forked from chrismattmann/tika-similarity
-
Notifications
You must be signed in to change notification settings - Fork 0
/
generateLevelCluster.py
executable file
·66 lines (55 loc) · 2.05 KB
/
generateLevelCluster.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
#!/usr/bin/env python2.7
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
#
import json
import sys
_maxNumNode = 10
def main(argv = None) :
with open('clusters.json') as data_file:
data = json.load(data_file)
numOfCluster = len(data["children"])
for i in range(0, numOfCluster):
numOfPic = len(data["children"][i]["children"])
if numOfPic > _maxNumNode:
level = levelNum(data["children"][i]["children"])
for j in range(1, level) :
clusterChildren = generateLevel(data["children"][i]["children"])
data["children"][i]["children"] = clusterChildren
with open("levelCluster.json", "w") as f:
f.write(json.dumps(data, sort_keys=True, indent=4, separators=(',', ': ')))
def levelNum(data, level = 1):
cluster = {}
numOfChildren = len(data)
while numOfChildren / _maxNumNode>0:
numOfChildren = numOfChildren / _maxNumNode
level = level+1
return level
def generateLevel(data):
clusters = []
numOfChildren = len(data)
numOfGroup = numOfChildren / _maxNumNode
for i in range(0, numOfGroup+1) :
clusterData = []
clusterGroupData ={}
for j in range(_maxNumNode*i, min(_maxNumNode*(i+1), numOfChildren)):
clusterData.append(data[j])
clusterGroupData = {"name" : "group"+str(i), "children": clusterData}
clusters.append(clusterGroupData)
return clusters
if __name__ == "__main__" :
sys.exit(main())