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

# -*- coding: utf-8 -*-
"""
Created on Sun Aug 12 12:19:34 2018

@author: Luove
"""
from sklearn import svm
from sklearn import metrics
import pandas as pd 
import numpy as np
from numpy.random import shuffle
#from random import seed
#import pickle #保存模型和加载模型
import os


os.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seed
n=0.8
train=data[:int(n*len(data)),:]
test=data[int(n*len(data)):,:]

#建模数据 整理
#k=30 
m=100
record=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_test
33        0.950617        0.95122
'''
''' 计算一下整体 
 accurary_data
 0.95073891625615758
'''
k=33
x_train=train[:,2:]*k
y_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:]*k
datay_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

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