课后作业——新闻文本分类

引言：

　　本次任务是做一个新闻文本分类的算法，算法选择朴素贝叶斯实现。可以实现对新闻内容的一个具体分类。

　　环境：jupter nookbook,py3.8

1.导入数据

df_new= pd.read_excel('./data/123.xlsx').astype(str) 
df_news=pd.DataFrame(df_new)
df_news.head()

 

2.用jieba分词进行分词

content_S = []
for line in content:
    current_segment = jieba.lcut(line)
    if len(current_segment) > 1 and current_segment != '\r\t':
        content_S.append(current_segment)
content_S[1000]

 

 3.加载停用词，并遍历去除停用词

def drop_stopwords(contents,stopwords):
    contents_clean = []
    all_words = []
    for line in contents:
        line_clean = []
        for word in line:
            if word in stopwords or word==' ':
                continue
            line_clean.append(word)
            all_words.append(word)
        contents_clean.append(line_clean)
    return contents_clean,all_words
contents = df_content.content_S.values.tolist()
stopwords = stopwords.stopword.values.tolist()
contents_clean,all_words = drop_stopwords(contents,stopwords)

df_content = pd.DataFrame({'contents_clean':contents_clean})
df_content.head()

 

 4.提取关键词

import jieba.analyse
index = 2500
print(df_news['content'][index])
content_S_str = ''.join(content_S[index])
print(' '.join(jieba.analyse.extract_tags(content_S_str,topK=10,withWeight=False)))

 

 5.lab向量化

df_train = pd.DataFrame({'contents_clean':contents_clean,'label':df_news['category']})
df_train.tail()
df_train.label.unique()

6.使用sklearn模型训练数据集

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(df_train['contents_clean'].values,df_train['label'].values,random_state = 1)
print(x_test)
from sklearn.feature_extraction.text import CountVectorizer
vec = CountVectorizer(analyzer='word',max_features=4000,lowercase=False,ngram_range=(1,3))
vec.fit(words)
cv=vec.fit_transform(words)
from sklearn.naive_bayes import MultinomialNB
classifier = MultinomialNB()
classifier.fit(vec.transform(words),y_train)
test_words = []
for line_index in range(len(x_test)):
    try:
        #x_train[line_index][word_index] = str(x_train[line_index][word_index])
        test_words.append(' '.join(x_test[line_index]))
    except:
         print (line_index,word_index)

7.算法准确率

classifier.score(vec.transform(test_words),y_test)