def test_kmeans_simple_X(client=None):
pipe = Pipeline([steps.Flatten(),
MiniBatchKMeans(n_clusters=6)])
fitted = pipe.fit_ensemble(X=X, **ENSEMBLE_KWARGS)
_train_asserts(fitted, ENSEMBLE_KWARGS['saved_ensemble_size'])
pred = fitted.predict_many(X=X)
assert len(pred) == len(fitted.ensemble)
def test_kmeans_simple_sampler(client=None):
pipe = Pipeline([steps.Flatten(), MiniBatchKMeans(n_clusters=6)])
kw = SAMPLER_DATA_SOURCE.copy()
kw.update(ENSEMBLE_KWARGS)
fitted = pipe.fit_ensemble(**kw)
ens = fitted.ensemble
_train_asserts(fitted, ENSEMBLE_KWARGS['saved_ensemble_size'])
pred = fitted.predict_many(**SAMPLER_DATA_SOURCE)
assert len(pred) == len(SAMPLER_DATA_SOURCE['args_list']) * len(ens)
def test_supervised_feat_select_X_y(client=None):
'''Has a ModifySample step to get necessary y data'''
pipe = Pipeline([steps.Flatten(),
steps.SelectPercentile(score_func=f_classif, percentile=50),
SGDClassifier()])
en = dict(method_kwargs=dict(classes=[0, 1, 2]), **ENSEMBLE_KWARGS)
en.update(X_Y_DATA_SOURCE)
fitted = pipe.fit_ensemble(**en)
_train_asserts(fitted, en['saved_ensemble_size'])
pred = fitted.predict_many(**X_Y_DATA_SOURCE)
assert len(pred) == len(fitted.ensemble)
def test_simple():
p = Pipeline([steps.Flatten(), MiniBatchKMeans(n_clusters=5),])
args_list = [(100, 200, 5)] * 10 # (height, width, bands)
data_source = dict(sampler=example_sampler, args_list=args_list)
ensemble_kw = dict(ngen=2, init_ensemble_size=2)
ensemble_kw.update(data_source)
fitted = p.fit_ensemble(**ensemble_kw)
tagged_fitted_models = fitted.ensemble
(tag1, model1), (tag2, model2) = tagged_fitted_models # ensemble size of 2 here
X = example_sampler(100, 400, 5)
pred1 = model1.predict(X)
pred2 = model2.predict(X)
assert pred1.shape == pred2.shape == (400 * 100,)
def test_kmeans_model_selection(client=None):
pipe = Pipeline([
steps.Flatten(), ('pca', steps.Transform(IncrementalPCA())),
('kmeans', MiniBatchKMeans(n_clusters=5))
],
scoring=kmeans_aic,
scoring_kwargs={'score_weights': [-1]})
def samp(*args, **kwargs):
return random_elm_store(bands=12, mn=0, mx=1, height=20, width=40)
en = ENSEMBLE_KWARGS.copy()
n_clusters_choices = list(range(3, 10))
def init(pipe, **kwargs):
estimators = []
for _ in range(100):
n_components = np.random.choice(np.arange(2, 6))
n_clusters = np.random.choice(n_clusters_choices)
estimator = copy.deepcopy(pipe)
estimator.set_params(kmeans__n_clusters=n_clusters,
pca__n_components=n_components)
estimators.append(estimator)
return estimators
en['ngen'] = 20
en['model_scoring'] = kmeans_aic
en['ensemble_init_func'] = init
en['model_selection_kwargs'] = dict(drop_n=30,
evolve_n=30,
choices=n_clusters_choices)
en['model_selection'] = kmeans_model_averaging
sa = SAMPLER_DATA_SOURCE.copy()
sa['sampler'] = samp
en.update(sa)
fitted = pipe.fit_ensemble(**en)
assert len(fitted.ensemble) == en['saved_ensemble_size']
preds = fitted.predict_many(**sa)
assert len(preds) == len(fitted.ensemble) * len(
SAMPLER_DATA_SOURCE['args_list'])
