def getLabels(data, centroids):
m,_ = data.shape
labels=np.arange(m)
for idxdata, valdata in enumerate(data):
centroid=0
MIN_VALUE=sys.float_info.max
for idxcent, valcent in enumerate(centroids):
if similarity.euclidean(valcent,valdata)<MIN_VALUE:
MIN_VALUE=similarity.euclidean(valcent,valdata)
centroid=idxcent
np.put(labels, idxdata, centroid)
return labels
#-*- coding: utf-8 -*-
import similarity as sim
if __name__=="__main__":
#辞書
dictionary = {
"A":{"apple":2.5,"mikan":2.5,"banana":5.0,"melon":2.0},
"B":{"apple":2.5,"banana":1.5,"kiui":3.0,"melon":4.0}
}
#ユークリッド距離
value = sim.euclidean(dictionary,"A","B")
print str(value)
#ピアソン相関
value = sim.pearson(dictionary,"A","B")
print str(value)
#コサイン類似度
value = sim.cosine(dictionary,"A","B")
print str(value)