fasttext模型　训练THUCNews

# _*_coding:utf-8 _*_
import fasttext
import jieba
from sklearn import metrics
import random
def read_file(filename):
    i=0;
    sentences =[]
    out = open(‘data/cnews/fast_test.txt‘,‘a+‘)
    with open(filename) as ft:
        for line in ft:
            label, content = line.strip().split(‘\t‘)
            segs = jieba.cut(content)
            segs = filter(lambda x:len(x)>1,segs)
            sentences.append("__label__"+str(label)+"\t"+" ".join(segs))
        random.shuffle(sentences)
        for sentence in sentences:
            out.write(sentence+"\n")
    out.close()
read_file(‘data/cnews/cnews.train.txt‘)
classifier = fasttext.supervised(‘data/cnews/fast_train.txt‘,‘new_fasttext.model‘)
classifier = fasttext.load_model(‘new_fasttext.model.bin‘)
categories = [‘体育‘,  ‘财经‘,‘房产‘,‘家居‘,‘教育‘, ‘科技‘, ‘时尚‘, ‘时政‘, ‘游戏‘, ‘娱乐‘]
read_file(‘data/cnews/cnews.test.txt‘)
result = classifier.test(‘data/cnews/fast_test.txt‘)
print("准确率为：%f"%result.precision)
print("召回率为: %f"%result.recall)
with open(‘data/cnews/cnews.test.txt‘) as fw:
    contents,labels = [],[]
    for line in fw:
        label ,content = line.strip().split(‘\t‘)
        segs = jieba.cut(content)
        segs = filter(lambda x:len(x)>1,segs)
        contents.append(" ".join(segs))
        labels.append(‘__label__‘+label)
    label_predict = [e[0] for e in classifier.predict(contents)]
    print("Precision,Recall and F1-Score....")
    print(metrics.classification_report(labels,label_predict,target_names=categories))