Python samples_generator.make_classification函数代码示例

def make_sparse_data(use_feature_hashing=False):
    """
    Function to create sparse data with two features always zero
    in the training set and a different one always zero in the
    test set
    """
    # Create training data
    X, y = make_classification(n_samples=500, n_features=3,
                               n_informative=3, n_redundant=0,
                               n_classes=2, random_state=1234567890)

    # we need features to be non-negative since we will be
    # using naive bayes laster
    X = np.abs(X)

    # make sure that none of the features are zero
    X[np.where(X == 0)] += 1

    # since we want to use SKLL's FeatureSet class, we need to
    # create a list of IDs
    ids = ['EXAMPLE_{}'.format(n) for n in range(1, 501)]

    # create a list of dictionaries as the features
    # with f1 and f5 always 0
    feature_names = ['f{}'.format(n) for n in range(1, 6)]
    features = []
    for row in X:
        row = [0] + row.tolist() + [0]
        features.append(dict(zip(feature_names, row)))

    # use a FeatureHasher if we are asked to do feature hashing
    vectorizer = FeatureHasher(n_features=4) if use_feature_hashing else None
    train_fs = FeatureSet('train_sparse', ids,
                          features=features, labels=y,
                          vectorizer=vectorizer)

    # now create the test set with f4 always 0 but nothing else
    X, y = make_classification(n_samples=100, n_features=4,
                               n_informative=4, n_redundant=0,
                               n_classes=2, random_state=1234567890)
    X = np.abs(X)
    X[np.where(X == 0)] += 1
    ids = ['EXAMPLE_{}'.format(n) for n in range(1, 101)]

    # create a list of dictionaries as the features
    # with f4 always 0
    feature_names = ['f{}'.format(n) for n in range(1, 6)]
    features = []
    for row in X:
        row = row.tolist()
        row = row[:3] + [0] + row[3:]
        features.append(dict(zip(feature_names, row)))

    test_fs = FeatureSet('test_sparse', ids,
                         features=features, labels=y,
                         vectorizer=vectorizer)

    return train_fs, test_fs

def test_linearsvc_parameters():
    """
    Test possible parameter combinations in LinearSVC
    """
    # Generate list of possible parameter combinations
    losses = ['hinge', 'squared_hinge', 'logistic_regression', 'foo']
    penalties, duals = ['l1', 'l2', 'bar'], [True, False]

    X, y = make_classification(n_samples=5, n_features=5)

    for loss, penalty, dual in itertools.product(losses, penalties, duals):
        clf = svm.LinearSVC(penalty=penalty, loss=loss, dual=dual)
        if ((loss, penalty) == ('hinge', 'l1') or
                (loss, penalty, dual) == ('hinge', 'l2', False) or
                (penalty, dual) == ('l1', True) or
                loss == 'foo' or penalty == 'bar'):

            assert_raises_regexp(ValueError,
                                 "Unsupported set of arguments.*penalty='%s.*"
                                 "loss='%s.*dual=%s"
                                 % (penalty, loss, dual),
                                 clf.fit, X, y)
        else:
            clf.fit(X, y)

    # Incorrect loss value - test if explicit error message is raised
    assert_raises_regexp(ValueError, ".*loss='L3' is not supported.*",
                         svm.LinearSVC(loss="L3").fit, X, y)

def test_f_classif_multi_class():
    """
    Test whether the F test yields meaningful results
    on a simple simulated classification problem
    """
    X, Y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    F, pv = f_classif(X, Y)
    assert (F > 0).all()
    assert (pv > 0).all()
    assert (pv < 1).all()
    assert (pv[:5] < 0.05).all()
    assert (pv[5:] > 1.0e-5).all()

def test_select_heuristics_classif():
    # Test whether the relative univariate feature selection
    # gets the correct items in a simple classification problem
    # with the fdr, fwe and fpr heuristics
    X, y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    univariate_filter = SelectFwe(f_classif, alpha=0.01)
    X_r = univariate_filter.fit(X, y).transform(X)
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    for mode in ["fdr", "fpr", "fwe"]:
        X_r2 = GenericUnivariateSelect(f_classif, mode=mode, param=0.01).fit(X, y).transform(X)
        assert_array_equal(X_r, X_r2)
        support = univariate_filter.get_support()
        assert_array_almost_equal(support, gtruth)

def test_select_percentile_classif_sparse():
    # Test whether the relative univariate feature selection
    # gets the correct items in a simple classification problem
    # with the percentile heuristic
    X, y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )
    X = sparse.csr_matrix(X)
    univariate_filter = SelectPercentile(f_classif, percentile=25)
    X_r = univariate_filter.fit(X, y).transform(X)
    X_r2 = GenericUnivariateSelect(f_classif, mode="percentile", param=25).fit(X, y).transform(X)
    assert_array_equal(X_r.toarray(), X_r2.toarray())
    support = univariate_filter.get_support()
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    assert_array_equal(support, gtruth)

    X_r2inv = univariate_filter.inverse_transform(X_r2)
    assert_true(sparse.issparse(X_r2inv))
    support_mask = safe_mask(X_r2inv, support)
    assert_equal(X_r2inv.shape, X.shape)
    assert_array_equal(X_r2inv[:, support_mask].toarray(), X_r.toarray())
    # Check other columns are empty
    assert_equal(X_r2inv.getnnz(), X_r.getnnz())

def test_select_kbest_all():
    # Test whether k="all" correctly returns all features.
    X, y = make_classification(n_samples=20, n_features=10, shuffle=False, random_state=0)

    univariate_filter = SelectKBest(f_classif, k="all")
    X_r = univariate_filter.fit(X, y).transform(X)
    assert_array_equal(X, X_r)

def test_f_classif():
    # Test whether the F test yields meaningful results
    # on a simple simulated classification problem
    X, y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    F, pv = f_classif(X, y)
    F_sparse, pv_sparse = f_classif(sparse.csr_matrix(X), y)
    assert_true((F > 0).all())
    assert_true((pv > 0).all())
    assert_true((pv < 1).all())
    assert_true((pv[:5] < 0.05).all())
    assert_true((pv[5:] > 1.0e-4).all())
    assert_array_almost_equal(F_sparse, F)
    assert_array_almost_equal(pv_sparse, pv)

def test_mismatch_labels_features():
    """
    Test to catch mistmatch between the shape of the labels vector and the feature matrix
    """

    # get a 100 instances with 4 features but ignore the labels we
    # get from here
    X, y = make_classification(n_samples=100, n_features=4,
                               n_informative=4, n_redundant=0,
                               n_classes=3, random_state=1234567890)

    # double-stack y to ensure we don't match the number of feature rows
    y2 = np.hstack([y, y])

    # convert the features into a list of dictionaries
    feature_names = ['f{}'.format(n) for n in range(1, 5)]
    features = []
    for row in X:
        features.append(dict(zip(feature_names, row)))

    # get 100 ids
    ids = ['EXAMPLE_{}'.format(i) for i in range(100)]

    # This should raise a ValueError
    FeatureSet('test', ids, features=features, labels=y2)

def test_select_kbest_classif():
    # Test whether the relative univariate feature selection
    # gets the correct items in a simple classification problem
    # with the k best heuristic
    X, y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    univariate_filter = SelectKBest(f_classif, k=5)
    X_r = univariate_filter.fit(X, y).transform(X)
    X_r2 = GenericUnivariateSelect(f_classif, mode="k_best", param=5).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    assert_array_equal(support, gtruth)

def test_grid_search_sparse_scoring():
    X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)

    clf = LinearSVC()
    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

    X_ = sp.csr_matrix(X_)
    clf = LinearSVC()
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
    cv.fit(X_[:180], y_[:180])
    y_pred2 = cv.predict(X_[180:])
    C2 = cv.best_estimator_.C

    assert_array_equal(y_pred, y_pred2)
    assert_equal(C, C2)
    # Smoke test the score
    #np.testing.assert_allclose(f1_score(cv.predict(X_[:180]), y[:180]),
    #                        cv.score(X_[:180], y[:180]))

    # test loss where greater is worse
    def f1_loss(y_true_, y_pred_):
        return -f1_score(y_true_, y_pred_)
    F1Loss = Scorer(f1_loss, greater_is_better=False)
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring=F1Loss)
    cv.fit(X_[:180], y_[:180])
    y_pred3 = cv.predict(X_[180:])
    C3 = cv.best_estimator_.C

    assert_equal(C, C3)
    assert_array_equal(y_pred, y_pred3)

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_select_fwe_classif():
    """
    Test whether the relative univariate feature selection
    gets the correct items in a simple classification problem
    with the fpr heuristic
    """
    X, Y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    univariate_filter = SelectFwe(f_classif, alpha=0.01)
    X_r = univariate_filter.fit(X, Y).transform(X)
    X_r2 = GenericUnivariateSelect(f_classif, mode="fwe", param=0.01).fit(X, Y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    assert np.sum(np.abs(support - gtruth)) < 2

def test_mutual_info_classif():
    X, y = make_classification(
        n_samples=100,
        n_features=5,
        n_informative=1,
        n_redundant=1,
        n_repeated=0,
        n_classes=2,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    # Test in KBest mode.
    univariate_filter = SelectKBest(mutual_info_classif, k=2)
    X_r = univariate_filter.fit(X, y).transform(X)
    X_r2 = GenericUnivariateSelect(mutual_info_classif, mode="k_best", param=2).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(5)
    gtruth[:2] = 1
    assert_array_equal(support, gtruth)

    # Test in Percentile mode.
    univariate_filter = SelectPercentile(mutual_info_classif, percentile=40)
    X_r = univariate_filter.fit(X, y).transform(X)
    X_r2 = GenericUnivariateSelect(mutual_info_classif, mode="percentile", param=40).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(5)
    gtruth[:2] = 1
    assert_array_equal(support, gtruth)

def test_grid_search_precomputed_kernel():
    """Test that grid search works when the input features are given in the
    form of a precomputed kernel matrix """
    X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)

    # compute the training kernel matrix corresponding to the linear kernel
    K_train = np.dot(X_[:180], X_[:180].T)
    y_train = y_[:180]

    clf = SVC(kernel='precomputed')
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]})
    cv.fit(K_train, y_train)

    assert_true(cv.best_score_ >= 0)

    # compute the test kernel matrix
    K_test = np.dot(X_[180:], X_[:180].T)
    y_test = y_[180:]

    y_pred = cv.predict(K_test)

    assert_true(np.mean(y_pred == y_test) >= 0)

    # test error is raised when the precomputed kernel is not array-like
    # or sparse
    assert_raises(ValueError, cv.fit, K_train.tolist(), y_train)

def test_grid_search_precomputed_kernel_error_kernel_function():
    """Test that grid search returns an error when using a kernel_function"""
    X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)
    kernel_function = lambda x1, x2: np.dot(x1, x2.T)
    clf = SVC(kernel=kernel_function)
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]})
    assert_raises(ValueError, cv.fit, X_, y_)