def check_transformer_pickle(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)
    n_samples, n_features = X.shape
    X = StandardScaler().fit_transform(X)
    X -= X.min()
    # catch deprecation warnings
    with warnings.catch_warnings(record=True):
        transformer = Transformer()
    if not hasattr(transformer, 'transform'):
        return
    set_random_state(transformer)
    set_fast_parameters(transformer)

    # fit
    if name in CROSS_DECOMPOSITION:
        random_state = np.random.RandomState(seed=12345)
        y_ = np.vstack([y, 2 * y + random_state.randint(2, size=len(y))])
        y_ = y_.T
    else:
        y_ = y

    transformer.fit(X, y_)
    X_pred = transformer.fit(X, y_).transform(X)
    pickled_transformer = pickle.dumps(transformer)
    unpickled_transformer = pickle.loads(pickled_transformer)
    pickled_X_pred = unpickled_transformer.transform(X)

    assert_array_almost_equal(pickled_X_pred, X_pred)

def check_target_type(name, Estimator):
    X = np.random.random((20, 2))
    y = np.linspace(0, 1, 20)
    estimator = Estimator()
    set_random_state(estimator)
    with warns(UserWarning, match='should be of types'):
        estimator.fit(X, y)

def test_get_metric_works_does_not_raise(estimator, build_dataset):
  """Tests that the metric returned by get_metric does not raise errors (or
  warnings) similarly to the distance functions in scipy.spatial.distance"""
  input_data, labels, _, X = build_dataset()
  model = clone(estimator)
  set_random_state(model)
  model.fit(input_data, labels)
  metric = model.get_metric()

  list_test_get_metric_doesnt_raise = [(X[0], X[1]),
                                       (X[0].tolist(), X[1].tolist()),
                                       (X[0][None], X[1][None])]

  for u, v in list_test_get_metric_doesnt_raise:
    with pytest.warns(None) as record:
      metric(u, v)
    assert len(record) == 0

  # Test that the scalar case works
  model.transformer_ = np.array([3.1])
  metric = model.get_metric()
  for u, v in [(5, 6.7), ([5], [6.7]), ([[5]], [[6.7]])]:
    with pytest.warns(None) as record:
      metric(u, v)
    assert len(record) == 0

def check_estimators_overwrite_params(name, Estimator):
    X, y = make_blobs(random_state=0, n_samples=9)
    y = multioutput_estimator_convert_y_2d(name, y)
    # some want non-negative input
    X -= X.min()
    with warnings.catch_warnings(record=True):
        # catch deprecation warnings
        estimator = Estimator()

    set_fast_parameters(estimator)
    set_random_state(estimator)

    # Make a physical copy of the orginal 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))

def test_set_random_state():
    lda = LDA()
    tree = DecisionTreeClassifier()
    # LDA doesn't have random state: smoke test
    set_random_state(lda, 3)
    set_random_state(tree, 3)
    assert_equal(tree.random_state, 3)

def check_estimators_pickle(name, Estimator):
    """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()

    # some estimators only take multioutputs
    y = multioutput_estimator_convert_y_2d(name, y)

    # catch deprecation warnings
    with warnings.catch_warnings(record=True):
        estimator = Estimator()

    set_random_state(estimator)
    set_fast_parameters(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)
    unpickled_estimator = pickle.loads(pickled_estimator)

    for method in result:
        unpickled_result = getattr(unpickled_estimator, method)(X)
        assert_array_almost_equal(result[method], unpickled_result)

def test_class_weight_classifiers():
    # test that class_weight works and that the semantics are consistent
    classifiers = all_estimators(type_filter="classifier")

    with warnings.catch_warnings(record=True):
        classifiers = [c for c in classifiers if "class_weight" in c[1]().get_params().keys()]

    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=0.5, random_state=0)
        for name, Classifier in classifiers:
            if name == "NuSVC":
                # the sparse version has a parameter that doesn't do anything
                continue
            if name.endswith("NB"):
                # NaiveBayes classifiers have a somewhat different interface.
                # FIXME SOON!
                continue
            if n_centers == 2:
                class_weight = {0: 1000, 1: 0.0001}
            else:
                class_weight = {0: 1000, 1: 0.0001, 2: 0.0001}

            with warnings.catch_warnings(record=True):
                classifier = Classifier(class_weight=class_weight)
            if hasattr(classifier, "n_iter"):
                classifier.set_params(n_iter=100)

            set_random_state(classifier)
            classifier.fit(X_train, y_train)
            y_pred = classifier.predict(X_test)
            assert_greater(np.mean(y_pred == 0), 0.9)

def test_various_scoring_on_tuples_learners(estimator, build_dataset,
                                            with_preprocessor):
  """Tests that scikit-learn's scoring returns something finite,
  for other scoring than default scoring. (List of scikit-learn's scores can be
  found in sklearn.metrics.scorer). For each type of output (predict,
  predict_proba, decision_function), we test a bunch of scores.
  We only test on pairs learners because quadruplets don't have a y argument.
  """
  input_data, labels, preprocessor, _ = build_dataset(with_preprocessor)
  estimator = clone(estimator)
  estimator.set_params(preprocessor=preprocessor)
  set_random_state(estimator)

  # scores that need a predict function: every tuples learner should have a
  # predict function (whether the pair is of positive samples or negative
  # samples)
  for scoring in ['accuracy', 'f1']:
    check_score_is_finite(scoring, estimator, input_data, labels)
  # scores that need a predict_proba:
  if hasattr(estimator, "predict_proba"):
    for scoring in ['neg_log_loss', 'brier_score']:
      check_score_is_finite(scoring, estimator, input_data, labels)
  # scores that need a decision_function: every tuples learner should have a
  # decision function (the metric between points)
  for scoring in ['roc_auc', 'average_precision', 'precision', 'recall']:
    check_score_is_finite(scoring, estimator, input_data, labels)

def test_set_random_state():
    lda = LinearDiscriminantAnalysis()
    tree = DecisionTreeClassifier()
    # Linear Discriminant Analysis doesn't have random state: smoke test
    set_random_state(lda, 3)
    set_random_state(tree, 3)
    assert_equal(tree.random_state, 3)

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)
        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_))

def check_class_weight_balanced_linear_classifier(name, Classifier):
    """Test class weights with non-contiguous class labels."""
    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])

    with warnings.catch_warnings(record=True):
        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)
    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_array_almost_equal(coef_balanced, coef_manual)

def check_estimators_overwrite_params(name, Estimator):
    X, y = make_blobs(random_state=0, n_samples=9)
    y = multioutput_estimator_convert_y_2d(name, y)
    # some want non-negative input
    X -= X.min()
    with warnings.catch_warnings(record=True):
        # catch deprecation warnings
        estimator = Estimator()

    if name == 'MiniBatchDictLearning' or name == 'MiniBatchSparsePCA':
        # FIXME
        # for MiniBatchDictLearning and MiniBatchSparsePCA
        estimator.batch_size = 1

    set_fast_parameters(estimator)

    set_random_state(estimator)

    params = estimator.get_params()
    estimator.fit(X, y)
    new_params = estimator.get_params()
    for k, v in params.items():
        assert_false(np.any(new_params[k] != v),
                     "Estimator %s changes its parameter %s"
                     " from %s to %s during fit."
                     % (name, k, v, new_params[k]))

def test_regressors_int():
    # test if regressors can cope with integer labels (by converting them to
    # float)
    regressors = all_estimators(type_filter='regressor')
    boston = load_boston()
    X, y = boston.data, boston.target
    X, y = shuffle(X, y, random_state=0)
    X = StandardScaler().fit_transform(X)
    y = np.random.randint(2, size=X.shape[0])
    for name, Reg in regressors:
        if Reg in dont_test or Reg in (CCA,):
            continue
        # catch deprecation warnings
        with warnings.catch_warnings(record=True):
            # separate estimators to control random seeds
            reg1 = Reg()
            reg2 = Reg()
        set_random_state(reg1)
        set_random_state(reg2)

        if Reg in (_PLS, PLSCanonical, PLSRegression):
            y_ = np.vstack([y, 2 * y + np.random.randint(2, size=len(y))])
            y_ = y_.T
        else:
            y_ = y

        # fit
        reg1.fit(X, y_)
        pred1 = reg1.predict(X)
        reg2.fit(X, y_.astype(np.float))
        pred2 = reg2.predict(X)
        assert_array_almost_equal(pred1, pred2, 2, name)

def check_regressors_int(name, Regressor, X, y):
    if name == 'OrthogonalMatchingPursuitCV':
        # FIXME: This test is unstable on Travis, see issue #3190.
        check_skip_travis()
    rnd = np.random.RandomState(0)
    # catch deprecation warnings
    with warnings.catch_warnings(record=True):
        # separate estimators to control random seeds
        regressor_1 = Regressor()
        regressor_2 = Regressor()
    set_random_state(regressor_1)
    set_random_state(regressor_2)

    if name in ('_PLS', 'PLSCanonical', 'PLSRegression'):
        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_array_almost_equal(pred1, pred2, 2, name)

def check_regressors_int(name, Regressor):
    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(name, y)
    rnd = np.random.RandomState(0)
    # catch deprecation warnings
    with warnings.catch_warnings(record=True):
        # separate estimators to control random seeds
        regressor_1 = Regressor()
        regressor_2 = Regressor()
    set_fast_parameters(regressor_1)
    set_fast_parameters(regressor_2)
    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_array_almost_equal(pred1, pred2, 2, name)

def check_classifiers_input_shapes(name, Classifier):
    iris = load_iris()
    X, y = iris.data, iris.target
    X, y = shuffle(X, y, random_state=1)
    X = StandardScaler().fit_transform(X)
    # catch deprecation warnings
    with warnings.catch_warnings(record=True):
        classifier = Classifier()
    set_fast_parameters(classifier)
    set_random_state(classifier)
    # fit
    classifier.fit(X, y)
    y_pred = classifier.predict(X)

    set_random_state(classifier)
    # 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)
        classifier.fit(X, y[:, np.newaxis])
    msg = "expected 1 DataConversionWarning, got: %s" % (
        ", ".join([str(w_x) for w_x in w]))
    assert_equal(len(w), 1, msg)
    assert_array_equal(y_pred, classifier.predict(X))

def check_estimators_overwrite_params(name, Estimator, X, y):
    with warnings.catch_warnings(record=True):
        # catch deprecation warnings
        estimator = Estimator()

    if hasattr(estimator, 'batch_size'):
        # FIXME
        # for MiniBatchDictLearning
        estimator.batch_size = 1

    if name in ['GaussianRandomProjection',
                'SparseRandomProjection']:
        # Due to the jl lemma and very few samples, the number
        # of components of the random matrix projection will be
        # greater
        # than the number of features.
        # So we impose a smaller number (avoid "auto" mode)
        estimator = Estimator(n_components=1)
    elif name == "SelectKBest":
        estimator = Estimator(k=1)

    set_random_state(estimator)

    params = estimator.get_params()
    estimator.fit(X, y)
    new_params = estimator.get_params()
    for k, v in params.items():
        assert_false(np.any(new_params[k] != v),
                     "Estimator %s changes its parameter %s"
                     " from %s to %s during fit."
                     % (name, k, v, new_params[k]))

def check_class_weight_auto_linear_classifier(name, Classifier):
    """Test class weights with non-contiguous class labels."""
    X = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
                  [1.0, 1.0], [1.0, 0.0]])
    y = [1, 1, 1, -1, -1]

    with warnings.catch_warnings(record=True):
        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)
    set_random_state(classifier)

    # Let the model compute the class frequencies
    classifier.set_params(class_weight='auto')
    coef_auto = classifier.fit(X, y).coef_.copy()

    # Count each label occurrence to reweight manually
    mean_weight = (1. / 3 + 1. / 2) / 2
    class_weight = {
        1: 1. / 3 / mean_weight,
        -1: 1. / 2 / mean_weight,
    }
    classifier.set_params(class_weight=class_weight)
    coef_manual = classifier.fit(X, y).coef_.copy()

    assert_array_almost_equal(coef_auto, coef_manual)

def check_clustering(name, Alg):
    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
    with warnings.catch_warnings(record=True):
        alg = Alg()
    set_fast_parameters(alg)
    if hasattr(alg, "n_clusters"):
        alg.set_params(n_clusters=3)
    set_random_state(alg)
    if name == 'AffinityPropagation':
        alg.set_params(preference=-100)
        alg.set_params(max_iter=100)

    # fit
    alg.fit(X)
    # with lists
    alg.fit(X.tolist())

    assert_equal(alg.labels_.shape, (n_samples,))
    pred = alg.labels_
    assert_greater(adjusted_rand_score(pred, y), 0.4)
    # fit another time with ``fit_predict`` and compare results
    if name is 'SpectralClustering':
        # there is no way to make Spectral clustering deterministic :(
        return
    set_random_state(alg)
    with warnings.catch_warnings(record=True):
        pred2 = alg.fit_predict(X)
    assert_array_equal(pred, pred2)

def check_pipeline_consistency(name, Estimator):
    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()
    y = multioutput_estimator_convert_y_2d(name, y)
    estimator = Estimator()
    set_fast_parameters(estimator)
    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_array_almost_equal(result, result_pipe)