def test_classes_to_clusters(self):
"""
Tests the classes_to_clusters method.
"""
loader = converters.Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(self.datafile("anneal.arff"))
self.assertIsNotNone(data)
#data.class_is_last()
train = dataset.Instances.copy_instances(data, 0, data.num_instances)
train.delete_last_attribute()
cls = clusterers.Clusterer(classname="weka.clusterers.SimpleKMeans")
self.assertIsNotNone(cls, msg="Failed to instantiate clusterer!")
cls.build_clusterer(train)
test = dataset.Instances.copy_instances(data, 0, data.num_instances)
test.class_is_last()
evl = clusterers.ClusterEvaluation()
self.assertIsNotNone(cls, msg="Failed to instantiate evaluation!")
evl.set_model(cls)
evl.test_model(test)
self.assertEqual([2, 4],
evl.classes_to_clusters.tolist(),
msg="classes to clusters differs")
def test_clusterevaluation(self):
"""
Tests the ClusterEvaluation class.
"""
loader = converters.Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(self.datafile("anneal.arff"))
self.assertIsNotNone(data)
data.delete_last_attribute()
# simple test set
test = dataset.Instances.copy_instances(data, 0, 10)
cls = clusterers.Clusterer(classname="weka.clusterers.SimpleKMeans")
self.assertIsNotNone(cls, msg="Failed to instantiate clusterer!")
cls.build_clusterer(data)
evl = clusterers.ClusterEvaluation()
self.assertIsNotNone(cls, msg="Failed to instantiate evaluation!")
evl.set_model(cls)
evl.test_model(test)
self.assertGreater(len(evl.cluster_results), 0, msg="No evaluation string!")
self.assertEqual(0.0, evl.log_likelihood, msg="log_likelihood differs")
self.assertEqual(2, evl.num_clusters, msg="num_clusters differs")
self.assertEquals(
[1., 0., 0., 1., 1., 1., 0., 0., 0., 0.], evl.cluster_assignments.tolist(),
msg="cluster_assignments differs")
# cross-validation
cls = clusterers.Clusterer(classname="weka.clusterers.EM", options=["-I", "3", "-X", "2", "-max", "5"])
self.assertIsNotNone(cls, msg="Failed to instantiate clusterer!")
llh = clusterers.ClusterEvaluation.crossvalidate_model(cls, data, 10, classes.Random(1))
self.assertAlmostEqual(-34.397, llh, places=3, msg="Failed to cross-validate clusterer!")
def test_plot_cluster_assignments(self):
"""
Tests the plot_cluster_assignments method.
"""
loader = converters.Loader("weka.core.converters.ArffLoader")
data = loader.load_file(self.datafile("iris.arff"))
data.delete_last_attribute()
# build a clusterer and output model
clusterer = clusterers.Clusterer(
classname="weka.clusterers.SimpleKMeans", options=["-N", "3"])
clusterer.build_clusterer(data)
evaluation = clusterers.ClusterEvaluation()
evaluation.set_model(clusterer)
evaluation.test_model(data)
plot.plot_cluster_assignments(evaluation,
data,
inst_no=True,
wait=False)