# _*_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 = [‘體育‘,  ‘財經‘,‘房產‘,‘家居‘,‘教育‘, ‘科技‘, ‘時尚‘, ‘時政‘, ‘遊戲‘, ‘娛樂‘]
read_file(‘data/cnews/cnews.test.txt‘)
result = classifier.test(‘data/cnews/fast_test.txt
 
‘)
print("準確率為：%f"%result.precision)
print("召回率為: %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))

關於fasttext的使用一些疑問：fasttext.supervised的參數label_prefix　一直提示我這個參數使用有問題...　然而，搜素了半天，我也沒搞明白這個參數哪裏有問題

還有一點需要註意的地方：fasttext的識別標簽統一需要在標簽前面加上"__label__"

後續會更新fastext的原理

fasttext模型　訓練THUCNews