# -*- coding: utf-8 -*-
"""
Created on Fri Sep 1 11:56:12 2017
@author: piaodexin
"""
#
import pandas as pd
import numpy as np
#生成正标签数据
x1=np.random.randn(50,2)+40
y1=np.ones((50,1))
data1=np.hstack([x1,y1])
#生成负标签数据
x2=np.random.randn(50,2)
y2=-np.ones((50,1))
data2=np.hstack([x2,y2])
#将数据合并
data=np.vstack([data1,data2])
from sklearn import cross_validation
#将原始数据分成训练数据，和测试数据
train_x,test_x,train_y,test_y=cross_validation.train_test_split(data[:,:-1],data[:,-1],test_size=0.25,
random_state=0,stratify=data[:,-1])
#初始化权重和偏差
w=np.random.randn(2)
b=np.ones(1)
#设置学习率
a=0.1
c=0
#进行3000轮实验
while c<3000:
for i in range(len(train_x)):
#如果某次分类错误，则修改权值和偏差
if train_y[i]*(np.sum(w*train_x[i])+b)<=0:
w+=a*train_y[i]*train_x[i]
b=a*train_y[i]
c+=1
#最后在测试集上检验正确率
count=0
for i in range(len(test_x)):
if train_y[i]*(np.sum(w*train_x[i])+b)<=0:
count+=1
precision=(len(test_x)-count)/len(test_x)
转载请注明原文地址: https://www.6miu.com/read-78481.html
