# -*- coding:UTF-8 -*-

 __author__ = 'tao'

 import csv

 import cv2

 import sys

 import numpy as np

 import math

 filename = 'F:/*机器学习/data/train.csv'

 ufilename = unicode(filename , "utf8") #这一块主要是因为汉字路径 也就是python调用open打开文件时，其路径必须要转换为utf-8格式

 list=[]

 result=[]

 row=0

 colum=0;

 with open(ufilename, 'r') as f:

     data = f.readlines()  #dat中所有字符串读入data

     for line in data:

         odom = line.split(',')        #将单个数据分隔开存好

         colum=len(odom)

         if 'PM2.5'in odom:

             lists= map(int, odom[3:12])#第三个开始开始数据  一直取9个数

             results= map(int, odom[12:13])#取第10个数

             list.append(lists)

             result.append(results)

             # print odom

         row=row+1

 #print("原始数据是：{0}行 ：{1}列 的数据".format(row, colum))

 print("有{0}个训练数据".format(len(list)))

 #y=w0*x0+w1*x1+w2*x2+w3*x3+w4*x4+w5*x5+w6*x6+w7*x7+w8*x8+b0

 #

 alpha=0.0001

 b_0=np.random.rand(1,1)

 th_0 = np.random.rand(1,1);

 th_1 = np.random.rand(1,1);

 th_2 = np.random.rand(1,1);

 th_3 = np.random.rand(1,1);

 th_4=  np.random.rand(1,1);

 th_5 = np.random.rand(1,1);

 th_6 = np.random.rand(1,1);

 th_7 = np.random.rand(1,1);

 th_8 = np.random.rand(1,1);

 for k in range(1000):

     length = len(list)

     jtheta = 0

     total = 0

     sum_total = 0

     for id in range(length):

         # print("当前序号{0}训练数据".format(id))

         xset= np.array(list[id]) #一行 X数值

         yset= np.array(result[id]) # 要估计值

         total = total + b_0 + th_0 * xset[0]+ th_1 * xset[1]+ th_2 * xset[2]+ th_3 * xset[3]+ th_4 * xset[4]+ th_5 * xset[5]+ th_6 * xset[6]+ th_7 * xset[7]+ th_8 * xset[8]- yset

         # print( "当前误差{0}".format(b_0 + th_0 * xset[0]+ th_1 * xset[1]+ th_2 * xset[2]+ th_3 * xset[3]+ th_4 * xset[4]+ th_5 * xset[5]+ th_6 * xset[6]+ th_7 * xset[7]+ th_8 * xset[8]- yset))

         tmpb0 = b_0  - alpha/length*(total)

         tmp0 = th_0  -  alpha/length*(total)*xset[0]

         tmp1 = th_1  -  alpha/length*(total)*xset[1]

         tmp2 = th_2  -  alpha/length*(total)*xset[2]

         tmp3 = th_3  -  alpha/length*(total)*xset[3]

         tmp4 = th_4  -  alpha/length*(total)*xset[4]

         tmp5 = th_5  -  alpha/length*(total)*xset[5]

         tmp6 = th_6  -  alpha/length*(total)*xset[6]

         tmp7 = th_7  -  alpha/length*(total)*xset[7]

         tmp8 = th_8  -  alpha/length*(total)*xset[8]

         b_0 = tmpb0

         th_0 = tmp0

         th_1 = tmp1

         th_2 = tmp2

         th_3 = tmp3

         th_4 = tmp4

         th_5 = tmp5

         th_6 = tmp6

         th_7 = tmp7

         th_8 = tmp8

         sum_total = sum_total + b_0 + th_0 * xset[0]+ th_1 * xset[1]+ th_2 * xset[2]+ th_3 * xset[3]+ th_4 * xset[4]+ th_5 * xset[5]+ th_6 * xset[6]+ th_7 * xset[7]+ th_8 * xset[8] - yset

         jtheta_1 = 0.5 * length * math.pow(sum_total,2)

         comp = math.fabs(jtheta_1 - jtheta)

         if id==length-1:

                 print "%10.5f   %10.5f  %10.5f  %10.5f %10.5f   %10.5f  %10.5f  %10.5f %10.5f   %10.5f  %10.5f  %10.5f \n" %(comp,jtheta * dgree,b_0,th_0,th_1,th_2,th_3,th_4,th_5,th_6,th_7,th_8)

         jtheta = jtheta_1

 #

 print("-训练得到的权值如下--")

 print " %10.5f %10.5f  %10.5f %10.5f   %10.5f  %10.5f  %10.5f %10.5f   %10.5f  %10.5f \n" %(b_0,th_0,th_1,th_2,th_3,th_4,th_5,th_6,th_7,th_8)

 #测试训练集

 for k in range(len(list)):

     xset = np.array(list[k])

     nptresult= np.array(result[k])

     # print(xset)

     # print("预测数据{0}".format( b_0 + th_0 * xset[0]+ th_1 * xset[1]+ th_2 * xset[2]+ th_3 * xset[3]+ th_4 * xset[4]+ th_5 * xset[5]+ th_6 * xset[6]+ th_7 * xset[7]+ th_8 * xset[8]))

     # print("真实数据{0}".format(nptresult))

     error= b_0 + th_0 * xset[0]+ th_1 * xset[1]+ th_2 * xset[2]+ th_3 * xset[3]+ th_4 * xset[4]+ th_5 * xset[5]+ th_6 * xset[6]+ th_7 * xset[7]+ th_8 * xset[8]-nptresult

     print("训练集的实际误差{0}".format(error))

 #读取测试集数据

 testfilename = 'F:/*机器学习/data/test_X.csv'

 utestfilename = unicode(testfilename , "utf8") #这一块主要是因为汉字路径 也就是python调用open打开文件时，其路径必须要转换为utf-8格式

 testlist=[]

 testrow=0

 testcolum=0;

 with open(utestfilename, 'r') as f:

     data = f.readlines()  #dat中所有字符串读入data

     for line in data:

         odom = line.split(',')        #将单个数据分隔开存好

         colum=len(odom)

         if 'PM2.5'in odom:

             testlists= map(int, odom[2:11])#第三个开始开始数据  一直取9个数

             testlist.append(testlists)

             # print odom

         testrow=row+1

 print("测试数据是：{0}行 ：{1}列 的数据".format(testrow, testcolum))

 print("有{0}个测试数据".format(len(testlist)))

 print(testlist)

 #输出最后的测试结果

 csvfile = file('d:\\csv_result.csv', 'wb')

 writer = csv.writer(csvfile)

 writer.writerow(['id', 'value'])

 for k in range(len(testlist)):

     id_list=[]

     xset = np.array(testlist[k])

     result= b_0 + th_0 * xset[0]+ th_1 * xset[1]+ th_2 * xset[2]+ th_3 * xset[3]+ th_4 * xset[4]+ th_5 * xset[5]+ th_6 * xset[6]+ th_7 * xset[7]+ th_8 * xset[8]

     int_result = int(result)

     if(int_result<0):

         int_result=0

     id_list = [('id_{0}'.format(k), '{0}'.format(int_result))]

     print(id_list)

     writer.writerows(id_list)

 csvfile.close()

#y=w0*x0+w1*x1+w2*x2+w3*x3+w4*x4+w5*x5+w6*x6+w7*x7+w8*x8+b0

#

alpha=0.0001

b_0=np.random.rand(1,1)

th = np.random.rand(1,9);

batch=20

for k in range(5000):

    length = len(list)

    jtheta = 0

    total = 0

    sum_total = 0

    count=0

    for j in range(batch): #batch

        # print("当前序号{0}训练数据".format(id))

        xset= np.array(list[j+count*batch]) #一行 X数值

        yset= np.array(result[j+count*batch]) # 要估计值

        total = total+b_0 +np.dot(th,xset)- yset

        # print( "当前误差{0}".format(b_0 +np.dot(th,xset)- yset))

    b_0 = b_0  - alpha/batch*(total)

    th = th  -  alpha/batch*(total)*xset

    count = count +1

    if(count>=len(list)/batch):

      break;

    if(j==batch-1):

        print " %10.5f  %10.5f %10.5f   %10.5f  %10.5f  %10.5f %10.5f   %10.5f  %10.5f  %10.5f \n" %(b_0,th[0][0],th[0][1],th[0][2],th[0][3],th[0][4],th[0][5],th[0][6],th[0][7],th[0][8])

#

print("-训练得到的权值如下--")

print" %10.5f %10.5f  %10.5f %10.5f   %10.5f  %10.5f  %10.5f %10.5f   %10.5f  %10.5f \n" %(b_0,th[0][0],th[0][1],th[0][2],th[0][3],th[0][4],th[0][5],th[0][6],th[0][7],th[0][8])