Python preprocessing.KBinsDiscretizer方法代码示例

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_encode_options():
    est = KBinsDiscretizer(n_bins=[2, 3, 3, 3],
                           encode='ordinal').fit(X)
    Xt_1 = est.transform(X)
    est = KBinsDiscretizer(n_bins=[2, 3, 3, 3],
                           encode='onehot-dense').fit(X)
    Xt_2 = est.transform(X)
    assert not sp.issparse(Xt_2)
    assert_array_equal(OneHotEncoder(
                           categories=[np.arange(i) for i in [2, 3, 3, 3]],
                           sparse=False)
                       .fit_transform(Xt_1), Xt_2)
    est = KBinsDiscretizer(n_bins=[2, 3, 3, 3],
                           encode='onehot').fit(X)
    Xt_3 = est.transform(X)
    assert sp.issparse(Xt_3)
    assert_array_equal(OneHotEncoder(
                           categories=[np.arange(i) for i in [2, 3, 3, 3]],
                           sparse=True)
                       .fit_transform(Xt_1).toarray(),
                       Xt_3.toarray()) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_nonuniform_strategies(
        strategy, expected_2bins, expected_3bins, expected_5bins):
    X = np.array([0, 0.5, 2, 3, 9, 10]).reshape(-1, 1)

    # with 2 bins
    est = KBinsDiscretizer(n_bins=2, strategy=strategy, encode='ordinal')
    Xt = est.fit_transform(X)
    assert_array_equal(expected_2bins, Xt.ravel())

    # with 3 bins
    est = KBinsDiscretizer(n_bins=3, strategy=strategy, encode='ordinal')
    Xt = est.fit_transform(X)
    assert_array_equal(expected_3bins, Xt.ravel())

    # with 5 bins
    est = KBinsDiscretizer(n_bins=5, strategy=strategy, encode='ordinal')
    Xt = est.fit_transform(X)
    assert_array_equal(expected_5bins, Xt.ravel()) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_ordinal_uniform(self):
        X = np.array([[1.2, 3.2, 1.3, -5.6], [4.3, -3.2, 5.7, 1.0],
                      [0, 3.2, 4.7, -8.9]])
        model = KBinsDiscretizer(n_bins=3,
                                 encode="ordinal",
                                 strategy="uniform").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", FloatTensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.float32),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOrdinalUniform",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_onehot_dense_uniform(self):
        X = np.array([[1.2, 3.2, 1.3, -5.6], [4.3, -3.2, 5.7, 1.0],
                      [0, 3.2, 4.7, -8.9]])
        model = KBinsDiscretizer(n_bins=[3, 2, 3, 4],
                                 encode="onehot-dense",
                                 strategy="uniform").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", FloatTensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.float32),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOneHotDenseUniform",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_ordinal_uniform_int(self):
        X = np.array([[1, 3, 3, -6], [3, -2, 5, 0], [0, 2, 7, -9]])
        model = KBinsDiscretizer(n_bins=3,
                                 encode="ordinal",
                                 strategy="uniform").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOrdinalUniformInt",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_ordinal_quantile_int(self):
        X = np.array([
            [1, 3, 3, -6], [3, -2, 5, 0], [0, 2, 7, -9],
            [-1, 0, 1, -16], [31, -5, 15, 10], [12, -2, 8, -19],
            [12, 13, 31, -16], [0, -21, 15, 30], [10, 22, 71, -91]
            ])
        model = KBinsDiscretizer(n_bins=[3, 2, 3, 4],
                                 encode="ordinal",
                                 strategy="quantile").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOrdinalQuantileInt",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_ordinal_kmeans_int(self):
        X = np.array([
            [1, 3, 3, -6], [3, -2, 5, 0], [0, 2, 7, -9],
            [-1, 0, 1, -16], [31, -5, 15, 10], [12, -2, 8, -19]
            ])
        model = KBinsDiscretizer(n_bins=3, encode="ordinal",
                                 strategy="kmeans").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOrdinalKMeansInt",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_onehot_dense_uniform_int(self):
        X = np.array([[1, 3, 3, -6], [3, -2, 5, 0], [0, 2, 7, -9]])
        model = KBinsDiscretizer(n_bins=[3, 2, 3, 4],
                                 encode="onehot-dense",
                                 strategy="uniform").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOneHotDenseUniformInt",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_model_k_bins_discretiser_onehot_dense_quantile_int(self):
        X = np.array([[1, 3, 3, -6], [3, -2, 5, 0], [0, 2, 7, -9]])
        model = KBinsDiscretizer(n_bins=[3, 2, 3, 4],
                                 encode="onehot-dense",
                                 strategy="quantile").fit(X)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn KBinsDiscretiser",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnKBinsDiscretiserOneHotDenseQuantileInt",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_fit_transform(strategy, expected):
    est = KBinsDiscretizer(n_bins=3, encode='ordinal', strategy=strategy)
    est.fit(X)
    assert_array_equal(expected, est.transform(X)) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_valid_n_bins():
    KBinsDiscretizer(n_bins=2).fit_transform(X)
    KBinsDiscretizer(n_bins=np.array([2])[0]).fit_transform(X)
    assert KBinsDiscretizer(n_bins=2).fit(X).n_bins_.dtype == np.dtype(np.int) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_invalid_n_bins():
    est = KBinsDiscretizer(n_bins=1)
    assert_raise_message(ValueError, "KBinsDiscretizer received an invalid "
                         "number of bins. Received 1, expected at least 2.",
                         est.fit_transform, X)

    est = KBinsDiscretizer(n_bins=1.1)
    assert_raise_message(ValueError, "KBinsDiscretizer received an invalid "
                         "n_bins type. Received float, expected int.",
                         est.fit_transform, X) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_invalid_n_bins_array():
    # Bad shape
    n_bins = np.full((2, 4), 2.)
    est = KBinsDiscretizer(n_bins=n_bins)
    assert_raise_message(ValueError,
                         "n_bins must be a scalar or array of shape "
                         "(n_features,).", est.fit_transform, X)

    # Incorrect number of features
    n_bins = [1, 2, 2]
    est = KBinsDiscretizer(n_bins=n_bins)
    assert_raise_message(ValueError,
                         "n_bins must be a scalar or array of shape "
                         "(n_features,).", est.fit_transform, X)

    # Bad bin values
    n_bins = [1, 2, 2, 1]
    est = KBinsDiscretizer(n_bins=n_bins)
    assert_raise_message(ValueError,
                         "KBinsDiscretizer received an invalid number of bins "
                         "at indices 0, 3. Number of bins must be at least 2, "
                         "and must be an int.",
                         est.fit_transform, X)

    # Float bin values
    n_bins = [2.1, 2, 2.1, 2]
    est = KBinsDiscretizer(n_bins=n_bins)
    assert_raise_message(ValueError,
                         "KBinsDiscretizer received an invalid number of bins "
                         "at indices 0, 2. Number of bins must be at least 2, "
                         "and must be an int.",
                         est.fit_transform, X) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_fit_transform_n_bins_array(strategy, expected):
    est = KBinsDiscretizer(n_bins=[2, 3, 3, 3], encode='ordinal',
                           strategy=strategy).fit(X)
    assert_array_equal(expected, est.transform(X))

    # test the shape of bin_edges_
    n_features = np.array(X).shape[1]
    assert est.bin_edges_.shape == (n_features, )
    for bin_edges, n_bins in zip(est.bin_edges_, est.n_bins_):
        assert bin_edges.shape == (n_bins + 1, ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import KBinsDiscretizer [as 别名]
def test_same_min_max(strategy):
    warnings.simplefilter("always")
    X = np.array([[1, -2],
                  [1, -1],
                  [1, 0],
                  [1, 1]])
    est = KBinsDiscretizer(strategy=strategy, n_bins=3, encode='ordinal')
    assert_warns_message(UserWarning,
                         "Feature 0 is constant and will be replaced "
                         "with 0.", est.fit, X)
    assert est.n_bins_[0] == 1
    # replace the feature with zeros
    Xt = est.transform(X)
    assert_array_equal(Xt[:, 0], np.zeros(X.shape[0]))