def blp_en(pTrains,pTests):
trains=[CDocument(label,p.en) for label,p in pTrains]
tests=[CDocument(label,p.en) for label,p in pTests]
for d in trains+tests:
d.words['SMOOTH']=1
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def classify_translate_cerelation(pTrains,pTests):
dict=CEDict()
pmi=PMI()
trains=[]
tests=[]
for label,p in pTrains:
words=getTranlateFeaturesCERelation(p,dict,pmi)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getTranlateFeaturesCERelation(p,dict,pmi)
tests.append(CDocument(label,words))
return me_classify(trains,tests)
def classify_sentiment(pTrains,pTests):
cn_lexicon=CnSentimentLexicon()
en_lexicon=EnSentimentLexicon()
trains=[]
tests=[]
for label,p in pTrains:
words=getSentimentFeatures(p,cn_lexicon,en_lexicon)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getSentimentFeatures(p,cn_lexicon,en_lexicon)
tests.append(CDocument(label,words))
return me_classify(trains,tests)
def blp_translate_simple(pTrains,pTests):
dict=CEDict()
trains=[]
tests=[]
for label,p in pTrains:
words=getTranlateFeatures(p,dict)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getTranlateFeatures(p,dict)
tests.append(CDocument(label,words))
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def classify_translate_simple(pTrains,pTests):
dict=CEDict()
syn=Synonym()
# lm=LanguageModel()
trains=[]
tests=[]
for label,p in pTrains:
words=getTranlateFeatures(p,dict)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getTranlateFeatures(p,dict)
tests.append(CDocument(label,words))
return me_classify(trains,tests)
def blp_sentiment(pTrains,pTests):
cn_lexicon=CnSentimentLexicon()
en_lexicon=EnSentimentLexicon()
trains=[]
tests=[]
for label,p in pTrains:
words=getSentimentFeatures(p,cn_lexicon,en_lexicon)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getSentimentFeatures(p,cn_lexicon,en_lexicon)
tests.append(CDocument(label,words))
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def blp_translate_pmi(pTrains,pTests):
dict=CEDict()
syn=Synonym()
pmi=PMI()
trains=[]
tests=[]
for label,p in pTrains:
words= getTranlateFeaturesPMI(p,dict,pmi)
trains.append(CDocument(label,words))
for label,p in pTests:
words= getTranlateFeaturesPMI(p,dict,pmi)
tests.append(CDocument(label,words))
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def blp_translate_lm(pTrains,pTests):
dict=CEDict()
syn=Synonym()
lm=LanguageModel()
trains=[]
tests=[]
for label,p in pTrains:
words=getTranslateFeaturesByLM(p,dict,lm)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getTranslateFeaturesByLM(p,dict,lm)
tests.append(CDocument(label,words))
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def mMakeBooks(self, mynBooks):
# A collection has lots of books
for icoll in xrange(mynBooks):
ndocsize = util.fnnCalcDocSize(self.nValue)
cDoc = CDocument(ndocsize, self.sClientID, self.ID)
self.lDocIDs.append(cDoc.ID)
self.lDocIDsRemaining.append(cDoc.ID)
self.nDocsRemaining += 1
return self.ID
def blp_sense_sentiment(pTrains,pTests):
dict=CEDict()
pmi=PMI()
cn_lexicon=CnSentimentLexicon()
en_lexicon=EnSentimentLexicon()
trains=[]
tests=[]
for label,p in pTrains:
words=getFeaturesSenseAndSentiment(p,dict,pmi,cn_lexicon,en_lexicon)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getFeaturesSenseAndSentiment(p,dict,pmi,cn_lexicon,en_lexicon)
tests.append(CDocument(label,words))
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def blp_translate_cerelation(pTrains,pTests):
dict=CEDict()
pmi=PMI()
trains=[]
tests=[]
for label,p in pTrains:
words=getTranlateFeaturesCERelation(p,dict,pmi)
trains.append(CDocument(label,words))
for label,p in pTests:
words=getTranlateFeaturesCERelation(p,dict,pmi)
tests.append(CDocument(label,words))
# for d in trains+tests:
# d.words['SMOOTH']=1
blp=BLP(trains+tests)
blp.LP_Classify(trains,tests)
def classify_en(pTrains,pTests):
trains=[CDocument(label,p.en) for label,p in pTrains]
tests=[CDocument(label,p.en) for label,p in pTests]
return me_classify(trains,tests)
def classify_all(pTrains,pTests):
trains=[CDocument(label,p.words) for label,p in pTrains]
tests=[CDocument(label,p.words) for label,p in pTests]
return me_classify(trains,tests)