基于SVM的分类器Python实现

本文代码来之《数据分析与挖掘实战》，在此基础上补充完善了一下~

代码是基于SVM的分类器Python实现，原文章节题目和code关系不大，或者说给出已处理好数据的方法缺失、源是图像数据更是不见踪影，一句话就是练习分类器（▼㉨▼メ）

源代码直接给好了K=30，就试了试怎么选的，挑选规则设定比较单一，有好主意请不吝赐教哟

 1 # -*- coding: utf-8 -*-
 2 """
 3 Created on Sun Aug 12 12:19:34 2018
 4 
 5 @author: Luove
 6 """
 7 from sklearn import svm
 8 from sklearn import metrics
 9 import pandas as pd 
10 import numpy as np
11 from numpy.random import shuffle
12 #from random import seed
13 #import pickle #保存模型和加载模型
14 import os
15 
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:]*k
37     y_train=train[:,0].astype(int)
38     x_test=test[:,2:]*k
39     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=33
61     accurary_train  accurary_test
62 33        0.950617        0.95122
63 '''
64 ''' 计算一下整体 
65  accurary_data
66  0.95073891625615758
67 '''
68 k=33
69 x_train=train[:,2:]*k
70 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:]*k
76 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

REF：

《数据分析与挖掘实战》

源代码及数据需要可自取：https://github.com/Luove/Data