跟我学算法-贝叶斯文本分类器

#读入数据,属性命名为[‘category‘,‘theme‘,‘URL‘,‘content‘]
df_new = pd.read_table(‘./data/val.txt‘, names=[‘category‘,‘theme‘,‘URL‘,‘content‘], encoding=‘utf-8‘)
df_new.dropna() #去除为空的数据
print(df_new.head())

#把df_new的content的值转换为列表形式
content = df_new.content.values.tolist()
#将每一行拆分成一个个词语
content_S = []
for line in content:
    current_segement = jieba.lcut(line)
    if len(current_segement) > 1 and current_segement != ‘\r\n‘:
        content_S.append(current_segement)

print(content_S[1000])

#形成一个字典类的容器
df_content = pd.DataFrame({‘content_S‘:content_S})
print(df_content.head())
stopwords=pd.read_csv("stopwords.txt",index_col=False,sep="\t",quoting=3,names=[‘stopword‘], encoding=‘utf-8‘)
# 与停用表进行比对，如果存在就去除
def drop_stopwords(content, stopwords):
    content_clean = []
    all_words = []  #用于统计词频
    for line in content:
        line_clean = []
        for words in line:
            if words in stopwords:
                continue
            line_clean.append(words)
            all_words.append(str(words))
        content_clean.append(line_clean)
    return content_clean, all_words

#把df_content的值变成一个列表
content = df_content.content_S.values.tolist()
stopwords = stopwords.stopword.values.tolist()
content_clean, all_words = drop_stopwords(content, stopwords)
#构建一个新的字典用于储存去除停用表的内容
df_content = pd.DataFrame({‘content_clean‘ : content_clean})

#基于贝叶斯进行文本分类
#创建字典,X为内容， y为种类
df_train = pd.DataFrame({‘content_clean‘:content_clean, ‘label‘:df_new[‘category‘]})

#查看y一共有几个类别
print(df_train.label.unique())

#为了方便计算,把对应的label字符类型转换为数字
label_mapping = {"汽车": 1, "财经": 2, "科技": 3, "健康": 4, "体育":5, "教育": 6,"文化": 7,"军事": 8,"娱乐": 9,"时尚": 0}
df_train[‘label‘] = df_train[‘label‘].map(label_mapping)

# 将数据分割为训练集和测试集
from sklearn.model_selection import  train_test_split

x_train, x_test, y_train, y_test = train_test_split(df_train[‘content_clean‘].values, df_train[‘label‘].values, random_state=1)

#将样本组合成带空格的字符串["dog cat fish","dog cat cat","fish bird", ‘bird‘]
words = []
for line in x_train:
    try:
        words.append(‘ ‘.join(line))
    except:
        print(line)

print(words[0])


from sklearn.feature_extraction.text import CountVectorizer

#构建对应的词汇统计表
vec = CountVectorizer(analyzer=‘word‘, max_features=4000,  lowercase = False)
vec.fit(words)

#构建贝叶斯的训练模型
from sklearn.naive_bayes import MultinomialNB
classifier = MultinomialNB()
classifier.fit(vec.transform(words), y_train)

#构建test_words的字符串
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)
#最后的训练结果
classifier.score(vec.transform(test_words), y_test)

from sklearn.feature_extraction.text import TfidfVectorizer

vectorizer = TfidfVectorizer(analyzer=‘word‘, max_features=4000,  lowercase = False)
vectorizer.fit(words)


from sklearn.naive_bayes import MultinomialNB
classifier = MultinomialNB()
classifier.fit(vectorizer.transform(words), y_train)
classifier.score(vectorizer.transform(test_words), y_test)