mirror of
https://github.com/fxsjy/jieba.git
synced 2025-07-10 00:01:33 +08:00
Merge pull request #240 from sing1ee/master
build stable sort for graph iteration
This commit is contained in:
commit
4e05cde07e
@ -7,6 +7,7 @@ import collections
|
||||
from operator import itemgetter
|
||||
import jieba.posseg as pseg
|
||||
|
||||
|
||||
class UndirectWeightedGraph:
|
||||
d = 0.85
|
||||
|
||||
@ -22,13 +23,15 @@ class UndirectWeightedGraph:
|
||||
ws = collections.defaultdict(float)
|
||||
outSum = collections.defaultdict(float)
|
||||
|
||||
giter = list(self.graph.items()) # these two lines for build stable iteration
|
||||
giter.sort()
|
||||
wsdef = 1.0 / (len(self.graph) or 1.0)
|
||||
for n, out in self.graph.items():
|
||||
for n, out in giter:
|
||||
ws[n] = wsdef
|
||||
outSum[n] = sum((e[2] for e in out), 0.0)
|
||||
|
||||
for x in xrange(10): # 10 iters
|
||||
for n, inedges in self.graph.items():
|
||||
for x in range(10): # 10 iters
|
||||
for n, inedges in giter:
|
||||
s = 0
|
||||
for e in inedges:
|
||||
s += e[2] / outSum[e[1]] * ws[e[1]]
|
||||
@ -36,7 +39,7 @@ class UndirectWeightedGraph:
|
||||
|
||||
(min_rank, max_rank) = (sys.float_info[0], sys.float_info[3])
|
||||
|
||||
for w in itervalues(ws):
|
||||
for _, w in ws.items():
|
||||
if w < min_rank:
|
||||
min_rank = w
|
||||
elif w > max_rank:
|
||||
@ -64,9 +67,9 @@ def textrank(sentence, topK=10, withWeight=False, allowPOS=['ns', 'n', 'vn', 'v'
|
||||
cm = collections.defaultdict(int)
|
||||
span = 5
|
||||
words = list(pseg.cut(sentence))
|
||||
for i in xrange(len(words)):
|
||||
for i in range(len(words)):
|
||||
if words[i].flag in pos_filt:
|
||||
for j in xrange(i + 1, i + span):
|
||||
for j in range(i + 1, i + span):
|
||||
if j >= len(words):
|
||||
break
|
||||
if words[j].flag not in pos_filt:
|
||||
@ -75,7 +78,6 @@ def textrank(sentence, topK=10, withWeight=False, allowPOS=['ns', 'n', 'vn', 'v'
|
||||
|
||||
for terms, w in cm.items():
|
||||
g.addEdge(terms[0], terms[1], w)
|
||||
|
||||
nodes_rank = g.rank()
|
||||
if withWeight:
|
||||
tags = sorted(nodes_rank.items(), key=itemgetter(1), reverse=True)
|
||||
|
Loading…
x
Reference in New Issue
Block a user