def check_classifiers_classes(name, Classifier):
    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_)
        # catch deprecation warnings
        with warnings.catch_warnings(record=True):
            classifier = Classifier()
        if name == 'BernoulliNB':
            classifier.set_params(binarize=X.mean())
        set_fast_parameters(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_))

def test_precision_recall_f1_score_binary():
    """Test Precision Recall and F1 Score for binary classification task"""
    y_true, y_pred, _ = make_prediction(binary=True)

    # detailed measures for each class
    p, r, f, s = precision_recall_fscore_support(y_true, y_pred, average=None)
    assert_array_almost_equal(p, [0.73, 0.85], 2)
    assert_array_almost_equal(r, [0.88, 0.68], 2)
    assert_array_almost_equal(f, [0.80, 0.76], 2)
    assert_array_equal(s, [25, 25])

    # individual scoring function that can be used for grid search: in the
    # binary class case the score is the value of the measure for the positive
    # class (e.g. label == 1)
    ps = precision_score(y_true, y_pred)
    assert_array_almost_equal(ps, 0.85, 2)

    rs = recall_score(y_true, y_pred)
    assert_array_almost_equal(rs, 0.68, 2)

    fs = f1_score(y_true, y_pred)
    assert_array_almost_equal(fs, 0.76, 2)

    assert_almost_equal(fbeta_score(y_true, y_pred, beta=2),
                        (1 + 2 ** 2) * ps * rs / (2 ** 2 * ps + rs), 2)

def test_radius_neighbors_classifier_when_no_neighbors():
    """ Test radius-based classifier when no neighbors found.
    In this case it should rise an informative exception """

    X = np.array([[1.0, 1.0], [2.0, 2.0]])
    y = np.array([1, 2])
    radius = 0.1

    z1 = np.array([[1.01, 1.01], [2.01, 2.01]])  # no outliers
    z2 = np.array([[1.01, 1.01], [1.4, 1.4]])    # one outlier

    weight_func = _weight_func

    for outlier_label in [0, -1, None]:
        for algorithm in ALGORITHMS:
            for weights in ['uniform', 'distance', weight_func]:
                rnc = neighbors.RadiusNeighborsClassifier
                clf = rnc(radius=radius, weights=weights, algorithm=algorithm,
                          outlier_label=outlier_label)
                clf.fit(X, y)
                assert_array_equal(np.array([1, 2]),
                                   clf.predict(z1))
                if outlier_label is None:
                    assert_raises(ValueError, clf.predict, z2)
                elif False:
                    assert_array_equal(np.array([1, outlier_label]),
                                       clf.predict(z2))

def test_kneighbors_classifier_predict_proba():
    """Test KNeighborsClassifier.predict_proba() method"""
    X = np.array([[0, 2, 0],
                  [0, 2, 1],
                  [2, 0, 0],
                  [2, 2, 0],
                  [0, 0, 2],
                  [0, 0, 1]])
    y = np.array([4, 4, 5, 5, 1, 1])
    cls = neighbors.KNeighborsClassifier(n_neighbors=3, p=1)  # cityblock dist
    cls.fit(X, y)
    y_prob = cls.predict_proba(X)
    real_prob = np.array([[0, 2. / 3, 1. / 3],
                          [1. / 3, 2. / 3, 0],
                          [1. / 3, 0, 2. / 3],
                          [0, 1. / 3, 2. / 3],
                          [2. / 3, 1. / 3, 0],
                          [2. / 3, 1. / 3, 0]])
    assert_array_equal(real_prob, y_prob)
    # Check that it also works with non integer labels
    cls.fit(X, y.astype(str))
    y_prob = cls.predict_proba(X)
    assert_array_equal(real_prob, y_prob)
    # Check that it works with weights='distance'
    cls = neighbors.KNeighborsClassifier(
        n_neighbors=2, p=1, weights='distance')
    cls.fit(X, y)
    y_prob = cls.predict_proba(np.array([[0, 2, 0], [2, 2, 2]]))
    real_prob = np.array([[0, 1, 0], [0, 0.4, 0.6]])
    assert_array_almost_equal(real_prob, y_prob)

def test_deprecated_score_func():
    # test that old deprecated way of passing a score / loss function is still
    # supported
    X, y = make_classification(n_samples=200, n_features=100, random_state=0)
    clf = LinearSVC(random_state=0)
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
    cv.fit(X[:180], y[:180])
    y_pred = cv.predict(X[180:])
    C = cv.best_estimator_.C

    clf = LinearSVC(random_state=0)
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, score_func=f1_score)
    with warnings.catch_warnings(record=True):
        # catch deprecation warning
        cv.fit(X[:180], y[:180])
    y_pred_func = cv.predict(X[180:])
    C_func = cv.best_estimator_.C

    assert_array_equal(y_pred, y_pred_func)
    assert_equal(C, C_func)

    # test loss where greater is worse
    def f1_loss(y_true_, y_pred_):
        return -f1_score(y_true_, y_pred_)

    clf = LinearSVC(random_state=0)
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, loss_func=f1_loss)
    with warnings.catch_warnings(record=True):
        # catch deprecation warning
        cv.fit(X[:180], y[:180])
    y_pred_loss = cv.predict(X[180:])
    C_loss = cv.best_estimator_.C

    assert_array_equal(y_pred, y_pred_loss)
    assert_equal(C, C_loss)

def test_int_input():
    X_list = [[0, 0], [10, 10], [12, 9], [-1, 1], [2, 0], [8, 10]]
    for dtype in [np.int32, np.int64]:
        X_int = np.array(X_list, dtype=dtype)
        X_int_csr = sp.csr_matrix(X_int)
        init_int = X_int[:2]

        fitted_models = [
            KMeans(n_clusters=2).fit(X_int),
            KMeans(n_clusters=2, init=init_int, n_init=1).fit(X_int),
            # mini batch kmeans is very unstable on such a small dataset hence
            # we use many inits
            MiniBatchKMeans(n_clusters=2, n_init=10, batch_size=2).fit(X_int),
            MiniBatchKMeans(n_clusters=2, n_init=10, batch_size=2).fit(X_int_csr),
            MiniBatchKMeans(n_clusters=2, batch_size=2,
                            init=init_int, n_init=1).fit(X_int),
            MiniBatchKMeans(n_clusters=2, batch_size=2,
                            init=init_int, n_init=1).fit(X_int_csr),
        ]

        for km in fitted_models:
            assert_equal(km.cluster_centers_.dtype, np.float64)

        expected_labels = [0, 1, 1, 0, 0, 1]
        scores = np.array([v_measure_score(expected_labels, km.labels_)
                           for km in fitted_models])
        assert_array_equal(scores, np.ones(scores.shape[0]))

def test_sparse_fit_params():
    iris = load_iris()
    X, y = iris.data, iris.target
    clf = MockClassifier()
    fit_params = {'sparse_sample_weight': coo_matrix(np.eye(X.shape[0]))}
    a = cval.cross_val_score(clf, X, y, fit_params=fit_params)
    assert_array_equal(a, np.ones(3))

def test_ovo_ties():
    # test that ties are broken using the decision function, not defaulting to
    # the smallest label
    X = np.array([[1, 2], [2, 1], [-2, 1], [-2, -1]])
    y = np.array([2, 0, 1, 2])
    multi_clf = OneVsOneClassifier(Perceptron())
    ovo_prediction = multi_clf.fit(X, y).predict(X)

    # recalculate votes to make sure we have a tie
    predictions = np.vstack([clf.predict(X) for clf in multi_clf.estimators_])
    scores = np.vstack([clf.decision_function(X)
                        for clf in multi_clf.estimators_])
    # classifiers are in order 0-1, 0-2, 1-2
    # aggregate votes:
    votes = np.zeros((4, 3))
    votes[np.arange(4), predictions[0]] += 1
    votes[np.arange(4), 2 * predictions[1]] += 1
    votes[np.arange(4), 1 + predictions[2]] += 1
    # for the first point, there is one vote per class
    assert_array_equal(votes[0, :], 1)
    # for the rest, there is no tie and the prediction is the argmax
    assert_array_equal(np.argmax(votes[1:], axis=1), ovo_prediction[1:])
    # for the tie, the prediction is the class with the highest score
    assert_equal(ovo_prediction[0], 0)
    # in the zero-one classifier, the score for 0 is greater than the score for
    # one.
    assert_greater(scores[0][0], scores[0][1])
    # score for one is greater than score for zero
    assert_greater(scores[2, 0] - scores[0, 0], scores[0, 0] + scores[1, 0])
    # score for one is greater than score for two
    assert_greater(scores[2, 0] - scores[0, 0], -scores[1, 0] - scores[2, 0])

def test_cross_val_generator_mask_indices_same():
    # Test that the cross validation generators return the same results when
    # indices=True and when indices=False
    y = np.array([0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2])
    labels = np.array([1, 1, 2, 3, 3, 3, 4])

    loo_mask = cval.LeaveOneOut(5, indices=False)
    loo_ind = cval.LeaveOneOut(5, indices=True)
    lpo_mask = cval.LeavePOut(10, 2, indices=False)
    lpo_ind = cval.LeavePOut(10, 2, indices=True)
    kf_mask = cval.KFold(10, 5, indices=False, shuffle=True, random_state=1)
    kf_ind = cval.KFold(10, 5, indices=True, shuffle=True, random_state=1)
    skf_mask = cval.StratifiedKFold(y, 3, indices=False)
    skf_ind = cval.StratifiedKFold(y, 3, indices=True)
    lolo_mask = cval.LeaveOneLabelOut(labels, indices=False)
    lolo_ind = cval.LeaveOneLabelOut(labels, indices=True)
    lopo_mask = cval.LeavePLabelOut(labels, 2, indices=False)
    lopo_ind = cval.LeavePLabelOut(labels, 2, indices=True)

    for cv_mask, cv_ind in [(loo_mask, loo_ind), (lpo_mask, lpo_ind),
                            (kf_mask, kf_ind), (skf_mask, skf_ind),
                            (lolo_mask, lolo_ind), (lopo_mask, lopo_ind)]:
        for (train_mask, test_mask), (train_ind, test_ind) in \
                zip(cv_mask, cv_ind):
            assert_array_equal(np.where(train_mask)[0], train_ind)
            assert_array_equal(np.where(test_mask)[0], test_ind)

def test_spectral_clustering():
    S = np.array([[1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
                  [1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
                  [1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
                  [0.2, 0.2, 0.2, 1.0, 1.0, 1.0, 1.0],
                  [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
                  [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
                  [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0]])

    for eigen_solver in ('arpack', 'lobpcg'):
        for assign_labels in ('kmeans', 'discretize'):
            for mat in (S, sparse.csr_matrix(S)):
                model = SpectralClustering(random_state=0, n_clusters=2,
                                           affinity='precomputed',
                                           eigen_solver=eigen_solver,
                                           assign_labels=assign_labels
                                           ).fit(mat)
                labels = model.labels_
                if labels[0] == 0:
                    labels = 1 - labels

                assert_array_equal(labels, [1, 1, 1, 0, 0, 0, 0])

                model_copy = loads(dumps(model))
                assert_equal(model_copy.n_clusters, model.n_clusters)
                assert_equal(model_copy.eigen_solver, model.eigen_solver)
                assert_array_equal(model_copy.labels_, model.labels_)

def test_predict_iris():
    # Test logistic regression with the iris dataset
    n_samples, n_features = iris.data.shape

    target = iris.target_names[iris.target]

    # Test that both multinomial and OvR solvers handle
    # multiclass data correctly and give good accuracy
    # score (>0.95) for the training data.
    for clf in [LogisticRegression(C=len(iris.data)),
                LogisticRegression(C=len(iris.data), solver='lbfgs',
                                   multi_class='multinomial'),
                LogisticRegression(C=len(iris.data), solver='newton-cg',
                                   multi_class='multinomial'),
                LogisticRegression(C=len(iris.data), solver='sag', tol=1e-2,
                                   multi_class='ovr', random_state=42),
                LogisticRegression(C=len(iris.data), solver='saga', tol=1e-2,
                                   multi_class='ovr', random_state=42)
                ]:
        clf.fit(iris.data, target)
        assert_array_equal(np.unique(target), clf.classes_)

        pred = clf.predict(iris.data)
        assert_greater(np.mean(pred == target), .95)

        probabilities = clf.predict_proba(iris.data)
        assert_array_almost_equal(probabilities.sum(axis=1),
                                  np.ones(n_samples))

        pred = iris.target_names[probabilities.argmax(axis=1)]
        assert_greater(np.mean(pred == target), .95)

def test_logistic_regressioncv_class_weights():
    X, y = make_classification(n_samples=20, n_features=20, n_informative=10,
                               n_classes=3, random_state=0)

    # Test the liblinear fails when class_weight of type dict is
    # provided, when it is multiclass. However it can handle
    # binary problems.
    clf_lib = LogisticRegressionCV(class_weight={0: 0.1, 1: 0.2},
                                   solver='liblinear')
    assert_raises(ValueError, clf_lib.fit, X, y)
    y_ = y.copy()
    y_[y == 2] = 1
    clf_lib.fit(X, y_)
    assert_array_equal(clf_lib.classes_, [0, 1])

    # Test for class_weight=auto
    X, y = make_classification(n_samples=20, n_features=20, n_informative=10,
                               random_state=0)
    clf_lbf = LogisticRegressionCV(solver='lbfgs', fit_intercept=False,
                                   class_weight='auto')
    clf_lbf.fit(X, y)
    clf_lib = LogisticRegressionCV(solver='liblinear', fit_intercept=False,
                                   class_weight='auto')
    clf_lib.fit(X, y)
    assert_array_almost_equal(clf_lib.coef_, clf_lbf.coef_, decimal=4)

def test_feature_union_weights():
    # test feature union with transformer weights
    iris = load_iris()
    X = iris.data
    y = iris.target
    pca = RandomizedPCA(n_components=2, random_state=0)
    select = SelectKBest(k=1)
    # test using fit followed by transform
    fs = FeatureUnion([("pca", pca), ("select", select)],
                      transformer_weights={"pca": 10})
    fs.fit(X, y)
    X_transformed = fs.transform(X)
    # test using fit_transform
    fs = FeatureUnion([("pca", pca), ("select", select)],
                      transformer_weights={"pca": 10})
    X_fit_transformed = fs.fit_transform(X, y)
    # test it works with transformers missing fit_transform
    fs = FeatureUnion([("mock", TransfT()), ("pca", pca), ("select", select)],
                      transformer_weights={"mock": 10})
    X_fit_transformed_wo_method = fs.fit_transform(X, y)
    # check against expected result

    # We use a different pca object to control the random_state stream
    assert_array_almost_equal(X_transformed[:, :-1], 10 * pca.fit_transform(X))
    assert_array_equal(X_transformed[:, -1],
                       select.fit_transform(X, y).ravel())
    assert_array_almost_equal(X_fit_transformed[:, :-1],
                              10 * pca.fit_transform(X))
    assert_array_equal(X_fit_transformed[:, -1],
                       select.fit_transform(X, y).ravel())
    assert_equal(X_fit_transformed_wo_method.shape, (X.shape[0], 7))

def test_feature_union():
    # basic sanity check for feature union
    iris = load_iris()
    X = iris.data
    X -= X.mean(axis=0)
    y = iris.target
    svd = TruncatedSVD(n_components=2, random_state=0)
    select = SelectKBest(k=1)
    fs = FeatureUnion([("svd", svd), ("select", select)])
    fs.fit(X, y)
    X_transformed = fs.transform(X)
    assert_equal(X_transformed.shape, (X.shape[0], 3))

    # check if it does the expected thing
    assert_array_almost_equal(X_transformed[:, :-1], svd.fit_transform(X))
    assert_array_equal(X_transformed[:, -1],
                       select.fit_transform(X, y).ravel())

    # test if it also works for sparse input
    # We use a different svd object to control the random_state stream
    fs = FeatureUnion([("svd", svd), ("select", select)])
    X_sp = sparse.csr_matrix(X)
    X_sp_transformed = fs.fit_transform(X_sp, y)
    assert_array_almost_equal(X_transformed, X_sp_transformed.toarray())

    # test setting parameters
    fs.set_params(select__k=2)
    assert_equal(fs.fit_transform(X, y).shape, (X.shape[0], 4))

    # test it works with transformers missing fit_transform
    fs = FeatureUnion([("mock", TransfT()), ("svd", svd), ("select", select)])
    X_transformed = fs.fit_transform(X, y)
    assert_equal(X_transformed.shape, (X.shape[0], 8))

def test_staged_predict_proba():
    # Test whether staged predict proba eventually gives
    # the same prediction.
    X, y = datasets.make_hastie_10_2(n_samples=1200,
                                     random_state=1)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]
    clf = GradientBoostingClassifier(n_estimators=20)
    # test raise NotFittedError if not fitted
    assert_raises(NotFittedError, lambda X: np.fromiter(
        clf.staged_predict_proba(X), dtype=np.float64), X_test)

    clf.fit(X_train, y_train)

    # test if prediction for last stage equals ``predict``
    for y_pred in clf.staged_predict(X_test):
        assert_equal(y_test.shape, y_pred.shape)

    assert_array_equal(clf.predict(X_test), y_pred)

    # test if prediction for last stage equals ``predict_proba``
    for staged_proba in clf.staged_predict_proba(X_test):
        assert_equal(y_test.shape[0], staged_proba.shape[0])
        assert_equal(2, staged_proba.shape[1])

    assert_array_almost_equal(clf.predict_proba(X_test), staged_proba)

def check_warm_start(name, random_state=42):
    # Test if fitting incrementally with warm start gives a forest of the
    # right size and the same results as a normal fit.
    X, y = hastie_X, hastie_y
    ForestEstimator = FOREST_ESTIMATORS[name]
    clf_ws = None
    for n_estimators in [5, 10]:
        if clf_ws is None:
            clf_ws = ForestEstimator(n_estimators=n_estimators,
                                     random_state=random_state,
                                     warm_start=True)
        else:
            clf_ws.set_params(n_estimators=n_estimators)
        clf_ws.fit(X, y)
        assert_equal(len(clf_ws), n_estimators)

    clf_no_ws = ForestEstimator(n_estimators=10, random_state=random_state,
                                warm_start=False)
    clf_no_ws.fit(X, y)

    assert_equal(set([tree.random_state for tree in clf_ws]),
                 set([tree.random_state for tree in clf_no_ws]))

    assert_array_equal(clf_ws.apply(X), clf_no_ws.apply(X),
                       err_msg="Failed with {0}".format(name))

def test_ovr_multilabel_predict_proba():
    base_clf = MultinomialNB(alpha=1)
    for au in (False, True):
        X, Y = datasets.make_multilabel_classification(n_samples=100,
                                                       n_features=20,
                                                       n_classes=5,
                                                       n_labels=3,
                                                       length=50,
                                                       allow_unlabeled=au,
                                                       return_indicator=True,
                                                       random_state=0)
        X_train, Y_train = X[:80], Y[:80]
        X_test, Y_test = X[80:], Y[80:]
        clf = OneVsRestClassifier(base_clf).fit(X_train, Y_train)

        # decision function only estimator. Fails in current implementation.
        decision_only = OneVsRestClassifier(svm.SVR()).fit(X_train, Y_train)
        assert_raises(AttributeError, decision_only.predict_proba, X_test)

        # Estimator with predict_proba disabled, depending on parameters.
        decision_only = OneVsRestClassifier(svm.SVC(probability=False))
        decision_only.fit(X_train, Y_train)
        assert_raises(AttributeError, decision_only.predict_proba, X_test)

        Y_pred = clf.predict(X_test)
        Y_proba = clf.predict_proba(X_test)

        # predict assigns a label if the probability that the
        # sample has the label is greater than 0.5.
        pred = Y_proba > .5
        assert_array_equal(pred, Y_pred)

def test_Y_is_not_None():
    rng = np.random.RandomState(0)
    hm = HammingKernel()
    X = rng.randint(0, 4, (5, 3))

    hm = HammingKernel(length_scale=[1.0, 1.0, 1.0])
    assert_array_equal(hm(X), hm(X, X))

def test_ovr_multilabel():
    # Toy dataset where features correspond directly to labels.
    X = np.array([[0, 4, 5], [0, 5, 0], [3, 3, 3], [4, 0, 6], [6, 0, 0]])
    y = [["spam", "eggs"], ["spam"], ["ham", "eggs", "spam"],
         ["ham", "eggs"], ["ham"]]
    #y = [[1, 2], [1], [0, 1, 2], [0, 2], [0]]
    Y = np.array([[0, 1, 1],
                  [0, 1, 0],
                  [1, 1, 1],
                  [1, 0, 1],
                  [1, 0, 0]])

    classes = set("ham eggs spam".split())

    for base_clf in (MultinomialNB(), LinearSVC(random_state=0),
                     LinearRegression(), Ridge(),
                     ElasticNet(), Lasso(alpha=0.5)):
        # test input as lists of tuples
        clf = assert_warns(DeprecationWarning,
                           OneVsRestClassifier(base_clf).fit,
                           X, y)
        assert_equal(set(clf.classes_), classes)
        y_pred = clf.predict([[0, 4, 4]])[0]
        assert_equal(set(y_pred), set(["spam", "eggs"]))
        assert_true(clf.multilabel_)

        # test input as label indicator matrix
        clf = OneVsRestClassifier(base_clf).fit(X, Y)
        y_pred = clf.predict([[0, 4, 4]])[0]
        assert_array_equal(y_pred, [0, 1, 1])
        assert_true(clf.multilabel_)

def test_make_swiss_roll():
    X, t = make_swiss_roll(n_samples=5, noise=0.0, random_state=0)

    assert_equal(X.shape, (5, 3), "X shape mismatch")
    assert_equal(t.shape, (5,), "t shape mismatch")
    assert_array_equal(X[:, 0], t * np.cos(t))
    assert_array_equal(X[:, 2], t * np.sin(t))