ARTICLE_NAME = ["Computer","Entertainment","Sports","Science","Economy","World",'Politics','Society']
ARTICLE = {"Computer":"","Entertainment":"","Sports":"","Science":"","Economy":"","World":"","Politics":"","Society":""}
ret=[]
data_train = [[] for row in range(8)]
train_num = 0
train_sum = 0
for n in ARTICLE_NAME:
data_range = countline('/Users/Soma/Onedrive/News_Dataset/article'+n+'.txt')
train_sum += data_range
for col in range(data_range):
data_train[train_num].append(None)
train_num += 1
label_train = [None for col in range(train_sum)]
article_data = [None for col in range(train_sum)]
num =0
num3 =0
dictionary = corpora.Dictionary.load_from_text('test_dic4.txt')
M.pp(M.isMecab("香川ループ弾「衝撃」と賞賛"))
test=[[]for col in range(6)]
test[0].append("a")
test[0].append("b")
test[0].append("c")
test[1].append("d")
test[1].append("e")
print (test)
"Sports": "",
"Science": "",
"Economy": "",
"World": "",
"Politics": "",
"Society": "",
}
dictionary = corpora.Dictionary.load_from_text("noun_dic.txt")
for n in ARTICLE_NAME:
print "\n" + n + " LDA modl cleate..\n"
f = codecs.open("/Users/Soma/Onedrive/News_Dataset/article" + n + ".txt", "r")
ARTICLE[n] = f.readlines()
f.close()
data_train = [dictionary.doc2bow(M.isMecab(j)) for j in ARTICLE[n]]
tfidf_corpus = gensim.corpora.MmCorpus("news_noun_" + n + ".mm")
lda = models.LdaModel(corpus=tfidf_corpus, id2word=dictionary, num_topics=30)
lda.save("model_" + n + ".lda")
if __name__ == "__main__":
print "cleate_dic.."
# CD.cleate_dic()
cleate_lda_model()
lda = models.LdaModel.load("model_Sports.lda")
lda2 = models.LdaModel.load("model_Computer.lda")
for n in range(30):
M.pp(lda.print_topics(n + 1))
for n in range(30):
M.pp(lda2.print_topics(n + 1))
