1.简介
fasttext是facebook开源的一个词向量与文本分类工具，在2016年开源，典型应用场景是“带监督的文本分类问题”。提供简单而高效的文本分类和表征学习的方法，性能比肩深度学习而且速度更快。
fastText结合了自然语言处理和机器学习中最成功的理念。这些包括了使用词袋以及n-gram袋表征语句，还有使用子字(subword)信息，并通过隐藏表征在类别间共享信息。我们另外采用了一个softmax层级(利用了类别不均衡分布的优势)来加速运算过程。
2.训练实例
# -*- coding: utf-8 -*-
from sklearn.externals import joblib
import pandas as pd
import numpy as np
import warnings
import jieba
import re
import time
import fasttext
import random
from stop_words import stop_word
from sklearn.model_selection import train_test_split
from matplotlib import pyplot as plt
from sklearn.metrics import confusion_matrix
warnings.filterwarnings('ignore')
data_content = pd.read_excel('语料.xlsx', index_col = None, encoding = 'utf-8')
contents = data_content['语料'].values
targets = data_content['敏感等级(1高度、2敏感、3不敏感）'].values
jieba.load_userdict("key_word.csv")
source = []
#数据处理
for i in range (0,len(contents)):
content= contents[i]
content_string = re.sub("\|uid|Name|content|dtype|object|[\]\[\:\...\：\.\！\,\，\·\…\～\。\;\；\⃢\-\─\*\—\”\《\》]|[\/\？\?\、\~\】\【\（\）\)\__\____]", "", content)
content_cut = ''.join(content_string.split())
content_seglist = jieba.lcut(content_cut,cut_all=False)
content_seglist = [word.strip().replace('\ufeff', '') for word in content_seglist if word not in stop_word]#去除停用词
content_seglist = ' '.join(i for i in content_seglist)
content_text = "__label__"+str(targets[i])+" , "+ content_seglist
source.append(content_text)
x_train, x_test, y_train, y_test = train_test_split(source, targets, test_size = 0.1, random_state=33)
train_text = open('data/train_data.txt', 'w', encoding = 'utf-8')
for sentence in x_train:
#print (sentence)
train_text.write(sentence +"\n")
test_text = open('data/test_data.txt', 'w', encoding = 'utf-8')
for sentence in x_test:
test_text.write(sentence +"\n")
classifier = fasttext.supervised('data/train_data.txt', 'model/classifier.model', label_prefix='__label__')
#result = classifier.test('data/train_data.txt')
labels = classifier.predict_proba('data/test_data.txt', k=3)
print ('输出预测结果')
print (result)
print (labels)
print ('P@1:', result.precision)
print ('R@1:', result.recall)
print ('F@1:', result.f1score)
print ('Number of examples:', result.nexamples)
3.多进程预测
# -*- coding: utf-8 -*-
from sklearn.externals import joblib
import pandas as pd
import numpy as np
import warnings
import jieba
import re
import time
import fasttext
import random
import pymysql as mydb
import threading,time
import queue
from multiprocessing import Process, Pool, freeze_support
from multiprocessing import cpu_count
from stop_words import stop_word
from sklearn.model_selection import train_test_split
from matplotlib import pyplot as plt
from sklearn.metrics import confusion_matrix
warnings.filterwarnings('ignore')
#查询数据
db = mydb.connect(host='XXXXXX', port=XXXX, user='XXXXX', passwd='XXXXX', db='XXXX', charset='utf8') #使用此数据库，需在sql查询加上b.yes_no
sql_cmd = "select a.tieba_name, a.post_url, case a.title when '' then 'empty' else a.title end title, case a.content when '' then 'empty' else a.content end content, a.floor, (case when b.reply IS NULL then 'null' when b.reply = '' then 'empty' else b.reply end) reply, from_unixtime(a.time, '%Y-%m-%d') time from s_content_tieba a left join s_huifu_tieba b on a.content_id = b.post_id where from_unixtime(a.time, '%Y-%m-%d') between '2018-11-26' and '2018-11-27'"
data_set = pd.read_sql(sql_cmd, db)
db.close()
#data_set = data_set1.iloc[0:10000,]
#data_set['content_label'] = ''
#data_set['content_prob'] = ''
#data_set['reply_label'] = ''
#data_set['reply_prob'] = ''
lens = (len(data_set))
idx = [i for i in range (lens)]
contents = data_set['content'].values
replies = data_set['reply'].values
jieba.load_userdict("key_word.csv")
pre_model = fasttext.load_model('model/classifier.model.bin', label_prefix='__label__')
#content_labs = []
#reply_labs = []
print ('开始预测')
def consumer(i):
print(i)
content_one= contents[i]
#print ('content_one')
content_string = re.sub("\|uid|Name|content|dtype|object|[\]\[\:\...\：\.\！\,\，\·\…\～\。\;\；\⃢\-\─\*\—\”\《\》]|[\/\？\?\、\~\】\【\（\）\)\__\____]", "", content_one)
content_cut = ''.join(content_string.split())
content_seglist1 = jieba.lcut(content_cut,cut_all=False)
content_seglist2 = [word.strip().replace('\ufeff', '') for word in content_seglist1 if word not in stop_word]#去除停用词
if len(content_seglist2)> 0:
content_seglist3 = [' '.join(j for j in content_seglist2)]
#print ('kaishiyuce')
result_pre = pre_model.predict(content_seglist3)
content_labels = result_pre[0][0]
#data_set['content_prob'].iloc[i]=result_pre[0][0][1]
#data_set['content_label'].iloc[i]=result_pre[0][0][0]
#data_set['content_prob'].iloc[i]=result_pre[0][0][1]
else:
content_labels = 'empty'
reply_one= replies[i]
reply_string = re.sub("\|uid|Name|content|dtype|object|[\]\[\:\...\：\.\！\,\，\·\…\～\。\;\；\⃢\-\─\*\—\”\《\》]|[\/\？\?\、\~\】\【\（\）\)\__\____]|回复.*?：|回复.*?:|回复\s(\S+)", "", reply_one)
reply_cut = ''.join(reply_string.split())
reply_seglist1 = jieba.lcut(reply_cut,cut_all=False)
reply_seglist2 = [word.strip().replace('\ufeff', '') for word in reply_seglist1 if word not in stop_word]#去除停用词
if len(reply_seglist2)> 0:
reply_seglist3 = [' '.join(j for j in reply_seglist2)]
result_pre2 = pre_model.predict(reply_seglist3)
reply_labels=result_pre2[0][0]
else:
reply_labels = 'empty'
#data_set['reply_prob'].iloc[i]=result_pre2[0][0][1]
#data_set['reply_label'].iloc[i]=result_pre2[0][0][0]
#data_set['reply_prob'].iloc[i]=result_pre2[0][0][1]
return content_labels, reply_labels
b_time1 = time.time()
pool = Pool(cpu_count())
th = []
th.append(pool.map_async(consumer, idx))
pool.close()
pool.join()
#print (th.get())
ths = []
for a in th:
ths.append(a.get())
thx = [e[0] for e in ths[0]]
thy = [e[1] for e in ths[0]]
data_set['content_label'] = thx
data_set['reply_label'] = thy
#data.to_csv('data.csv')
print (time.time() - b_time1)
#print (time.time() - b_time1)
data_set['序号'] = [a for a in range (len(data_set))]
data_mg1 = pd.pivot_table(data_set, index=['tieba_name', 'post_url', 'title', 'content', 'content_label', 'floor', 'reply', 'reply_label', 'time'])
#data_mg1 = pd.pivot_table(data_set, index=['tieba_name', 'post_url', 'title', 'content', 'content_label', 'content_prob', 'floor', 'reply', 'reply_label', 'reply_prob', 'time'])
data_mg1['序号'] = [a for a in range (len(data_mg1))]
now_date = time.strftime('%Y%m%d',time.localtime(time.time()))
data_mg1.to_csv('data/匹配结果'+now_date+'.csv')
4.总结
fasttext非常简单易用，如果你想快速感受一下类深度学习的效果，可以尝试一把。它可以完成无监督的词向量的学习，学习出来词向量，保持住词和词之间，相关词之间是一个距离比较近的情况；
也可以用于有监督学习的文本分类任务，（新闻文本分类，垃圾邮件分类、情感分析中文本情感分析，电商中用户评论的褒贬分析）。详细原理及词向量应用可参考https://blog.csdn.net/john_bh/article/details/79268850