sklearn中的朴素贝叶斯模型及其应用

from sklearn import datasets
iris=datasets.load_iris()

from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()  #构造
pred = gnb.fit(iris.data, iris.target)  #拟合
y_pred = pred.predict(iris.data) #预测

print(iris.data.shape[0],(iris.target != y_pred).sum())
      
结果：150 6

from sklearn import datasets
iris = datasets.load_iris()

from  sklearn.naive_bayes import BernoulliNB
gnb = BernoulliNB() #构造
pred = gnb.fit(iris.data, iris.target)  #拟合
y_pred = pred.predict(iris.data)    #预测

print(iris.data.shape[0],(iris.target !=y_pred).sum())

结果:150 100

from sklearn import datasets
iris = datasets.load_iris()

from  sklearn.naive_bayes import MultinomialNB
gnb = MultinomialNB() #构造
pred = gnb.fit(iris.data, iris.target)  #拟合
y_pred = pred.predict(iris.data)    #预测

print(iris.data.shape[0],(iris.target !=y_pred).sum())

结果： 150 7

from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import cross_val_score
gnb = GaussianNB()
scores=cross_val_score(gnb,iris.data, iris.target, cv=10)
print("Accuracy:%.3f"%scores.mean())

结果：

Accuracy:0.953

from sklearn import datasets, linear_model
from sklearn.model_selection import cross_val_predict
diabetes = datasets.load_diabetes()
X = diabetes.data[:150]
y = diabetes.target[:150]
lasso = linear_model.Lasso()
y_pred = cross_val_predict(lasso, X, y, cv=3)

import csv
file_path=r‘E:\SMSSpamCollectionjsn.txt‘
sms=open(file_path,‘r‘,encoding=‘utf-8‘)
sms_data=[]
sms_label=[]
csv_reader=csv.reader(sms,delimiter=‘\t‘)
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(line[1])
sms.close()
sms_data=str(sms_data) #字符串
sms_data=sms_data.lower() #大小写
sms_data=sms_data.split() #列表
sms_data1=[] #处理后的内容

i=0
for i in sms_data:#去掉长度小于3的单词
    if len(i)>4:
        sms_data1.append(i)
        continue