def test_set_params_get_params():
'''Assert setting with double underscore
parameter names will work ok'''
p = Pipeline(flat_poly_var_kmeans)
kw = dict(kmeans__n_clusters=9,
poly__interaction_only=False,
var__threshold=1e-8)
p.set_params(**kw)
params = p.get_params()
for k, v in kw.items():
assert k in params and params[k] == v
with pytest.raises(ValueError):
p.set_params(kmeans_n_clusters=9) # no double underscore
def ensemble_init_func(pipe, **kw):
'''Create an ensemble of regression models to predict soil moisture
where PCA, scaling, and/or log transformation may follow preamble
steps of flattening a Dataset and extracting the Y data, among other
preprocessors.
Parameters:
pipe: Ignored
**kw: Keyword arguments:
scalers: List of (name, scaler) tuples such as
[('StandardScaler', steps.StandardScaler(with_mean=True)),
('RobustScaler', steps.RobustScaler(with_centering=True))]
n_components: List of PCA # of components to try. May include None
if skipping PCA step
estimators: List of (name, estimator) tuples where estimator
may be any scikit-learn-like regressor, e.g.
[('estimator', LinearRegression())]
log: Log transform step, e.g.:
('log', steps.ModifySample(log_scaler))
summary: String summary of premable steps to prepend to
parameter summary
Returns:
ensemble: List of Pipeline instances
'''
ensemble = []
scalers = kw['scalers']
n_components = kw['n_components']
pca = kw['pca']
estimators = kw['estimators']
preamble = kw['preamble']
summary_template = kw['summary']
minmax_bounds = kw['minmax_bounds']
log = kw['log']
for s_label_0, scale_0 in scalers:
if 'MinMax' in s_label_0:
# Make MinMaxScaler objects
labels = [s_label_0 + repr(mb) for mb in minmax_bounds]
scalers_with_params = [scale_0(*mb) for mb in minmax_bounds]
scalers_with_params = zip(labels, scalers_with_params)
elif scale_0:
# Just keep the StandardScaler as is
scalers_with_params = [(s_label_0, scale_0())]
else:
# No scaling
scalers_with_params = [(s_label_0, None)]
for s_label, scale in scalers_with_params:
for n_c in n_components:
for e_label, estimator in estimators:
scale_step = [scale] if scale else []
if 'MinMax' in s_label:
# Log transform only works with MinMaxScaler
# and positive min bound
scale_step += [log]
pca_step = [pca()] if n_c and scale else []
new = Pipeline(
preamble() + scale_step + pca_step + [estimator()],
**pipeline_kw)
if pca_step:
new.set_params(pca__n_components=n_c)
msg = '{} components'.format(n_c)
else:
msg = ' (None)'
args = (s_label, msg, e_label)
summary = ': Scaler: {} PCA: {} Estimator: {}'.format(
*args)
new.summary = summary_template + summary
print(new.summary)
ensemble.append(new)
return ensemble
