Python testing.assert_equal函数代码示例

def test_kfold_valueerrors():
    # Check that errors are raised if there is not enough samples
    assert_raises(ValueError, cval.KFold, 3, 4)

    # Check that a warning is raised if the least populated class has too few
    # members.
    with warnings.catch_warnings(record=True) as w:
        warnings.simplefilter('always')
        y = [3, 3, -1, -1, 2]
        cv = cval.StratifiedKFold(y, 3)
        # checking there was only one warning.
        assert_equal(len(w), 1)
        # checking it has the right type
        assert_equal(w[0].category, Warning)
        # checking it's the right warning. This might be a bad test since it's
        # a characteristic of the code and not a behavior
        assert_true("The least populated class" in str(w[0]))

        # Check that despite the warning the folds are still computed even
        # though all the classes are not necessarily represented at on each
        # side of the split at each split
        check_cv_coverage(cv, expected_n_iter=3, n_samples=len(y))

    # Error when number of folds is <= 1
    assert_raises(ValueError, cval.KFold, 2, 0)
    assert_raises(ValueError, cval.KFold, 2, 1)
    assert_raises(ValueError, cval.StratifiedKFold, y, 0)
    assert_raises(ValueError, cval.StratifiedKFold, y, 1)

    # When n is not integer:
    assert_raises(ValueError, cval.KFold, 2.5, 2)

    # When n_folds is not integer:
    assert_raises(ValueError, cval.KFold, 5, 1.5)
    assert_raises(ValueError, cval.StratifiedKFold, y, 1.5)

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_RadiusNeighborsRegressor_multioutput_with_uniform_weight():
    """Test radius neighbors in multi-output regression (uniform weight)"""

    rng = check_random_state(0)
    n_features = 5
    n_samples = 40
    n_output = 4

    X = rng.rand(n_samples, n_features)
    y = rng.rand(n_samples, n_output)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

    for algorithm, weights in product(ALGORITHMS, [None, 'uniform']):

        rnn = neighbors. RadiusNeighborsRegressor(weights=weights,
                                                  algorithm=algorithm)
        rnn.fit(X_train, y_train)

        neigh_idx = rnn.radius_neighbors(X_test, return_distance=False)
        y_pred_idx = np.array([np.mean(y_train[idx], axis=0)
                               for idx in neigh_idx])

        y_pred_idx = np.array(y_pred_idx)
        y_pred = rnn.predict(X_test)

        assert_equal(y_pred_idx.shape, y_test.shape)
        assert_equal(y_pred.shape, y_test.shape)
        assert_array_almost_equal(y_pred, y_pred_idx)

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_ridge():
    # Ridge regression convergence test using score
    # TODO: for this test to be robust, we should use a dataset instead
    # of np.random.
    rng = np.random.RandomState(0)
    alpha = 1.0

    for solver in ("svd", "sparse_cg", "cholesky", "lsqr"):
        # With more samples than features
        n_samples, n_features = 6, 5
        y = rng.randn(n_samples)
        X = rng.randn(n_samples, n_features)

        ridge = Ridge(alpha=alpha, solver=solver)
        ridge.fit(X, y)
        assert_equal(ridge.coef_.shape, (X.shape[1], ))
        assert_greater(ridge.score(X, y), 0.47)

        if solver == "cholesky":
            # Currently the only solver to support sample_weight.
            ridge.fit(X, y, sample_weight=np.ones(n_samples))
            assert_greater(ridge.score(X, y), 0.47)

        # With more features than samples
        n_samples, n_features = 5, 10
        y = rng.randn(n_samples)
        X = rng.randn(n_samples, n_features)
        ridge = Ridge(alpha=alpha, solver=solver)
        ridge.fit(X, y)
        assert_greater(ridge.score(X, y), .9)

        if solver == "cholesky":
            # Currently the only solver to support sample_weight.
            ridge.fit(X, y, sample_weight=np.ones(n_samples))
            assert_greater(ridge.score(X, y), 0.9)

def test_load_fake_lfw_pairs():
    lfw_pairs_train = fetch_lfw_pairs(data_home=SCIKIT_LEARN_DATA,
                                      download_if_missing=False)

    # The data is croped around the center as a rectangular bounding box
    # around the face. Colors are converted to gray levels:
    assert_equal(lfw_pairs_train.pairs.shape, (10, 2, 62, 47))

    # the target is whether the person is the same or not
    assert_array_equal(lfw_pairs_train.target, [1, 1, 1, 1, 1, 0, 0, 0, 0, 0])

    # names of the persons can be found using the target_names array
    expected_classes = ['Different persons', 'Same person']
    assert_array_equal(lfw_pairs_train.target_names, expected_classes)

    # It is possible to ask for the original data without any croping or color
    # conversion
    lfw_pairs_train = fetch_lfw_pairs(data_home=SCIKIT_LEARN_DATA, resize=None,
                                      slice_=None, color=True,
                                      download_if_missing=False)
    assert_equal(lfw_pairs_train.pairs.shape, (10, 2, 250, 250, 3))

    # the ids and class names are the same as previously
    assert_array_equal(lfw_pairs_train.target, [1, 1, 1, 1, 1, 0, 0, 0, 0, 0])
    assert_array_equal(lfw_pairs_train.target_names, expected_classes)

def test_cross_val_predict_input_types():
    clf = Ridge()
    # Smoke test
    predictions = cval.cross_val_predict(clf, X, y)
    assert_equal(predictions.shape, (10,))

    # test with multioutput y
    predictions = cval.cross_val_predict(clf, X_sparse, X)
    assert_equal(predictions.shape, (10, 2))

    predictions = cval.cross_val_predict(clf, X_sparse, y)
    assert_array_equal(predictions.shape, (10,))

    # test with multioutput y
    predictions = cval.cross_val_predict(clf, X_sparse, X)
    assert_array_equal(predictions.shape, (10, 2))

    # test with X and y as list
    list_check = lambda x: isinstance(x, list)
    clf = CheckingClassifier(check_X=list_check)
    predictions = cval.cross_val_predict(clf, X.tolist(), y.tolist())

    clf = CheckingClassifier(check_y=list_check)
    predictions = cval.cross_val_predict(clf, X, y.tolist())

    # test with 3d X and
    X_3d = X[:, :, np.newaxis]
    check_3d = lambda x: x.ndim == 3
    clf = CheckingClassifier(check_X=check_3d)
    predictions = cval.cross_val_predict(clf, X_3d, y)
    assert_array_equal(predictions.shape, (10,))

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))

def test_make_s_curve():
    X, t = make_s_curve(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], np.sin(t))
    assert_array_equal(X[:, 2], np.sign(t) * (np.cos(t) - 1))

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 check_warm_start_oob(name):
    # Test that the warm start computes oob score when asked.
    X, y = hastie_X, hastie_y
    ForestEstimator = FOREST_ESTIMATORS[name]
    # Use 15 estimators to avoid 'some inputs do not have OOB scores' warning.
    clf = ForestEstimator(n_estimators=15, max_depth=3, warm_start=False,
                          random_state=1, bootstrap=True, oob_score=True)
    clf.fit(X, y)

    clf_2 = ForestEstimator(n_estimators=5, max_depth=3, warm_start=False,
                            random_state=1, bootstrap=True, oob_score=False)
    clf_2.fit(X, y)

    clf_2.set_params(warm_start=True, oob_score=True, n_estimators=15)
    clf_2.fit(X, y)

    assert_true(hasattr(clf_2, 'oob_score_'))
    assert_equal(clf.oob_score_, clf_2.oob_score_)

    # Test that oob_score is computed even if we don't need to train
    # additional trees.
    clf_3 = ForestEstimator(n_estimators=15, max_depth=3, warm_start=True,
                            random_state=1, bootstrap=True, oob_score=False)
    clf_3.fit(X, y)
    assert_true(not(hasattr(clf_3, 'oob_score_')))

    clf_3.set_params(oob_score=True)
    ignore_warnings(clf_3.fit)(X, y)

    assert_equal(clf.oob_score_, clf_3.oob_score_)

def test_check_estimator_clones():
    # check that check_estimator doesn't modify the estimator it receives
    from sklearn.datasets import load_iris
    iris = load_iris()

    for Estimator in [GaussianMixture, LinearRegression,
                      RandomForestClassifier, NMF, SGDClassifier,
                      MiniBatchKMeans]:
        with ignore_warnings(category=FutureWarning):
            # when 'est = SGDClassifier()'
            est = Estimator()
        set_checking_parameters(est)
        set_random_state(est)
        # without fitting
        old_hash = joblib.hash(est)
        check_estimator(est)
        assert_equal(old_hash, joblib.hash(est))

        with ignore_warnings(category=FutureWarning):
            # when 'est = SGDClassifier()'
            est = Estimator()
        set_checking_parameters(est)
        set_random_state(est)
        # with fitting
        est.fit(iris.data + 10, iris.target)
        old_hash = joblib.hash(est)
        check_estimator(est)
        assert_equal(old_hash, joblib.hash(est))

def test_compute_full_tree():
    """Test that the full tree is computed if n_clusters is small"""
    rng = np.random.RandomState(0)
    X = rng.randn(10, 2)
    connectivity = kneighbors_graph(X, 5, include_self=False)

    # When n_clusters is less, the full tree should be built
    # that is the number of merges should be n_samples - 1
    agc = AgglomerativeClustering(n_clusters=2, connectivity=connectivity)
    agc.fit(X)
    n_samples = X.shape[0]
    n_nodes = agc.children_.shape[0]
    assert_equal(n_nodes, n_samples - 1)

    # When n_clusters is large, greater than max of 100 and 0.02 * n_samples.
    # we should stop when there are n_clusters.
    n_clusters = 101
    X = rng.randn(200, 2)
    connectivity = kneighbors_graph(X, 10, include_self=False)
    agc = AgglomerativeClustering(n_clusters=n_clusters,
                                  connectivity=connectivity)
    agc.fit(X)
    n_samples = X.shape[0]
    n_nodes = agc.children_.shape[0]
    assert_equal(n_nodes, n_samples - n_clusters)

def test_symmetry():
    """Test the symmetry of score and loss functions"""
    random_state = check_random_state(0)
    y_true = random_state.randint(0, 2, size=(20, ))
    y_pred = random_state.randint(0, 2, size=(20, ))

    # We shouldn't forget any metrics
    assert_equal(set(SYMMETRIC_METRICS).union(NOT_SYMMETRIC_METRICS,
                                              THRESHOLDED_METRICS,
                                              METRIC_UNDEFINED_MULTICLASS),
                 set(ALL_METRICS))

    assert_equal(
        set(SYMMETRIC_METRICS).intersection(set(NOT_SYMMETRIC_METRICS)),
        set([]))

    # Symmetric metric
    for name in SYMMETRIC_METRICS:
        metric = ALL_METRICS[name]
        assert_almost_equal(metric(y_true, y_pred),
                            metric(y_pred, y_true),
                            err_msg="%s is not symmetric" % name)

    # Not symmetric metrics
    for name in NOT_SYMMETRIC_METRICS:
        metric = ALL_METRICS[name]
        assert_true(np.any(metric(y_true, y_pred) != metric(y_pred, y_true)),
                    msg="%s seems to be symmetric" % name)

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)