Python实现基于SVM的分类器的方法

# -*- coding: utf-8 -*-"""Created on Sun Aug 12 12:19:34 2018@author: Luove"""from sklearn import svmfrom sklearn import metricsimport pandas as pd import numpy as npfrom numpy.random import shuffle#from random import seed#import pickle #保存模型和加载模型import osos.getcwd()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')inputfile = '../data/moment.csv'data=pd.read_csv(inputfile)data.head()data=data.as_matrix()#seed(10)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seedn=0.8train=data[:int(n*len(data)),:]test=data[int(n*len(data)):,:]#建模数据 整理#k=30 m=100record=pd.DataFrame(columns=['acurrary_train','acurrary_test']) for k in range(1,m+1):  # 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  x_train=train[:,2:]*k  y_train=train[:,0].astype(int)  x_test=test[:,2:]*k  y_test=test[:,0].astype(int)    model=svm.SVC()  model.fit(x_train,y_train)  #pickle.dump(model,open('../tmp/svm1.model','wb'))#保存模型  #model=pickle.load(open('../tmp/svm1.model','rb'))#加载模型  #模型评价 混淆矩阵  cm_train=metrics.confusion_matrix(y_train,model.predict(x_train))  cm_test=metrics.confusion_matrix(y_test,model.predict(x_test))    pd.DataFrame(cm_train,index=range(1,6),columns=range(1,6))  accurary_train=np.trace(cm_train)/cm_train.sum()   #准确率计算#  accurary_train=model.score(x_train,y_train)             #使用model自带的方法求准确率  pd.DataFrame(cm_test,index=range(1,6),columns=range(1,6))  accurary_test=np.trace(cm_test)/cm_test.sum()  record=record.append(pd.DataFrame([accurary_train,accurary_test],index=['accurary_train','accurary_test']).T)record.index=range(1,m+1)find_k=record.sort_values(by=['accurary_train','accurary_test'],ascending=False) # 生成一个copy 不改变原变量find_k[(find_k['accurary_train']>0.95) & (find_k['accurary_test']>0.95) & (find_k['accurary_test']>=find_k['accurary_train'])]#len(find_k[(find_k['accurary_train']>0.95) & (find_k['accurary_test']>0.95)])''' k=33  accurary_train accurary_test33    0.950617    0.95122'''''' 计算一下整体  accurary_data 0.95073891625615758'''k=33x_train=train[:,2:]*ky_train=train[:,0].astype(int)model=svm.SVC()model.fit(x_train,y_train)model.score(x_train,y_train)model.score(datax_train,datay_train)datax_train=data[:,2:]*kdatay_train=data[:,0].astype(int)cm_data=metrics.confusion_matrix(datay_train,model.predict(datax_train))pd.DataFrame(cm_data,index=range(1,6),columns=range(1,6))accurary_data=np.trace(cm_data)/cm_data.sum()accurary_data