1.使用朴素贝叶斯模型对iris数据集进行花分类,尝试使用3种不同类型的朴素贝叶斯:高斯分布型,多项式型,伯努利型
#高斯分布型 import numpy as np from sklearn.datasets import load_iris from sklearn.naive_bayes import GaussianNB iris=load_iris() gnb=GaussianNB() pred=gnb.fit(iris.data,iris.target) y_pre=pred.predict(iris.data) print("总数:",iris.data.shape[0],"错误个数:",(iris.target!=y_pre).sum())
#伯努利型 import numpy as np from sklearn.datasets import load_iris from sklearn.naive_bayes import BernoulliNB iris=load_iris() gnb=BernoulliNB() pred=gnb.fit(iris.data,iris.target) y_pre=pred.predict(iris.data) print("总数:",iris.data.shape[0],"错误个数:",(iris.target!=y_pre).sum())
#多项式型 import numpy as np from sklearn.datasets import load_iris from sklearn.naive_bayes import MultinomialNB iris=load_iris() gnb=MultinomialNB() pred=gnb.fit(iris.data,iris.target) y_pre=pred.predict(iris.data) print("总数:",iris.data.shape[0],"错误个数:",(iris.target!=y_pre).sum())
iris.data[66]
gnb.predict([[5.6, 3. , 4.5, 1.5]])
2.使用sklearn.model_selection.cross_val_score(),对模型进行验证
#高斯分布型 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())
from sklearn.naive_bayes import BernoulliNB from sklearn.model_selection import cross_val_score gnb=BernoulliNB() scores=cross_val_score(gnb,iris.data,iris.target,cv=10) print("Accuracy:%.3f"%scores.mean())
from sklearn.naive_bayes import MultinomialNB from sklearn.model_selection import cross_val_score gnb=MultinomialNB() scores=cross_val_score(gnb,iris.data,iris.target,cv=10) print("Accuracy:%.3f"%scores.mean())
import csv file_path=r'F:\sms.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(); print("邮件总数:",len(sms_label)) sms_label
sms_data