def cluster(self,
vectors,
assign_clusters=False,
ClusterNum=None,
DisType='cos',
Stype='avg',
trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if ('cos' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = cosine_distance(
vectors[i], vectors[j])
elif ('euc' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = euclidean_distance(
vectors[i], vectors[j])
self._dendrogram = Dendrogram(
[numpy.array(vector, numpy.float64) for vector in vectors])
result = VectorSpaceClusterer.cluster(self, vectors, assign_clusters,
ClusterNum, Stype, trace)
if (2 == len(vectors[0])): # 二维样本则显示可视化结果
self.draw_2D(vectors, result)
return result
def cluster(self, vectors, assign_clusters=False,ClusterNum=None, DisType='euc',Stype='mean',trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if(0==l):
return []
if('cos'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = cosine_distance(vectors[i], vectors[j])
elif('euc'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = euclidean_distance(vectors[i], vectors[j])
result = VectorSpaceClusterer.cluster(self, vectors,assign_clusters,ClusterNum, Stype, trace)
#/////////////////////// 测试，输出距离 /////////////////
# m = 0
# for k,v in self._distMap:
# m +=1
# print v,"\t",
# if (m%7==0):
# print
#/////////////////////////////////////////////////////
if(2==len(vectors[0])): # 二维样本则显示可视化结果
draw_2D_cluster(vectors, result)
return result
def cluster(self,
vectors,
assign_clusters=False,
ClusterNum=None,
DisType='euc',
Stype='mean',
trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if (0 == l):
return []
if ('cos' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = cosine_distance(
vectors[i], vectors[j])
elif ('euc' == DisType):
for i in range(l):
for j in range(i + 1, l):
self._distMap[(i, j)] = euclidean_distance(
vectors[i], vectors[j])
result = VectorSpaceClusterer.cluster(self, vectors, assign_clusters,
ClusterNum, Stype, trace)
#/////////////////////// 测试，输出距离 /////////////////
# m = 0
# for k,v in self._distMap:
# m +=1
# print v,"\t",
# if (m%7==0):
# print
#/////////////////////////////////////////////////////
if (2 == len(vectors[0])): # 二维样本则显示可视化结果
draw_2D_cluster(vectors, result)
return result
def cluster(self, vectors, assign_clusters=False, DisType='cos',Stype='avg',trace=False):
# stores the merge order
#-------------------------------------------------
self._distMap.clear() # 每次聚类不同样本之前必须更新
#-------------------------------------------------
l = len(vectors)
if('cos'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = cosine_distance(vectors[i], vectors[j])
elif('euc'==DisType):
for i in range(l):
for j in range(i+1,l):
self._distMap[(i,j)] = euclidean_distance(vectors[i], vectors[j])
self._dendrogram = Dendrogram(
[numpy.array(vector, numpy.float64) for vector in vectors])
result = VectorSpaceClusterer.cluster(self, vectors,assign_clusters, Stype, trace)
return result