def testDetect(self):
texts = [
(u"The quick brown",'en'),
(u"Le renard brun rapide saute par-dessus le chien paresseux",'fr'),
(u"@Ja_Nina HERRLICH :) ich hab nix auf planeten gefunden..deine version klingt absolut logisch :D",'de'),
(u"En Google somos plenamente conscientes de la confianza que los usuarios depositan ",'es'),
(u"Noi di Google siamo perfettamente consapevoli della fiducia che riponi in noi e della ",'it'),
(u'русский язык','ru'),
(u'','other')
]
ld = LangDetect(languages = supportedLangs)
r1 = []
r2 = []
for text,lang in texts:
res = ld.detect(text)
r1.append(res[0])
r2.append(lang)
assert r1==r2
def loadCls():
ThreadedTCPServer.langCls = LangDetect(supportedLangs)
ThreadedTCPServer.moodCls = MoodDetect(MoodDetectTrainer())
import sys
sys.path.append('../../')
import socket
import os
from tracker.lib.moodClassifierClient import MoodClassifierTCPClient
from tracker.lib.lang_detection import LangDetect
from tracker.lib.supportedLangs import supportedLangs
import cPickle
import linecache
#MCC = MoodClassifierTCPClient('srv1.cyhex.com',6666)
MCC = MoodClassifierTCPClient('127.0.0.1', 6666)
cls_data = {'nc': 1, 'pc': 1, 'n': 1, 'p': 1, 'n#': 1, 'p#': 1}
langClassifier = LangDetect(supportedLangs)
tweetsPFile = "/home/gx/Sites/SMM/trunk/tracker/data/tweets_positive_test.dat"
tweetsNFile = "/home/gx/Sites/SMM/trunk/tracker/data/tweets_negative_test.dat"
def stripSmiles(text):
emos = [
':)', ':-)', ';-)', ': )', ':d', '=)', ':p', ';)', '<3', ':(', ':-(',
': ('
]
for item in emos:
text = text.replace(item, "")
return text
