def dont_test_with_gridsearchcv2_auto(self):
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score, make_scorer
from sklearn.model_selection import GridSearchCV
lr = LogisticRegression(random_state=42)
pca = PCA(random_state=42, svd_solver="arpack")
trainable = pca >> lr
from sklearn.pipeline import Pipeline
scikit_pipeline = Pipeline([
(pca.name(), PCA(random_state=42, svd_solver="arpack")),
(lr.name(), LogisticRegression(random_state=42)),
])
all_parameters = get_grid_search_parameter_grids(trainable,
num_samples=1)
# otherwise the test takes too long
parameters = random.sample(all_parameters, 2)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
clf = GridSearchCV(scikit_pipeline,
parameters,
cv=2,
scoring=make_scorer(accuracy_score))
iris = load_iris()
clf.fit(iris.data, iris.target)
predicted = clf.predict(iris.data)
accuracy_with_lale_operators = accuracy_score(
iris.target, predicted)
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.linear_model import LogisticRegression as SklearnLR
from sklearn.pipeline import Pipeline
scikit_pipeline = Pipeline([
(pca.name(), SklearnPCA(random_state=42, svd_solver="arpack")),
(lr.name(), SklearnLR(random_state=42)),
])
with warnings.catch_warnings():
warnings.simplefilter("ignore")
clf = GridSearchCV(scikit_pipeline,
parameters,
cv=2,
scoring=make_scorer(accuracy_score))
iris = load_iris()
clf.fit(iris.data, iris.target)
predicted = clf.predict(iris.data)
accuracy_with_scikit_operators = accuracy_score(
iris.target, predicted)
self.assertEqual(accuracy_with_lale_operators,
accuracy_with_scikit_operators)
def test_with_gridsearchcv3_auto(self):
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score, make_scorer
from sklearn.model_selection import GridSearchCV
lr = LogisticRegression()
from sklearn.pipeline import Pipeline
scikit_pipeline = Pipeline(
[(Nystroem().name(), Nystroem()), (lr.name(), LogisticRegression())]
)
all_parameters = get_grid_search_parameter_grids(
Nystroem() >> lr, num_samples=1
)
# otherwise the test takes too long
parameters = random.sample(all_parameters, 2)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
clf = GridSearchCV(
scikit_pipeline, parameters, cv=2, scoring=make_scorer(accuracy_score)
)
iris = load_iris()
clf.fit(iris.data, iris.target)
_ = clf.predict(iris.data)
