词袋模型介绍+TF-IDF算法介绍（实战）

词袋模型

from sklearn.datasets import fetch_20newsgroups
#导入新闻数据集
from sklearn.model_selection import train_test_split
#导入数据切分所需包

news = fetch_20newsgroups(subset='test')
#subset='all'所有的数据集都导入，若等于train只导入训练集，test只导入测试集
print(news.target_names)
print(len(news.data))#数据集长度，共有多少篇文章
print(len(news.target))#标签数量

print(len(news.target_names))#这些文章共有20个种类

news.data[0]#选一篇文章来查看

print(news.target[0])#打印第0篇文章的标签是第多少个
print(news.target_names[news.target[0]])#打印标签

#数据切分
x_train,x_test,y_train,y_test = train_test_split(news.data,news.target)

# train = fetch_20newsgroups(subset='train')
# x_train = train.data
# y_train = train.target
# test = fetch_20newsgroups(subset='test')
# x_test = test.data
# y_test = test.target

from sklearn.feature_extraction.text import CountVectorizer

texts=["dog cat fish","dog cat cat","fish bird", 'bird']
cv = CountVectorizer()#实例化这个类
cv_fit=cv.fit_transform(texts)


print(cv.get_feature_names())#特征的描述
print(cv_fit.toarray())#变成一个array形式

print(cv_fit.toarray().sum(axis=0))#将结果纵轴方向累加起来

from sklearn import model_selection 
from sklearn.naive_bayes import MultinomialNB

cv = CountVectorizer()
cv_data = cv.fit_transform(x_train)
mul_nb = MultinomialNB()#多项式的贝叶斯模型

#交叉验证然后求平均值
scores = model_selection.cross_val_score(mul_nb, cv_data, y_train, cv=3, scoring='accuracy')  
print("Accuracy: %0.3f" % (scores.mean())) 

TF-IDF

from sklearn.feature_extraction.text import TfidfVectorizer
# 文本文档列表
text = ["The quick brown fox jumped over the lazy dog.",
"The dog.",
"The fox"]
# 创建变换函数
vectorizer = TfidfVectorizer()
# 词条化以及创建词汇表
vectorizer.fit(text)
# 总结
print(vectorizer.vocabulary_)
print(vectorizer.idf_)
# 编码文档
vector = vectorizer.transform([text[0]])
# 总结编码文档
print(vector.shape)
print(vector.toarray())

# 创建变换函数
vectorizer = TfidfVectorizer()
# 词条化以及创建词汇表
tfidf_train = vectorizer.fit_transform(x_train)

scores = model_selection.cross_val_score(mul_nb, tfidf_train, y_train, cv=3,
                                         scoring='accuracy') 
print("Accuracy: %0.3f" % (scores.mean())) 

def get_stop_words():
    result = set()
    #将英文常用的停用词存入stopwords_en.txt
    for line in open('stopwords_en.txt', 'r').readlines():
        result.add(line.strip())#去掉换行符
    return result

# 加载停用词
stop_words = get_stop_words()
# 创建变换函数
vectorizer = TfidfVectorizer(stop_words=stop_words)

#alpha=0.01做平滑的，默认值为1
mul_nb = MultinomialNB(alpha=0.01)

# 词条化以及创建词汇表
tfidf_train = vectorizer.fit_transform(x_train)

scores = model_selection.cross_val_score(mul_nb, tfidf_train, y_train, cv=3, 
                                         scoring='accuracy') 
print("Accuracy: %0.3f" % (scores.mean())) 

# 切分数据集
tfidf_data = vectorizer.fit_transform(news.data)
x_train,x_test,y_train,y_test = train_test_split(tfidf_data,news.target)

mul_nb.fit(x_train,y_train)
print(mul_nb.score(x_train, y_train))

print(mul_nb.score(x_test, y_test))