我们从Python开源项目中，提取了以下8个代码示例，用于说明如何使用sklearn.base.is_classifier()。
def _grid_search(self, train_X, train_y): if callable(self.inner_cv): # inner_cv = self.inner_cv(train_X, train_y) inner_cv = self.inner_cv.split(train_X, train_y) else: # inner_cv = _check_cv(self.inner_cv, train_X, train_y, # classifier=is_classifier(self.estimator)) inner_cv = _check_cv(self.inner_cv, train_y, classifier=is_classifier( self.estimator)).split(train_X, train_y) master = MPIGridSearchCVMaster(self.param_grid, inner_cv, self.estimator, self.scorer_, self.fit_params) return master.run(train_X, train_y)
def fit(self, X, y): """Fit the model to the training data.""" 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)) cv = _check_cv(self.cv, 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 cross_val_score(estimator, X, y=None, groups=None, scoring=None, cv=None, n_jobs=1, verbose=0, fit_params=None, pre_dispatch='2*n_jobs'): """ Evaluate a score by cross-validation """ if not isinstance(scoring, (list, tuple)): scoring = [scoring] X, y, groups = indexable(X, y, groups) cv = check_cv(cv, y, classifier=is_classifier(estimator)) splits = list(cv.split(X, y, groups)) scorer = [check_scoring(estimator, scoring=s) for s in scoring] # 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) scores = parallel(delayed(_fit_and_score)(clone(estimator), X, y, scorer, train, test, verbose, None, fit_params) for train, test in splits) group_order = [] if hasattr(cv, 'groups'): group_order = [np.array(cv.groups)[test].tolist()[0] for _, test in splits] return np.squeeze(np.array(scores)), group_order
def permutation_test_score(estimator, X, y, groups=None, cv=None, n_permutations=100, n_jobs=1, random_state=0, verbose=0, scoring=None): """ Evaluate the significance of a cross-validated score with permutations, as in test 1 of [Ojala2010]_. A modification of original sklearn's permutation test score function to evaluate p-value outside this function, so that the score can be reused from outside. .. [Ojala2010] Ojala and Garriga. Permutation Tests for Studying Classifier Performance. The Journal of Machine Learning Research (2010) vol. 11 """ X, y, groups = indexable(X, y, groups) cv = check_cv(cv, y, classifier=is_classifier(estimator)) scorer = check_scoring(estimator, scoring=scoring) random_state = check_random_state(random_state) # We clone the estimator to make sure that all the folds are # independent, and that it is pickle-able. permutation_scores = Parallel(n_jobs=n_jobs, verbose=verbose)( delayed(_permutation_test_score)( clone(estimator), X, _shuffle(y, groups, random_state), groups, cv, scorer) for _ in range(n_permutations)) permutation_scores = np.array(permutation_scores) return permutation_scores
def _set_cv(cv, clf=None, X=None, y=None): from sklearn.base import is_classifier # Set the default cross-validation depending on whether clf is classifier # or regressor. if check_version('sklearn', '0.18'): from sklearn.model_selection import (check_cv, StratifiedKFold, KFold) if isinstance(cv, (int, np.int)): XFold = StratifiedKFold if is_classifier(clf) else KFold cv = XFold(n_folds=cv) cv = check_cv(cv=cv, y=y, classifier=is_classifier(clf)) else: from sklearn.cross_validation import (check_cv, StratifiedKFold, KFold) if isinstance(cv, (int, np.int)): if is_classifier(clf): cv = StratifiedKFold(y=y, n_folds=cv) else: cv = KFold(n=len(y), n_folds=cv) cv = check_cv(cv=cv, X=X, y=y, classifier=is_classifier(clf)) # Extract train and test set to retrieve them at predict time if hasattr(cv, 'split'): cv_splits = [(train, test) for train, test in cv.split(X=np.zeros_like(y), y=y)] else: # XXX support sklearn.cross_validation cv cv_splits = [(train, test) for train, test in cv] if not np.all([len(train) for train, _ in cv_splits]): raise ValueError('Some folds do not have any train epochs.') return cv, cv_splits
def test_is_classifier(): svc = SVC() assert_true(is_classifier(svc)) assert_true(is_classifier(GridSearchCV(svc, {'C': [0.1, 1]}))) assert_true(is_classifier(Pipeline([('svc', svc)]))) assert_true(is_classifier(Pipeline([('svc_cv', GridSearchCV(svc, {'C': [0.1, 1]}))])))
def fit(self, X, y): """Actual fitting, performing the search over parameters.""" parameter_iterable = ParameterGrid(self.param_grid) estimator = self.estimator cv = self.cv n_samples = _num_samples(X) X, y = indexable(X, y) if y is not None: if len(y) != n_samples: raise ValueError('Target variable (y) has a different number ' 'of samples (%i) than data (X: %i samples)' % (len(y), n_samples)) cv = check_cv(cv, X, y, classifier=is_classifier(estimator)) if self.verbose > 0: if isinstance(parameter_iterable, Sized): n_candidates = len(parameter_iterable) print("Fitting {0} folds for each of {1} candidates, totalling" " {2} fits".format(len(cv), n_candidates, n_candidates * len(cv))) base_estimator = clone(self.estimator) pre_dispatch = self.pre_dispatch out = Parallel( n_jobs=self.n_jobs, verbose=self.verbose, pre_dispatch=pre_dispatch )(delayed(cv_fit_and_score)(clone(base_estimator), X, y, self.scoring, parameters, cv=cv) for parameters in parameter_iterable) best = sorted(out, key=lambda x: x[0])[-1] self.best_params_ = best[1] self.best_score_ = best[0] 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[1]) 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): """Actual fitting, performing the search over parameters.""" parameter_iterable = ParameterSampler(self.param_distributions, self.n_iter, random_state=self.random_state) estimator = self.estimator cv = self.cv n_samples = _num_samples(X) X, y = indexable(X, y) if y is not None: if len(y) != n_samples: raise ValueError('Target variable (y) has a different number ' 'of samples (%i) than data (X: %i samples)' % (len(y), n_samples)) cv = check_cv(cv, X, y, classifier=is_classifier(estimator)) if self.verbose > 0: if isinstance(parameter_iterable, Sized): n_candidates = len(parameter_iterable) print("Fitting {0} folds for each of {1} candidates, totalling" " {2} fits".format(len(cv), n_candidates, n_candidates * len(cv))) base_estimator = clone(self.estimator) pre_dispatch = self.pre_dispatch out = Parallel( n_jobs=self.n_jobs, verbose=self.verbose, pre_dispatch=pre_dispatch )( delayed(cv_fit_and_score)(clone(base_estimator), X, y, self.scoring, parameters, cv=cv) for parameters in parameter_iterable) best = sorted(out, reverse=True)[0] self.best_params_ = best[1] self.best_score_ = best[0] 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[1]) 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
