def test_small(c, s, a, b):
X, y = make_classification(n_samples=100, n_features=5, chunks=(10, 5))
model = SGDClassifier(tol=1e-3, penalty="elasticnet")
params = {"alpha": [0.1, 0.5, 0.75, 1.0]}
search = IncrementalSearch(model, params, n_initial_parameters="grid")
yield search.fit(X, y, classes=[0, 1])
X_, = yield c.compute([X])
search.predict(X_)
def test_numpy_array(c, s, a, b):
X, y = make_classification(n_samples=100, n_features=5, chunks=(10, 5))
X, y = yield c.compute([X, y])
model = SGDClassifier(tol=1e-3, penalty="elasticnet")
params = {"alpha": np.logspace(-2, 10, 10), "l1_ratio": np.linspace(0.01, 1, 20)}
search = IncrementalSearch(model, params, n_initial_parameters=10)
yield search.fit(X, y, classes=[0, 1])
def test_transform(c, s, a, b):
X, y = make_classification(n_samples=100, n_features=5, chunks=(10, 5))
model = MiniBatchKMeans(random_state=0)
params = {"n_clusters": [3, 4, 5], "n_init": [1, 2]}
search = IncrementalSearch(model, params, n_initial_parameters="grid")
yield search.fit(X, y)
X_, = yield c.compute([X])
result = search.transform(X_)
assert result.shape == (100, search.best_estimator_.n_clusters)
def test_search_max_iter(c, s, a, b):
X, y = make_classification(n_samples=100, n_features=5, chunks=(10, 5))
model = SGDClassifier(tol=1e-3, penalty="elasticnet")
params = {"alpha": np.logspace(-2, 10, 10), "l1_ratio": np.linspace(0.01, 1, 20)}
search = IncrementalSearch(model, params, n_initial_parameters=10, max_iter=1)
yield search.fit(X, y, classes=[0, 1])
for d in search.history_results_:
assert d["partial_fit_calls"] <= 1
def test_gridsearch(c, s, a, b):
X, y = make_classification(n_samples=100, n_features=5, chunks=(10, 5))
model = SGDClassifier(tol=1e-3)
params = {"alpha": np.logspace(-2, 10, 3), "l1_ratio": np.linspace(0.01, 1, 2)}
search = IncrementalSearch(model, params, n_initial_parameters="grid")
yield search.fit(X, y, classes=[0, 1])
assert {frozenset(d["params"].items()) for d in search.history_results_} == {
frozenset(d.items()) for d in ParameterGrid(params)
}
def test_search_patience(c, s, a, b):
X, y = make_classification(n_samples=100, n_features=5, chunks=(10, 5))
class ConstantClassifier(SGDClassifier):
def score(*args, **kwargs):
return 0.5
model = ConstantClassifier(tol=1e-3)
params = {
"alpha": np.logspace(-2, 10, 100),
"l1_ratio": np.linspace(0.01, 1, 200)
}
search = IncrementalSearch(model,
params,
n_initial_parameters=10,
patience=2)
yield search.fit(X, y, classes=[0, 1])
assert search.history_results_
for d in search.history_results_:
assert d["partial_fit_calls"] <= 3
assert isinstance(search.best_estimator_, SGDClassifier)
assert search.best_score_ > 0
assert "visualize" not in search.__dict__
X_test, y_test = yield c.compute([X, y])
search.predict(X_test)
search.score(X_test, y_test)
def test_search(c, s, a, b):
X, y = make_classification(n_samples=1000, n_features=5, chunks=(100, 5))
model = SGDClassifier(tol=1e-3, loss="log", penalty="elasticnet")
params = {
"alpha": np.logspace(-2, 2, 100),
"l1_ratio": np.linspace(0.01, 1, 200)
}
search = IncrementalSearch(model,
params,
n_initial_parameters=10,
max_iter=10)
yield search.fit(X, y, classes=[0, 1])
assert search.history_results_
for d in search.history_results_:
assert d["partial_fit_calls"] <= search.max_iter + 1
assert isinstance(search.best_estimator_, SGDClassifier)
assert search.best_score_ > 0
assert "visualize" not in search.__dict__
assert search.best_params_
X_, = yield c.compute([X])
proba = search.predict_proba(X_)
log_proba = search.predict_log_proba(X_)
assert proba.shape == (1000, 2)
assert log_proba.shape == (1000, 2)
decision = search.decision_function(X_)
assert decision.shape == (1000, )