本文整理汇总了Python中sklearn.pipeline.make_pipeline方法的典型用法代码示例。如果您正苦于以下问题:Python pipeline.make_pipeline方法的具体用法?Python pipeline.make_pipeline怎么用?Python pipeline.make_pipeline使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.pipeline
的用法示例。
在下文中一共展示了pipeline.make_pipeline方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: main
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def main():
raw_data = load_iris()
data = pd.DataFrame(raw_data["data"], columns=raw_data["feature_names"])
pipeline = FeatureUnion([
("1", make_pipeline(
FunctionTransformer(lambda X: X.loc[:, ["sepal length (cm)"]]),
# other transformations
)),
("2", make_pipeline(
FunctionTransformer(lambda X: X.loc[:, ["sepal width (cm)"]]),
# other transformations
))
])
X = pipeline.fit_transform(data)
print(X["sepal length (cm)"].mean())
print(X["sepal width (cm)"].mean())
示例2: main
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def main():
raw_data = load_iris()
data = pd.DataFrame(raw_data["data"], columns=raw_data["feature_names"])
data.loc[:, "class"] = raw_data["target"]
pipeline = PandasFeatureUnion([
("1", make_pipeline(
PandasTransform(lambda X: X.loc[:, ["sepal length (cm)"]]),
# other transformations
)),
("2", make_pipeline(
PandasTransform(lambda X: X.loc[:, ["sepal width (cm)"]]),
# other transformations
))
])
X = pipeline.fit_transform(data)
print(X["sepal length (cm)"].mean())
print(X["sepal width (cm)"].mean())
示例3: main
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def main():
raw_data = load_iris()
data = pd.DataFrame(raw_data["data"], columns=raw_data["feature_names"])
data.loc[:, "class"] = raw_data["target"]
pipeline = FeatureUnion([
("1", make_pipeline(
PandasTransform(lambda X: X.loc[:, ["sepal length (cm)"]]),
# other transformations
)),
("2", make_pipeline(
PandasTransform(lambda X: X.loc[:, ["sepal width (cm)"]]),
# other transformations
))
])
X = pipeline.fit_transform(data)
print(X["sepal length (cm)"].mean())
print(X["sepal width (cm)"].mean())
示例4: test_gradient_boosting_with_init_pipeline
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_gradient_boosting_with_init_pipeline():
# Check that the init estimator can be a pipeline (see issue #13466)
X, y = make_regression(random_state=0)
init = make_pipeline(LinearRegression())
gb = GradientBoostingRegressor(init=init)
gb.fit(X, y) # pipeline without sample_weight works fine
with pytest.raises(
ValueError,
match='The initial estimator Pipeline does not support sample '
'weights'):
gb.fit(X, y, sample_weight=np.ones(X.shape[0]))
# Passing sample_weight to a pipeline raises a ValueError. This test makes
# sure we make the distinction between ValueError raised by a pipeline that
# was passed sample_weight, and a ValueError raised by a regular estimator
# whose input checking failed.
with pytest.raises(
ValueError,
match='nu <= 0 or nu > 1'):
# Note that NuSVR properly supports sample_weight
init = NuSVR(gamma='auto', nu=1.5)
gb = GradientBoostingRegressor(init=init)
gb.fit(X, y, sample_weight=np.ones(X.shape[0]))
示例5: test_pipeline
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_pipeline():
# Render a pipeline object
pipeline = make_pipeline(StandardScaler(), LogisticRegression(C=999))
expected = """
Pipeline(memory=None,
steps=[('standardscaler',
StandardScaler(copy=True, with_mean=True, with_std=True)),
('logisticregression',
LogisticRegression(C=999, class_weight=None, dual=False,
fit_intercept=True, intercept_scaling=1,
l1_ratio=None, max_iter=100,
multi_class='warn', n_jobs=None,
penalty='l2', random_state=None,
solver='warn', tol=0.0001, verbose=0,
warm_start=False))],
verbose=False)"""
expected = expected[1:] # remove first \n
assert pipeline.__repr__() == expected
示例6: test_make_pipeline
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_make_pipeline():
t1 = Transf()
t2 = Transf()
pipe = make_pipeline(t1, t2)
assert isinstance(pipe, Pipeline)
assert_equal(pipe.steps[0][0], "transf-1")
assert_equal(pipe.steps[1][0], "transf-2")
pipe = make_pipeline(t1, t2, FitParamT())
assert isinstance(pipe, Pipeline)
assert_equal(pipe.steps[0][0], "transf-1")
assert_equal(pipe.steps[1][0], "transf-2")
assert_equal(pipe.steps[2][0], "fitparamt")
assert_raise_message(
TypeError,
'Unknown keyword arguments: "random_parameter"',
make_pipeline, t1, t2, random_parameter='rnd'
)
示例7: test_lasso_cv_with_some_model_selection
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_lasso_cv_with_some_model_selection():
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import StratifiedKFold
from sklearn import datasets
from sklearn.linear_model import LassoCV
diabetes = datasets.load_diabetes()
X = diabetes.data
y = diabetes.target
pipe = make_pipeline(
StandardScaler(),
LassoCV(cv=StratifiedKFold(n_splits=5))
)
pipe.fit(X, y)
示例8: build_language_classifier
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def build_language_classifier(texts, labels, verbose=False, random_state=None):
"""Train a text classifier with scikit-learn
The text classifier is composed of two elements assembled in a pipeline:
- A text feature extractor (`TfidfVectorizer`) that extract the relative
frequencies of unigrams, bigrams and trigrams of characters in the text.
- An instance of `SGDClassifier` for the classification it-self. To speed
up training it is recommended to enable early stopping.
`random_state` is passed to the underlying `SGDClassifier` instance.
"""
language_classifier = make_pipeline(
TfidfVectorizer(analyzer="char", ngram_range=(1, 3),
min_df=2, max_df=0.9, norm="l2", dtype=np.float32),
SGDClassifier(early_stopping=True, validation_fraction=0.2,
n_iter_no_change=3, max_iter=1000, tol=1e-3,
alpha=1e-5, penalty="l2", verbose=verbose,
random_state=random_state)
)
return language_classifier.fit(texts, labels)
示例9: test_time
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_time(pipeline_name, name, path):
if pipeline_name == "LR":
pipeline = make_pipeline(LogisticRegression())
if pipeline_name == "FGS":
pipeline = make_pipeline(FeatureGradientSelector(), LogisticRegression())
if pipeline_name == "Tree":
pipeline = make_pipeline(SelectFromModel(ExtraTreesClassifier(n_estimators=50)), LogisticRegression())
test_benchmark = Benchmark()
print("Dataset:\t", name)
print("Pipeline:\t", pipeline_name)
starttime = datetime.datetime.now()
test_benchmark.run_test(pipeline, name, path)
endtime = datetime.datetime.now()
print("Used time: ", (endtime - starttime).microseconds/1000)
print("")
示例10: test
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test():
url_zip_train = 'https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/rcv1_train.binary.bz2'
urllib.request.urlretrieve(url_zip_train, filename='train.bz2')
f_svm = open('train.svm', 'wt')
with bz2.open('train.bz2', 'rb') as f_zip:
data = f_zip.read()
f_svm.write(data.decode('utf-8'))
f_svm.close()
X, y = load_svmlight_file('train.svm')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
pipeline = make_pipeline(FeatureGradientSelector(n_epochs=1, n_features=10), LogisticRegression())
# pipeline = make_pipeline(SelectFromModel(ExtraTreesClassifier(n_estimators=50)), LogisticRegression())
pipeline.fit(X_train, y_train)
print("Pipeline Score: ", pipeline.score(X_train, y_train))
示例11: test_mdr_sklearn_pipeline
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_mdr_sklearn_pipeline():
"""Ensure that MDR can be used as a transformer in a scikit-learn pipeline"""
features = np.array([[2, 0],
[0, 0],
[0, 1],
[0, 0],
[0, 0],
[0, 0],
[0, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 0],
[0, 0],
[0, 0],
[1, 1],
[1, 1]])
classes = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0])
clf = make_pipeline(MDR(), LogisticRegression())
cv_scores = cross_val_score(clf, features, classes, cv=StratifiedKFold(n_splits=5, shuffle=True))
assert np.mean(cv_scores) > 0.
示例12: test_mdr_sklearn_pipeline_parallel
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_mdr_sklearn_pipeline_parallel():
"""Ensure that MDR can be used as a transformer in a parallelized scikit-learn pipeline"""
features = np.array([[2, 0],
[0, 0],
[0, 1],
[0, 0],
[0, 0],
[0, 0],
[0, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 0],
[0, 0],
[0, 0],
[1, 1],
[1, 1]])
classes = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0])
clf = make_pipeline(MDR(), LogisticRegression())
cv_scores = cross_val_score(clf, features, classes, cv=StratifiedKFold(n_splits=5, shuffle=True), n_jobs=-1)
assert np.mean(cv_scores) > 0.
示例13: test_compare_with_sklearn
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_compare_with_sklearn(self):
from lale.operators import make_pipeline
tfm = PCA()
clf = LogisticRegression(LogisticRegression.solver.lbfgs, LogisticRegression.multi_class.auto)
trainable = make_pipeline(tfm, clf)
digits = sklearn.datasets.load_digits()
trained = trainable.fit(digits.data, digits.target)
predicted = trained.predict(digits.data)
from sklearn.pipeline import make_pipeline as scikit_make_pipeline
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.linear_model import LogisticRegression as SklearnLR
sklearn_pipeline = scikit_make_pipeline(SklearnPCA(), SklearnLR(solver="lbfgs", multi_class="auto"))
sklearn_pipeline.fit(digits.data, digits.target)
predicted_sklearn = sklearn_pipeline.predict(digits.data)
from sklearn.metrics import accuracy_score
lale_score = accuracy_score(digits.target, predicted)
scikit_score = accuracy_score(digits.target, predicted_sklearn)
self.assertEqual(lale_score, scikit_score)
示例14: test_import_from_sklearn_pipeline_feature_union
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_import_from_sklearn_pipeline_feature_union(self):
from sklearn.pipeline import FeatureUnion
from sklearn.decomposition import PCA
from sklearn.kernel_approximation import Nystroem
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import make_pipeline
union = FeatureUnion([("pca", PCA(n_components=1)), ("nys", Nystroem(n_components=2, random_state=42))])
sklearn_pipeline = make_pipeline(union, KNeighborsClassifier())
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
self.assertEqual(len(lale_pipeline.edges()), 3)
from lale.lib.sklearn.pca import PCAImpl
from lale.lib.sklearn.nystroem import NystroemImpl
from lale.lib.lale.concat_features import ConcatFeaturesImpl
from lale.lib.sklearn.k_neighbors_classifier import KNeighborsClassifierImpl
self.assertEqual(lale_pipeline.edges()[0][0]._impl_class(), PCAImpl)
self.assertEqual(lale_pipeline.edges()[0][1]._impl_class(), ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[1][0]._impl_class(), NystroemImpl)
self.assertEqual(lale_pipeline.edges()[1][1]._impl_class(), ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[2][0]._impl_class(), ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[2][1]._impl_class(), KNeighborsClassifierImpl)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
示例15: test_bagging_with_pipeline
# 需要导入模块: from sklearn import pipeline [as 别名]
# 或者: from sklearn.pipeline import make_pipeline [as 别名]
def test_bagging_with_pipeline():
estimator = BaggingClassifier(make_pipeline(SelectKBest(k=1),
DecisionTreeClassifier()),
max_features=2)
estimator.fit(iris.data, iris.target)
assert isinstance(estimator[0].steps[-1][1].random_state, int)