def test_select_percentile():
t = steps.SelectPercentile(percentile=50, score_func='f_classif')
X_new, y2, sample_weight = t.fit_transform(flat_X, y)
assert np.all(y == y2)
assert sample_weight is None
assert isinstance(X_new, ElmStore)
assert hasattr(X_new, 'flat')
assert X_new.flat.values.shape[1] < flat_X.flat.values.shape[1]
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)
from api_example import data_source
ELM_EXAMPLE_DATA_PATH = os.environ['ELM_EXAMPLE_DATA_PATH']
def make_example_y_data(X, y=None, sample_weight=None, **kwargs):
fitted = MiniBatchKMeans(n_clusters=5).fit(X.flat.values)
y = fitted.predict(X.flat.values)
return (X, y, sample_weight)
pipeline_steps = [
steps.Flatten(),
steps.ModifySample(make_example_y_data),
('top_n', steps.SelectPercentile(percentile=80, score_func=f_classif)),
('kmeans', MiniBatchKMeans(n_clusters=4))
]
pipeline = Pipeline(pipeline_steps, scoring=kmeans_aic)
param_grid = {
'kmeans__n_clusters': list(range(5, 10)),
'control': {
'select_method': 'selNSGA2',
'crossover_method': 'cxTwoPoint',
'mutate_method': 'mutUniformInt',
'init_pop': 'random',
'indpb': 0.5,
'mutpb': 0.9,
'cxpb': 0.3,
'eta': 20,
'ngen': 2,