Python Pipeline.predict_proba方法代码示例

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_methods_pca_svm():
    # Test the various methods of the pipeline (pca + svm).
    iris = load_iris()
    X = iris.data
    y = iris.target
    # Test with PCA + SVC
    clf = SVC(probability=True, random_state=0)
    pca = PCA()
    pipe = Pipeline([('pca', pca), ('svc', clf)])
    pipe.fit(X, y)
    pipe.predict(X)
    pipe.predict_proba(X)
    pipe.predict_log_proba(X)
    pipe.score(X, y)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_methods_anova():
    # Test the various methods of the pipeline (anova).
    iris = load_iris()
    X = iris.data
    y = iris.target
    # Test with Anova + LogisticRegression
    clf = LogisticRegression()
    filter1 = SelectKBest(f_classif, k=2)
    pipe = Pipeline([('anova', filter1), ('logistic', clf)])
    pipe.fit(X, y)
    pipe.predict(X)
    pipe.predict_proba(X)
    pipe.predict_log_proba(X)
    pipe.score(X, y)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_methods_pca_svm():
    # Test the various methods of the pipeline (pca + svm).
    iris = load_iris()
    X = iris.data
    y = iris.target
    # Test with PCA + SVC
    clf = SVC(gamma='scale', probability=True, random_state=0)
    pca = PCA(svd_solver='full', n_components='mle', whiten=True)
    pipe = Pipeline([('pca', pca), ('svc', clf)])
    pipe.fit(X, y)
    pipe.predict(X)
    pipe.predict_proba(X)
    pipe.predict_log_proba(X)
    pipe.score(X, y)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_methods_anova_rus():
    # Test the various methods of the pipeline (anova).
    X, y = make_classification(n_classes=2, class_sep=2, weights=[0.1, 0.9],
                               n_informative=3, n_redundant=1, flip_y=0,
                               n_features=20, n_clusters_per_class=1,
                               n_samples=5000, random_state=0)
    # Test with RandomUnderSampling + Anova + LogisticRegression
    clf = LogisticRegression()
    rus = RandomUnderSampler(random_state=0)
    filter1 = SelectKBest(f_classif, k=2)
    pipe = Pipeline([('rus', rus), ('anova', filter1), ('logistic', clf)])
    pipe.fit(X, y)
    pipe.predict(X)
    pipe.predict_proba(X)
    pipe.predict_log_proba(X)
    pipe.score(X, y)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_methods_preprocessing_svm():
    # Test the various methods of the pipeline (preprocessing + svm).
    iris = load_iris()
    X = iris.data
    y = iris.target
    n_samples = X.shape[0]
    n_classes = len(np.unique(y))
    scaler = StandardScaler()
    pca = PCA(n_components=2)
    clf = SVC(probability=True, random_state=0, decision_function_shape='ovr')

    for preprocessing in [scaler, pca]:
        pipe = Pipeline([('preprocess', preprocessing), ('svc', clf)])
        pipe.fit(X, y)

        # check shapes of various prediction functions
        predict = pipe.predict(X)
        assert_equal(predict.shape, (n_samples,))

        proba = pipe.predict_proba(X)
        assert_equal(proba.shape, (n_samples, n_classes))

        log_proba = pipe.predict_log_proba(X)
        assert_equal(log_proba.shape, (n_samples, n_classes))

        decision_function = pipe.decision_function(X)
        assert_equal(decision_function.shape, (n_samples, n_classes))

        pipe.score(X, y)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_methods_rus_pca_svm():
    # Test the various methods of the pipeline (pca + svm).
    X, y = make_classification(n_classes=2, class_sep=2, weights=[0.1, 0.9],
                               n_informative=3, n_redundant=1, flip_y=0,
                               n_features=20, n_clusters_per_class=1,
                               n_samples=5000, random_state=0)

    # Test with PCA + SVC
    clf = SVC(probability=True, random_state=0)
    pca = PCA()
    rus = RandomUnderSampler(random_state=0)
    pipe = Pipeline([('rus', rus), ('pca', pca), ('svc', clf)])
    pipe.fit(X, y)
    pipe.predict(X)
    pipe.predict_proba(X)
    pipe.predict_log_proba(X)
    pipe.score(X, y)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_memory_transformer():
    iris = load_iris()
    X = iris.data
    y = iris.target
    cachedir = mkdtemp()
    try:
        memory = Memory(cachedir=cachedir, verbose=10)
        # Test with Transformer + SVC
        clf = SVC(probability=True, random_state=0)
        transf = DummyTransf()
        pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
        cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
                               memory=memory)

        # Memoize the transformer at the first fit
        cached_pipe.fit(X, y)
        pipe.fit(X, y)
        # Get the time stamp of the tranformer in the cached pipeline
        expected_ts = cached_pipe.named_steps['transf'].timestamp_
        # Check that cached_pipe and pipe yield identical results
        assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
        assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
        assert_array_equal(pipe.predict_log_proba(X),
                           cached_pipe.predict_log_proba(X))
        assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
        assert_array_equal(pipe.named_steps['transf'].means_,
                           cached_pipe.named_steps['transf'].means_)
        assert not hasattr(transf, 'means_')
        # Check that we are reading the cache while fitting
        # a second time
        cached_pipe.fit(X, y)
        # Check that cached_pipe and pipe yield identical results
        assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
        assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
        assert_array_equal(pipe.predict_log_proba(X),
                           cached_pipe.predict_log_proba(X))
        assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
        assert_array_equal(pipe.named_steps['transf'].means_,
                           cached_pipe.named_steps['transf'].means_)
        assert cached_pipe.named_steps['transf'].timestamp_ == expected_ts
        # Create a new pipeline with cloned estimators
        # Check that even changing the name step does not affect the cache hit
        clf_2 = SVC(probability=True, random_state=0)
        transf_2 = DummyTransf()
        cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
                                 memory=memory)
        cached_pipe_2.fit(X, y)

        # Check that cached_pipe and pipe yield identical results
        assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
        assert_array_equal(pipe.predict_proba(X),
                           cached_pipe_2.predict_proba(X))
        assert_array_equal(pipe.predict_log_proba(X),
                           cached_pipe_2.predict_log_proba(X))
        assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
        assert_array_equal(pipe.named_steps['transf'].means_,
                           cached_pipe_2.named_steps['transf_2'].means_)
        assert cached_pipe_2.named_steps['transf_2'].timestamp_ == expected_ts
    finally:
        shutil.rmtree(cachedir)

# 需要导入模块: from imblearn.pipeline import Pipeline [as 别名]
# 或者: from imblearn.pipeline.Pipeline import predict_proba [as 别名]
def test_pipeline_memory_sampler():
    X, y = make_classification(
        n_classes=2,
        class_sep=2,
        weights=[0.1, 0.9],
        n_informative=3,
        n_redundant=1,
        flip_y=0,
        n_features=20,
        n_clusters_per_class=1,
        n_samples=5000,
        random_state=0)
    cachedir = mkdtemp()
    try:
        memory = Memory(cachedir=cachedir, verbose=10)
        # Test with Transformer + SVC
        clf = SVC(probability=True, random_state=0)
        transf = DummySampler()
        pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
        cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
                               memory=memory)

        # Memoize the transformer at the first fit
        cached_pipe.fit(X, y)
        pipe.fit(X, y)
        # Get the time stamp of the tranformer in the cached pipeline
        expected_ts = cached_pipe.named_steps['transf'].timestamp_
        # Check that cached_pipe and pipe yield identical results
        assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
        assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
        assert_array_equal(pipe.predict_log_proba(X),
                           cached_pipe.predict_log_proba(X))
        assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
        assert_array_equal(pipe.named_steps['transf'].means_,
                           cached_pipe.named_steps['transf'].means_)
        assert not hasattr(transf, 'means_')
        # Check that we are reading the cache while fitting
        # a second time
        cached_pipe.fit(X, y)
        # Check that cached_pipe and pipe yield identical results
        assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
        assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
        assert_array_equal(pipe.predict_log_proba(X),
                           cached_pipe.predict_log_proba(X))
        assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
        assert_array_equal(pipe.named_steps['transf'].means_,
                           cached_pipe.named_steps['transf'].means_)
        assert cached_pipe.named_steps['transf'].timestamp_ == expected_ts
        # Create a new pipeline with cloned estimators
        # Check that even changing the name step does not affect the cache hit
        clf_2 = SVC(probability=True, random_state=0)
        transf_2 = DummySampler()
        cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
                                 memory=memory)
        cached_pipe_2.fit(X, y)

        # Check that cached_pipe and pipe yield identical results
        assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
        assert_array_equal(pipe.predict_proba(X),
                           cached_pipe_2.predict_proba(X))
        assert_array_equal(pipe.predict_log_proba(X),
                           cached_pipe_2.predict_log_proba(X))
        assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
        assert_array_equal(pipe.named_steps['transf'].means_,
                           cached_pipe_2.named_steps['transf_2'].means_)
        assert cached_pipe_2.named_steps['transf_2'].timestamp_ == expected_ts
    finally:
        shutil.rmtree(cachedir)