基于朴素贝叶斯的图书信息分类

import  numpy
import  jieba
import  pandas
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer

# 加载数据
data = pandas.read_csv('data/data.csv',encoding='ansi')
print(data)
print(data.columns)

# 将特征值与目标值转化为为数值类型
data.loc[data.loc[:,'评价'] == '好评','评价'] =0
data.loc[data.loc[:,'评价'] == '差评','评价'] =1


# 将object 转化为 int类型
data.loc[:,'评价'] = data.loc[:,'评价'].astype('int')

# 转化为特征值为数值类型
content_list = []
for tmp in data.loc[:,'内容 ']:
    res = jieba.cut(tmp,cut_all=False)

    # 组装分词
    res_str = ','.join(res)

    content_list.append(res_str)

# 处理停用词
stop_words = []
with open("data/stopwords.txt",encoding='utf-8') as f:
    lines = f.readlines()
    for line in lines:
        line_obj = line.strip()
        stop_words.append(line_obj)

# 取出重复停用词
stop_words = list(set(stop_words))

# 进行统计词数
con_vec = CountVectorizer(stop_words=stop_words)

# 统计分词
X = con_vec.fit_transform(content_list)

feature = X.toarray()
# 获取分词结果
names = con_vec.get_feature_names()
print(names)

# 将特征值与目标值组成完整的数据
new_data  = numpy.concatenate((feature,data.loc[:,'评价'].values.reshape((-1,1))),axis=1)
print(new_data)

print('*-'*40)
#获取训练集和预测集的
train_data = new_data[:8,:]

test_data = new_data[10:,:]

# 拆分特征值和目标值
x_train = train_data[:,:-1]
y_train = train_data[:,-1]

x_test = test_data[:,:-1]
y_test = test_data[:,-1]

# 进行朴素贝叶斯分类 alpha--平滑系数
nb = MultinomialNB(alpha=1.0)

# 训练数据
nb.fit(x_train,y_train)

# 预测数据
y_predict = nb.predict(x_test)

# 准确率
score = nb.score(x_test,y_test)

print(score)