垃圾文件分类

import pandas as pd
from sklearn import linear_model
from sklearn.feature_extraction.text import TfidfVectorizer
f = open("D:\深度学习\smsspamcollection(1)\SMSSpamCollection.txt",'r', encoding='UTF-8')
#file = pd.read_csv(f)

df=pd.read_csv(f,delimiter='\t',header=None)
y,X_train=df[0],df[1]

vectorizer=TfidfVectorizer()
x=vectorizer.fit_transform(X_train)

print(x)

lr=linear_model.LogisticRegression()
lr.fit(x,y)

testX=vectorizer.transform(["URGENT! You phone number 123 had won a prize!",
                            "Hey,Whats up"])
predictions=lr.predict(testX)
print(predictions)

 所需数据集下载https://download.csdn.net/download/devilangel2/12150884