Python testing.assert_almost_equal函数代码示例

def test_check_scoring():
    """Test all branches of check_scoring"""
    estimator = EstimatorWithoutFit()
    pattern = (r"estimator should a be an estimator implementing 'fit' method,"
               r" .* was passed")
    assert_raises_regexp(TypeError, pattern, check_scoring, estimator)

    estimator = EstimatorWithFitAndScore()
    estimator.fit([[1]], [1])
    scorer = check_scoring(estimator)
    assert_almost_equal(scorer(estimator, [[1]], [1]), 1.0)

    estimator = EstimatorWithFitAndPredict()
    estimator.fit([[1]], [1])
    pattern = (r"If no scoring is specified, the estimator passed should have"
               r" a 'score' method\. The estimator .* does not\.")
    assert_raises_regexp(TypeError, pattern, check_scoring, estimator)

    scorer = check_scoring(estimator, "accuracy")
    assert_almost_equal(scorer(estimator, [[1]], [1]), 1.0)

    estimator = EstimatorWithFit()
    pattern = (r"The estimator passed should have a 'score'"
               r" or a 'predict' method\. The estimator .* does not\.")
    assert_raises_regexp(TypeError, pattern, check_scoring, estimator,
                         "accuracy")

    estimator = EstimatorWithFit()
    scorer = check_scoring(estimator, allow_none=True)
    assert_true(scorer is None)

def test_accessible_kl_divergence():
    # Ensures that the accessible kl_divergence matches the computed value
    random_state = check_random_state(0)
    X = random_state.randn(100, 2)
    tsne = TSNE(n_iter_without_progress=2, verbose=2,
                random_state=0, method='exact')

    old_stdout = sys.stdout
    sys.stdout = StringIO()
    try:
        tsne.fit_transform(X)
    finally:
        out = sys.stdout.getvalue()
        sys.stdout.close()
        sys.stdout = old_stdout

    # The output needs to contain the accessible kl_divergence as the error at
    # the last iteration
    for line in out.split('\n')[::-1]:
        if 'Iteration' in line:
            _, _, error = line.partition('error = ')
            if error:
                error, _, _ = error.partition(',')
                break
    assert_almost_equal(tsne.kl_divergence_, float(error), decimal=5)

def test_randomized_pca_check_list():
    """Test that the projection by RandomizedPCA on list data is correct"""
    X = [[1.0, 0.0], [0.0, 1.0]]
    X_transformed = RandomizedPCA(n_components=1, random_state=0).fit(X).transform(X)
    assert_equal(X_transformed.shape, (2, 1))
    assert_almost_equal(X_transformed.mean(), 0.00, 2)
    assert_almost_equal(X_transformed.std(), 0.71, 2)

def test_randomized_svd_low_rank_with_noise():
    """Check that extmath.randomized_svd can handle noisy matrices"""
    n_samples = 100
    n_features = 500
    rank = 5
    k = 10

    # generate a matrix X wity structure approximate rank `rank` and an
    # important noisy component
    X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
                             effective_rank=rank, tail_strength=0.5,
                             random_state=0)
    assert_equal(X.shape, (n_samples, n_features))

    # compute the singular values of X using the slow exact method
    _, s, _ = linalg.svd(X, full_matrices=False)

    # compute the singular values of X using the fast approximate method
    # without the iterated power method
    _, sa, _ = randomized_svd(X, k, n_iter=0)

    # the approximation does not tolerate the noise:
    assert_greater(np.abs(s[:k] - sa).max(), 0.05)

    # compute the singular values of X using the fast approximate method with
    # iterated power method
    _, sap, _ = randomized_svd(X, k, n_iter=5)

    # the iterated power method is helping getting rid of the noise:
    assert_almost_equal(s[:k], sap, decimal=3)

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_fetch_rcv1():
    try:
        data1 = fetch_rcv1(shuffle=False, download_if_missing=False)
    except IOError as e:
        if e.errno == errno.ENOENT:
            raise SkipTest("Download RCV1 dataset to run this test.")

    X1, Y1 = data1.data, data1.target
    cat_list, s1 = data1.target_names.tolist(), data1.sample_id

    # test sparsity
    assert_true(sp.issparse(X1))
    assert_true(sp.issparse(Y1))
    assert_equal(60915113, X1.data.size)
    assert_equal(2606875, Y1.data.size)

    # test shapes
    assert_equal((804414, 47236), X1.shape)
    assert_equal((804414, 103), Y1.shape)
    assert_equal((804414,), s1.shape)
    assert_equal(103, len(cat_list))

    # test ordering of categories
    first_categories = [u'C11', u'C12', u'C13', u'C14', u'C15', u'C151']
    assert_array_equal(first_categories, cat_list[:6])

    # test number of sample for some categories
    some_categories = ('GMIL', 'E143', 'CCAT')
    number_non_zero_in_cat = (5, 1206, 381327)
    for num, cat in zip(number_non_zero_in_cat, some_categories):
        j = cat_list.index(cat)
        assert_equal(num, Y1[:, j].data.size)

    # test shuffling and subset
    data2 = fetch_rcv1(shuffle=True, subset='train', random_state=77,
                       download_if_missing=False)
    X2, Y2 = data2.data, data2.target
    s2 = data2.sample_id

    # test return_X_y option
    fetch_func = partial(fetch_rcv1, shuffle=False, subset='train',
                         download_if_missing=False)
    check_return_X_y(data2, fetch_func)

    # The first 23149 samples are the training samples
    assert_array_equal(np.sort(s1[:23149]), np.sort(s2))

    # test some precise values
    some_sample_ids = (2286, 3274, 14042)
    for sample_id in some_sample_ids:
        idx1 = s1.tolist().index(sample_id)
        idx2 = s2.tolist().index(sample_id)

        feature_values_1 = X1[idx1, :].toarray()
        feature_values_2 = X2[idx2, :].toarray()
        assert_almost_equal(feature_values_1, feature_values_2)

        target_values_1 = Y1[idx1, :].toarray()
        target_values_2 = Y2[idx2, :].toarray()
        assert_almost_equal(target_values_1, target_values_2)

def test_multilabel_hamming_loss():
    # Dense label indicator matrix format
    y1 = np.array([[0, 1, 1], [1, 0, 1]])
    y2 = np.array([[0, 0, 1], [1, 0, 1]])

    assert_equal(hamming_loss(y1, y2), 1 / 6)
    assert_equal(hamming_loss(y1, y1), 0)
    assert_equal(hamming_loss(y2, y2), 0)
    assert_equal(hamming_loss(y2, np.logical_not(y2)), 1)
    assert_equal(hamming_loss(y1, np.logical_not(y1)), 1)
    assert_equal(hamming_loss(y1, np.zeros(y1.shape)), 4 / 6)
    assert_equal(hamming_loss(y2, np.zeros(y1.shape)), 0.5)

    with ignore_warnings():  # sequence of sequences is deprecated
        # List of tuple of label
        y1 = [(1, 2,), (0, 2,)]
        y2 = [(2,), (0, 2,)]

        assert_equal(hamming_loss(y1, y2), 1 / 6)
        assert_equal(hamming_loss(y1, y1), 0)
        assert_equal(hamming_loss(y2, y2), 0)
        assert_equal(hamming_loss(y2, [(), ()]), 0.75)
        assert_equal(hamming_loss(y1, [tuple(), (10, )]), 0.625)
        assert_almost_equal(hamming_loss(y2, [tuple(), (10, )],
                                         classes=np.arange(11)), 0.1818, 2)

    def test_average_binary_computed_correctly(self):
        """Checks the SGDClassifier correctly computes the average weights"""
        eta = 0.1
        alpha = 2.0
        n_samples = 20
        n_features = 10
        rng = np.random.RandomState(0)
        X = rng.normal(size=(n_samples, n_features))
        w = rng.normal(size=n_features)

        clf = self.factory(
            loss="squared_loss",
            learning_rate="constant",
            eta0=eta,
            alpha=alpha,
            fit_intercept=True,
            n_iter=1,
            average=True,
            shuffle=False,
        )

        # simple linear function without noise
        y = np.dot(X, w)
        y = np.sign(y)

        clf.fit(X, y)

        average_weights, average_intercept = self.asgd(X, y, eta, alpha)
        average_weights = average_weights.reshape(1, -1)
        assert_array_almost_equal(clf.coef_, average_weights, decimal=14)
        assert_almost_equal(clf.intercept_, average_intercept, decimal=14)

    def test_sgd_multiclass_average(self):
        eta = 0.001
        alpha = 0.01
        """Multi-class average test case"""
        clf = self.factory(
            loss="squared_loss",
            learning_rate="constant",
            eta0=eta,
            alpha=alpha,
            fit_intercept=True,
            n_iter=1,
            average=True,
            shuffle=False,
        )

        np_Y2 = np.array(Y2)
        clf.fit(X2, np_Y2)
        classes = np.unique(np_Y2)

        for i, cl in enumerate(classes):
            y_i = np.ones(np_Y2.shape[0])
            y_i[np_Y2 != cl] = -1
            average_coef, average_intercept = self.asgd(X2, y_i, eta, alpha)
            assert_array_almost_equal(average_coef, clf.coef_[i], decimal=16)
            assert_almost_equal(average_intercept, clf.intercept_[i], decimal=16)

def test_dtype_match_cholesky():
    # Test different alphas in cholesky solver to ensure full coverage.
    # This test is separated from test_dtype_match for clarity.
    rng = np.random.RandomState(0)
    alpha = (1.0, 0.5)

    n_samples, n_features, n_target = 6, 7, 2
    X_64 = rng.randn(n_samples, n_features)
    y_64 = rng.randn(n_samples, n_target)
    X_32 = X_64.astype(np.float32)
    y_32 = y_64.astype(np.float32)

    # Check type consistency 32bits
    ridge_32 = Ridge(alpha=alpha, solver='cholesky')
    ridge_32.fit(X_32, y_32)
    coef_32 = ridge_32.coef_

    # Check type consistency 64 bits
    ridge_64 = Ridge(alpha=alpha, solver='cholesky')
    ridge_64.fit(X_64, y_64)
    coef_64 = ridge_64.coef_

    # Do all the checks at once, like this is easier to debug
    assert coef_32.dtype == X_32.dtype
    assert coef_64.dtype == X_64.dtype
    assert ridge_32.predict(X_32).dtype == X_32.dtype
    assert ridge_64.predict(X_64).dtype == X_64.dtype
    assert_almost_equal(ridge_32.coef_, ridge_64.coef_, decimal=5)

def test_lasso_cv():
    X, y, X_test, y_test = build_dataset()
    max_iter = 150
    clf = LassoCV(n_alphas=10, eps=1e-3, max_iter=max_iter).fit(X, y)
    assert_almost_equal(clf.alpha_, 0.056, 2)

    clf = LassoCV(n_alphas=10, eps=1e-3, max_iter=max_iter, precompute=True)
    clf.fit(X, y)
    assert_almost_equal(clf.alpha_, 0.056, 2)

    # Check that the lars and the coordinate descent implementation
    # select a similar alpha
    lars = LassoLarsCV(normalize=False, max_iter=30).fit(X, y)
    # for this we check that they don't fall in the grid of
    # clf.alphas further than 1
    assert_true(np.abs(
        np.searchsorted(clf.alphas_[::-1], lars.alpha_) -
        np.searchsorted(clf.alphas_[::-1], clf.alpha_)) <= 1)
    # check that they also give a similar MSE
    mse_lars = interpolate.interp1d(lars.cv_alphas_, lars.cv_mse_path_.T)
    np.testing.assert_approx_equal(mse_lars(clf.alphas_[5]).mean(),
                                   clf.mse_path_[5].mean(), significant=2)

    # test set
    assert_greater(clf.score(X_test, y_test), 0.99)

def test_dtype_match():
    rng = np.random.RandomState(0)
    alpha = 1.0

    n_samples, n_features = 6, 5
    X_64 = rng.randn(n_samples, n_features)
    y_64 = rng.randn(n_samples)
    X_32 = X_64.astype(np.float32)
    y_32 = y_64.astype(np.float32)

    solvers = ["svd", "sparse_cg", "cholesky", "lsqr"]
    for solver in solvers:

        # Check type consistency 32bits
        ridge_32 = Ridge(alpha=alpha, solver=solver)
        ridge_32.fit(X_32, y_32)
        coef_32 = ridge_32.coef_

        # Check type consistency 64 bits
        ridge_64 = Ridge(alpha=alpha, solver=solver)
        ridge_64.fit(X_64, y_64)
        coef_64 = ridge_64.coef_

        # Do the actual checks at once for easier debug
        assert coef_32.dtype == X_32.dtype
        assert coef_64.dtype == X_64.dtype
        assert ridge_32.predict(X_32).dtype == X_32.dtype
        assert ridge_64.predict(X_64).dtype == X_64.dtype
        assert_almost_equal(ridge_32.coef_, ridge_64.coef_, decimal=5)

def test_ovr_partial_fit():
    # Test if partial_fit is working as intented
    X, y = shuffle(iris.data, iris.target, random_state=0)
    ovr = OneVsRestClassifier(MultinomialNB())
    ovr.partial_fit(X[:100], y[:100], np.unique(y))
    ovr.partial_fit(X[100:], y[100:])
    pred = ovr.predict(X)
    ovr2 = OneVsRestClassifier(MultinomialNB())
    pred2 = ovr2.fit(X, y).predict(X)

    assert_almost_equal(pred, pred2)
    assert_equal(len(ovr.estimators_), len(np.unique(y)))
    assert_greater(np.mean(y == pred), 0.65)

    # Test when mini batches doesn't have all classes
    ovr = OneVsRestClassifier(MultinomialNB())
    ovr.partial_fit(iris.data[:60], iris.target[:60], np.unique(iris.target))
    ovr.partial_fit(iris.data[60:], iris.target[60:])
    pred = ovr.predict(iris.data)
    ovr2 = OneVsRestClassifier(MultinomialNB())
    pred2 = ovr2.fit(iris.data, iris.target).predict(iris.data)
    
    assert_almost_equal(pred, pred2)
    assert_equal(len(ovr.estimators_), len(np.unique(iris.target)))
    assert_greater(np.mean(iris.target == pred), 0.65)

def test_ovo_partial_fit_predict():
    X, y = shuffle(iris.data, iris.target)
    ovo1 = OneVsOneClassifier(MultinomialNB())
    ovo1.partial_fit(X[:100], y[:100], np.unique(y))
    ovo1.partial_fit(X[100:], y[100:])
    pred1 = ovo1.predict(X)

    ovo2 = OneVsOneClassifier(MultinomialNB())
    ovo2.fit(X, y)
    pred2 = ovo2.predict(X)
    assert_equal(len(ovo1.estimators_), n_classes * (n_classes - 1) / 2)
    assert_greater(np.mean(y == pred1), 0.65)
    assert_almost_equal(pred1, pred2)

    # Test when mini-batches don't have all target classes
    ovo1 = OneVsOneClassifier(MultinomialNB())
    ovo1.partial_fit(iris.data[:60], iris.target[:60], np.unique(iris.target))
    ovo1.partial_fit(iris.data[60:], iris.target[60:])
    pred1 = ovo1.predict(iris.data)
    ovo2 = OneVsOneClassifier(MultinomialNB())
    pred2 = ovo2.fit(iris.data, iris.target).predict(iris.data)

    assert_almost_equal(pred1, pred2)
    assert_equal(len(ovo1.estimators_), len(np.unique(iris.target)))
    assert_greater(np.mean(iris.target == pred1), 0.65)

def test_pca():
    # PCA on dense arrays
    X = iris.data

    for n_comp in np.arange(X.shape[1]):
        pca = PCA(n_components=n_comp, svd_solver='full')

        X_r = pca.fit(X).transform(X)
        np.testing.assert_equal(X_r.shape[1], n_comp)

        X_r2 = pca.fit_transform(X)
        assert_array_almost_equal(X_r, X_r2)

        X_r = pca.transform(X)
        X_r2 = pca.fit_transform(X)
        assert_array_almost_equal(X_r, X_r2)

        # Test get_covariance and get_precision
        cov = pca.get_covariance()
        precision = pca.get_precision()
        assert_array_almost_equal(np.dot(cov, precision),
                                  np.eye(X.shape[1]), 12)

    # test explained_variance_ratio_ == 1 with all components
    pca = PCA(svd_solver='full')
    pca.fit(X)
    assert_almost_equal(pca.explained_variance_ratio_.sum(), 1.0, 3)