in econml/sklearn_extensions/model_selection.py [0:0]
def _cross_val_predict(estimator, X, y=None, *, groups=None, cv=None,
n_jobs=None, verbose=0, fit_params=None,
pre_dispatch='2*n_jobs', method='predict', safe=True):
"""This is a fork from :meth:`~sklearn.model_selection.cross_val_predict` to allow for
non-safe cloning of the models for each fold.
Parameters
----------
estimator : estimator object implementing 'fit' and 'predict'
The object to use to fit the data.
X : array-like of shape (n_samples, n_features)
The data to fit. Can be, for example a list, or an array at least 2d.
y : array-like of shape (n_samples,) or (n_samples, n_outputs), \
default=None
The target variable to try to predict in the case of
supervised learning.
groups : array-like of shape (n_samples,), default=None
Group labels for the samples used while splitting the dataset into
train/test set. Only used in conjunction with a "Group" :term:`cv`
instance (e.g., :class:`GroupKFold`).
cv : int, cross-validation generator or an iterable, default=None
Determines the cross-validation splitting strategy.
Possible inputs for cv are:
- None, to use the default 5-fold cross validation,
- int, to specify the number of folds in a `(Stratified)KFold`,
- CV splitter,
- An iterable yielding (train, test) splits as arrays of indices.
For int/None inputs, if the estimator is a classifier and ``y`` is
either binary or multiclass, :class:`StratifiedKFold` is used. In all
other cases, :class:`KFold` is used.
Refer :ref:`User Guide <cross_validation>` for the various
cross-validation strategies that can be used here.
.. versionchanged:: 0.22
``cv`` default value if None changed from 3-fold to 5-fold.
n_jobs : int, default=None
The number of CPUs to use to do the computation.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See :term:`Glossary <n_jobs>`
for more details.
verbose : int, default=0
The verbosity level.
fit_params : dict, defualt=None
Parameters to pass to the fit method of the estimator.
pre_dispatch : int or str, default='2*n_jobs'
Controls the number of jobs that get dispatched during parallel
execution. Reducing this number can be useful to avoid an
explosion of memory consumption when more jobs get dispatched
than CPUs can process. This parameter can be:
- None, in which case all the jobs are immediately
created and spawned. Use this for lightweight and
fast-running jobs, to avoid delays due to on-demand
spawning of the jobs
- An int, giving the exact number of total jobs that are
spawned
- A str, giving an expression as a function of n_jobs,
as in '2*n_jobs'
method : str, default='predict'
Invokes the passed method name of the passed estimator. For
method='predict_proba', the columns correspond to the classes
in sorted order.
safe : bool, default=True
Whether to clone with safe option.
Returns
-------
predictions : ndarray
This is the result of calling ``method``
"""
X, y, groups = indexable(X, y, groups)
cv = check_cv(cv, y, classifier=is_classifier(estimator))
splits = list(cv.split(X, y, groups))
test_indices = np.concatenate([test for _, test in splits])
if not _check_is_permutation(test_indices, _num_samples(X)):
raise ValueError('cross_val_predict only works for partitions')
# If classification methods produce multiple columns of output,
# we need to manually encode classes to ensure consistent column ordering.
encode = method in ['decision_function', 'predict_proba',
'predict_log_proba'] and y is not None
if encode:
y = np.asarray(y)
if y.ndim == 1:
le = LabelEncoder()
y = le.fit_transform(y)
elif y.ndim == 2:
y_enc = np.zeros_like(y, dtype=int)
for i_label in range(y.shape[1]):
y_enc[:, i_label] = LabelEncoder().fit_transform(y[:, i_label])
y = y_enc
# We clone the estimator to make sure that all the folds are
# independent, and that it is pickle-able.
parallel = Parallel(n_jobs=n_jobs, verbose=verbose,
pre_dispatch=pre_dispatch)
predictions = parallel(delayed(_fit_and_predict)(
clone(estimator, safe=safe), X, y, train, test, verbose, fit_params, method)
for train, test in splits)
from pkg_resources import parse_version
if parse_version(sklearn.__version__) < parse_version("0.24.0"):
# Prior to 0.24.0, this private scikit-learn method returned a tuple of two values
predictions = [p[0] for p in predictions]
inv_test_indices = np.empty(len(test_indices), dtype=int)
inv_test_indices[test_indices] = np.arange(len(test_indices))
if sp.issparse(predictions[0]):
predictions = sp.vstack(predictions, format=predictions[0].format)
elif encode and isinstance(predictions[0], list):
# `predictions` is a list of method outputs from each fold.
# If each of those is also a list, then treat this as a
# multioutput-multiclass task. We need to separately concatenate
# the method outputs for each label into an `n_labels` long list.
n_labels = y.shape[1]
concat_pred = []
for i_label in range(n_labels):
label_preds = np.concatenate([p[i_label] for p in predictions])
concat_pred.append(label_preds)
predictions = concat_pred
else:
predictions = np.concatenate(predictions)
if isinstance(predictions, list):
return [p[inv_test_indices] for p in predictions]
else:
return predictions[inv_test_indices]