def test_centroid(self):
# Assert center of list of vectors.
v = vector.centroid([{
"cat": 1
}, {
"cat": 0.5,
"dog": 1
}],
keys=["cat", "dog"])
self.assertEqual(v, {"cat": 0.75, "dog": 0.5})
print "pattern.vector.centroid()"
def _generate_clusters(self, k=10, p=0.8, maxlevel=10):
"""Use KMEANS method by default, and choose the initial k values by KMPP method.
k is the number of clusters.
p is to control the error of KMEANS, when p=1.0 is faster with small error.
"""
if self.method == "kmeans":
from pattern.vector import KMEANS, KMPP
self.clusters = self.corpus.cluster(method=KMEANS,
k=k,
seed=KMPP,
p=p,
iterations=10)
doc_list = []
# For each cluster, calculate the centroid, and calculate the doc (vector) which is nearest to the centroid.
for cluster in self.clusters:
c = centroid(cluster)
d_min = (cluster[0].vector, c)
for doc in cluster:
d = distance(doc.vector, c)
if distance(doc.vector, c) < d_min:
d_min = d
doc_min = doc
doc_list.append(doc_min)
self.centroids = [i.name for i in doc_list]
self.clusters = [[i.name for i in cluster]
for cluster in self.clusters]
elif self.method == 'covertree':
def mydistance(doc_name1, doc_name2):
v1 = self.corpus.document(doc_name1).vector
v2 = self.corpus.document(doc_name2).vector
return distance(v1, v2)
self.covertree = Covertree(mydistance, maxlevel)
for i, doc in enumerate(self.corpus):
tree_node = myTree(doc.name)
self.covertree.insert(tree_node, self.covertree.ct, 0)
self.covertree.merge_levels()
self.centroids, self.clusters = self.covertree.clustering_from_ct(
k)
def _generate_clusters(self, k=10, p=0.8, maxlevel=10):
"""Use KMEANS method by default, and choose the initial k values by KMPP method.
k is the number of clusters.
p is to control the error of KMEANS, when p=1.0 is faster with small error.
"""
if self.method == "kmeans":
from pattern.vector import KMEANS, KMPP
self.clusters = self.corpus.cluster(method=KMEANS, k=k, seed=KMPP, p=p, iterations=10)
doc_list = []
# For each cluster, calculate the centroid, and calculate the doc (vector) which is nearest to the centroid.
for cluster in self.clusters:
c = centroid(cluster)
d_min = (cluster[0].vector, c)
for doc in cluster:
d = distance(doc.vector, c)
if distance(doc.vector, c) < d_min:
d_min = d
doc_min = doc
doc_list.append(doc_min)
self.centroids = [i.name for i in doc_list]
self.clusters = [[i.name for i in cluster] for cluster in self.clusters]
elif self.method == 'covertree':
def mydistance(doc_name1, doc_name2):
v1 = self.corpus.document(doc_name1).vector
v2 = self.corpus.document(doc_name2).vector
return distance(v1, v2)
self.covertree = Covertree(mydistance, maxlevel)
for i, doc in enumerate(self.corpus):
tree_node = myTree(doc.name)
self.covertree.insert(tree_node, self.covertree.ct, 0)
self.covertree.merge_levels()
self.centroids, self.clusters = self.covertree.clustering_from_ct(k)
def test_centroid(self):
# Assert center of list of vectors.
v = vector.centroid([{"cat":1}, {"cat":0.5, "dog":1}], features=["cat", "dog"])
self.assertEqual(v, {"cat":0.75, "dog":0.5})
print("pattern.vector.centroid()")
def test_centroid(self):
# Assert centroid of recursive Cluster.
v = vector.Cluster(({"a": 1}, vector.Cluster(({"a": 2}, {"a": 4}))))
self.assertAlmostEqual(vector.centroid(v)["a"], 2.33, places=2)
print("pattern.vector.centroid()")
def test_centroid(self):
# Assert centroid of recursive Cluster.
v = vector.Cluster(({"a": 1}, vector.Cluster(({"a": 2}, {"a": 4}))))
self.assertAlmostEqual(vector.centroid(v)["a"], 2.33, places=2)
print "pattern.vector.centroid()"
def variance(cluster):
return avg([distance(centroid(cluster), v) for v in cluster])
