机器学习实验：使用3种朴素贝叶斯算法对iris()、breast_cancer()和wine()数据集进行训练

机器学习实验：使用3种朴素贝叶斯算法对iris()、breast_cancer()和wine()数据集进行训练

实验内容：
分别使用3种朴素贝叶斯算法对iris()、breast_cancer()和wine()数据集进行训练，并通过比较其分类效果分析不同算法对不同数据集的适用情况。

实现代码：

• 导入相关库

  import pandas as pd
  import numpy as np
  import sklearn.metrics as metrics
  from sklearn.preprocessing import label_binarize
  from sklearn.datasets import load_iris
  from sklearn.datasets import load_wine
  from sklearn.datasets import load_breast_cancer
  from sklearn.model_selection import train_test_split
  import sklearn.naive_bayes as bayes
  

• 导入数据集

  iris = load_iris()  #iris数据集
  cancer = load_breast_cancer()   #乳腺癌数据集
  wine = load_wine()  #红酒数据集
  

• 对iris数据集进行训练

  #对iris数据集处理
  #1.处理数据集
  X_iris=iris.data
  Y_iris=iris.target
  train_x_iris,test_x_iris,train_y_iris,test_y_iris=train_test_split(X_iris,Y_iris,test_size=0.3,random_state=2)
  # print(train_x_iris.shape)   #(105, 4)
  # print(test_x_iris.shape)    #(45, 4)
  
  
  #2.获取朴素贝叶斯分类器的高斯模型,并训练
  gaussian = bayes.GaussianNB()
  bernoulli = bayes.BernoulliNB()
  multionmial =bayes.MultinomialNB()
  
  gaussian.fit(train_x_iris,train_y_iris)
  bernoulli.fit(train_x_iris,train_y_iris)
  multionmial.fit(train_x_iris,train_y_iris)    #输入数据出现负值,不能使用MultinomialNB
  
  #3.进行预测
  test_y_gaussianHat_iris = gaussian.predict(test_x_iris)
  test_y_bernoulliHat_iris = bernoulli.predict(test_x_iris)
  test_y_multionmialHat_iris = multionmial.predict(test_x_iris)
  
  #4.输出准确率
  score_gaussian = gaussian.score(test_x_iris,test_y_iris)
  score_bernoulli = bernoulli.score(test_x_iris,test_y_iris)
  score_multionmial = multionmial.score(test_x_iris,test_y_iris)
  print("gaussian score:"+str(score_gaussian))
  print("bernoulli score:"+str(score_bernoulli))
  print("multionmial score:"+str(score_multionmial))
  # gaussian score:0.9777777777777777
  # bernoulli score:0.28888888888888886
  # multionmial score:0.9111111111111111
  
  

• 对breast_cancer数据集训练

  #对breast_cancer数据集处理
  #1.处理数据集
  X_cancer=cancer.data
  Y_cancer=cancer.target
  train_x_cancer,test_x_cancer,train_y_cancer,test_y_cancer=train_test_split(X_cancer,Y_cancer,test_size=0.3,random_state=2)
  # print(train_x_cancer.shape)   #(398,30)
  # print(test_x_cancer.shape)    #(171,30)
  
  #2.获取朴素贝叶斯分类器的高斯模型,并训练
  gaussian = bayes.GaussianNB()
  bernoulli = bayes.BernoulliNB()
  multionmial =bayes.MultinomialNB()
  
  gaussian.fit(train_x_cancer,train_y_cancer)
  bernoulli.fit(train_x_cancer,train_y_cancer)
  multionmial.fit(train_x_cancer,train_y_cancer)    #输入数据出现负值,不能使用MultinomialNB
  
  #3.进行预测
  test_y_gaussianHat_cancer = gaussian.predict(test_x_cancer)
  test_y_bernoulliHat_cancer = bernoulli.predict(test_x_cancer)
  test_y_multionmialHat_cancer = multionmial.predict(test_x_cancer)
  
  #4.输出准确率
  score_gaussian = gaussian.score(test_x_cancer,test_y_cancer)
  score_bernoulli = bernoulli.score(test_x_cancer,test_y_cancer)
  score_multionmial = multionmial.score(test_x_cancer,test_y_cancer)
  
  print("gaussian score:"+str(score_gaussian))
  print("bernoulli score:"+str(score_bernoulli))
  print("multionmial score:"+str(score_multionmial))
  # gaussian score:0.9415204678362573
  # bernoulli score:0.6081871345029239
  # multionmial score:0.8888888888888888
  

• 对breast_wine数据集训练

  #对breast_wine数据集处理
  #1.处理数据集
  X_wine=wine.data
  Y_wine=wine.target
  train_x_wine,test_x_wine,train_y_wine,test_y_wine=train_test_split(X_wine,Y_wine,test_size=0.3,random_state=2)
  # print(train_x_wine.shape)   #(124, 13)
  # print(test_x_wine.shape)    #(54,13)
  
  #2.获取朴素贝叶斯分类器的高斯模型,并训练
  gaussian = bayes.GaussianNB()
  bernoulli = bayes.BernoulliNB()
  multionmial =bayes.MultinomialNB()
  
  gaussian.fit(train_x_wine,train_y_wine)
  bernoulli.fit(train_x_wine,train_y_wine)
  multionmial.fit(train_x_wine,train_y_wine)    #输入数据出现负值,不能使用MultinomialNB
  
  #3.进行预测
  test_y_gaussianHat_wine = gaussian.predict(test_x_wine)
  test_y_bernoulliHat_wine = bernoulli.predict(test_x_wine)
  test_y_multionmialHat_wine = multionmial.predict(test_x_wine)
  
  #4.输出准确率
  score_gaussian = gaussian.score(test_x_wine,test_y_wine)
  score_bernoulli = bernoulli.score(test_x_wine,test_y_wine)
  score_multionmial = multionmial.score(test_x_wine,test_y_wine)
  
  print("gaussian score:"+str(score_gaussian))
  print("bernoulli score:"+str(score_bernoulli))
  print("multionmial score:"+str(score_multionmial))
  # gaussian score:0.9629629629629629
  # bernoulli score:0.37037037037037035
  # multionmial score:0.8888888888888888
  

总结: sklearn提供多个朴素贝叶斯分类器，他们的主要区别在于假设了不同的概率分布，这三种常用的朴素贝叶斯分类器区别如下：

• 高斯朴素贝叶斯分类器（GaussianNB）：适合于连续值
• 多项式贝叶斯分类器（MultimomialNB）：适合于离散值（如：计数）
• 伯努利贝叶斯分类器（BernoulliNB）：适合于二值

不同朴素贝叶斯模型的区别，主要在于它们对概率分布𝑃(𝑋i|C)所做的不同假设。