def getCityTopWords(trainCity0Rss, trainCity1Rss):
"""
获取城市中评论中最多的词汇
:param trainCity1Rss:
:param trainCity0Rss:
"""
initialDocList, fullText, cityTypes = loadRSSText(trainCity0Rss, trainCity1Rss)
vocaList = bayes.createVocabularyList(initialDocList)
trainVocabularyMattrix = []
# 将训练的文档集合针对vocaList进行标记
for words in initialDocList:
signedFeatureList = bayes.checkSignedFeatureList(vocaList, words)
trainVocabularyMattrix.append(signedFeatureList)
p_WiBasedOnClass0, p_WiBasedOnClass1, pAbusive = bayes.trainNavieBayesian(trainVocabularyMattrix, cityTypes)
topCity0Words = []
topCity1Words = []
for i in range(len(p_WiBasedOnClass0)):
if p_WiBasedOnClass0[i] > -6.0:
topCity0Words.append(vocaList[i])
if p_WiBasedOnClass1[i] > -6.0:
topCity1Words.append(vocaList[i])
print "*******City0最常用20的词汇*********"
for word in topCity0Words[:20]:
print word
print "*******City1最常用的词汇*********"
for word in topCity1Words[:20]:
print word
def trainNavieBayesianTest():
wordsList, classTypes = bayes.loadDataSet()
vocaList = bayes.createVocabularyList(wordsList)
# 将feature对应的标记为0,1
trainVocabularyMattrix = []
for words in wordsList:
trainVocabularyMattrix.append(bayes.checkSignedFeatureList(vocaList, words))
# print np.array(trainVocabularyMattrix)
p_WiBasedOnClass0, p_WiBasedOnClass1, pAbusive = bayes.trainNavieBayesian(trainVocabularyMattrix, classTypes)
print p_WiBasedOnClass0, '\n'
print p_WiBasedOnClass1
print pAbusive
