def test_warm_start(random_state=42):
# Test if fitting incrementally with warm start gives a forest of the
# right size and the same results as a normal fit.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf_ws = None
for n_estimators in [5, 10]:
if clf_ws is None:
clf_ws = EasyEnsembleClassifier(
n_estimators=n_estimators,
random_state=random_state,
warm_start=True,
)
else:
clf_ws.set_params(n_estimators=n_estimators)
clf_ws.fit(X, y)
assert len(clf_ws) == n_estimators
clf_no_ws = EasyEnsembleClassifier(
n_estimators=10, random_state=random_state, warm_start=False
)
clf_no_ws.fit(X, y)
assert {pipe.steps[-1][1].random_state for pipe in clf_ws} == {
pipe.steps[-1][1].random_state for pipe in clf_no_ws
}
def test_warm_start_smaller_n_estimators():
# Test if warm start'ed second fit with smaller n_estimators raises error.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf = EasyEnsembleClassifier(n_estimators=5, warm_start=True)
clf.fit(X, y)
clf.set_params(n_estimators=4)
with pytest.raises(ValueError):
clf.fit(X, y)
def test_warm_start_smaller_n_estimators():
# Test if warm start'ed second fit with smaller n_estimators raises error.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf = EasyEnsembleClassifier(n_estimators=5, warm_start=True)
clf.fit(X, y)
clf.set_params(n_estimators=4)
with pytest.raises(ValueError):
clf.fit(X, y)
def test_warm_start_equivalence():
# warm started classifier with 5+5 estimators should be equivalent to
# one classifier with 10 estimators
X, y = make_hastie_10_2(n_samples=20, random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)
clf_ws = EasyEnsembleClassifier(n_estimators=5, warm_start=True, random_state=3141)
clf_ws.fit(X_train, y_train)
clf_ws.set_params(n_estimators=10)
clf_ws.fit(X_train, y_train)
y1 = clf_ws.predict(X_test)
clf = EasyEnsembleClassifier(n_estimators=10, warm_start=False, random_state=3141)
clf.fit(X_train, y_train)
y2 = clf.predict(X_test)
assert_allclose(y1, y2)
def test_warm_start_equivalence():
# warm started classifier with 5+5 estimators should be equivalent to
# one classifier with 10 estimators
X, y = make_hastie_10_2(n_samples=20, random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)
clf_ws = EasyEnsembleClassifier(
n_estimators=5, warm_start=True, random_state=3141)
clf_ws.fit(X_train, y_train)
clf_ws.set_params(n_estimators=10)
clf_ws.fit(X_train, y_train)
y1 = clf_ws.predict(X_test)
clf = EasyEnsembleClassifier(
n_estimators=10, warm_start=False, random_state=3141)
clf.fit(X_train, y_train)
y2 = clf.predict(X_test)
assert_allclose(y1, y2)
def test_warm_start(random_state=42):
# Test if fitting incrementally with warm start gives a forest of the
# right size and the same results as a normal fit.
X, y = make_hastie_10_2(n_samples=20, random_state=1)
clf_ws = None
for n_estimators in [5, 10]:
if clf_ws is None:
clf_ws = EasyEnsembleClassifier(
n_estimators=n_estimators,
random_state=random_state,
warm_start=True)
else:
clf_ws.set_params(n_estimators=n_estimators)
clf_ws.fit(X, y)
assert len(clf_ws) == n_estimators
clf_no_ws = EasyEnsembleClassifier(
n_estimators=10, random_state=random_state, warm_start=False)
clf_no_ws.fit(X, y)
assert (set([pipe.steps[-1][1].random_state for pipe in clf_ws]) == set(
[pipe.steps[-1][1].random_state for pipe in clf_no_ws]))
