python支持向量机分类器怎么用_基于SVM的分类器Python实现

1 #-*- coding: utf-8 -*-

2 """

3 Created on Sun Aug 12 12:19:34 20184

5 @author: Luove6 """

7 from sklearn importsvm8 from sklearn importmetrics9 importpandas as pd10 importnumpy as np11 from numpy.random importshuffle12 #from random import seed

13 #import pickle #保存模型和加载模型

14 importos15

16

17 os.getcwd()18 os.chdir('D:/Analyze/Python Matlab/Python/BookCodes/Python数据分析与挖掘实战/图书配套数据、代码/chapter9/demo/code')19 inputfile = '../data/moment.csv'

20 data=pd.read_csv(inputfile)21

22 data.head()23 data=data.as_matrix()24 #seed(10)

25 shuffle(data) #随机重排，按列，同列重排，因是随机的每次运算会导致结果有差异，可在之前设置seed

26 n=0.8

27 train=data[:int(n*len(data)),:]28 test=data[int(n*len(data)):,:]29

30 #建模数据 整理

31 #k=30

32 m=100

33 record=pd.DataFrame(columns=['acurrary_train','acurrary_test'])34 for k in range(1,m+1):35 #k特征扩大倍数，特征值在0-1之间，彼此区分度太小，扩大以提高区分度和准确率

36 x_train=train[:,2:]*k37 y_train=train[:,0].astype(int)38 x_test=test[:,2:]*k39 y_test=test[:,0].astype(int)40

41 model=svm.SVC()42 model.fit(x_train,y_train)43 #pickle.dump(model,open('../tmp/svm1.model','wb'))#保存模型

44 #model=pickle.load(open('../tmp/svm1.model','rb'))#加载模型

45 #模型评价 混淆矩阵

46 cm_train=metrics.confusion_matrix(y_train,model.predict(x_train))47 cm_test=metrics.confusion_matrix(y_test,model.predict(x_test))48

49 pd.DataFrame(cm_train,index=range(1,6),columns=range(1,6))50 accurary_train=np.trace(cm_train)/cm_train.sum() #准确率计算

51 #accurary_train=model.score(x_train,y_train) #使用model自带的方法求准确率

52 pd.DataFrame(cm_test,index=range(1,6),columns=range(1,6))53 accurary_test=np.trace(cm_test)/cm_test.sum()54 record=record.append(pd.DataFrame([accurary_train,accurary_test],index=['accurary_train','accurary_test']).T)55

56 record.index=range(1,m+1)57 find_k=record.sort_values(by=['accurary_train','accurary_test'],ascending=False) #生成一个copy 不改变原变量

58 find_k[(find_k['accurary_train']>0.95) & (find_k['accurary_test']>0.95) & (find_k['accurary_test']>=find_k['accurary_train'])]59 #len(find_k[(find_k['accurary_train']>0.95) & (find_k['accurary_test']>0.95)])

60 '''k=3361 accurary_train accurary_test62 33 0.950617 0.9512263 '''

64 '''计算一下整体65 accurary_data66 0.9507389162561575867 '''

68 k=33

69 x_train=train[:,2:]*k70 y_train=train[:,0].astype(int)71 model=svm.SVC()72 model.fit(x_train,y_train)73 model.score(x_train,y_train)74 model.score(datax_train,datay_train)75 datax_train=data[:,2:]*k76 datay_train=data[:,0].astype(int)77 cm_data=metrics.confusion_matrix(datay_train,model.predict(datax_train))78 pd.DataFrame(cm_data,index=range(1,6),columns=range(1,6))79 accurary_data=np.trace(cm_data)/cm_data.sum()80 accurary_data