《机器学习实战》第8章学习笔记（回归）之预测乐高玩具套装的价格

原文中通过Google提供的API来抓取价格，但由于现在访问不了Google,所以，直接通过文本给的html文件直接读取价格信息。然后进一步进行分析预测。

代码实现：

# -*- coding: utf-8 -*-
"""
Created on Mon May  7 09:55:34 2018

@author: lizihua
"""
#from time import sleep
#import json
#import urllib
#from BeautifulSoup import BeautifulSoup
from bs4 import BeautifulSoup
from numpy import random,zeros,mat,var, mean,array,nonzero,multiply,linalg,eye,shape,exp,ones
import numpy as np
import matplotlib.pyplot as plt
"""
#由于Google购物API关闭，采用下一段读取网页文件代码代替此爬虫过程
def searchForSet(retX,retY,setNum,yr,numPce,origPrc):
    sleep(10)
    myAPIstr = 'get from code.google.com'
    searchURL = 'https://www.googleapis.com/shopping/search/v1/public/products?key=%s&country=US&q=lego+%d&alt=json' % (myAPIstr, setNum)
    pg = urllib.request.urlopen(searchURL)
    retDict = json.loads(pg.read())
    for i in range(len(retDict['items'])):
        try:
            currItem = retDict['items'][i]
            if currItem['product']['condition'] == 'new':
                newFlag = 1
            else: newFlag = 0
            listOfInv = currItem['product']['inventories']
            for item in listOfInv:
                sellingPrice = item['price']
                if  sellingPrice > origPrc * 0.5:
                    print ("%d\t%d\t%d\t%f\t%f" % (yr,numPce,newFlag,origPrc, sellingPrice))
                    retX.append([yr, numPce, newFlag, origPrc])
                    retY.append(sellingPrice)
        except: print ('problem with item %d' % i)

def setDataCollect(retX, retY):
    searchForSet(retX, retY, 8288, 2006, 800, 49.99)
    searchF