from __future__ import print_function import types import warnings import sys import traceback import pickle from copy import deepcopy import numpy as np from scipy import sparse from scipy.stats import rankdata import struct from sklearn.externals.six.moves import zip from sklearn.externals.joblib import hash, Memory from sklearn.utils.testing import assert_raises from sklearn.utils.testing import assert_raises_regex from sklearn.utils.testing import assert_raise_message from sklearn.utils.testing import assert_equal from sklearn.utils.testing import assert_not_equal from sklearn.utils.testing import assert_true from sklearn.utils.testing import assert_false from sklearn.utils.testing import assert_in from sklearn.utils.testing import assert_array_equal from sklearn.utils.testing import assert_allclose from sklearn.utils.testing import assert_allclose_dense_sparse from sklearn.utils.testing import assert_warns_message from sklearn.utils.testing import META_ESTIMATORS from sklearn.utils.testing import set_random_state from sklearn.utils.testing import assert_greater from sklearn.utils.testing import assert_greater_equal from sklearn.utils.testing import SkipTest from sklearn.utils.testing import ignore_warnings from sklearn.utils.testing import assert_dict_equal from sklearn.discriminant_analysis import LinearDiscriminantAnalysis from sklearn.base import (clone, TransformerMixin, ClusterMixin, BaseEstimator, is_classifier, is_regressor) from sklearn.metrics import accuracy_score, adjusted_rand_score, f1_score from sklearn.random_projection import BaseRandomProjection from sklearn.feature_selection import SelectKBest from sklearn.svm.base import BaseLibSVM from sklearn.linear_model.stochastic_gradient import BaseSGD from sklearn.pipeline import make_pipeline from sklearn.exceptions import ConvergenceWarning from sklearn.exceptions import DataConversionWarning from sklearn.exceptions import SkipTestWarning from sklearn.model_selection import train_test_split from sklearn.utils import shuffle from sklearn.utils.fixes import signature from sklearn.utils.validation import has_fit_parameter, _num_samples from sklearn.preprocessing import StandardScaler from sklearn.datasets import load_iris, load_boston, make_blobs BOSTON = None CROSS_DECOMPOSITION = ['PLSCanonical', 'PLSRegression', 'CCA', 'PLSSVD'] MULTI_OUTPUT = ['CCA', 'DecisionTreeRegressor', 'ElasticNet', 'ExtraTreeRegressor', 'ExtraTreesRegressor', 'GaussianProcess', 'GaussianProcessRegressor', 'KNeighborsRegressor', 'KernelRidge', 'Lars', 'Lasso', 'LassoLars', 'LinearRegression', 'MultiTaskElasticNet', 'MultiTaskElasticNetCV', 'MultiTaskLasso', 'MultiTaskLassoCV', 'OrthogonalMatchingPursuit', 'PLSCanonical', 'PLSRegression', 'RANSACRegressor', 'RadiusNeighborsRegressor', 'RandomForestRegressor', 'Ridge', 'RidgeCV'] def _yield_non_meta_checks(name, estimator): yield check_estimators_dtypes yield check_fit_score_takes_y yield check_dtype_object yield check_sample_weights_pandas_series yield check_sample_weights_list yield check_estimators_fit_returns_self # Check that all estimator yield informative messages when # trained on empty datasets yield check_estimators_empty_data_messages if name not in CROSS_DECOMPOSITION + ['SpectralEmbedding']: # SpectralEmbedding is non-deterministic, # see issue #4236 # cross-decomposition's "transform" returns X and Y yield check_pipeline_consistency if name not in ['Imputer']: # Test that all estimators check their input for NaN's and infs yield check_estimators_nan_inf if name not in ['GaussianProcess']: # FIXME! # in particular GaussianProcess! yield check_estimators_overwrite_params if hasattr(estimator, 'sparsify'): yield check_sparsify_coefficients yield check_estimator_sparse_data # Test that estimators can be pickled, and once pickled # give the same answer as before. yield check_estimators_pickle def _yield_classifier_checks(name, classifier): # test classifiers can handle non-array data yield check_classifier_data_not_an_array # test classifiers trained on a single label always return this label yield check_classifiers_one_label yield check_classifiers_classes yield check_estimators_partial_fit_n_features # basic consistency testing yield check_classifiers_train yield check_classifiers_regression_target if (name not in ["MultinomialNB", "LabelPropagation", "LabelSpreading"] and # TODO some complication with -1 label name not in ["DecisionTreeClassifier", "ExtraTreeClassifier"]): # We don't raise a warning in these classifiers, as # the column y interface is used by the forests. yield check_supervised_y_2d # test if NotFittedError is raised yield check_estimators_unfitted if 'class_weight' in classifier.get_params().keys(): yield check_class_weight_classifiers yield check_non_transformer_estimators_n_iter # test if predict_proba is a monotonic transformation of decision_function yield check_decision_proba_consistency @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_supervised_y_no_nan(name, estimator_orig): # Checks that the Estimator targets are not NaN. estimator = clone(estimator_orig) rng = np.random.RandomState(888) X = rng.randn(10, 5) y = np.ones(10) * np.inf y = multioutput_estimator_convert_y_2d(estimator, y) errmsg = "Input contains NaN, infinity or a value too large for " \ "dtype('float64')." try: estimator.fit(X, y) except ValueError as e: if str(e) != errmsg: raise ValueError("Estimator {0} raised error as expected, but " "does not match expected error message" .format(name)) else: raise ValueError("Estimator {0} should have raised error on fitting " "array y with NaN value.".format(name)) def _yield_regressor_checks(name, regressor): # TODO: test with intercept # TODO: test with multiple responses # basic testing yield check_regressors_train yield check_regressor_data_not_an_array yield check_estimators_partial_fit_n_features yield check_regressors_no_decision_function yield check_supervised_y_2d yield check_supervised_y_no_nan if name != 'CCA': # check that the regressor handles int input yield check_regressors_int if name != "GaussianProcessRegressor": # Test if NotFittedError is raised yield check_estimators_unfitted yield check_non_transformer_estimators_n_iter def _yield_transformer_checks(name, transformer): # All transformers should either deal with sparse data or raise an # exception with type TypeError and an intelligible error message if name not in ['AdditiveChi2Sampler', 'Binarizer', 'Normalizer', 'PLSCanonical', 'PLSRegression', 'CCA', 'PLSSVD']: yield check_transformer_data_not_an_array # these don't actually fit the data, so don't raise errors if name not in ['AdditiveChi2Sampler', 'Binarizer', 'FunctionTransformer', 'Normalizer']: # basic tests yield check_transformer_general yield check_transformers_unfitted # Dependent on external solvers and hence accessing the iter # param is non-trivial. external_solver = ['Isomap', 'KernelPCA', 'LocallyLinearEmbedding', 'RandomizedLasso', 'LogisticRegressionCV'] if name not in external_solver: yield check_transformer_n_iter def _yield_clustering_checks(name, clusterer): yield check_clusterer_compute_labels_predict if name not in ('WardAgglomeration', "FeatureAgglomeration"): # this is clustering on the features # let's not test that here. yield check_clustering yield check_estimators_partial_fit_n_features yield check_non_transformer_estimators_n_iter def _yield_all_checks(name, estimator): for check in _yield_non_meta_checks(name, estimator): yield check if is_classifier(estimator): for check in _yield_classifier_checks(name, estimator): yield check if is_regressor(estimator): for check in _yield_regressor_checks(name, estimator): yield check if isinstance(estimator, TransformerMixin): for check in _yield_transformer_checks(name, estimator): yield check if isinstance(estimator, ClusterMixin): for check in _yield_clustering_checks(name, estimator): yield check yield check_fit2d_predict1d yield check_fit2d_1sample yield check_fit2d_1feature yield check_fit1d_1feature yield check_fit1d_1sample yield check_get_params_invariance yield check_dict_unchanged yield check_dont_overwrite_parameters def check_estimator(Estimator): """Check if estimator adheres to scikit-learn conventions. This estimator will run an extensive test-suite for input validation, shapes, etc. Additional tests for classifiers, regressors, clustering or transformers will be run if the Estimator class inherits from the corresponding mixin from sklearn.base. This test can be applied to classes or instances. Classes currently have some additional tests that related to construction, while passing instances allows the testing of multiple options. Parameters ---------- estimator : estimator object or class Estimator to check. Estimator is a class object or instance. """ if isinstance(Estimator, type): # got a class name = Estimator.__name__ check_parameters_default_constructible(name, Estimator) check_no_fit_attributes_set_in_init(name, Estimator) estimator = Estimator() else: # got an instance estimator = Estimator name = type(estimator).__name__ for check in _yield_all_checks(name, estimator): try: check(name, estimator) except SkipTest as message: # the only SkipTest thrown currently results from not # being able to import pandas. warnings.warn(message, SkipTestWarning) def _boston_subset(n_samples=200): global BOSTON if BOSTON is None: boston = load_boston() X, y = boston.data, boston.target X, y = shuffle(X, y, random_state=0) X, y = X[:n_samples], y[:n_samples] X = StandardScaler().fit_transform(X) BOSTON = X, y return BOSTON def set_checking_parameters(estimator): # set parameters to speed up some estimators and # avoid deprecated behaviour params = estimator.get_params() if ("n_iter" in params and estimator.__class__.__name__ != "TSNE" and not isinstance(estimator, BaseSGD)): estimator.set_params(n_iter=5) if "max_iter" in params: warnings.simplefilter("ignore", ConvergenceWarning) if estimator.max_iter is not None: estimator.set_params(max_iter=min(5, estimator.max_iter)) # LinearSVR, LinearSVC if estimator.__class__.__name__ in ['LinearSVR', 'LinearSVC']: estimator.set_params(max_iter=20) # NMF if estimator.__class__.__name__ == 'NMF': estimator.set_params(max_iter=100) # MLP if estimator.__class__.__name__ in ['MLPClassifier', 'MLPRegressor']: estimator.set_params(max_iter=100) if "n_resampling" in params: # randomized lasso estimator.set_params(n_resampling=5) if "n_estimators" in params: # especially gradient boosting with default 100 estimator.set_params(n_estimators=min(5, estimator.n_estimators)) if "max_trials" in params: # RANSAC estimator.set_params(max_trials=10) if "n_init" in params: # K-Means estimator.set_params(n_init=2) if "decision_function_shape" in params: # SVC estimator.set_params(decision_function_shape='ovo') if estimator.__class__.__name__ == "SelectFdr": # be tolerant of noisy datasets (not actually speed) estimator.set_params(alpha=.5) if estimator.__class__.__name__ == "TheilSenRegressor": estimator.max_subpopulation = 100 if isinstance(estimator, BaseRandomProjection): # Due to the jl lemma and often very few samples, the number # of components of the random matrix projection will be probably # greater than the number of features. # So we impose a smaller number (avoid "auto" mode) estimator.set_params(n_components=2) if isinstance(estimator, SelectKBest): # SelectKBest has a default of k=10 # which is more feature than we have in most case. estimator.set_params(k=1) class NotAnArray(object): " An object that is convertable to an array" def __init__(self, data): self.data = data def __array__(self, dtype=None): return self.data def _is_32bit(): """Detect if process is 32bit Python.""" return struct.calcsize('P') * 8 == 32 def check_estimator_sparse_data(name, estimator_orig): rng = np.random.RandomState(0) X = rng.rand(40, 10) X[X < .8] = 0 X_csr = sparse.csr_matrix(X) y = (4 * rng.rand(40)).astype(np.int) # catch deprecation warnings with ignore_warnings(category=DeprecationWarning): estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) for sparse_format in ['csr', 'csc', 'dok', 'lil', 'coo', 'dia', 'bsr']: X = X_csr.asformat(sparse_format) # catch deprecation warnings with ignore_warnings(category=(DeprecationWarning, FutureWarning)): if name in ['Scaler', 'StandardScaler']: estimator = clone(estimator).set_params(with_mean=False) else: estimator = clone(estimator) # fit and predict try: with ignore_warnings(category=(DeprecationWarning, FutureWarning)): estimator.fit(X, y) if hasattr(estimator, "predict"): pred = estimator.predict(X) assert_equal(pred.shape, (X.shape[0],)) if hasattr(estimator, 'predict_proba'): probs = estimator.predict_proba(X) assert_equal(probs.shape, (X.shape[0], 4)) except TypeError as e: if 'sparse' not in repr(e): print("Estimator %s doesn't seem to fail gracefully on " "sparse data: error message state explicitly that " "sparse input is not supported if this is not the case." % name) raise except Exception: print("Estimator %s doesn't seem to fail gracefully on " "sparse data: it should raise a TypeError if sparse input " "is explicitly not supported." % name) raise @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_sample_weights_pandas_series(name, estimator_orig): # check that estimators will accept a 'sample_weight' parameter of # type pandas.Series in the 'fit' function. estimator = clone(estimator_orig) if has_fit_parameter(estimator, "sample_weight"): try: import pandas as pd X = pd.DataFrame([[1, 1], [1, 2], [1, 3], [2, 1], [2, 2], [2, 3]]) y = pd.Series([1, 1, 1, 2, 2, 2]) weights = pd.Series([1] * 6) try: estimator.fit(X, y, sample_weight=weights) except ValueError: raise ValueError("Estimator {0} raises error if " "'sample_weight' parameter is of " "type pandas.Series".format(name)) except ImportError: raise SkipTest("pandas is not installed: not testing for " "input of type pandas.Series to class weight.") @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_sample_weights_list(name, estimator_orig): # check that estimators will accept a 'sample_weight' parameter of # type list in the 'fit' function. if has_fit_parameter(estimator_orig, "sample_weight"): estimator = clone(estimator_orig) rnd = np.random.RandomState(0) X = rnd.uniform(size=(10, 3)) y = np.arange(10) % 3 y = multioutput_estimator_convert_y_2d(estimator, y) sample_weight = [3] * 10 # Test that estimators don't raise any exception estimator.fit(X, y, sample_weight=sample_weight) @ignore_warnings(category=(DeprecationWarning, FutureWarning, UserWarning)) def check_dtype_object(name, estimator_orig): # check that estimators treat dtype object as numeric if possible rng = np.random.RandomState(0) X = rng.rand(40, 10).astype(object) y = (X[:, 0] * 4).astype(np.int) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) estimator.fit(X, y) if hasattr(estimator, "predict"): estimator.predict(X) if hasattr(estimator, "transform"): estimator.transform(X) try: estimator.fit(X, y.astype(object)) except Exception as e: if "Unknown label type" not in str(e): raise X[0, 0] = {'foo': 'bar'} msg = "argument must be a string or a number" assert_raises_regex(TypeError, msg, estimator.fit, X, y) @ignore_warnings def check_dict_unchanged(name, estimator_orig): # this estimator raises # ValueError: Found array with 0 feature(s) (shape=(23, 0)) # while a minimum of 1 is required. # error if name in ['SpectralCoclustering']: return rnd = np.random.RandomState(0) if name in ['RANSACRegressor']: X = 3 * rnd.uniform(size=(20, 3)) else: X = 2 * rnd.uniform(size=(20, 3)) y = X[:, 0].astype(np.int) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 if hasattr(estimator, "n_best"): estimator.n_best = 1 set_random_state(estimator, 1) estimator.fit(X, y) for method in ["predict", "transform", "decision_function", "predict_proba"]: if hasattr(estimator, method): dict_before = estimator.__dict__.copy() getattr(estimator, method)(X) assert_dict_equal(estimator.__dict__, dict_before, 'Estimator changes __dict__ during %s' % method) def is_public_parameter(attr): return not (attr.startswith('_') or attr.endswith('_')) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_dont_overwrite_parameters(name, estimator_orig): # check that fit method only changes or sets private attributes if hasattr(estimator_orig.__init__, "deprecated_original"): # to not check deprecated classes return estimator = clone(estimator_orig) rnd = np.random.RandomState(0) X = 3 * rnd.uniform(size=(20, 3)) y = X[:, 0].astype(np.int) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 set_random_state(estimator, 1) dict_before_fit = estimator.__dict__.copy() estimator.fit(X, y) dict_after_fit = estimator.__dict__ public_keys_after_fit = [key for key in dict_after_fit.keys() if is_public_parameter(key)] attrs_added_by_fit = [key for key in public_keys_after_fit if key not in dict_before_fit.keys()] # check that fit doesn't add any public attribute assert_true(not attrs_added_by_fit, ('Estimator adds public attribute(s) during' ' the fit method.' ' Estimators are only allowed to add private attributes' ' either started with _ or ended' ' with _ but %s added' % ', '.join(attrs_added_by_fit))) # check that fit doesn't change any public attribute attrs_changed_by_fit = [key for key in public_keys_after_fit if (dict_before_fit[key] is not dict_after_fit[key])] assert_true(not attrs_changed_by_fit, ('Estimator changes public attribute(s) during' ' the fit method. Estimators are only allowed' ' to change attributes started' ' or ended with _, but' ' %s changed' % ', '.join(attrs_changed_by_fit))) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_fit2d_predict1d(name, estimator_orig): # check by fitting a 2d array and predicting with a 1d array rnd = np.random.RandomState(0) X = 3 * rnd.uniform(size=(20, 3)) y = X[:, 0].astype(np.int) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 set_random_state(estimator, 1) estimator.fit(X, y) for method in ["predict", "transform", "decision_function", "predict_proba"]: if hasattr(estimator, method): assert_raise_message(ValueError, "Reshape your data", getattr(estimator, method), X[0]) @ignore_warnings def check_fit2d_1sample(name, estimator_orig): # check by fitting a 2d array and prediting with a 1d array rnd = np.random.RandomState(0) X = 3 * rnd.uniform(size=(1, 10)) y = X[:, 0].astype(np.int) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 set_random_state(estimator, 1) try: estimator.fit(X, y) except ValueError: pass @ignore_warnings def check_fit2d_1feature(name, estimator_orig): # check by fitting a 2d array and prediting with a 1d array rnd = np.random.RandomState(0) X = 3 * rnd.uniform(size=(10, 1)) y = X[:, 0].astype(np.int) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 set_random_state(estimator, 1) try: estimator.fit(X, y) except ValueError: pass @ignore_warnings def check_fit1d_1feature(name, estimator_orig): # check fitting 1d array with 1 feature rnd = np.random.RandomState(0) X = 3 * rnd.uniform(size=(20)) y = X.astype(np.int) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 set_random_state(estimator, 1) try: estimator.fit(X, y) except ValueError: pass @ignore_warnings def check_fit1d_1sample(name, estimator_orig): # check fitting 1d array with 1 feature rnd = np.random.RandomState(0) X = 3 * rnd.uniform(size=(20)) y = np.array([1]) estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) if hasattr(estimator, "n_components"): estimator.n_components = 1 if hasattr(estimator, "n_clusters"): estimator.n_clusters = 1 set_random_state(estimator, 1) try: estimator.fit(X, y) except ValueError: pass @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_transformer_general(name, transformer): X, y = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]], random_state=0, n_features=2, cluster_std=0.1) X = StandardScaler().fit_transform(X) X -= X.min() _check_transformer(name, transformer, X, y) _check_transformer(name, transformer, X.tolist(), y.tolist()) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_transformer_data_not_an_array(name, transformer): X, y = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]], random_state=0, n_features=2, cluster_std=0.1) X = StandardScaler().fit_transform(X) # We need to make sure that we have non negative data, for things # like NMF X -= X.min() - .1 this_X = NotAnArray(X) this_y = NotAnArray(np.asarray(y)) _check_transformer(name, transformer, this_X, this_y) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_transformers_unfitted(name, transformer): X, y = _boston_subset() transformer = clone(transformer) assert_raises((AttributeError, ValueError), transformer.transform, X) def _check_transformer(name, transformer_orig, X, y): if name in ('CCA', 'LocallyLinearEmbedding', 'KernelPCA') and _is_32bit(): # Those transformers yield non-deterministic output when executed on # a 32bit Python. The same transformers are stable on 64bit Python. # FIXME: try to isolate a minimalistic reproduction case only depending # on numpy & scipy and/or maybe generate a test dataset that does not # cause such unstable behaviors. msg = name + ' is non deterministic on 32bit Python' raise SkipTest(msg) n_samples, n_features = np.asarray(X).shape transformer = clone(transformer_orig) set_random_state(transformer) # fit if name in CROSS_DECOMPOSITION: y_ = np.c_[y, y] y_[::2, 1] *= 2 else: y_ = y transformer.fit(X, y_) # fit_transform method should work on non fitted estimator transformer_clone = clone(transformer) X_pred = transformer_clone.fit_transform(X, y=y_) if isinstance(X_pred, tuple): for x_pred in X_pred: assert_equal(x_pred.shape[0], n_samples) else: # check for consistent n_samples assert_equal(X_pred.shape[0], n_samples) if hasattr(transformer, 'transform'): if name in CROSS_DECOMPOSITION: X_pred2 = transformer.transform(X, y_) X_pred3 = transformer.fit_transform(X, y=y_) else: X_pred2 = transformer.transform(X) X_pred3 = transformer.fit_transform(X, y=y_) if isinstance(X_pred, tuple) and isinstance(X_pred2, tuple): for x_pred, x_pred2, x_pred3 in zip(X_pred, X_pred2, X_pred3): assert_allclose_dense_sparse( x_pred, x_pred2, atol=1e-2, err_msg="fit_transform and transform outcomes " "not consistent in %s" % transformer) assert_allclose_dense_sparse( x_pred, x_pred3, atol=1e-2, err_msg="consecutive fit_transform outcomes " "not consistent in %s" % transformer) else: assert_allclose_dense_sparse( X_pred, X_pred2, err_msg="fit_transform and transform outcomes " "not consistent in %s" % transformer, atol=1e-2) assert_allclose_dense_sparse( X_pred, X_pred3, atol=1e-2, err_msg="consecutive fit_transform outcomes " "not consistent in %s" % transformer) assert_equal(_num_samples(X_pred2), n_samples) assert_equal(_num_samples(X_pred3), n_samples) # raises error on malformed input for transform if hasattr(X, 'T'): # If it's not an array, it does not have a 'T' property assert_raises(ValueError, transformer.transform, X.T) @ignore_warnings def check_pipeline_consistency(name, estimator_orig): if name in ('CCA', 'LocallyLinearEmbedding', 'KernelPCA') and _is_32bit(): # Those transformers yield non-deterministic output when executed on # a 32bit Python. The same transformers are stable on 64bit Python. # FIXME: try to isolate a minimalistic reproduction case only depending # scipy and/or maybe generate a test dataset that does not # cause such unstable behaviors. msg = name + ' is non deterministic on 32bit Python' raise SkipTest(msg) # check that make_pipeline(est) gives same score as est X, y = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]], random_state=0, n_features=2, cluster_std=0.1) X -= X.min() estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) set_random_state(estimator) pipeline = make_pipeline(estimator) estimator.fit(X, y) pipeline.fit(X, y) funcs = ["score", "fit_transform"] for func_name in funcs: func = getattr(estimator, func_name, None) if func is not None: func_pipeline = getattr(pipeline, func_name) result = func(X, y) result_pipe = func_pipeline(X, y) assert_allclose_dense_sparse(result, result_pipe) @ignore_warnings def check_fit_score_takes_y(name, estimator_orig): # check that all estimators accept an optional y # in fit and score so they can be used in pipelines rnd = np.random.RandomState(0) X = rnd.uniform(size=(10, 3)) y = np.arange(10) % 3 estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) set_random_state(estimator) funcs = ["fit", "score", "partial_fit", "fit_predict", "fit_transform"] for func_name in funcs: func = getattr(estimator, func_name, None) if func is not None: func(X, y) args = [p.name for p in signature(func).parameters.values()] if args[0] == "self": # if_delegate_has_method makes methods into functions # with an explicit "self", so need to shift arguments args = args[1:] assert_true(args[1] in ["y", "Y"], "Expected y or Y as second argument for method " "%s of %s. Got arguments: %r." % (func_name, type(estimator).__name__, args)) @ignore_warnings def check_estimators_dtypes(name, estimator_orig): rnd = np.random.RandomState(0) X_train_32 = 3 * rnd.uniform(size=(20, 5)).astype(np.float32) X_train_64 = X_train_32.astype(np.float64) X_train_int_64 = X_train_32.astype(np.int64) X_train_int_32 = X_train_32.astype(np.int32) y = X_train_int_64[:, 0] y = multioutput_estimator_convert_y_2d(estimator_orig, y) methods = ["predict", "transform", "decision_function", "predict_proba"] for X_train in [X_train_32, X_train_64, X_train_int_64, X_train_int_32]: estimator = clone(estimator_orig) set_random_state(estimator, 1) estimator.fit(X_train, y) for method in methods: if hasattr(estimator, method): getattr(estimator, method)(X_train) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_estimators_empty_data_messages(name, estimator_orig): e = clone(estimator_orig) set_random_state(e, 1) X_zero_samples = np.empty(0).reshape(0, 3) # The precise message can change depending on whether X or y is # validated first. Let us test the type of exception only: assert_raises(ValueError, e.fit, X_zero_samples, []) X_zero_features = np.empty(0).reshape(3, 0) # the following y should be accepted by both classifiers and regressors # and ignored by unsupervised models y = multioutput_estimator_convert_y_2d(e, np.array([1, 0, 1])) msg = ("0 feature\(s\) \(shape=\(3, 0\)\) while a minimum of \d* " "is required.") assert_raises_regex(ValueError, msg, e.fit, X_zero_features, y) @ignore_warnings(category=DeprecationWarning) def check_estimators_nan_inf(name, estimator_orig): # Checks that Estimator X's do not contain NaN or inf. rnd = np.random.RandomState(0) X_train_finite = rnd.uniform(size=(10, 3)) X_train_nan = rnd.uniform(size=(10, 3)) X_train_nan[0, 0] = np.nan X_train_inf = rnd.uniform(size=(10, 3)) X_train_inf[0, 0] = np.inf y = np.ones(10) y[:5] = 0 y = multioutput_estimator_convert_y_2d(estimator_orig, y) error_string_fit = "Estimator doesn't check for NaN and inf in fit." error_string_predict = ("Estimator doesn't check for NaN and inf in" " predict.") error_string_transform = ("Estimator doesn't check for NaN and inf in" " transform.") for X_train in [X_train_nan, X_train_inf]: # catch deprecation warnings with ignore_warnings(category=(DeprecationWarning, FutureWarning)): estimator = clone(estimator_orig) set_random_state(estimator, 1) # try to fit try: estimator.fit(X_train, y) except ValueError as e: if 'inf' not in repr(e) and 'NaN' not in repr(e): print(error_string_fit, estimator, e) traceback.print_exc(file=sys.stdout) raise e except Exception as exc: print(error_string_fit, estimator, exc) traceback.print_exc(file=sys.stdout) raise exc else: raise AssertionError(error_string_fit, estimator) # actually fit estimator.fit(X_train_finite, y) # predict if hasattr(estimator, "predict"): try: estimator.predict(X_train) except ValueError as e: if 'inf' not in repr(e) and 'NaN' not in repr(e): print(error_string_predict, estimator, e) traceback.print_exc(file=sys.stdout) raise e except Exception as exc: print(error_string_predict, estimator, exc) traceback.print_exc(file=sys.stdout) else: raise AssertionError(error_string_predict, estimator) # transform if hasattr(estimator, "transform"): try: estimator.transform(X_train) except ValueError as e: if 'inf' not in repr(e) and 'NaN' not in repr(e): print(error_string_transform, estimator, e) traceback.print_exc(file=sys.stdout) raise e except Exception as exc: print(error_string_transform, estimator, exc) traceback.print_exc(file=sys.stdout) else: raise AssertionError(error_string_transform, estimator) @ignore_warnings def check_estimators_pickle(name, estimator_orig): """Test that we can pickle all estimators""" check_methods = ["predict", "transform", "decision_function", "predict_proba"] X, y = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]], random_state=0, n_features=2, cluster_std=0.1) # some estimators can't do features less than 0 X -= X.min() estimator = clone(estimator_orig) # some estimators only take multioutputs y = multioutput_estimator_convert_y_2d(estimator, y) set_random_state(estimator) estimator.fit(X, y) result = dict() for method in check_methods: if hasattr(estimator, method): result[method] = getattr(estimator, method)(X) # pickle and unpickle! pickled_estimator = pickle.dumps(estimator) if estimator.__module__.startswith('sklearn.'): assert_true(b"version" in pickled_estimator) unpickled_estimator = pickle.loads(pickled_estimator) for method in result: unpickled_result = getattr(unpickled_estimator, method)(X) assert_allclose_dense_sparse(result[method], unpickled_result) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_estimators_partial_fit_n_features(name, estimator_orig): # check if number of features changes between calls to partial_fit. if not hasattr(estimator_orig, 'partial_fit'): return estimator = clone(estimator_orig) X, y = make_blobs(n_samples=50, random_state=1) X -= X.min() try: if is_classifier(estimator): classes = np.unique(y) estimator.partial_fit(X, y, classes=classes) else: estimator.partial_fit(X, y) except NotImplementedError: return assert_raises(ValueError, estimator.partial_fit, X[:, :-1], y) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_clustering(name, clusterer_orig): clusterer = clone(clusterer_orig) X, y = make_blobs(n_samples=50, random_state=1) X, y = shuffle(X, y, random_state=7) X = StandardScaler().fit_transform(X) n_samples, n_features = X.shape # catch deprecation and neighbors warnings if hasattr(clusterer, "n_clusters"): clusterer.set_params(n_clusters=3) set_random_state(clusterer) if name == 'AffinityPropagation': clusterer.set_params(preference=-100) clusterer.set_params(max_iter=100) # fit clusterer.fit(X) # with lists clusterer.fit(X.tolist()) assert_equal(clusterer.labels_.shape, (n_samples,)) pred = clusterer.labels_ assert_greater(adjusted_rand_score(pred, y), 0.4) # fit another time with ``fit_predict`` and compare results if name == 'SpectralClustering': # there is no way to make Spectral clustering deterministic :( return set_random_state(clusterer) with warnings.catch_warnings(record=True): pred2 = clusterer.fit_predict(X) assert_array_equal(pred, pred2) @ignore_warnings(category=DeprecationWarning) def check_clusterer_compute_labels_predict(name, clusterer_orig): """Check that predict is invariant of compute_labels""" X, y = make_blobs(n_samples=20, random_state=0) clusterer = clone(clusterer_orig) if hasattr(clusterer, "compute_labels"): # MiniBatchKMeans if hasattr(clusterer, "random_state"): clusterer.set_params(random_state=0) X_pred1 = clusterer.fit(X).predict(X) clusterer.set_params(compute_labels=False) X_pred2 = clusterer.fit(X).predict(X) assert_array_equal(X_pred1, X_pred2) @ignore_warnings(category=DeprecationWarning) def check_classifiers_one_label(name, classifier_orig): error_string_fit = "Classifier can't train when only one class is present." error_string_predict = ("Classifier can't predict when only one class is " "present.") rnd = np.random.RandomState(0) X_train = rnd.uniform(size=(10, 3)) X_test = rnd.uniform(size=(10, 3)) y = np.ones(10) # catch deprecation warnings with ignore_warnings(category=(DeprecationWarning, FutureWarning)): classifier = clone(classifier_orig) # try to fit try: classifier.fit(X_train, y) except ValueError as e: if 'class' not in repr(e): print(error_string_fit, classifier, e) traceback.print_exc(file=sys.stdout) raise e else: return except Exception as exc: print(error_string_fit, classifier, exc) traceback.print_exc(file=sys.stdout) raise exc # predict try: assert_array_equal(classifier.predict(X_test), y) except Exception as exc: print(error_string_predict, classifier, exc) raise exc @ignore_warnings # Warnings are raised by decision function def check_classifiers_train(name, classifier_orig): X_m, y_m = make_blobs(n_samples=300, random_state=0) X_m, y_m = shuffle(X_m, y_m, random_state=7) X_m = StandardScaler().fit_transform(X_m) # generate binary problem from multi-class one y_b = y_m[y_m != 2] X_b = X_m[y_m != 2] for (X, y) in [(X_m, y_m), (X_b, y_b)]: classes = np.unique(y) n_classes = len(classes) n_samples, n_features = X.shape classifier = clone(classifier_orig) if name in ['BernoulliNB', 'MultinomialNB']: X -= X.min() set_random_state(classifier) # raises error on malformed input for fit assert_raises(ValueError, classifier.fit, X, y[:-1]) # fit classifier.fit(X, y) # with lists classifier.fit(X.tolist(), y.tolist()) assert_true(hasattr(classifier, "classes_")) y_pred = classifier.predict(X) assert_equal(y_pred.shape, (n_samples,)) # training set performance if name not in ['BernoulliNB', 'MultinomialNB']: assert_greater(accuracy_score(y, y_pred), 0.83) # raises error on malformed input for predict assert_raises(ValueError, classifier.predict, X.T) if hasattr(classifier, "decision_function"): try: # decision_function agrees with predict decision = classifier.decision_function(X) if n_classes == 2: assert_equal(decision.shape, (n_samples,)) dec_pred = (decision.ravel() > 0).astype(np.int) assert_array_equal(dec_pred, y_pred) if (n_classes == 3 and # 1on1 of LibSVM works differently not isinstance(classifier, BaseLibSVM)): assert_equal(decision.shape, (n_samples, n_classes)) assert_array_equal(np.argmax(decision, axis=1), y_pred) # raises error on malformed input assert_raises(ValueError, classifier.decision_function, X.T) # raises error on malformed input for decision_function assert_raises(ValueError, classifier.decision_function, X.T) except NotImplementedError: pass if hasattr(classifier, "predict_proba"): # predict_proba agrees with predict y_prob = classifier.predict_proba(X) assert_equal(y_prob.shape, (n_samples, n_classes)) assert_array_equal(np.argmax(y_prob, axis=1), y_pred) # check that probas for all classes sum to one assert_allclose(np.sum(y_prob, axis=1), np.ones(n_samples)) # raises error on malformed input assert_raises(ValueError, classifier.predict_proba, X.T) # raises error on malformed input for predict_proba assert_raises(ValueError, classifier.predict_proba, X.T) if hasattr(classifier, "predict_log_proba"): # predict_log_proba is a transformation of predict_proba y_log_prob = classifier.predict_log_proba(X) assert_allclose(y_log_prob, np.log(y_prob), 8, atol=1e-9) assert_array_equal(np.argsort(y_log_prob), np.argsort(y_prob)) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_estimators_fit_returns_self(name, estimator_orig): """Check if self is returned when calling fit""" X, y = make_blobs(random_state=0, n_samples=9, n_features=4) # some want non-negative input X -= X.min() estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) set_random_state(estimator) assert_true(estimator.fit(X, y) is estimator) @ignore_warnings def check_estimators_unfitted(name, estimator_orig): """Check that predict raises an exception in an unfitted estimator. Unfitted estimators should raise either AttributeError or ValueError. The specific exception type NotFittedError inherits from both and can therefore be adequately raised for that purpose. """ # Common test for Regressors as well as Classifiers X, y = _boston_subset() est = clone(estimator_orig) msg = "fit" if hasattr(est, 'predict'): assert_raise_message((AttributeError, ValueError), msg, est.predict, X) if hasattr(est, 'decision_function'): assert_raise_message((AttributeError, ValueError), msg, est.decision_function, X) if hasattr(est, 'predict_proba'): assert_raise_message((AttributeError, ValueError), msg, est.predict_proba, X) if hasattr(est, 'predict_log_proba'): assert_raise_message((AttributeError, ValueError), msg, est.predict_log_proba, X) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_supervised_y_2d(name, estimator_orig): if "MultiTask" in name: # These only work on 2d, so this test makes no sense return if name == "GaussianProcess": # Workaround: https://github.com/scikit-learn/scikit-learn/issues/10562 return rnd = np.random.RandomState(0) X = rnd.uniform(size=(10, 3)) y = np.arange(10) % 3 estimator = clone(estimator_orig) set_random_state(estimator) # fit estimator.fit(X, y) y_pred = estimator.predict(X) set_random_state(estimator) # Check that when a 2D y is given, a DataConversionWarning is # raised with warnings.catch_warnings(record=True) as w: warnings.simplefilter("always", DataConversionWarning) warnings.simplefilter("ignore", RuntimeWarning) estimator.fit(X, y[:, np.newaxis]) y_pred_2d = estimator.predict(X) msg = "expected 1 DataConversionWarning, got: %s" % ( ", ".join([str(w_x) for w_x in w])) if name not in MULTI_OUTPUT: # check that we warned if we don't support multi-output assert_greater(len(w), 0, msg) assert_true("DataConversionWarning('A column-vector y" " was passed when a 1d array was expected" in msg) assert_allclose(y_pred.ravel(), y_pred_2d.ravel()) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_classifiers_classes(name, classifier_orig): X, y = make_blobs(n_samples=30, random_state=0, cluster_std=0.1) X, y = shuffle(X, y, random_state=7) X = StandardScaler().fit_transform(X) # We need to make sure that we have non negative data, for things # like NMF X -= X.min() - .1 y_names = np.array(["one", "two", "three"])[y] for y_names in [y_names, y_names.astype('O')]: if name in ["LabelPropagation", "LabelSpreading"]: # TODO some complication with -1 label y_ = y else: y_ = y_names classes = np.unique(y_) classifier = clone(classifier_orig) if name == 'BernoulliNB': classifier.set_params(binarize=X.mean()) set_random_state(classifier) # fit classifier.fit(X, y_) y_pred = classifier.predict(X) # training set performance assert_array_equal(np.unique(y_), np.unique(y_pred)) if np.any(classifier.classes_ != classes): print("Unexpected classes_ attribute for %r: " "expected %s, got %s" % (classifier, classes, classifier.classes_)) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_regressors_int(name, regressor_orig): X, _ = _boston_subset() X = X[:50] rnd = np.random.RandomState(0) y = rnd.randint(3, size=X.shape[0]) y = multioutput_estimator_convert_y_2d(regressor_orig, y) rnd = np.random.RandomState(0) # separate estimators to control random seeds regressor_1 = clone(regressor_orig) regressor_2 = clone(regressor_orig) set_random_state(regressor_1) set_random_state(regressor_2) if name in CROSS_DECOMPOSITION: y_ = np.vstack([y, 2 * y + rnd.randint(2, size=len(y))]) y_ = y_.T else: y_ = y # fit regressor_1.fit(X, y_) pred1 = regressor_1.predict(X) regressor_2.fit(X, y_.astype(np.float)) pred2 = regressor_2.predict(X) assert_allclose(pred1, pred2, atol=1e-2, err_msg=name) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_regressors_train(name, regressor_orig): X, y = _boston_subset() y = StandardScaler().fit_transform(y.reshape(-1, 1)) # X is already scaled y = y.ravel() regressor = clone(regressor_orig) y = multioutput_estimator_convert_y_2d(regressor, y) rnd = np.random.RandomState(0) if not hasattr(regressor, 'alphas') and hasattr(regressor, 'alpha'): # linear regressors need to set alpha, but not generalized CV ones regressor.alpha = 0.01 if name == 'PassiveAggressiveRegressor': regressor.C = 0.01 # raises error on malformed input for fit assert_raises(ValueError, regressor.fit, X, y[:-1]) # fit if name in CROSS_DECOMPOSITION: y_ = np.vstack([y, 2 * y + rnd.randint(2, size=len(y))]) y_ = y_.T else: y_ = y set_random_state(regressor) regressor.fit(X, y_) regressor.fit(X.tolist(), y_.tolist()) y_pred = regressor.predict(X) assert_equal(y_pred.shape, y_.shape) # TODO: find out why PLS and CCA fail. RANSAC is random # and furthermore assumes the presence of outliers, hence # skipped if name not in ('PLSCanonical', 'CCA', 'RANSACRegressor'): assert_greater(regressor.score(X, y_), 0.5) @ignore_warnings def check_regressors_no_decision_function(name, regressor_orig): # checks whether regressors have decision_function or predict_proba rng = np.random.RandomState(0) X = rng.normal(size=(10, 4)) regressor = clone(regressor_orig) y = multioutput_estimator_convert_y_2d(regressor, X[:, 0]) if hasattr(regressor, "n_components"): # FIXME CCA, PLS is not robust to rank 1 effects regressor.n_components = 1 regressor.fit(X, y) funcs = ["decision_function", "predict_proba", "predict_log_proba"] for func_name in funcs: func = getattr(regressor, func_name, None) if func is None: # doesn't have function continue # has function. Should raise deprecation warning msg = func_name assert_warns_message(DeprecationWarning, msg, func, X) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_class_weight_classifiers(name, classifier_orig): if name == "NuSVC": # the sparse version has a parameter that doesn't do anything raise SkipTest if name.endswith("NB"): # NaiveBayes classifiers have a somewhat different interface. # FIXME SOON! raise SkipTest for n_centers in [2, 3]: # create a very noisy dataset X, y = make_blobs(centers=n_centers, random_state=0, cluster_std=20) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0) n_centers = len(np.unique(y_train)) if n_centers == 2: class_weight = {0: 1000, 1: 0.0001} else: class_weight = {0: 1000, 1: 0.0001, 2: 0.0001} classifier = clone(classifier_orig).set_params( class_weight=class_weight) if hasattr(classifier, "n_iter"): classifier.set_params(n_iter=100) if hasattr(classifier, "max_iter"): classifier.set_params(max_iter=1000) if hasattr(classifier, "min_weight_fraction_leaf"): classifier.set_params(min_weight_fraction_leaf=0.01) set_random_state(classifier) classifier.fit(X_train, y_train) y_pred = classifier.predict(X_test) # XXX: Generally can use 0.89 here. On Windows, LinearSVC gets # 0.88 (Issue #9111) assert_greater(np.mean(y_pred == 0), 0.87) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_class_weight_balanced_classifiers(name, classifier_orig, X_train, y_train, X_test, y_test, weights): classifier = clone(classifier_orig) if hasattr(classifier, "n_iter"): classifier.set_params(n_iter=100) if hasattr(classifier, "max_iter"): classifier.set_params(max_iter=1000) set_random_state(classifier) classifier.fit(X_train, y_train) y_pred = classifier.predict(X_test) classifier.set_params(class_weight='balanced') classifier.fit(X_train, y_train) y_pred_balanced = classifier.predict(X_test) assert_greater(f1_score(y_test, y_pred_balanced, average='weighted'), f1_score(y_test, y_pred, average='weighted')) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_class_weight_balanced_linear_classifier(name, Classifier): """Test class weights with non-contiguous class labels.""" # this is run on classes, not instances, though this should be changed X = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0], [1.0, 1.0], [1.0, 0.0]]) y = np.array([1, 1, 1, -1, -1]) classifier = Classifier() if hasattr(classifier, "n_iter"): # This is a very small dataset, default n_iter are likely to prevent # convergence classifier.set_params(n_iter=1000) if hasattr(classifier, "max_iter"): classifier.set_params(max_iter=1000) set_random_state(classifier) # Let the model compute the class frequencies classifier.set_params(class_weight='balanced') coef_balanced = classifier.fit(X, y).coef_.copy() # Count each label occurrence to reweight manually n_samples = len(y) n_classes = float(len(np.unique(y))) class_weight = {1: n_samples / (np.sum(y == 1) * n_classes), -1: n_samples / (np.sum(y == -1) * n_classes)} classifier.set_params(class_weight=class_weight) coef_manual = classifier.fit(X, y).coef_.copy() assert_allclose(coef_balanced, coef_manual) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_estimators_overwrite_params(name, estimator_orig): X, y = make_blobs(random_state=0, n_samples=9) # some want non-negative input X -= X.min() estimator = clone(estimator_orig) y = multioutput_estimator_convert_y_2d(estimator, y) set_random_state(estimator) # Make a physical copy of the original estimator parameters before fitting. params = estimator.get_params() original_params = deepcopy(params) # Fit the model estimator.fit(X, y) # Compare the state of the model parameters with the original parameters new_params = estimator.get_params() for param_name, original_value in original_params.items(): new_value = new_params[param_name] # We should never change or mutate the internal state of input # parameters by default. To check this we use the joblib.hash function # that introspects recursively any subobjects to compute a checksum. # The only exception to this rule of immutable constructor parameters # is possible RandomState instance but in this check we explicitly # fixed the random_state params recursively to be integer seeds. assert_equal(hash(new_value), hash(original_value), "Estimator %s should not change or mutate " " the parameter %s from %s to %s during fit." % (name, param_name, original_value, new_value)) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_no_fit_attributes_set_in_init(name, Estimator): """Check that Estimator.__init__ doesn't set trailing-_ attributes.""" # this check works on classes, not instances estimator = Estimator() for attr in dir(estimator): if attr.endswith("_") and not attr.startswith("__"): # This check is for properties, they can be listed in dir # while at the same time have hasattr return False as long # as the property getter raises an AttributeError assert_false( hasattr(estimator, attr), "By convention, attributes ending with '_' are " 'estimated from data in scikit-learn. Consequently they ' 'should not be initialized in the constructor of an ' 'estimator but in the fit method. Attribute {!r} ' 'was found in estimator {}'.format(attr, name)) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_sparsify_coefficients(name, estimator_orig): X = np.array([[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [-1, -2], [2, 2], [-2, -2]]) y = [1, 1, 1, 2, 2, 2, 3, 3, 3] est = clone(estimator_orig) est.fit(X, y) pred_orig = est.predict(X) # test sparsify with dense inputs est.sparsify() assert_true(sparse.issparse(est.coef_)) pred = est.predict(X) assert_array_equal(pred, pred_orig) # pickle and unpickle with sparse coef_ est = pickle.loads(pickle.dumps(est)) assert_true(sparse.issparse(est.coef_)) pred = est.predict(X) assert_array_equal(pred, pred_orig) @ignore_warnings(category=DeprecationWarning) def check_classifier_data_not_an_array(name, estimator_orig): X = np.array([[3, 0], [0, 1], [0, 2], [1, 1], [1, 2], [2, 1]]) y = [1, 1, 1, 2, 2, 2] y = multioutput_estimator_convert_y_2d(estimator_orig, y) check_estimators_data_not_an_array(name, estimator_orig, X, y) @ignore_warnings(category=DeprecationWarning) def check_regressor_data_not_an_array(name, estimator_orig): X, y = _boston_subset(n_samples=50) y = multioutput_estimator_convert_y_2d(estimator_orig, y) check_estimators_data_not_an_array(name, estimator_orig, X, y) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_estimators_data_not_an_array(name, estimator_orig, X, y): if name in CROSS_DECOMPOSITION: raise SkipTest # separate estimators to control random seeds estimator_1 = clone(estimator_orig) estimator_2 = clone(estimator_orig) set_random_state(estimator_1) set_random_state(estimator_2) y_ = NotAnArray(np.asarray(y)) X_ = NotAnArray(np.asarray(X)) # fit estimator_1.fit(X_, y_) pred1 = estimator_1.predict(X_) estimator_2.fit(X, y) pred2 = estimator_2.predict(X) assert_allclose(pred1, pred2, atol=1e-2, err_msg=name) def check_parameters_default_constructible(name, Estimator): # this check works on classes, not instances classifier = LinearDiscriminantAnalysis() # test default-constructibility # get rid of deprecation warnings with ignore_warnings(category=(DeprecationWarning, FutureWarning)): if name in META_ESTIMATORS: estimator = Estimator(classifier) else: estimator = Estimator() # test cloning clone(estimator) # test __repr__ repr(estimator) # test that set_params returns self assert_true(estimator.set_params() is estimator) # test if init does nothing but set parameters # this is important for grid_search etc. # We get the default parameters from init and then # compare these against the actual values of the attributes. # this comes from getattr. Gets rid of deprecation decorator. init = getattr(estimator.__init__, 'deprecated_original', estimator.__init__) try: def param_filter(p): """Identify hyper parameters of an estimator""" return (p.name != 'self' and p.kind != p.VAR_KEYWORD and p.kind != p.VAR_POSITIONAL) init_params = [p for p in signature(init).parameters.values() if param_filter(p)] except (TypeError, ValueError): # init is not a python function. # true for mixins return params = estimator.get_params() if name in META_ESTIMATORS: # they can need a non-default argument init_params = init_params[1:] for init_param in init_params: assert_not_equal(init_param.default, init_param.empty, "parameter %s for %s has no default value" % (init_param.name, type(estimator).__name__)) assert_in(type(init_param.default), [str, int, float, bool, tuple, type(None), np.float64, types.FunctionType, Memory]) if init_param.name not in params.keys(): # deprecated parameter, not in get_params assert_true(init_param.default is None) continue if (issubclass(Estimator, BaseSGD) and init_param.name in ['tol', 'max_iter']): # To remove in 0.21, when they get their future default values continue param_value = params[init_param.name] if isinstance(param_value, np.ndarray): assert_array_equal(param_value, init_param.default) else: assert_equal(param_value, init_param.default, init_param.name) def multioutput_estimator_convert_y_2d(estimator, y): # Estimators in mono_output_task_error raise ValueError if y is of 1-D # Convert into a 2-D y for those estimators. if "MultiTask" in estimator.__class__.__name__: return np.reshape(y, (-1, 1)) return y @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_non_transformer_estimators_n_iter(name, estimator_orig): # Test that estimators that are not transformers with a parameter # max_iter, return the attribute of n_iter_ at least 1. # These models are dependent on external solvers like # libsvm and accessing the iter parameter is non-trivial. not_run_check_n_iter = ['Ridge', 'SVR', 'NuSVR', 'NuSVC', 'RidgeClassifier', 'SVC', 'RandomizedLasso', 'LogisticRegressionCV', 'LinearSVC', 'LogisticRegression'] # Tested in test_transformer_n_iter not_run_check_n_iter += CROSS_DECOMPOSITION if name in not_run_check_n_iter: return # LassoLars stops early for the default alpha=1.0 the iris dataset. if name == 'LassoLars': estimator = clone(estimator_orig).set_params(alpha=0.) else: estimator = clone(estimator_orig) if hasattr(estimator, 'max_iter'): iris = load_iris() X, y_ = iris.data, iris.target y_ = multioutput_estimator_convert_y_2d(estimator, y_) set_random_state(estimator, 0) if name == 'AffinityPropagation': estimator.fit(X) else: estimator.fit(X, y_) # HuberRegressor depends on scipy.optimize.fmin_l_bfgs_b # which doesn't return a n_iter for old versions of SciPy. if not (name == 'HuberRegressor' and estimator.n_iter_ is None): assert_greater_equal(estimator.n_iter_, 1) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_transformer_n_iter(name, estimator_orig): # Test that transformers with a parameter max_iter, return the # attribute of n_iter_ at least 1. estimator = clone(estimator_orig) if hasattr(estimator, "max_iter"): if name in CROSS_DECOMPOSITION: # Check using default data X = [[0., 0., 1.], [1., 0., 0.], [2., 2., 2.], [2., 5., 4.]] y_ = [[0.1, -0.2], [0.9, 1.1], [0.1, -0.5], [0.3, -0.2]] else: X, y_ = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]], random_state=0, n_features=2, cluster_std=0.1) X -= X.min() - 0.1 set_random_state(estimator, 0) estimator.fit(X, y_) # These return a n_iter per component. if name in CROSS_DECOMPOSITION: for iter_ in estimator.n_iter_: assert_greater_equal(iter_, 1) else: assert_greater_equal(estimator.n_iter_, 1) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_get_params_invariance(name, estimator_orig): # Checks if get_params(deep=False) is a subset of get_params(deep=True) class T(BaseEstimator): """Mock classifier """ def __init__(self): pass def fit(self, X, y): return self def transform(self, X): return X e = clone(estimator_orig) shallow_params = e.get_params(deep=False) deep_params = e.get_params(deep=True) assert_true(all(item in deep_params.items() for item in shallow_params.items())) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_classifiers_regression_target(name, estimator_orig): # Check if classifier throws an exception when fed regression targets boston = load_boston() X, y = boston.data, boston.target e = clone(estimator_orig) msg = 'Unknown label type: ' assert_raises_regex(ValueError, msg, e.fit, X, y) @ignore_warnings(category=(DeprecationWarning, FutureWarning)) def check_decision_proba_consistency(name, estimator_orig): # Check whether an estimator having both decision_function and # predict_proba methods has outputs with perfect rank correlation. centers = [(2, 2), (4, 4)] X, y = make_blobs(n_samples=100, random_state=0, n_features=4, centers=centers, cluster_std=1.0, shuffle=True) X_test = np.random.randn(20, 2) + 4 estimator = clone(estimator_orig) if (hasattr(estimator, "decision_function") and hasattr(estimator, "predict_proba")): estimator.fit(X, y) a = estimator.predict_proba(X_test)[:, 1] b = estimator.decision_function(X_test) assert_array_equal(rankdata(a), rankdata(b))