sklearn学习之贝叶斯分类

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_37195257/article/details/79871600

样本还是选用的鸢尾花，iris，多么美丽的花儿

# -*- coding: utf-8 -*-
import sklearn
from sklearn import naive_bayes
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn import datasets
import pandas as pd
import numpy


def getData_1():

    iris = datasets.load_iris()
    X = iris.data   #样本特征矩阵，150*4矩阵，每行一个样本，每个样本维度是4
    y = iris.target #样本类别矩阵，150维行向量，每个元素代表一个样本的类别


    df1=pd.DataFrame(X, columns =['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm'])
    df1['target']=y

    return df1

df=getData_1()


X_train, X_test, y_train, y_test = train_test_split(df.iloc[:,0:3],df['target'], test_size=0.3, random_state=42)
print X_train, X_test, y_train, y_test

model =  naive_bayes.GaussianNB()  # 高斯贝叶斯
model.fit(X_train,y_train)
predict=model.predict(X_test)
print predict
print y_test.values
a=0
for i in range(len(predict)):

    if predict[i] == y_test.values[i]:
        a=a+1


score=float(a)/len(predict)
print '贝叶斯准确率:%3f' %(score)

print '贝叶斯:{:.3f}'.format(model.score(X_test, y_test))

结果：

predict：[1 0 2 1 2 0 1 2 1 1 2 0 0 0 0 2 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 1 1
 0 0 0 1 1 2 0 0]
y_test.values：[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
 0 0 0 2 1 1 0 0]
贝叶斯准确率:0.888889
贝叶斯:0.889