机器学习实验：朴素贝叶斯算法实现对iris鸢尾花数据集的分类

机器学习实验：朴素贝叶斯算法实现对iris鸢尾花数据集的分类

实验内容：

代码如下：

导入相关库

import pandas as pd import numpy as np import matplotlib.colors as colors import matplotlib as mpl import matplotlib.pyplot as plt 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 from sklearn.decomposition import PCA mpl.rcParams['font.sans-serif']=[u'simHei'] mpl.rcParams['axes.unicode_minus']=False

导入数据集，并对数据集进行处理

iris = load_iris() #iris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) 123456

实现绘图函数

def drawing(train_x,test_x,train_y,test_y,Name='Gaussian',N=500): if(Name=='Gaussian'): model = bayes.GaussianNB() elif(Name == 'Bernoulli'): model = bayes.BernoulliNB() elif(Name == 'Multinomial'): model = bayes.MultinomialNB() else: model = bayes.GaussianNB() #默认 pca=PCA(n_components=2) #降为二维train_x_iris=pca.fit_transform(train_x_iris,train_y_iris) #(105, 2)test_x_iris=pca.fit_transform(test_x_iris,test_y_iris) #(45, 2) model.fit(train_x,train_y) min_train_x1,min_train_x2=np.min(train_x,axis=0) max_train_x1,max_train_x2=np.max(train_x,axis=0) min_test_x1,min_test_x2=np.min(test_x,axis=0) max_test_x1,max_test_x2=np.max(test_x,axis=0) x1min=min(min_train_x1,min_test_x1) x1max=max(max_train_x1,max_test_x1) x1=np.linspace(x1min,x1max,N) x2min=min(min_train_x2,min_test_x2) x2max=max(max_train_x2,max_test_x2) x2=np.linspace(x2min,x2max,N) x1,x2=np.meshgrid(x1,x2) X=np.c_[x1.ravel(),x2.ravel()] y_hat=model.predict(X) plt.figure() plt.subplot(2,1,1) cmp=colors.ListedColormap([u'indigo', u'gold', u'hotpink', u'firebrick', u'indianred']) plt.pcolormesh(x1,x2,y_hat.reshape(x1.shape),shading='auto',cmap=cmp) plt.scatter(train_x[:,0],train_x[:,1],c=train_y) plt.scatter(test_x[:,0],test_x[:,1],c=test_y) plt.title(Name+":"+str(model.score(test_x,test_y))) plt.subplot(2,1,2) label=label_binarize(test_y,classes=(0,1,2)) fpr,tpr,threofor=metrics.roc_curve(label.ravel(),model.predict_proba(test_x).ravel()) plt.plot(fpr,tpr,c="red",label="ROC") plt.title("AUC"+str(metrics.auc(fpr,tpr))) plt.legend() plt.tight_layout() plt.show()

对数据集进行分类及预测

#1.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 #2.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) #3.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

实现绘图，并实现决策边的绘制

# 绘图 drawing(train_x_iris,test_x_iris,train_y_iris,test_y_iris,'Gaussian') drawing(train_x_iris,test_x_iris,train_y_iris,test_y_iris,'Bernoulli') # drawing(train_x_iris,test_x_iris,train_y_iris,test_y_iris,'Multinomial')#报错：Negative values in data passed to MultinomialNB (input X)，可能原因：数据降维后出现负值不适合于Multinomial模型 1234

结果如下：