def _model_fit_and_score(estimator_str,
X,
y,
scorer,
train,
test,
verbose,
parameters,
fit_params,
return_train_score=False,
return_parameters=False,
return_n_test_samples=False,
return_times=False,
error_score='raise'):
"""
"""
if verbose > 1:
msg = '[CV model=%s]' % estimator_str.upper()
if parameters is not None:
msg += ' %s' % (', '.join('%s=%s' % (k, v)
for k, v in parameters.items()))
LOG.info("%s %s", msg, (89 - len(msg)) * '.')
estimator = _clf_build(estimator_str)
# Adjust length of sample weights
fit_params = fit_params if fit_params is not None else {}
fit_params = dict([(k, _index_param_value(X, v, train))
for k, v in fit_params.items()])
if parameters is not None:
estimator.set_params(**parameters)
start_time = time.time()
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
try:
if y_train is None:
estimator.fit(X_train, **fit_params)
else:
estimator.fit(X_train, y_train, **fit_params)
except Exception as e:
# Note fit time as time until error
fit_time = time.time() - start_time
score_time = 0.0
if error_score == 'raise':
raise
elif isinstance(error_score, numbers.Number):
test_score = error_score
if return_train_score:
train_score = error_score
warnings.warn(
"Classifier fit failed. The score on this train-test"
" partition for these parameters will be set to %f. "
"Details: \n%r" % (error_score, e), FitFailedWarning)
else:
raise ValueError("error_score must be the string 'raise' or a"
" numeric value. (Hint: if using 'raise', please"
" make sure that it has been spelled correctly.)")
else:
fit_time = time.time() - start_time
scorer = check_scoring(estimator, scoring=scorer)
test_score = _score(estimator, X_test, y_test, scorer)
score_time = time.time() - start_time - fit_time
if return_train_score:
train_score = _score(estimator, X_train, y_train, scorer)
if verbose > 2:
msg += ", score=%f" % test_score
if verbose > 1:
total_time = score_time + fit_time
end_msg = "%s, total=%s" % (msg, logger.short_format_time(total_time))
LOG.info(end_msg)
ret = [train_score, test_score] if return_train_score else [test_score]
if return_n_test_samples:
ret.append(_num_samples(X_test))
if return_times:
ret.extend([fit_time, score_time])
if return_parameters:
ret.append((estimator_str, parameters))
return ret
def _fit_and_score(estimator,
X,
y,
scorer,
train,
test,
verbose,
parameters,
fit_params,
return_train_score=False,
return_parameters=False,
return_n_test_samples=False,
return_times=False,
error_score='raise'):
"""Fit estimator and compute scores for a given dataset split.
Parameters
----------
estimator : estimator object implementing 'fit'
The object to use to fit the data.
X : array-like of shape at least 2D
The data to fit.
y : array-like, optional, default: None
The target variable to try to predict in the case of
supervised learning.
scorer : A single callable or dict mapping scorer name to the callable
If it is a single callable, the return value for ``train_scores`` and
``test_scores`` is a single float.
For a dict, it should be one mapping the scorer name to the scorer
callable object / function.
The callable object / fn should have signature
``scorer(estimator, X, y)``.
train : array-like, shape (n_train_samples,)
Indices of training samples.
test : array-like, shape (n_test_samples,)
Indices of test samples.
verbose : integer
The verbosity level.
error_score : 'raise' (default) or numeric
Value to assign to the score if an error occurs in estimator fitting.
If set to 'raise', the error is raised. If a numeric value is given,
FitFailedWarning is raised. This parameter does not affect the refit
step, which will always raise the error.
parameters : dict or None
Parameters to be set on the estimator.
fit_params : dict or None
Parameters that will be passed to ``estimator.fit``.
return_train_score : boolean, optional, default: False
Compute and return score on training set.
return_parameters : boolean, optional, default: False
Return parameters that has been used for the estimator.
return_n_test_samples : boolean, optional, default: False
Whether to return the ``n_test_samples``
return_times : boolean, optional, default: False
Whether to return the fit/score times.
Returns
-------
train_scores : dict of scorer name -> float, optional
Score on training set (for all the scorers),
returned only if `return_train_score` is `True`.
test_scores : dict of scorer name -> float, optional
Score on testing set (for all the scorers).
n_test_samples : int
Number of test samples.
fit_time : float
Time spent for fitting in seconds.
score_time : float
Time spent for scoring in seconds.
parameters : dict or None, optional
The parameters that have been evaluated.
"""
if verbose > 1:
if parameters is None:
msg = ''
else:
msg = '%s' % (', '.join('%s=%s' % (k, v)
for k, v in parameters.items()))
print("[CV] %s %s" % (msg, (64 - len(msg)) * '.'))
# Adjust length of sample weights
fit_params = fit_params if fit_params is not None else {}
fit_params = dict([(k, _index_param_value(X, v, train))
for k, v in fit_params.items()])
if "indices" in inspect.signature(estimator.fit).parameters:
fit_params["indices"] = train # the different part
test_scores = {}
train_scores = {}
if parameters is not None:
estimator.set_params(**parameters)
start_time = time.time()
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
is_multimetric = not callable(scorer)
n_scorers = len(scorer.keys()) if is_multimetric else 1
try:
if y_train is None:
estimator.fit(X_train, **fit_params)
else:
estimator.fit(X_train, y_train, **fit_params)
except Exception as e:
# Note fit time as time until error
fit_time = time.time() - start_time
score_time = 0.0
if error_score == 'raise':
raise
elif isinstance(error_score, numbers.Number):
if is_multimetric:
test_scores = dict(
zip(scorer.keys(), [
error_score,
] * n_scorers))
if return_train_score:
train_scores = dict(
zip(scorer.keys(), [
error_score,
] * n_scorers))
else:
test_scores = error_score
if return_train_score:
train_scores = error_score
warnings.warn(
"Classifier fit failed. The score on this train-test"
" partition for these parameters will be set to %f. "
"Details: \n%r" % (error_score, e), FitFailedWarning)
else:
raise ValueError("error_score must be the string 'raise' or a"
" numeric value. (Hint: if using 'raise', please"
" make sure that it has been spelled correctly.)")
else:
fit_time = time.time() - start_time
# _score will return dict if is_multimetric is True
test_scores = _score(estimator, X_test, y_test, scorer, is_multimetric)
score_time = time.time() - start_time - fit_time
if return_train_score:
train_scores = _score(estimator, X_train, y_train, scorer,
is_multimetric)
if verbose > 2:
if is_multimetric:
for scorer_name, score in test_scores.items():
msg += ", %s=%s" % (scorer_name, score)
else:
msg += ", score=%s" % test_scores
if verbose > 1:
total_time = score_time + fit_time
end_msg = "%s, total=%s" % (msg, logger.short_format_time(total_time))
print("[CV] %s %s" % ((64 - len(end_msg)) * '.', end_msg))
ret = [train_scores, test_scores] if return_train_score else [test_scores]
if return_n_test_samples:
ret.append(_num_samples(X_test))
if return_times:
ret.extend([fit_time, score_time])
if return_parameters:
ret.append(parameters)
return ret
def cross_val_predict_custom(estimator, X, y=None, groups=None, cv=None,
n_jobs=None, verbose=0, fit_params=None,
pre_dispatch='2*n_jobs', method='predict',
# New stuff
sample_weights=None, objective=None):
""" A copy of the sklearn function but allows for different sample weights to be put in for each run. """
X, y, groups = indexable(X, y, groups)
cv = check_cv(cv, y, classifier=is_classifier(estimator))
# 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']
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=np.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)
prediction_blocks = parallel(delayed(_fit_and_predict)(
clone(estimator), X, y, train, test, verbose, fit_params, method, sample_weights, objective)
for train, test in cv.split(X, y, groups))
# Concatenate the predictions
predictions = [pred_block_i for pred_block_i, _ in prediction_blocks]
test_indices = np.concatenate([indices_i
for _, indices_i in prediction_blocks])
if not _check_is_permutation(test_indices, _num_samples(X)):
raise ValueError('cross_val_predict only works for partitions')
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]
def _model_fit_and_score(estimator_str, X, y, scorer, train, test, verbose,
parameters, fit_params, return_train_score=False,
return_parameters=False, return_n_test_samples=False,
return_times=False, error_score='raise'):
"""
"""
if verbose > 1:
msg = '[CV model=%s]' % estimator_str.upper()
if parameters is not None:
msg += ' %s' % (', '.join('%s=%s' % (k, v)
for k, v in parameters.items()))
LOG.info("%s %s", msg, (89 - len(msg)) * '.')
estimator = _clf_build(estimator_str)
# Adjust length of sample weights
fit_params = fit_params if fit_params is not None else {}
fit_params = dict([(k, _index_param_value(X, v, train))
for k, v in fit_params.items()])
if parameters is not None:
estimator.set_params(**parameters)
start_time = time.time()
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
try:
if y_train is None:
estimator.fit(X_train, **fit_params)
else:
estimator.fit(X_train, y_train, **fit_params)
except Exception as e:
# Note fit time as time until error
fit_time = time.time() - start_time
score_time = 0.0
if error_score == 'raise':
raise
elif isinstance(error_score, numbers.Number):
test_score = error_score
if return_train_score:
train_score = error_score
warnings.warn("Classifier fit failed. The score on this train-test"
" partition for these parameters will be set to %f. "
"Details: \n%r" % (error_score, e), FitFailedWarning)
else:
raise ValueError("error_score must be the string 'raise' or a"
" numeric value. (Hint: if using 'raise', please"
" make sure that it has been spelled correctly.)")
else:
fit_time = time.time() - start_time
scorer = check_scoring(estimator, scoring=scorer)
test_score = _score(estimator, X_test, y_test, scorer)
score_time = time.time() - start_time - fit_time
if return_train_score:
train_score = _score(estimator, X_train, y_train, scorer)
if verbose > 2:
msg += ", score=%f" % test_score
if verbose > 1:
total_time = score_time + fit_time
end_msg = "%s, total=%s" % (msg, logger.short_format_time(total_time))
LOG.info(end_msg)
ret = [train_score, test_score] if return_train_score else [test_score]
if return_n_test_samples:
ret.append(_num_samples(X_test))
if return_times:
ret.extend([fit_time, score_time])
if return_parameters:
ret.append((estimator_str, parameters))
return ret
def cross_val_pred2ict(estimator, X, y=None, groups=None, cv=None, n_jobs=1,
verbose=0, fit_params=None, pre_dispatch='2*n_jobs',
method='predict'):
"""Generate cross-validated estimates for each input data point
Read more in the :ref:`User Guide <cross_validation>`.
Parameters
----------
estimator : estimator object implementing 'fit' and 'predict'
The object to use to fit the data.
X : array-like
The data to fit. Can be, for example a list, or an array at least 2d.
y : array-like, optional, default: None
The target variable to try to predict in the case of
supervised learning.
groups : array-like, with shape (n_samples,), optional
Group labels for the samples used while splitting the dataset into
train/test set.
cv : int, cross-validation generator or an iterable, optional
Determines the cross-validation splitting strategy.
Possible inputs for cv are:
- None, to use the default 3-fold cross validation,
- integer, to specify the number of folds in a `(Stratified)KFold`,
- An object to be used as a cross-validation generator.
- An iterable yielding train, test splits.
For integer/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.
n_jobs : integer, optional
The number of CPUs to use to do the computation. -1 means
'all CPUs'.
verbose : integer, optional
The verbosity level.
fit_params : dict, optional
Parameters to pass to the fit method of the estimator.
pre_dispatch : int, or string, optional
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 string, giving an expression as a function of n_jobs,
as in '2*n_jobs'
method : string, optional, default: 'predict'
Invokes the passed method name of the passed estimator.
Returns
-------
predictions : ndarray
This is the result of calling ``method``
Examples
--------
>>> from sklearn import datasets, linear_model
>>> from sklearn.model_selection import cross_val_predict
>>> diabetes = datasets.load_diabetes()
>>> X = diabetes.data[:150]
>>> y = diabetes.target[:150]
>>> lasso = linear_model.Lasso()
>>> y_pred = cross_val_predict(lasso, X, y)
"""
X, y, groups = indexable(X, y, groups)
cv = check_cv(cv, y, classifier=is_classifier(estimator))
cv_iter = list(cv.split(X, y, groups))
# Ensure the estimator has implemented the passed decision function
if not callable(getattr(estimator, method)):
raise AttributeError('{} not implemented in estimator'
.format(method))
# 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)
prediction_blocks = parallel(delayed(_fit_and_predict)(
clone(estimator), X, y, train, test, verbose, fit_params, method)
for train, test in cv_iter)
# Concatenate the predictions
predictions = [pred_block_i for pred_block_i, _ in prediction_blocks]
test_target = [indices_i
for _, indices_i in prediction_blocks]
test_indices = np.concatenate(test_target)
preds = predictions
if not _check_is_permutation(test_indices, _num_samples(X)):
raise ValueError('cross_val_predict only works for partitions')
inv_test_indices = np.empty(len(test_indices), dtype=int)
inv_test_indices[test_indices] = np.arange(len(test_indices))
# Check for sparse predictions
if sp.issparse(predictions[0]):
predictions = sp.vstack(predictions, format=predictions[0].format)
else:
predictions = np.concatenate(predictions)
target = [(y[tt]) for tt in test_target]
return preds, target