def test_normalize_data(self):
# not normalized
self.widget.controls.normalize.setChecked(False)
data = Table("heart_disease")
self.send_signal(self.widget.Inputs.data, data)
kwargs = {
"eps": self.widget.eps,
"min_samples": self.widget.min_samples,
"metric": "euclidean"
}
clusters = DBSCAN(**kwargs)(data)
output = self.get_output(self.widget.Outputs.annotated_data)
output_clusters = output.metas[:, 0].copy()
output_clusters[np.isnan(output_clusters)] = -1
np.testing.assert_array_equal(output_clusters, clusters)
# normalized
self.widget.controls.normalize.setChecked(True)
kwargs = {
"eps": self.widget.eps,
"min_samples": self.widget.min_samples,
"metric": "euclidean"
}
for pp in (Continuize(), Normalize(), SklImpute()):
data = pp(data)
clusters = DBSCAN(**kwargs)(data)
output = self.get_output(self.widget.Outputs.annotated_data)
output_clusters = output.metas[:, 0].copy()
output_clusters[np.isnan(output_clusters)] = -1
np.testing.assert_array_equal(output_clusters, clusters)
def cluster(self):
if not self.check_data_size():
return
self.model = DBSCAN(eps=self.eps,
min_samples=self.min_samples,
metric=self.METRICS[self.metric_idx][1])(self.data)
self.send_data()