朴素贝叶斯算法Sklearn实现的学习笔记

工藤新饿

已于 2022-11-20 18:19:11 修改

阅读量402

点赞数

文章标签：算法 sklearn python

于 2022-11-20 18:14:54 首次发布

本文链接：https://blog.csdn.net/Legna01/article/details/127951792

版权

import numpy as np

#导入数据集生成器
from sklearn.datasets import make_blobs
#随机生成500个类别数是5的分类数据
X,y = make_blobs(n_samples = 500,centers = 5,random_state=8)
#数据可视化
import matplotlib.pyplot as plt
%matplotlib inline
plt.scatter(X[:,0],X[:,1],c = y,cmap=plt.cm.spring,edgecolors = 'k')
拆分训练集与测试集
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=8)
#导入朴素贝叶斯分类器
from sklearn.naive_bayes import BernoulliNB,MultinomialNB,GaussianNB

nb = BernoulliNB()#构建伯努利分布（二项分布）朴素贝叶斯分类器
nb.fit(X_train,y_train)
#拟合结果可视化
plt.figure(dpi=300)
x_min,x_max = X[:,0].min()-0.5,X[:,0].max()+0.5
y_min,y_max = X[:,1].min()-0.5,X[:,1].max()+0.5
xx,yy = np.meshgrid(np.arange(x_min,x_max,.02),
                   np.arange(y_min,y_max,.02))
z = nb.predict(np.c_[(xx.ravel(),yy.ravel())]).reshape(xx.shape)
plt.pcolormesh(xx,yy,z,cmap=plt.cm.Pastel1)
plt.scatter(X_train[:,0],X_train[:,1],c=y_train,cmap=plt.cm.cool,edgecolor='k')
plt.scatter(X_test[:,0],X_test[:,1],c = y_test,cmap=plt.cm.cool,marker='*',
            edgecolor='k')
plt.xlim(xx.min(),xx.max())
plt.ylim(yy.min(),yy.max())
plt.title('Classifier: BernoulliNB')
plt.show()

伯努利分布（二项分布）朴素贝叶斯（BernoulliNB）

#构建高斯分布（正态分布）朴素贝叶斯分类器
gnb = GaussianNB()
gnb.fit(X_train,y_train)
print('模型得分:{:.3f}'.format(gnb.score(X_test,y_test)))
#拟合结果可视化
plt.figure(dpi=300)
x_min,x_max = X[:,0].min()-0.5,X[:,0].max()+0.5
y_min,y_max = X[:,1].min()-0.5,X[:,1].max()+0.5
xx,yy = np.meshgrid(np.arange(x_min,x_max,.02),
                   np.arange(y_min,y_max,.02))
z = gnb.predict(np.c_[(xx.ravel(),yy.ravel())]).reshape(xx.shape)
plt.pcolormesh(xx,yy,z,cmap=plt.cm.Pastel1)
plt.scatter(X_train[:,0],X_train[:,1],c=y_train,cmap=plt.cm.cool,edgecolor='k')
plt.scatter(X_test[:,0],X_test[:,1],c=y_test,cmap=plt.cm.cool,marker='*',
            edgecolor='k')
plt.xlim(xx.min(),xx.max())
plt.ylim(yy.min(),yy.max())
plt.title('Classifier:GaussianNB')
plt.show()

高斯朴素贝叶斯（GaussianNB）

#导入数据预处理工具
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
scaler.fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)

#构建多项分布朴素贝叶斯分类器
mnb = MultinomialNB()
mnb.fit(X_train_scaled,y_train)
print('模型得分：{:.3f}'.format(mnb.score(X_test_scaled,y_test)))
#拟合结果可视化
plt.figure(dpi=300)
z = mnb.predict(scaler.transform(np.c_[xx.ravel(),yy.ravel()])).reshape(xx.shape)
plt.pcolormesh(xx,yy,z,cmap = plt.cm.Pastel1)
plt.scatter(X_train[:,0],X_train[:,1],c=y_train,cmap=plt.cm.cool,edgecolor='k')
plt.scatter(X_test[:,0],X_test[:,1],c=y_test,cmap=plt.cm.cool,marker='*',
            edgecolor='k')
plt.xlim(xx.min(),xx.max())
plt.ylim(yy.min(),yy.max())
plt.title('Classifier:MultinomialNB')
plt.show()

多项分布朴素贝叶斯（MultinomialNB）