def test_pipeline_create(self):
from lale.lib.sklearn import PCA, LogisticRegression
from lale.operators import Pipeline
pipeline = Pipeline(([('pca1', PCA()), ('lr1', LogisticRegression())]))
trained = pipeline.fit(self.X_train, self.y_train)
predictions = trained.predict(self.X_test)
from sklearn.metrics import accuracy_score
accuracy_score(self.y_test, predictions)
def test_import_from_sklearn_pipeline2(self):
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_regression
from sklearn import svm
from sklearn.pipeline import Pipeline
anova_filter = SelectKBest(f_regression, k=3)
clf = svm.SVC(kernel='linear')
sklearn_pipeline = Pipeline([('anova', anova_filter), ('svc', clf)])
sklearn_pipeline.fit(self.X_train, self.y_train)
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
lale_pipeline.predict(self.X_test)
def test_import_from_sklearn_pipeline2(self):
from sklearn.feature_selection import SelectKBest, f_regression
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC as SklearnSVC
anova_filter = SelectKBest(f_regression, k=3)
clf = SklearnSVC(kernel="linear")
sklearn_pipeline = Pipeline([("anova", anova_filter), ("svc", clf)])
sklearn_pipeline.fit(self.X_train, self.y_train)
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
lale_pipeline.predict(self.X_test)
def test_pipeline_create(self):
from lale.operators import Pipeline
pipeline = Pipeline(([("pca1", PCA()), ("lr1", LogisticRegression())]))
trained = pipeline.fit(self.X_train, self.y_train)
predictions = trained.predict(self.X_test)
accuracy_score(self.y_test, predictions)
def test_pipeline_clone(self):
from sklearn.base import clone
from lale.lib.sklearn import PCA, LogisticRegression
from lale.operators import Pipeline
pipeline = Pipeline(([('pca1', PCA()), ('lr1', LogisticRegression())]))
trained = pipeline.fit(self.X_train, self.y_train)
predictions = trained.predict(self.X_test)
from sklearn.metrics import accuracy_score
orig_acc = accuracy_score(self.y_test, predictions)
cloned_pipeline = clone(pipeline)
trained = cloned_pipeline.fit(self.X_train, self.y_train)
predictions = trained.predict(self.X_test)
from sklearn.metrics import accuracy_score
cloned_acc = accuracy_score(self.y_test, predictions)
self.assertEqual(orig_acc, cloned_acc)
def test_import_from_sklearn_pipeline_noop1(self):
from sklearn.pipeline import Pipeline
from sklearn.ensemble import GradientBoostingClassifier
from lale.helpers import import_from_sklearn_pipeline
pipe = Pipeline([('noop', NoOp()),
('gbc', GradientBoostingClassifier())])
imported_pipeline = import_from_sklearn_pipeline(pipe)
def test_import_from_sklearn_pipeline_noop(self):
from sklearn.pipeline import Pipeline
from sklearn.ensemble import GradientBoostingClassifier
from lale.helpers import import_from_sklearn_pipeline
pipe = Pipeline([('noop', None),
('gbc', GradientBoostingClassifier())])
with self.assertRaises(ValueError):
imported_pipeline = import_from_sklearn_pipeline(pipe)
def test_import_from_sklearn_pipeline3(self):
from sklearn.feature_selection import SelectKBest, f_regression
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC as SklearnSVC
anova_filter = SelectKBest(f_regression, k=3)
clf = SklearnSVC(kernel="linear")
sklearn_pipeline = Pipeline([("anova", anova_filter), ("svc", clf)])
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline, fitted=False)
with self.assertRaises(
ValueError
): # fitted=False returns a Trainable, so calling predict is invalid.
lale_pipeline.predict(self.X_test)
def test_import_from_sklearn_pipeline3(self):
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_regression
from sklearn import svm
from sklearn.pipeline import Pipeline
anova_filter = SelectKBest(f_regression, k=3)
clf = svm.SVC(kernel='linear')
sklearn_pipeline = Pipeline([('anova', anova_filter), ('svc', clf)])
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline,
fitted=False)
with self.assertRaises(
ValueError
): #fitted=False returns a Trainable, so calling predict is invalid.
lale_pipeline.predict(self.X_test)
def test_pipeline_clone(self):
from sklearn.base import clone
from lale.operators import Pipeline
pipeline = Pipeline(([("pca1", PCA()), ("lr1", LogisticRegression())]))
trained = pipeline.fit(self.X_train, self.y_train)
predictions = trained.predict(self.X_test)
orig_acc = accuracy_score(self.y_test, predictions)
cloned_pipeline = clone(pipeline)
trained = cloned_pipeline.fit(self.X_train, self.y_train)
predictions = trained.predict(self.X_test)
cloned_acc = accuracy_score(self.y_test, predictions)
self.assertEqual(orig_acc, cloned_acc)
def test_import_from_sklearn_pipeline(self):
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_regression
from sklearn import svm
from sklearn.pipeline import Pipeline
anova_filter = SelectKBest(f_regression, k=3)
clf = svm.SVC(kernel='linear')
sklearn_pipeline = Pipeline([('anova', anova_filter), ('svc', clf)])
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
for i, pipeline_step in enumerate(sklearn_pipeline.named_steps):
sklearn_step_params = sklearn_pipeline.named_steps[
pipeline_step].get_params()
lale_sklearn_params = lale_pipeline.steps(
)[i]._impl._wrapped_model.get_params()
self.assertEqual(sklearn_step_params, lale_sklearn_params)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline(self):
from sklearn.feature_selection import SelectKBest, f_regression
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC as SklearnSVC
anova_filter = SelectKBest(f_regression, k=3)
clf = SklearnSVC(kernel="linear")
sklearn_pipeline = Pipeline([("anova", anova_filter), ("svc", clf)])
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
for i, pipeline_step in enumerate(sklearn_pipeline.named_steps):
sklearn_step_params = sklearn_pipeline.named_steps[
pipeline_step].get_params()
lale_sklearn_params = lale_pipeline.steps(
)[i]._impl._wrapped_model.get_params()
self.assertEqual(sklearn_step_params, lale_sklearn_params)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline(self):
from sklearn.feature_selection import SelectKBest, f_regression
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC as SklearnSVC
anova_filter = SelectKBest(f_regression, k=3)
clf = SklearnSVC(kernel="linear")
sklearn_pipeline = Pipeline([("anova", anova_filter), ("svc", clf)])
lale_pipeline = typing.cast(
lale.operators.TrainablePipeline,
import_from_sklearn_pipeline(sklearn_pipeline),
)
for i, pipeline_step in enumerate(sklearn_pipeline.named_steps):
sklearn_step_params = sklearn_pipeline.named_steps[
pipeline_step].get_params()
lale_sklearn_params = self.get_sklearn_params(
lale_pipeline.steps_list()[i])
self.assertEqual(sklearn_step_params, lale_sklearn_params)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
