Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
nlp
===

自然语言处理,目前想识别的是帮短信分级,如垃圾短信,重要短信,一般短信,群发短信等等
自然语言处理,目前想识别的是帮短信分级,如垃圾短信,重要短信,一般短信,群发短信等等
7 changes: 7 additions & 0 deletions split/.idea/inspectionProfiles/profiles_settings.xml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 4 additions & 0 deletions split/.idea/misc.xml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 8 additions & 0 deletions split/.idea/modules.xml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

11 changes: 11 additions & 0 deletions split/.idea/split.iml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

196 changes: 196 additions & 0 deletions split/.idea/workspace.xml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 4 additions & 0 deletions split/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
nlp
===

自然语言处理,目前想识别的是帮短信分级,如垃圾短信,重要短信,一般短信,群发短信等等
Empty file added split/__init__.py
Empty file.
40 changes: 40 additions & 0 deletions split/bayes.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
#coding=utf-8
import re
import xml.dom.minidom
from mmseg import Algorithm, dict_load_defaults

class Bayes:
def __init__(self):
self.message_xml = open('message.xml', "r")
self.message = self.message_xml.read()
self.good = {}
self.bad = {}
import collections
self.total = collections.defaultdict(lambda: 1)
return

def get_messages(self):
pattern_message = re.compile('(<Body><\!\[CDATA\[)(.+?)(\]\]></Body>)')
self.message.decode('utf-8')
res = pattern_message.findall(self.message)
message_flag = open('message_flag', 'w')
for mes in res:
tmp = unicode(mes[1], 'utf-8')
print(tmp)
flag = raw_input()
message_flag.write(tmp.encode('utf-8') + ' ' + flag + '\n')
for word in Algorithm(tmp):
self.total[word] += 1
message_xml.close()
for i in self.total.keys():
print i,self.total[i]

def cuttest(self, text):
wlist = [word for word in Algorithm(text)]
tmp = "/".join(wlist)
print (tmp)
print ("================================")

if __name__ == '__main__':
bayes = Bayes()
bayes.get_messages()
Loading