def _fit(self, X, y, parameter_iterable):
"""Actual fitting, performing the search over parameters."""
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
X, y = indexable(X, y)
cv = check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
base_estimator = clone(self.estimator)
best = best_parameters(base_estimator, cv, X, y, parameter_iterable,
self.scorer_, self.fit_params, self.iid)
best = best.compute()
self.best_params_ = best.parameters
self.best_score_ = best.mean_validation_score
if isinstance(base_estimator, Pipeline):
base_estimator = base_estimator.to_sklearn().compute()
if self.refit:
# fit the best estimator using the entire dataset
# clone first to work around broken estimators
best_estimator = base_estimator.set_params(**best.parameters)
if y is not None:
self.best_estimator_ = best_estimator.fit(
X, y, **self.fit_params)
else:
self.best_estimator_ = best_estimator.fit(X, **self.fit_params)
return self
def _fit(self, X, y, parameter_iterable):
"""Actual fitting, performing the search over parameters."""
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
X, y = indexable(X, y)
cv = check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
base_estimator = clone(self.estimator)
best = best_parameters(base_estimator, cv, X, y, parameter_iterable,
self.scorer_, self.fit_params, self.iid)
best = best.compute()
self.best_params_ = best.parameters
self.best_score_ = best.mean_validation_score
if isinstance(base_estimator, Pipeline):
base_estimator = base_estimator.to_sklearn().compute()
if self.refit:
# fit the best estimator using the entire dataset
# clone first to work around broken estimators
best_estimator = base_estimator.set_params(**best.parameters)
if y is not None:
self.best_estimator_ = best_estimator.fit(X, y, **self.fit_params)
else:
self.best_estimator_ = best_estimator.fit(X, **self.fit_params)
return self
def fit(self, X, y):
X, y = check_X_y(X,
y,
force_all_finite=False,
multi_output=self.multi_output)
_check_param_grid(self.param_grid)
cv = _check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
if comm_rank == 0:
self._fit_master(X, y, cv)
else:
self._fit_slave()
return self
def fit(self, X, y):
if master:
LOG.info("comm_size:" + str(comm_size))
X, y = check_X_y(X, y, force_all_finite=False, multi_output=self.multi_output, accept_sparse='csr')
_check_param_grid(self.param_grid)
cv = check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
if master:
LOG.info("cv length:" + str(len(cv)))
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
if master:
self._fit_master(X, y, cv)
else:
self._fit_slave()
return self
def dynamic_cross_val_score(estimator, fv, esa_feature_list, unigram_feature_list, dynamic_X, y=None, scoring=None, cv=None,
verbose=0, fit_params=None):
print "dynamic cross val mit %s" % esa_feature_list + unigram_feature_list
vec = DictVectorizer()
tfidf = TfidfTransformer()
X = vec.fit_transform(fv).toarray()
# X= tfidf.fit_transform(X).toarray()
X, y = cross_validation.indexable(X, y)
cv = cross_validation.check_cv(cv, X, y, classifier=cross_validation.is_classifier(estimator))
scorer = cross_validation.check_scoring(estimator, scoring=scoring)
scores = []
cross_val_step = 0
for train, test in cv:
fv_copy = copy.deepcopy(fv)
#baue X in jedem Schritt neu
for i in range(0,len(fv)): #jedes i steht für einen featuredict
feature_dict = fv_copy[i]
dynamic_vec = dynamic_X[cross_val_step] #zeigt auf esa_vec
for feature in esa_feature_list:
feature_dict.update(dynamic_vec[find_index_for_dynamic_feature(feature)][i]) #das i-te feature-dict mit esa-feature updaten
for feature in unigram_feature_list:
feature_dict.update(dynamic_vec[find_index_for_dynamic_feature(feature)][i]) #das i-te feature-dict mit esa-feature updaten
X = vec.fit_transform(fv_copy).toarray()
# X = tfidf.fit_transform(X).toarray()
scores.append(cross_validation._fit_and_score(cross_validation.clone(estimator), X, y, scorer,
train, test, verbose, None, fit_params))
cross_val_step += 1
return np.array(scores)[:, 0]
def _fit(self, X, y, parameter_iterable):
"""Actual fitting, performing the search over parameters."""
cv = self.cv
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
X, y = indexable(X, y)
cv = check_cv(cv, X, y, classifier=is_classifier(self.estimator))
base_estimator = clone(self.estimator)
out = [_fit_and_score(clone(base_estimator), X, y, self.scorer_, train,
test, self.verbose, parameters, self.fit_params,
return_parameters=True,
error_score=self.error_score)
for parameters in parameter_iterable
for train, test in cv]
self._dask_value = value(out)
out, = compute(value(out))
n_fits = len(out)
n_folds = len(cv)
scores = list()
grid_scores = list()
for grid_start in range(0, n_fits, n_folds):
n_test_samples = 0
score = 0
all_scores = []
for this_score, this_n_test_samples, _, parameters in \
out[grid_start:grid_start + n_folds]:
all_scores.append(this_score)
if self.iid:
this_score *= this_n_test_samples
n_test_samples += this_n_test_samples
score += this_score
if self.iid:
score /= float(n_test_samples)
else:
score /= float(n_folds)
scores.append((score, parameters))
# TODO: shall we also store the test_fold_sizes?
grid_scores.append(_CVScoreTuple(
parameters,
score,
np.array(all_scores)))
# Store the computed scores
self.grid_scores_ = grid_scores
# Find the best parameters by comparing on the mean validation score:
# note that `sorted` is deterministic in the way it breaks ties
best = sorted(grid_scores, key=lambda x: x.mean_validation_score,
reverse=True)[0]
self.best_params_ = best.parameters
self.best_score_ = best.mean_validation_score
if self.refit:
# fit the best estimator using the entire dataset
# clone first to work around broken estimators
best_estimator = clone(base_estimator).set_params(
**best.parameters)
if y is not None:
best_estimator.fit(X, y, **self.fit_params)
else:
best_estimator.fit(X, **self.fit_params)
self.best_estimator_ = best_estimator
return self
def fit(self, X, y, fit_params=None, predict_params=None, X_test=None, y_test=None):
"""Do nested cross-validation.
If ``X_test`` and ``y_test`` are not provided, nested cross-validation using
``X`` and ``y`' is performed, i.e., data is first split into *K* folds, where
*K-1* folds are used for training and hyper-parameter selection and the
remaining fold for testing. The training portion is again split into *T* folds
to perform a grid-search over hyper-parameters. The parameters that achieved the
best average performance across the *T* inner cross-validation folds are selected.
Using these parameters, a model is trained on the entire training data and applied
to the *K*-th testing fold.
If ``X_test`` and ``y_test`` are provided, a regular cross-validation is performed on
``X`` and ``y`` to determine hyper-parameters as for the inner cross-validation above.
Using the best performing parameters, a model is trained on all of ``X`` and ``y`` and
applied to ``X_test`` and ``y_test`` for testing.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Feature matrix.
y : structured array, shape = [n_samples]
A structured array containing the binary event indicator
as first field, and time of event or time of censoring as
second field.
fit_params : dict
Additional arguments passed to the fit method.
predict_params : dict
Additional arguments passed to the predict method.
X_test : array-like, shape = [n_test_samples, n_features]
Hold-out data to perform testing on.
y_test : array-like or sequence, shape = [n_test_samples]
Target values of hold-out test data.
Returns
-------
self
"""
if y.dtype.names is None:
X, y = check_X_y(X, y)
else:
X, event, time = check_arrays_survival(X, y, force_all_finite=False)
y = numpy.fromiter(zip(event, time), dtype=[('event', numpy.bool), ('time', numpy.float64)])
if X_test is not None:
X_test, event_test, time_test = check_arrays_survival(X_test, y_test, force_all_finite=False)
y_test = numpy.fromiter(zip(event_test, time_test), dtype=[('event', numpy.bool), ('time', numpy.float64)])
cv = _check_cv(self.cv, X, y, classifier=is_classifier(self.estimator))
self.scorer_ = check_scoring(self.estimator, scoring=self.scoring)
self._dview, self._lview = self._init_cluster()
if X_test is None:
self._fit(X, y, cv, fit_params, predict_params)
else:
self._fit_holdout(X, y, fit_params, predict_params, X_test, y_test)
del self._dview
del self._lview
return self
