def train_trees(data, attributes):
clfs = []
evls = []
dt_y_hat = []
unused_attributes = []
for i, att in enumerate(attributes):
data.class_index = i
count_non_nans = np.count_nonzero(~np.isnan(data.values(i)))
if count_non_nans < 5:
unused_attributes.append(i)
print('Not using attribute {}, only {} real values\n\n'.format(
att, count_non_nans))
clfs.append(None)
evls.append(None)
dt_y_hat.append(None)
continue
this_clf = Classifier(classname='weka.classifiers.trees.J48',
options=['-U', '-B', '-M', '2'])
this_clf.build_classifier(data)
this_evl = Evaluation(data)
this_evl.crossvalidate_model(this_clf, data, 5, Random(1))
dt_y_hat.append(this_clf.distributions_for_instances(data))
clfs.append(this_clf)
evls.append(this_evl)
return clfs, evls, dt_y_hat, unused_attributes
