee="predict"),
)
return router
def _get_regressor(self, get_clone=False):
if self.regressor is None:
return LinearRegression()
return clone(self.regressor) if get_clone else self.regressor
|