Python datasets.make_multilabel_classification函数代码示例

def test_multilabel_representation_invariance():
    # Generate some data
    n_classes = 4
    n_samples = 50

    _, y1 = make_multilabel_classification(
        n_features=1, n_classes=n_classes, random_state=0, n_samples=n_samples, allow_unlabeled=True
    )
    _, y2 = make_multilabel_classification(
        n_features=1, n_classes=n_classes, random_state=1, n_samples=n_samples, allow_unlabeled=True
    )

    # To make sure at least one empty label is present
    y1 += [0] * n_classes
    y2 += [0] * n_classes

    y1_sparse_indicator = sp.coo_matrix(y1)
    y2_sparse_indicator = sp.coo_matrix(y2)

    for name in MULTILABELS_METRICS:
        metric = ALL_METRICS[name]

        # XXX cruel hack to work with partial functions
        if isinstance(metric, partial):
            metric.__module__ = "tmp"
            metric.__name__ = name

        measure = metric(y1, y2)

        # Check representation invariance
        assert_almost_equal(
            metric(y1_sparse_indicator, y2_sparse_indicator),
            measure,
            err_msg="%s failed representation invariance  " "between dense and sparse indicator " "formats." % name,
        )

def test_normalize_option_multilabel_classification():
    # Test in the multilabel case
    n_classes = 4
    n_samples = 100
    _, y_true = make_multilabel_classification(n_features=1, n_classes=n_classes, random_state=0, n_samples=n_samples)
    _, y_pred = make_multilabel_classification(n_features=1, n_classes=n_classes, random_state=1, n_samples=n_samples)

    # Be sure to have at least one empty label
    y_true += ([],)
    y_pred += ([],)
    n_samples += 1

    lb = LabelBinarizer().fit([range(n_classes)])
    y_true_binary_indicator = lb.transform(y_true)
    y_pred_binary_indicator = lb.transform(y_pred)

    for name, metrics in METRICS_WITH_NORMALIZE_OPTION.items():
        # List of list of labels
        measure = metrics(y_true, y_pred, normalize=True)
        assert_greater(measure, 0, msg="We failed to test correctly the normalize option")
        assert_almost_equal(
            metrics(y_true, y_pred, normalize=False) / n_samples, measure, err_msg="Failed with %s" % name
        )

        # Indicator matrix format
        measure = metrics(y_true_binary_indicator, y_pred_binary_indicator, normalize=True)
        assert_greater(measure, 0, msg="We failed to test correctly the normalize option")
        assert_almost_equal(
            metrics(y_true_binary_indicator, y_pred_binary_indicator, normalize=False) / n_samples,
            measure,
            err_msg="Failed with %s" % name,
        )

def test_sample_weight_invariance(n_samples=50):
    random_state = check_random_state(0)

    # binary
    random_state = check_random_state(0)
    y_true = random_state.randint(0, 2, size=(n_samples, ))
    y_pred = random_state.randint(0, 2, size=(n_samples, ))
    y_score = random_state.random_sample(size=(n_samples,))
    for name in ALL_METRICS:
        if (name in METRICS_WITHOUT_SAMPLE_WEIGHT or
                name in METRIC_UNDEFINED_BINARY):
            continue
        metric = ALL_METRICS[name]
        if name in THRESHOLDED_METRICS:
            yield _named_check(check_sample_weight_invariance, name), name,\
                  metric, y_true, y_score
        else:
            yield _named_check(check_sample_weight_invariance, name), name,\
                  metric, y_true, y_pred

    # multiclass
    random_state = check_random_state(0)
    y_true = random_state.randint(0, 5, size=(n_samples, ))
    y_pred = random_state.randint(0, 5, size=(n_samples, ))
    y_score = random_state.random_sample(size=(n_samples, 5))
    for name in ALL_METRICS:
        if (name in METRICS_WITHOUT_SAMPLE_WEIGHT or
                name in METRIC_UNDEFINED_BINARY_MULTICLASS):
            continue
        metric = ALL_METRICS[name]
        if name in THRESHOLDED_METRICS:
            yield _named_check(check_sample_weight_invariance, name), name,\
                  metric, y_true, y_score
        else:
            yield _named_check(check_sample_weight_invariance, name), name,\
                  metric, y_true, y_pred

    # multilabel indicator
    _, ya = make_multilabel_classification(n_features=1, n_classes=20,
                                           random_state=0, n_samples=100,
                                           allow_unlabeled=False)
    _, yb = make_multilabel_classification(n_features=1, n_classes=20,
                                           random_state=1, n_samples=100,
                                           allow_unlabeled=False)
    y_true = np.vstack([ya, yb])
    y_pred = np.vstack([ya, ya])
    y_score = random_state.randint(1, 4, size=y_true.shape)

    for name in (MULTILABELS_METRICS + THRESHOLDED_MULTILABEL_METRICS +
                 MULTIOUTPUT_METRICS):
        if name in METRICS_WITHOUT_SAMPLE_WEIGHT:
            continue

        metric = ALL_METRICS[name]
        if name in THRESHOLDED_METRICS:
            yield (_named_check(check_sample_weight_invariance, name), name,
                   metric, y_true, y_score)
        else:
            yield (_named_check(check_sample_weight_invariance, name), name,
                   metric, y_true, y_pred)

def test_normalize_option_multilabel_classification():
    # Test in the multilabel case
    n_classes = 4
    n_samples = 100

    # for both random_state 0 and 1, y_true and y_pred has at least one
    # unlabelled entry
    _, y_true = make_multilabel_classification(n_features=1,
                                               n_classes=n_classes,
                                               random_state=0,
                                               allow_unlabeled=True,
                                               n_samples=n_samples)
    _, y_pred = make_multilabel_classification(n_features=1,
                                               n_classes=n_classes,
                                               random_state=1,
                                               allow_unlabeled=True,
                                               n_samples=n_samples)

    # To make sure at least one empty label is present
    y_true += [0]*n_classes
    y_pred += [0]*n_classes

    for name in METRICS_WITH_NORMALIZE_OPTION:
        metrics = ALL_METRICS[name]
        measure = metrics(y_true, y_pred, normalize=True)
        assert_greater(measure, 0,
                       msg="We failed to test correctly the normalize option")
        assert_almost_equal(metrics(y_true, y_pred, normalize=False)
                            / n_samples, measure,
                            err_msg="Failed with %s" % name)

def test_multilabel_classification_report():
    n_classes = 4
    n_samples = 50

    _, y_true = make_multilabel_classification(n_features=1,
                                               n_samples=n_samples,
                                               n_classes=n_classes,
                                               random_state=0)

    _, y_pred = make_multilabel_classification(n_features=1,
                                               n_samples=n_samples,
                                               n_classes=n_classes,
                                               random_state=1)

    expected_report = """\
             precision    recall  f1-score   support

          0       0.50      0.67      0.57        24
          1       0.51      0.74      0.61        27
          2       0.29      0.08      0.12        26
          3       0.52      0.56      0.54        27

avg / total       0.45      0.51      0.46       104
"""

    report = classification_report(y_true, y_pred)
    assert_equal(report, expected_report)

def benchmark(metrics=tuple(v for k, v in sorted(METRICS.items())),
              formats=tuple(v for k, v in sorted(FORMATS.items())),
              samples=1000, classes=4, density=.2,
              n_times=5):
    """Times metric calculations for a number of inputs

    Parameters
    ----------
    metrics : array-like of callables (1d or 0d)
        The metric functions to time.

    formats : array-like of callables (1d or 0d)
        These may transform a dense indicator matrix into multilabel
        representation.

    samples : array-like of ints (1d or 0d)
        The number of samples to generate as input.

    classes : array-like of ints (1d or 0d)
        The number of classes in the input.

    density : array-like of ints (1d or 0d)
        The density of positive labels in the input.

    n_times : int
        Time calling the metric n_times times.

    Returns
    -------
    array of floats shaped like (metrics, formats, samples, classes, density)
        Time in seconds.
    """
    metrics = np.atleast_1d(metrics)
    samples = np.atleast_1d(samples)
    classes = np.atleast_1d(classes)
    density = np.atleast_1d(density)
    formats = np.atleast_1d(formats)
    out = np.zeros((len(metrics), len(formats), len(samples), len(classes),
                    len(density)), dtype=float)
    it = itertools.product(samples, classes, density)
    for i, (s, c, d) in enumerate(it):
        _, y_true = make_multilabel_classification(n_samples=s, n_features=1,
                                                   n_classes=c, n_labels=d * c,
                                                   return_indicator=True,
                                                   random_state=42)
        _, y_pred = make_multilabel_classification(n_samples=s, n_features=1,
                                                   n_classes=c, n_labels=d * c,
                                                   return_indicator=True,
                                                   random_state=84)
        for j, f in enumerate(formats):
            f_true = f(y_true)
            f_pred = f(y_pred)
            for k, metric in enumerate(metrics):
                t = timeit(partial(metric, f_true, f_pred), number=n_times)

                out[k, j].flat[i] = t
    return out

def test_grid_search_with_multioutput_data():
    # Test search with multi-output estimator

    X, y = make_multilabel_classification(random_state=0)

    est_parameters = {"max_depth": [1, 2, 3, 4]}
    cv = KFold(y.shape[0], random_state=0)

    estimators = [DecisionTreeRegressor(random_state=0), DecisionTreeClassifier(random_state=0)]

    # Test with grid search cv
    for est in estimators:
        grid_search = GridSearchCV(est, est_parameters, cv=cv)
        grid_search.fit(X, y)
        for parameters, _, cv_validation_scores in grid_search.grid_scores_:
            est.set_params(**parameters)

            for i, (train, test) in enumerate(cv):
                est.fit(X[train], y[train])
                correct_score = est.score(X[test], y[test])
                assert_almost_equal(correct_score, cv_validation_scores[i])

    # Test with a randomized search
    for est in estimators:
        random_search = RandomizedSearchCV(est, est_parameters, cv=cv, n_iter=3)
        random_search.fit(X, y)
        for parameters, _, cv_validation_scores in random_search.grid_scores_:
            est.set_params(**parameters)

            for i, (train, test) in enumerate(cv):
                est.fit(X[train], y[train])
                correct_score = est.score(X[test], y[test])
                assert_almost_equal(correct_score, cv_validation_scores[i])

 def get_multilabel(self):
     return make_multilabel_classification(n_samples=100,
                                           n_features=10,
                                           n_classes=5,
                                           n_labels=5,
                                           return_indicator=True,
                                           random_state=1)

def test_output_transformer():
    X, y = datasets.make_multilabel_classification(return_indicator=True)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)

    # Check that random_state are different
    transformer = GaussianRandomProjection(n_components=5, random_state=None)
    for name, ForestEstimator in FOREST_ESTIMATORS.items():
        est = ForestEstimator(random_state=5, output_transformer=transformer)
        est.fit(X_train, y_train)
        y_pred = est.predict(X_test)
        assert_equal(y_pred.shape, y_test.shape)

        random_state = [sub.output_transformer_.random_state
                        for sub in est.estimators_]

        assert_equal(len(set(random_state)), est.n_estimators)


    # Check that random_state are equals
    transformer = FixedStateTransformer(GaussianRandomProjection(
        n_components=5), random_seed=0)
    for name, ForestEstimator in FOREST_ESTIMATORS.items():
        est = ForestEstimator(random_state=5, output_transformer=transformer)
        est.fit(X_train, y_train)
        y_pred = est.predict(X_test)
        assert_equal(y_pred.shape, y_test.shape)


        random_state = [sub.output_transformer_.random_state
                        for sub in est.estimators_]

        assert_equal(len(set(random_state)), 1)
        assert_equal(random_state[0], 0)

    def get_codes(self):
        X, Y = make_multilabel_classification(n_samples=15, n_labels=8, n_classes=8, random_state=0)
        self.classifier_labels = Y
        self.classifier_error_codes = LabelBinarizer().fit_transform(Y)
        print self.classifier_labels
        print self.classifier_error_codes

        f = open('ecoc_classifiers', 'w')

        for row in self.classifier_labels:
            str_op = '['
            for label in row:
                str_op += str(label) + ','
            str_op += ']'
            f.write(str_op)
        f.write('\n')

        for row in self.classifier_error_codes:
            str_op = '['
            for label in row:
                str_op += str(label) + ','
            str_op += ']'
            f.write(str_op)
        f.flush()
        return

 def testMultiClassification(self):
     """TODO(ilblackdragon): Implement multi-output classification.
     """
     random.seed(42)
     n_classes = 5
     X, y = datasets.make_multilabel_classification(n_classes=n_classes,
                                                    random_state=42)

def check_alternative_lrap_implementation(lrap_score, n_classes=5,
                                          n_samples=20, random_state=0):
    _, y_true = make_multilabel_classification(n_features=1,
                                               allow_unlabeled=False,
                                               random_state=random_state,
                                               n_classes=n_classes,
                                               n_samples=n_samples)

    # Score with ties
    y_score = sparse_random_matrix(n_components=y_true.shape[0],
                                   n_features=y_true.shape[1],
                                   random_state=random_state)

    if hasattr(y_score, "toarray"):
        y_score = y_score.toarray()
    score_lrap = label_ranking_average_precision_score(y_true, y_score)
    score_my_lrap = _my_lrap(y_true, y_score)
    assert_almost_equal(score_lrap, score_my_lrap)

    # Uniform score
    random_state = check_random_state(random_state)
    y_score = random_state.uniform(size=(n_samples, n_classes))
    score_lrap = label_ranking_average_precision_score(y_true, y_score)
    score_my_lrap = _my_lrap(y_true, y_score)
    assert_almost_equal(score_lrap, score_my_lrap)

def test_ovr_fit_predict_sparse():
    for sparse in [sp.csr_matrix, sp.csc_matrix, sp.coo_matrix, sp.dok_matrix, sp.lil_matrix]:
        base_clf = MultinomialNB(alpha=1)

        X, Y = datasets.make_multilabel_classification(
            n_samples=100, n_features=20, n_classes=5, n_labels=3, length=50, allow_unlabeled=True, random_state=0
        )

        X_train, Y_train = X[:80], Y[:80]
        X_test = X[80:]

        clf = OneVsRestClassifier(base_clf).fit(X_train, Y_train)
        Y_pred = clf.predict(X_test)

        clf_sprs = OneVsRestClassifier(base_clf).fit(X_train, sparse(Y_train))
        Y_pred_sprs = clf_sprs.predict(X_test)

        assert_true(clf.multilabel_)
        assert_true(sp.issparse(Y_pred_sprs))
        assert_array_equal(Y_pred_sprs.toarray(), Y_pred)

        # Test predict_proba
        Y_proba = clf_sprs.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 > 0.5
        assert_array_equal(pred, Y_pred_sprs.toarray())

        # Test decision_function
        clf_sprs = OneVsRestClassifier(svm.SVC()).fit(X_train, sparse(Y_train))
        dec_pred = (clf_sprs.decision_function(X_test) > 0).astype(int)
        assert_array_equal(dec_pred, clf_sprs.predict(X_test).toarray())

def test_sparse_input():
    X, y = datasets.make_multilabel_classification(random_state=0,
                                                   n_samples=50)

    for name, sparse_matrix in product(FOREST_ESTIMATORS,
                                       (csr_matrix, csc_matrix, coo_matrix)):
        yield check_sparse_input, name, X, sparse_matrix(X), y

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)