def test_pipeline_sub_estimators():
iris = load_iris()
X, y = iris.data, iris.target
scaling = Pipeline([('transform', ScalingTransformer())])
pipe = Pipeline([('setup', None), ('missing', None), ('scaling', scaling),
('svc', SVC(kernel='linear', random_state=0))])
param_grid = [
{
'svc__C': [0.1, 0.1]
}, # Duplicates to test culling
{
'setup': [None],
'svc__C': [0.1, 1, 10],
'scaling': [ScalingTransformer(), None]
},
{
'setup': [SelectKBest()],
'setup__k': [1, 2],
'svc': [
SVC(kernel='linear', random_state=0, C=0.1),
SVC(kernel='linear', random_state=0, C=1),
SVC(kernel='linear', random_state=0, C=10)
]
}
]
gs = GridSearchCV(pipe, param_grid=param_grid, return_train_score=True)
gs.fit(X, y)
dgs = dcv.GridSearchCV(pipe,
param_grid=param_grid,
scheduler='sync',
return_train_score=True)
dgs.fit(X, y)
# Check best params match
assert gs.best_params_ == dgs.best_params_
# Check cv results match
res = pd.DataFrame(dgs.cv_results_)
sol = pd.DataFrame(gs.cv_results_)
# TODO: Failures on Py36 / sklearn dev with order here.
res = res.reindex(columns=sol.columns)
pd.util.testing.assert_index_equal(res.columns, sol.columns)
skip = [
'mean_fit_time', 'std_fit_time', 'mean_score_time', 'std_score_time'
]
res = res.drop(skip, axis=1)
sol = sol.drop(skip, axis=1)
assert res.equals(sol)
# Check SVC coefs match
np.testing.assert_allclose(gs.best_estimator_.named_steps['svc'].coef_,
dgs.best_estimator_.named_steps['svc'].coef_)
def test_pipeline_feature_union():
iris = load_iris()
X, y = iris.data, iris.target
pca = PCA(random_state=0)
kbest = SelectKBest()
empty_union = FeatureUnion([("first", None), ("second", None)])
empty_pipeline = Pipeline([("first", None), ("second", None)])
scaling = Pipeline([("transform", ScalingTransformer())])
svc = SVC(kernel="linear", random_state=0)
pipe = Pipeline([
("empty_pipeline", empty_pipeline),
("scaling", scaling),
("missing", None),
(
"union",
FeatureUnion(
[
("pca", pca),
("missing", None),
("kbest", kbest),
("empty_union", empty_union),
],
transformer_weights={"pca": 0.5},
),
),
("svc", svc),
])
param_grid = dict(
scaling__transform__factor=[1, 2],
union__pca__n_components=[1, 2, 3],
union__kbest__k=[1, 2],
svc__C=[0.1, 1, 10],
)
gs = GridSearchCV(pipe, param_grid=param_grid, cv=3, iid=True)
gs.fit(X, y)
dgs = dcv.GridSearchCV(pipe, param_grid=param_grid, scheduler="sync", cv=3)
dgs.fit(X, y)
# Check best params match
assert gs.best_params_ == dgs.best_params_
# Check PCA components match
sk_pca = gs.best_estimator_.named_steps["union"].transformer_list[0][1]
dk_pca = dgs.best_estimator_.named_steps["union"].transformer_list[0][1]
np.testing.assert_allclose(sk_pca.components_, dk_pca.components_)
# Check SelectKBest scores match
sk_kbest = gs.best_estimator_.named_steps["union"].transformer_list[2][1]
dk_kbest = dgs.best_estimator_.named_steps["union"].transformer_list[2][1]
np.testing.assert_allclose(sk_kbest.scores_, dk_kbest.scores_)
# Check SVC coefs match
np.testing.assert_allclose(
gs.best_estimator_.named_steps["svc"].coef_,
dgs.best_estimator_.named_steps["svc"].coef_,
)
def test_pipeline_feature_union():
iris = load_iris()
X, y = iris.data, iris.target
pca = PCA(random_state=0)
kbest = SelectKBest()
empty_union = FeatureUnion([('first', None), ('second', None)])
empty_pipeline = Pipeline([('first', None), ('second', None)])
scaling = Pipeline([('transform', ScalingTransformer())])
svc = SVC(kernel='linear', random_state=0)
pipe = Pipeline([('empty_pipeline', empty_pipeline), ('scaling', scaling),
('missing', None),
('union',
FeatureUnion([('pca', pca), ('missing', None),
('kbest', kbest),
('empty_union', empty_union)],
transformer_weights={'pca': 0.5})),
('svc', svc)])
param_grid = dict(scaling__transform__factor=[1, 2],
union__pca__n_components=[1, 2, 3],
union__kbest__k=[1, 2],
svc__C=[0.1, 1, 10])
gs = GridSearchCV(pipe, param_grid=param_grid)
gs.fit(X, y)
dgs = dcv.GridSearchCV(pipe, param_grid=param_grid, scheduler='sync')
dgs.fit(X, y)
# Check best params match
assert gs.best_params_ == dgs.best_params_
# Check PCA components match
sk_pca = gs.best_estimator_.named_steps['union'].transformer_list[0][1]
dk_pca = dgs.best_estimator_.named_steps['union'].transformer_list[0][1]
np.testing.assert_allclose(sk_pca.components_, dk_pca.components_)
# Check SelectKBest scores match
sk_kbest = gs.best_estimator_.named_steps['union'].transformer_list[2][1]
dk_kbest = dgs.best_estimator_.named_steps['union'].transformer_list[2][1]
np.testing.assert_allclose(sk_kbest.scores_, dk_kbest.scores_)
# Check SVC coefs match
np.testing.assert_allclose(gs.best_estimator_.named_steps['svc'].coef_,
dgs.best_estimator_.named_steps['svc'].coef_)
def test_feature_union(weights):
X = np.ones((10, 5))
y = np.zeros(10)
union = FeatureUnion(
[
("tr0", ScalingTransformer()),
("tr1", ScalingTransformer()),
("tr2", ScalingTransformer()),
]
)
factors = [(2, 3, 5), (2, 4, 5), (2, 4, 6), (2, 4, None), (None, None, None)]
params, sols, grid = [], [], []
for constants, w in product(factors, weights or [None]):
p = {}
for n, c in enumerate(constants):
if c is None:
p["tr%d" % n] = None
elif n == 3: # 3rd is always an estimator
p["tr%d" % n] = ScalingTransformer(c)
else:
p["tr%d__factor" % n] = c
sol = union.set_params(transformer_weights=w, **p).transform(X)
sols.append(sol)
if w is not None:
p["transformer_weights"] = w
params.append(p)
p2 = {"union__" + k: [v] for k, v in p.items()}
p2["est"] = [CheckXClassifier(sol[0])]
grid.append(p2)
# Need to recreate the union after setting estimators to `None` above
union = FeatureUnion(
[
("tr0", ScalingTransformer()),
("tr1", ScalingTransformer()),
("tr2", ScalingTransformer()),
]
)
pipe = Pipeline([("union", union), ("est", CheckXClassifier())])
gs = dcv.GridSearchCV(pipe, grid, refit=False, cv=2)
with warnings.catch_warnings(record=True):
gs.fit(X, y)
def test_pipeline_sub_estimators():
iris = load_iris()
X, y = iris.data, iris.target
scaling = Pipeline([("transform", ScalingTransformer())])
pipe = Pipeline([
("setup", None),
("missing", None),
("scaling", scaling),
("svc", SVC(kernel="linear", random_state=0)),
])
param_grid = [
{
"svc__C": [0.1, 0.1]
}, # Duplicates to test culling
{
"setup": [None],
"svc__C": [0.1, 1, 10],
"scaling": [ScalingTransformer(), None],
},
{
"setup": [SelectKBest()],
"setup__k": [1, 2],
"svc": [
SVC(kernel="linear", random_state=0, C=0.1),
SVC(kernel="linear", random_state=0, C=1),
SVC(kernel="linear", random_state=0, C=10),
],
},
]
gs = GridSearchCV(pipe,
param_grid=param_grid,
return_train_score=True,
cv=3,
**iid)
gs.fit(X, y)
dgs = dcv.GridSearchCV(pipe,
param_grid=param_grid,
scheduler="sync",
return_train_score=True,
cv=3)
dgs.fit(X, y)
# Check best params match
assert gs.best_params_ == dgs.best_params_
# Check cv results match
res = pd.DataFrame(dgs.cv_results_)
sol = pd.DataFrame(gs.cv_results_)
# TODO: Failures on Py36 / sklearn dev with order here.
res = res.reindex(columns=sol.columns)
pd.util.testing.assert_index_equal(res.columns, sol.columns)
skip = [
"mean_fit_time", "std_fit_time", "mean_score_time", "std_score_time"
]
res = res.drop(skip, axis=1)
sol = sol.drop(skip, axis=1)
pd.util.testing.assert_frame_equal(res,
sol,
check_exact=False,
check_less_precise=1)
# Check SVC coefs match
np.testing.assert_allclose(
gs.best_estimator_.named_steps["svc"].coef_,
dgs.best_estimator_.named_steps["svc"].coef_,
)