def cluster(train_features, targets, test_features, predictions, k_means=3):
"""Penalize test points that are too clustered.
Parameters
----------
train_features : array
Feature matrix for the training data.
targets : list
Training targets.
test_features : array
Feature matrix for the test data.
predictions : list
Predicted means.
k_means : int
Number of clusters.
"""
fit = []
cf = cluster_features(train_matrix=train_features,
train_target=targets,
k_means=k_means,
test_matrix=test_features,
test_target=predictions)
train_count = Counter(cf['train_order'])
for i, c in enumerate(cf['test_order']):
fit.append(predictions[i] / train_count[c])
return fit
def test_cluster(self):
"""Test clustering function."""
train_features, train_targets, test_features, \
test_targets = self.get_data()
cf = cluster_features(train_matrix=train_features,
train_target=train_targets,
test_matrix=test_features,
test_target=test_targets,
k=2)
self.assertTrue(len(cf['train_features']) == 2)
self.assertTrue(len(cf['train_target']) == 2)
self.assertTrue(len(cf['test_features']) == 2)
self.assertTrue(len(cf['test_target']) == 2)
def _cluster_fit(self):
"""Penalize test points that are too clustered."""
fit = []
cf = cluster_features(train_matrix=self.train_features,
train_target=self.targets,
k_means=self.k_means,
test_matrix=self.test_features,
test_target=self.predictions)
train_count = Counter(cf['train_order'])
for i, c in enumerate(cf['test_order']):
fit.append(self.predictions[i] / train_count[c])
return fit