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 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_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 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)
#! /usr/bin/env python
#coding=utf-8
import numpy as ny
from cedict import CEDict
import os
dict=CEDict() # init Chinese-English Dict
class CDocument:
def __init__(self,label,words):
self.label=label
self.words=words
class Post:
def __init__(self,content,happiness,sadness,anger,fear,surprise):
self.content=content
self.happiness=happiness.lower()
self.sadness=sadness.lower()
self.anger=anger.lower()
self.fear=fear.lower()
self.surprise=surprise.lower()
self.words={}
self.en={}
self.cn={}
for w in content.split():
w=w.lower()
self.words[w]=1
if isASCII(w):
if isRealEnglishWord(w):
self.en[w]=1
from cedict import CEDict
from datesolve import *
from event import *
ceDict = CEDict()
MONTHS = {'jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec'}
class CDocument:
def __init__(self, words, polarity, id, text, eventName):
self.words = words
self.polarity = polarity
if polarity == True:
self.label = 1
else:
self.label = 0
self.id = id
self.text = text
self.eventName = eventName
def __repr__(self):
return "Data id:% s text:% s event:% s label:% s" %(self.id, self.words, self.eventName, self.label)
def readTweets(path):
tweets = []
monthDict = getMonthDict()
for line in open(path, 'r').readlines():
line = line.strip()
if len(line) > 0:
line = line.lower()