Initial commit

8.8nlp.py

+# -*- coding: utf-8 -*-
+"""
+Created on Tue Aug  6 10:11:08 2019
+
+@author: admin
+"""
+
+import jieba
+from gensim import corpora,models,similarities
+import pandas as pd
+import codecs
+from sklearn.model_selection import train_test_split
+import numpy as np
+
+
+data=pd.read_excel('0731复印机（原数据-标准值）.xlsx')
+c=data.columns
+d=np.array(data)
+d=np.random.permutation(d)
+data=pd.DataFrame(d)
+data.columns=c
+
+x=data['标配纸盒容量（原）']
+y=data['标配纸盒容量_y']
+
+x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.21)
+#print(x_train.head())
+#print(data['标配纸盒容量（原）'].head())
+#print(type(x_train))
+#print(type(data['标配纸盒容量（原）']))
+#print(x.head())
+
+
+#删除特殊字符值
+A=('＋','；','：','（','(',')','）',"，",',','+','【','】')
+i = 0
+newlist = list()
+for text in x_train:   
+    b=''.join(c for c in text if c not in A)
+    #print(b)
+    i += 1
+    newlist.append(b)
+
+x_train=pd.DataFrame(data=newlist)
+#print(data['标配纸盒容量（原）'].head())
+
+#训练模型的数据集 
+Traintest_word = []
+for word in x_train[0]:
+    words_list = [words for words in jieba.cut(word)]   
+    Traintest_word.append(words_list)
+
+#print(Traintest_word)
+
+#测试用词
+i= 0
+y_pred=[]
+for z in x_test:
+    print('这是第%s次训练:'%i)
+    i+=1
+    doc_test =z
+    ##删除特殊字符值
+    doc_test = doc_test.replace('（','').replace('）','').replace(',','').replace('：','').replace(';','')
+    
+    #对测试数据进行jieba分词
+    doc_test_list = [word for word in jieba.cut(doc_test)]
+    #print(doc_test_list)
+    
+    #用dictionary方法获取词袋
+    dictionary = corpora.Dictionary(Traintest_word)
+    #print(dictionary)
+    #词袋中用数字对所有词进行了编号
+    a=dictionary.keys()
+    #print(a)
+    #使用doc2bow制作语料库，利用词袋模型中的字典将其映射到向量空间
+    corpus = [dictionary.doc2bow(doc) for doc in Traintest_word]
+    #print(corpus)
+    
+    #对测试文档也进行制作语料库，利用词袋模型中的字典将其映射到向量空间
+    doc_test_vec = dictionary.doc2bow(doc_test_list)
+    #print(doc_test_vec)
+    #使用TF-IDF模型对语料库建模
+    tfidf = models.TfidfModel(corpus)
+    #print(tfidf)
+    #获文档中，每个词的TF-IDF值 tfidf[corpus]
+    #对每个目标文档，分析测试文档的相似度
+    #model 实例化
+    index = similarities.SparseMatrixSimilarity(tfidf[corpus], num_features=len(dictionary.keys()))
+    
+    sim = index[tfidf[doc_test_vec]]
+    #print(len(sim))
+    #根据相似度排序是一个列表  表中每一项是一个元组   元组中前面是原句索引  后面是相似度
+    SimilaritiesList = sorted(enumerate(sim), key=lambda item: -item[1])
+    
+    #print(SimilaritiesList)
+    num = 0 
+    while(num<1):
+        Result_tutple = SimilaritiesList[num]    #获取元组   索引  相似度
+        Result_index = Result_tutple[0]    #获取索引
+        #print(Traintest_word[Result_index])    # 输出分词后数值
+        print(Result_tutple,y[Result_index])
+        num = num + 1
+        y_pred.append(y[Result_index])
+        
+print(y_pred[1])
+#print(type(y_pred))
+y_test=list(y_test)
+print(y_test[1])
+
+count=0
+for i in range(len(x_test)):
+    if y_test==y_pred:
+        count+=1
+
+print("Accuracy:",count/len(x_test))
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

8.8nlp_def.py

+# -*- coding: utf-8 -*-
+"""
+Created on Tue Aug  6 10:11:08 2019
+
+@author: admin
+"""
+
+import jieba
+from gensim import corpora,models,similarities
+import pandas as pd
+
+from sklearn.model_selection import train_test_split
+
+data=pd.read_excel('0731复印机（原数据-标准值）.xlsx')
+
+
+x=data['标配纸盒容量（原）']
+y=data['标配纸盒容量_y']
+#分割数据
+x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.11)
+
+class word_nlp():
+    #删除特殊字符值
+    def __init__(self,x_train,y_train,x_test):
+        self.x_train =x_train
+        self.y_train=y_train
+        self.x_test=x_test
+         
+        
+    def drop_charachaters(self):
+        A=('＋','；','：','（','(',')','）',"，",',','+','【','】')
+        newlist = []
+        for text in self.x_train: 
+            b=''.join(c for c in text if c not in A)
+            newlist.append(b)
+        return newlist
+    
+    ##训练模型的数据集 
+    def word_list(self,newlist):
+        Traintest_word = []
+        for word in newlist:
+            words_list = [words for words in jieba.cut(word)]   
+            Traintest_word.append(words_list)
+        return Traintest_word
+    
+    #model 运行
+    def model(self,Traintest_word):
+        i= 0
+        y_pred=[]
+        for line in self.x_test:
+            #print('这是第%s次训练:'%i)
+            i+=1
+            ##删除特殊字符值
+            doc_test = line.replace('（','').replace('）','').replace(',','').replace('：','').replace(';','').replace('+','')
+            
+            #对测试数据进行jieba分词
+            doc_test_list = [word for word in jieba.cut(doc_test)]
+            
+            #用dictionary方法获取词袋
+            dictionary = corpora.Dictionary(Traintest_word)
+    
+            #词袋中用数字对所有词进行了编号
+            dictionary.keys()
+    
+            #使用doc2bow制作语料库，利用词袋模型中的字典将其映射到向量空间
+            corpus = [dictionary.doc2bow(doc) for doc in Traintest_word]
+            
+            #对测试文档也进行制作语料库，利用词袋模型中的字典将其映射到向量空间
+            doc_test_vec = dictionary.doc2bow(doc_test_list)
+            
+            #print(doc_test_vec)
+            #使用TF-IDF模型对语料库建模
+            tfidf = models.TfidfModel(corpus)
+            
+            #print(tfidf)
+            #获文档中，每个词的TF-IDF值 tfidf[corpus]
+            #对每个目标文档，分析测试文档的相似度
+            #model 实例化
+            index = similarities.SparseMatrixSimilarity(tfidf[corpus], num_features=len(dictionary.keys()))
+            sim = index[tfidf[doc_test_vec]]
+            
+            #根据相似度排序是一个列表  表中每一项是一个元组   元组中前面是原句索引  后面是相似度
+            SimilaritiesList = sorted(enumerate(sim), key=lambda item: -item[1])
+     
+            num = 0 
+            while(num<1):
+                Result_tutple = SimilaritiesList[num]    #获取元组   索引  相似度
+                Result_index = Result_tutple[0]    #获取索引
+                #print(Traintest_word[Result_index])    # 输出分词后数值
+                #print(Result_tutple,y[Result_index])
+                num = num + 1
+                y_pred.append(self.y_train[Result_index])
+                
+        return y_pred
+        
+    #输出准确度
+    def scores(self,y_test,y_pred):
+        y_test=list(y_test)
+        from sklearn.metrics import accuracy_score
+        a=accuracy_score(y_pred,y_test)
+        b=accuracy_score(y_pred,y_test,normalize=False)
+        print('\n','Accuracy:',a,'\n','y_test的数目：',len(y_test),'\n','预测正确数：',b)
+            
+
+
+kk=word_nlp(x_train,y_train,x_test)
+#删除特殊字符
+newlist=kk.drop_charachaters()
+#训练模型的数据集 
+Traintest_word=kk.word_list(newlist)
+#运行model，进行预测
+y_pred=kk.model(Traintest_word)
+#输出准确度
+#kk.scores(y_test,y_pred)
+

Simi.py

+# -*- coding: utf-8 -*-
+"""
+Created on Mon Aug  5 10:30:11 2019
+
+@author: admin
+"""
+
+import pandas as pd
+import numpy as np
+import jieba
+import string
+from gensim import corpora
+from gensim.similarities import Similarity
+
+import random
+
+
+class Simi():
+    #删除特殊字符值
+    def __init__(self,x_train,y_train,x_test):
+        self.x_train =x_train
+        self.y_train=y_train
+        self.x_test=x_test
+        
+    def gen_similarity(self):
+
+        split_data=[]
+        data=np.array(self.x_train)
+        for i in data:
+            seg_list=jieba.lcut(i)
+        
+            split_data.append(seg_list)
+       
+        dictionary = corpora.Dictionary(split_data)
+        corpus = [dictionary.doc2bow(text) for text in split_data]
+        similarity = Similarity('-Similarity-index', corpus, num_features=800)
+        return dictionary,similarity
+
+    def start_end(self,string1,part):
+        start=string1.find(part)
+        end=start+len(part)
+        return start,end
+    
+    def predict(self):
+        dictionary,similarity=self.gen_similarity()
+        pre_data=[]
+        
+        for i in self.x_test:
+            if i[0]!='NULL' and i[1]=='NULL':
+               seg_test=jieba.lcut(i[0])                   
+               test_data_c= dictionary.doc2bow(seg_test)
+               similarity.num_best = 1
+               pre_y=[]
+               pre_y.append(i[0])
+               index=similarity[test_data_c][0][0]
+               y=self.y_train[index]
+               if y in i[0].upper():
+                   pre_y.append(y)
+               else:
+                   pre_y.append(i[1])
+               pre_y.append(i[2])
+               pre_data.append(pre_y) 
+            else:
+              pre_data.append(i)
+        return pd.DataFrame(pre_data)
+               
+           
+
+x_train=[]
+y_train=[]
+x_test=[]
+s=pd.read_csv('test_s.csv')
+s=s.iloc[:,1:]
+s=s.fillna('NULL')
+for i in np.array(s):
+    x_test.append(i)
+    if i[1]=='NULL':
+        
+        continue
+    
+    else:
+        x_train.append(i[0])
+        y_train.append(i[1])
+    
+    
+d=Simi(x_train,y_train,x_test)
+
+p=d.predict()
+
+
+    
\ No newline at end of file

Untitled Folder/.ipynb_checkpoints/Untitled-checkpoint.ipynb

+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Untitled Folder/.ipynb_checkpoints/Untitled1-checkpoint.ipynb

+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

bijiben_data_shenzhen.csv

+,CPU,count,id,mflag,price,price2,product_name,url,产品名称,品牌,系列_型号,显示屏尺寸,内存,独立显卡,原厂预装操作系统,硬盘,flag,序号
+0,I3-7130U,2,133,0,4500.0,,便携式计算机 宏碁/ACER TravelMate P249-9280,,,宏碁/ACER,P249,14英寸 ,标配DDR4 2666 4GB，可扩容至32GB ,集成显卡,Linux,无 HDD+128G SSD硬盘 SSD,True,323
+1,I3-8130U,2,134,0,4500.0,,便携式计算机 宏碁/ACER TravelMate P2410-8367,,,宏碁/ACER,P2410,14英寸 ,标配DDR4 2666 4GB，可扩容至20GB ,集成显卡,Linux,无 HDD+128G SSD硬盘 SSD,True,324
+2,I3-7130U,2,135,0,4500.0,,便携式计算机 宏碁/ACER TravelMate P449-9791,,,宏碁/ACER,P449,14英寸,标配DDR4 2666 4GB，可扩容至24GB  ,标配DDR4 2666 8GB，可扩容至32GB  ,Linux,无 HDD+128G SSD硬盘 SSD,True,325
+3,I5-7200U,0,139,True,5500.0,"7,999.00",便携式计算机 宏碁/ACER TravelMate P249-7387,http://www.szzfcg.cn/newmall/newGoodDisplay.do?method=view&id=7273918,宏碁 P249 笔记本电脑 i5-7200U /8G/128SSD+1T/DVDRW/940mx 2G独显/14寸/win10操作系统/四年保修（计价单位：台）,宏碁/ACER,P249,14英寸 ,配DDR4 2666 4GB，可扩容至32GB ,2GB  GDDR5,Linux,无 HDD+128G SSD硬盘 SSD,True,329
+4,I5-8250U,1,140,0,5500.0,,便携式计算机 宏碁/ACER TravelMate P2410-8270,,,宏碁/ACER,P2410,14英寸 ,标配DDR4 2666 4GB，可扩容至20GB ,2GB  GDDR5,Linux,无 HDD+128G SSD硬盘 SSD,True,330
+5,I5-7200U,1,143,0,6000.0,,便携式计算机 宏碁/ACER TravelMate P449-9388,,,宏碁/ACER,P449,14英寸 ,标配DDR4 2666 8GB，可扩容至24GB ,2GB  GDDR5,微软专业版,无 HDD+128G SSD硬盘 SSD,True,333
+6,I5-7200U,2,144,0,6000.0,,便携式计算机 宏碁/ACER TravelMate P648-9323,,,宏碁/ACER,P648,14英寸 ,标配DDR4 2666 8GB，可扩容至24GB ,2GB  GDDR3,微软专业版,无 HDD+128G SSD硬盘 SSD,True,334
+7,I5-7200U,1,146,0,6500.0,,便携式计算机 宏碁/ACER TravelMate P449-9352,,,宏碁/ACER,P449,14英寸 ,标配DDR4 2666 8GB，可扩容至24GB,2GB  GDDR5,微软专业版,无 HDD+256G SSD硬盘 SSD,True,336
+8,I5-7200U,2,147,0,6500.0,,便携式计算机 宏碁/ACER TravelMate P648-9293,,,宏碁/ACER,P648,14英寸 ,配DDR4 2666 8GB，可扩容至24GB ,2GB  GDDR3,Linux,无 HDD+256G SSD硬盘 SSD,True,337
+9,I7-7500U,2,148,0,7000.0,,便携式计算机 宏碁/ACER TravelMate P249-8109,,,宏碁/ACER,P249,14英寸,标配DDR4 2666 8GB，可扩容至32GB ,2GB  GDDR5,微软专业版,无 HDD+128G SSD硬盘 SSD,True,338
+10,I7-7500U,2,149,0,7000.0,,便携式计算机 宏碁/ACER TravelMate P648-9321,,,宏碁/ACER,P648,14英寸 ,标配DDR4 2666 8GB，可扩容至24GB ,2GB  GDDR5,微软专业版,无 HDD+128G SSD硬盘 SSD,True,339
+11,I7-8550U,2,150,0,7000.0,,便携式计算机 宏碁/ACER TravelMate X3410-8215,,,宏碁/ACER,X3410,14英寸 ,8GB；可扩容至32GB,2GB  GDDR5,微软专业版,无 HDD+128G SSD硬盘 SSD,True,340
+12,I3-8130U   ,1,151,0,4499.0,,便携式计算机 联想/lenovo K43c-80453,,,联想/lenovo,K43c,14英寸,标配DDR4 2400 4G,集成,DOS,1T HDD+无 SSD,True,341
+13,I3-8130U   ,2,153,0,4499.0,,便携式计算机 联想/lenovo K43c-80422,,,联想/lenovo,K43c,14英寸,标配DDR4 2400 8G,2G独显,DOS,无 HDD+256G SSD,True,343
+14,I7-8550U   ,2,162,0,6999.0,,便携式计算机 联想/lenovo K43c-80084,,,联想/lenovo,K43c,14英寸,标配DDR4 2400 8GB,AMD Radeon 530 2GB GDDR5,DOS,1TB，7200RPM  HDD+256GB SSD,True,352
+15,I3-8130U   ,2,164,0,4499.0,,便携式计算机 联想/ThinkPad L480-524,,,联想/ThinkPad,L480,14英寸,标配DDR4 4GB，可扩容至32GB,集成 Intel HD 620 / UHD 620,WIN10-H,无 HDD+128G SSD,True,354
+16,I7-8500U,2,170,0,6999.0,,便携式计算机 联想/ThinkPad L480-326,,,联想/ThinkPad,L480,14英寸,DDR4 2400 8GB，可扩容至32GB,AMD Radeon RX530 2GB,Win10 Home,无 HDD+128GB SSD,True,360
+17,I3-8130U,2,171,0,4399.0,,便携式计算机 惠普/HP HP 348 G4(i3-8130u),,,惠普/HP,348 G4,14英寸,标配DDR4 2400 8GB，可扩容至32GB ,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，7200RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,361
+18,I3-8130U,2,173,0,4072.0,,便携式计算机 戴尔/DELL Latitude 3490 配置1,,,戴尔/DELL,3490,14,4G,无,linux,集成 HDD+无 SSD,True,363
+19,I3-8130U,2,174,0,4490.0,,便携式计算机 戴尔/DELL Latitude 5290 配置1,,,戴尔/DELL,5290,"12.5"" ",4G,无,LINUX,1T HDD+无 SSD,True,364
+20,I3-8130U,2,175,0,4490.0,,便携式计算机 戴尔/DELL Latitude 5490 配置1,,,戴尔/DELL,5490,14,4G,无,LINUX,1T HDD+无 SSD,True,365
+21,I3-8130U,2,178,0,4990.0,,便携式计算机 戴尔/DELL Latitude 5490 配置2,,,戴尔/DELL,5490,14.0,4G,无,Ubuntu Linux 16.04,1T HDD+无 SSD,True,368
+22,I3-8130U,1,190,True,4499.0,"4,788.00",便携式计算机 惠普/HP HP ProBook 430 G5(i3-8130u),http://www.szzfcg.cn/newmall/newGoodDisplay.do?method=view&id=7274247,HP ProBook 430 G5-18010000059/i3-8130U/13.3寸/4G内存/500G硬盘/集成显卡/无光驱/无系统/包鼠,惠普/HP,430 G5,14英寸,标配DDR4 2400 4GB，可扩容至32GB,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，5400RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,380
+23,I3-8130U,1,190,True,4499.0,"4,464.00",便携式计算机 惠普/HP HP ProBook 430 G5(i3-8130u),http://www.szzfcg.cn/newmall/newGoodDisplay.do?method=view&id=5935972,惠普（HP） HP ProBook 430 G5-18010000059 笔记本电脑 Intel酷睿I3-8130U 2.2GHz双核/4G-DDR4内存/500G SATA硬盘/集显/无光驱/DOS/13.3寸/包鼠/一年保修 银色,惠普/HP,430 G5,14英寸,标配DDR4 2400 4GB，可扩容至32GB,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，5400RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,380
+24,I5-8250U,2,191,0,4899.0,,便携式计算机 惠普/HP HP 348 G4(i5-8250u+集成显卡),,,惠普/HP,348 G4,14英寸,标配DDR4 2400 4GB，可扩容至32GB,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，7200RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,381
+25,I5-8250U,2,194,0,5399.0,,便携式计算机 惠普/HP HP 348 G4(i5-8250u+2G独显),,,惠普/HP,348 G4,14英寸,标配DDR4 2400 4GB，可扩容至32GB,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，7200RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,384
+26,I5-8250U,2,196,0,5899.0,,便携式计算机 惠普/HP HP 348 G4(i5-8250u+2G独显+8G内存),,,惠普/HP,348 G4,14英寸,标配DDR4 2400 4GB，可扩容至32GB,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，7200RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,386
+27,I5-8250U,2,198,0,6399.0,,便携式计算机 惠普/HP HP 348 G4(i5-8250u+2G独显+8G内存+128G+1T双硬盘),,,惠普/HP,348 G4,14英寸,标配DDR4 2400 4GB，可扩容至32GB,Intel 集成高清显卡,Linux(含Neokylin 光盘),1TB，7200RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,388
+28,I7-8550U,2,201,0,6899.0,,便携式计算机 惠普/HP HP 348 G4( i7-8550u),,,惠普/HP,348 G4,14英寸,标配DDR4 2400 8GB，可扩容至32GB,Nvidia MX110 2G  GDDR5 ,Linux(含Neokylin 光盘),1TB，7200RPM  HDD+或128GB M.2 SSD(与1T SATA硬盘可二选一) SSD,True,391
+29,I3-8130U,2,206,0,4450.0,,便携式计算机 华硕/ASUS P1440UA813049X2,,,华硕/ASUS,P1440UA813049X2,14英寸,标配DDR4 2400MHz 4G 可升级至16G,无,神州网信（中国政府版）,1T HDD+无 SSD,True,396
+30,I5-8250U,2,207,0,4950.0,,便携式计算机 华硕/ASUS P1440UA825049X2,,,华硕/ASUS,P1440UA825049X2,14英寸,"DDR4 2400MHz 4G,可升级至16G",否,神州网信（中国政府版）,1TB HDD+无，可拓展M.2 SSD,True,397
+31,I5-8250U,2,208,0,5450.0,,便携式计算机 华硕/ASUS P1440UF825049S2,,,华硕/ASUS,P1440UF825049S2,14英寸,"DDR4 2400MHz 4G,可升级至16G",Nvidia MX130+2G GDDR5  ,神州网信（中国政府版）,1TB HDD+无，可拓展M.2 SSD,True,398
+32,I5-8250U,2,209,0,5950.0,,便携式计算机 华硕/ASUS P1440UF825089S2,,,华硕/ASUS,P1440UF825089S2,14英寸,"DDR4 2400MHz 8G,可升级至16G",Nvidia MX130+2G GDDR5 ,神州网信（中国政府版）,1TB HDD+无，可拓展M.2 SSD,True,399
+33,I5-8250U,2,210,0,6450.0,,便携式计算机 华硕/ASUS P1440UF825B89S2,,,华硕/ASUS,P1440UF825B89S2,14英寸,"DDR4 2400MHz 8G,可升级至16G",Nvidia MX130+2G GDDR5 ,神州网信（中国政府版）,无 HDD+256G SSD SSD,True,400
+34,I7-8550U,2,211,0,6950.0,,便携式计算机 华硕/ASUS P1440UF855089S2,,,华硕/ASUS,P1440UF855089S2,14英寸,"DDR4 2400MHz 8G,可升级至16G",Nvidia MX130+2G GDDR5 ,神州网信（中国政府版）,1TB HDD+无，可拓展M.2 SSD,True,401

bijiben_hubie_anhui_rate.csv

+,id,url,产品型号,price2,rate
+0,133,,,,
+1,134,,,,
+2,135,,,,
+3,136,,,,
+4,137,http://www.huiemall.com/HeFei/productdetail.html?productguid=918e271b-7f2a-4c03-ab2d-96dfc7fd7254,宏碁笔记本电脑TravelMateP2410I5-8250U/8G/256G+1T/14寸,4390.0,0.134
+5,138,,,,
+6,139,,,,
+7,140,http://www.huiemall.com/HeFei/productdetail.html?productguid=d4cde4bc-ab45-4f1b-bf04-4bd74c320da3,宏碁i5-8250U处理器TravelMateP2410-82198GB/1T+128SSD/2GB独显/14,4799.0,0.17472727272727273
+8,141,,,,
+9,142,,,,
+10,143,,,,
+11,144,,,,
+12,145,,,,
+13,146,,,,
+14,147,,,,
+15,148,,,,
+16,149,,,,
+17,150,,,,
+18,151,,,,
+19,152,http://www.huiemall.com/HeFei/productdetail.html?productguid=17784ead-a1c1-4ad5-aa61-6d0222ef1270,联想笔记本电脑昭阳K43c-80I5-8250U/8G/512G SSD/2G独显,4459.0,0.10402080416083216
+20,153,,,,
+21,154,http://www.huiemall.com/HeFei/productdetail.html?productguid=17784ead-a1c1-4ad5-aa61-6d0222ef1270,联想笔记本电脑昭阳K43c-80I5-8250U/8G/512G SSD/2G独显,4459.0,0.12002400480096019
+22,155,http://www.huiemall.com/HeFei/productdetail.html?productguid=d968dfd9-b0e4-47c5-8faf-4a126f6bc36f,联想笔记本电脑昭阳K43c-80031I5-8250U/4G/500G/2G/W10,3799.0,0.3127841425713766
+23,156,http://www.huiemall.com/HeFei/productdetail.html?productguid=d968dfd9-b0e4-47c5-8faf-4a126f6bc36f,联想笔记本电脑昭阳K43c-80031I5-8250U/4G/500G/2G/W10,3799.0,0.29096199308965265
+24,157,http://www.huiemall.com/HeFei/productdetail.html?productguid=deacc5e3-fe6f-4286-a589-1fd31ca33d02,联想14英寸高端商务办公手提笔记本电脑轻薄便携昭阳K43C-80i5-8250U 8G 1T+256G 2G独显,4279.0,0.3100516752792132
+25,160,http://www.huiemall.com/HeFei/productdetail.html?productguid=04cb00d8-d3dd-444d-8b04-dacd73ffe7e5,联想昭阳 商用笔记本 14英寸 K43c I5-8250U 8G 2G独显 WIN10,4189.0,0.2846591783351285
+26,162,,,,
+27,163,http://www.huiemall.com/HeFei/productdetail.html?productguid=da2b9f29-dbc6-4429-b48c-bc8d10adef35,联想ThinkpadL48020LTA1YMCDI5-8250U/4G/500G+128G/2G,4399.0,0.07201440288057612
+28,164,,,,
+29,166,http://www.huiemall.com/HeFei/productdetail.html?productguid=da2b9f29-dbc6-4429-b48c-bc8d10adef35,联想ThinkpadL48020LTA1YMCDI5-8250U/4G/500G+128G/2G,4399.0,0.1563920712856883
+30,167,http://www.huiemall.com/HeFei/productdetail.html?productguid=da2b9f29-dbc6-4429-b48c-bc8d10adef35,联想ThinkpadL48020LTA1YMCDI5-8250U/4G/500G+128G/2G,4399.0,0.2067011168528088
+31,168,http://www.huiemall.com/HeFei/productdetail.html?productguid=da2b9f29-dbc6-4429-b48c-bc8d10adef35,联想ThinkpadL48020LTA1YMCDI5-8250U/4G/500G+128G/2G,4399.0,0.1692568087398061
+32,169,http://www.huiemall.com/HeFei/productdetail.html?productguid=da2b9f29-dbc6-4429-b48c-bc8d10adef35,联想ThinkpadL48020LTA1YMCDI5-8250U/4G/500G+128G/2G,4399.0,0.22157254962301892
+33,170,,,,
+34,171,,,,
+35,173,,,,
+36,174,,,,
+37,175,,,,
+38,176,http://www.huiemall.com/HeFei/productdetail.html?productguid=c6cf8928-7930-4ded-b859-85d5f4fb478f,戴尔14英寸商用商务办公便携笔记本电脑Latitude3490i5-8250U/4G/1T/集显/WIN10,3798.0,0.15070140280561123
+39,177,http://www.huiemall.com/HeFei/productdetail.html?productguid=b8405ffe-5425-40bd-bf09-13fbd2fc820e,戴尔12.5英寸商用笔记本Latitude5290230025(i5-8250U 8G 256G固态 W10）,4789.0,-0.023847695390781562
+40,178,,,,
+41,179,http://www.huiemall.com/HeFei/productdetail.html?productguid=c6cf8928-7930-4ded-b859-85d5f4fb478f,戴尔14英寸商用商务办公便携笔记本电脑Latitude3490i5-8250U/4G/1T/集显/WIN10,3798.0,0.1544293695131684
+42,180,http://www.huiemall.com/HeFei/productdetail.html?productguid=a2bfee30-ff1b-4fe1-81b7-f79d79683283,戴尔14英寸商用商务办公便携笔记本电脑W10Latitude3490I5-8250U/8GB/128G+1T/2G独显,4298.0,0.22872971903442818
+43,181,http://www.huiemall.com/HeFei/productdetail.html?productguid=54ff8e30-6577-4fd9-a4f1-5b7141392034,戴尔14英寸笔记本电脑Latitude 5490 230015（I5-8250U 8G 1T 2G W10）,4297.0,0.3010928961748634
+44,182,http://www.huiemall.com/HeFei/productdetail.html?productguid=a2bfee30-ff1b-4fe1-81b7-f79d79683283,戴尔14英寸商用商务办公便携笔记本电脑W10Latitude3490I5-8250U/8GB/128G+1T/2G独显,4298.0,0.26198023494312883
+45,183,http://www.huiemall.com/HeFei/productdetail.html?productguid=a2bfee30-ff1b-4fe1-81b7-f79d79683283,戴尔14英寸商用商务办公便携笔记本电脑W10Latitude3490I5-8250U/8GB/128G+1T/2G独显,4298.0,0.2566142460684551
+46,184,http://www.huiemall.com/HeFei/productdetail.html?productguid=54ff8e30-6577-4fd9-a4f1-5b7141392034,戴尔14英寸笔记本电脑Latitude 5490 230015（I5-8250U 8G 1T 2G W10）,4297.0,0.3393989983305509
+47,185,http://www.huiemall.com/HeFei/productdetail.html?productguid=a2bfee30-ff1b-4fe1-81b7-f79d79683283,戴尔14英寸商用商务办公便携笔记本电脑W10Latitude3490I5-8250U/8GB/128G+1T/2G独显,4298.0,0.24470876333741473
+48,186,http://www.huiemall.com/HeFei/productdetail.html?productguid=a2bfee30-ff1b-4fe1-81b7-f79d79683283,戴尔14英寸商用商务办公便携笔记本电脑W10Latitude3490I5-8250U/8GB/128G+1T/2G独显,4298.0,0.2371024734982332
+49,187,http://www.huiemall.com/HeFei/productdetail.html?productguid=54ff8e30-6577-4fd9-a4f1-5b7141392034,戴尔14英寸笔记本电脑Latitude 5490 230015（I5-8250U 8G 1T 2G W10）,4297.0,0.33482280431432976
+50,188,http://www.huiemall.com/HeFei/productdetail.html?productguid=8bbd8e0e-3c9b-4664-96d9-06603742d234,戴尔商用笔记本Latitude3490230050i7-8550U/8G/128G+1T/14英寸,5350.0,0.23100537221795855
+51,189,http://www.huiemall.com/HeFei/productdetail.html?productguid=8bbd8e0e-3c9b-4664-96d9-06603742d234,戴尔商用笔记本Latitude3490230050i7-8550U/8G/128G+1T/14英寸,5350.0,0.20520457751998747
+52,190,,,,
+53,191,,,,
+54,194,,,,
+55,196,,,,
+56,198,,,,
+57,201,,,,
+58,206,,,,
+59,207,,,,
+60,208,,,,
+61,209,,,,
+62,210,,,,
+63,211,,,,

bijiben_hubie_db_rate.csv

+,id,产品编码,产品型号,指数价,指数价格差价率,电商平均价,电商价格差价率,政采平均价,政采价格差价率
+0,133,,,,,,,,
+1,134,,,,,,,,
+2,135,,,,,,,,
+3,136,a101003411223,宏碁 ACERTRAVELMATEP24914英寸商用笔记本I5-7200U4G1T940MX2G独显WIN10三年保修首年上门,3899.0,0.2082,3899.0,0.2082,,
+4,137,,,,,,,,
+5,138,a101003411237,宏碁 ACER TMP449-MG-TMP449-G2-MG-56L1 笔记本,4999.0,0.0882,4999.0,0.0882,,
+6,139,a101003411223,宏碁 ACERTRAVELMATEP24914英寸商用笔记本I5-7200U4G1T940MX2G独显WIN10三年保修首年上门,3899.0,0.18927272727272726,3899.0,0.18927272727272726,,
+7,140,,,,,,,,
+8,141,a101003411237,宏碁 ACER TMP449-MG-TMP449-G2-MG-56L1 笔记本,4999.0,0.08018181818181819,4999.0,0.08018181818181819,,
+9,142,a101003411223,宏碁 ACERTRAVELMATEP24914英寸商用笔记本I5-7200U4G1T940MX2G独显WIN10三年保修首年上门,3899.0,0.23683333333333334,3899.0,0.23683333333333334,,
+10,143,a101003411237,宏碁 ACER TMP449-MG-TMP449-G2-MG-56L1 笔记本,4999.0,0.13683333333333333,4999.0,0.13683333333333333,,
+11,144,,,,,,,,
+12,145,a101003411223,宏碁 ACERTRAVELMATEP24914英寸商用笔记本I5-7200U4G1T940MX2G独显WIN10三年保修首年上门,3899.0,0.24938461538461537,3899.0,0.24938461538461537,,
+13,146,a101003411237,宏碁 ACER TMP449-MG-TMP449-G2-MG-56L1 笔记本,4999.0,0.1570769230769231,4999.0,0.1570769230769231,,
+14,147,,,,,,,,
+15,148,,,,,,,,
+16,149,,,,,,,,
+17,150,,,,,,,,
+18,151,a101005163598,联想 LENOVO 昭阳 K43C-80（I3-8130U/4GB/128GB SSD/2GB独显/WIN10HB/14英寸）笔记本,,,,,,
+19,152,a101005163572,联想 LENOVO 昭阳 K43C-80（I5-8250U/4GB/500GB/2GB独显/WIN10HB/14英寸）笔记本,3867.69,0.2503120624124825,,,,
+20,153,a101005163598,联想 LENOVO 昭阳 K43C-80（I3-8130U/4GB/128GB SSD/2GB独显/WIN10HB/14英寸）笔记本,,,,,,
+21,154,a101005163588,联想 LENOVO 昭阳 K43C-80（I5-8250U/4GB/1TB/集成显卡/WIN10HB/14英寸）笔记本,3912.48,0.19334266853370674,,,,
+22,155,a101005163530,联想 LENOVO 昭阳 K43C-80（I5-8250U/4GB/1TB/2GB独显/WIN10HB/14英寸）笔记本,4181.76,0.23954173486088376,,,,
+23,156,a101005163379,联想 LENOVO 昭阳 K43C-80（I5-8250U/8GB/1TB/2GB独显/WIN10HB/14英寸）笔记本,4394.79,0.20080196399345338,,,,
+24,157,a101005163379,联想 LENOVO 昭阳 K43C-80（I5-8250U/8GB/1TB/2GB独显/WIN10HB/14英寸）笔记本,4394.79,0.2574112352058677,,,,
+25,158,a101005163382,联想 LENOVO 昭阳 K43C-80（I5-8250U/8GB/1TB+128GB SSD/2GB独显/WIN10HB/14英寸）笔记本,4706.21,0.2155009168194699,,,,
+26,159,a101005163382,联想 LENOVO 昭阳 K43C-80（I5-8250U/8GB/1TB+128GB SSD/2GB独显/WIN10HB/14英寸）笔记本,4706.21,0.2758562855823973,,,,
+27,160,a101005163380,联想 LENOVO 昭阳 K43C-80（I5-8250U/8GB/512GB SSD/2GB独显/WIN10HB/14英寸）笔记本,4999.32,0.20921372518849057,,,,
+28,161,a101005163393,联想 LENOVO 昭阳 K43C-80（I7-8550U/8GB/1TB/2GB独显/WIN10HB/14英寸）笔记本,5314.99,0.2320345763680526,,,5180.0,0.25132161737391057
+29,162,a101005163384,联想 LENOVO 昭阳 K43C-80（I7-8550U/8GB/1TB+256GB SSD/2GB独显/WIN10HB/14英寸）笔记本,5821.03,0.1683054722103158,,,,
+30,163,a101000934811,THINKPAD L480 K3CD（I5-8250U/8GB/1TB/2GB独显/WIN10HB）3年 笔记本,8670.0,-0.7223444688937788,8670.0,-0.7223444688937788,,
+31,164,,,,,,,,
+32,165,a101000934572,THINKPAD L380 F4CD（I3-8130U/4GB/256GB SSD/集成显卡/DOS或LINUX）笔记本,5000.0,-0.08913091798177372,,,5000.0,-0.08913091798177372
+33,166,a101000934811,THINKPAD L480 K3CD（I5-8250U/8GB/1TB/2GB独显/WIN10HB）3年 笔记本,8670.0,-0.5657392253136934,8670.0,-0.5657392253136934,,
+34,167,a101000934811,THINKPAD L480 K3CD（I5-8250U/8GB/1TB/2GB独显/WIN10HB）3年 笔记本,8670.0,-0.4552425404234039,8670.0,-0.4552425404234039,,
+35,168,a101000934260,THINKPAD L480 P2CD（I5-8250U/8GB/1TB+128GB SSD/2GB独显/WIN10HB）笔记本,6560.4,-0.009447607324203668,,,,
+36,169,a101000934735,THINKPAD L480 P3CD（I5-8250U/4GB/500GB+128GB SSD/2GB独显/WIN10HB）笔记本,5898.9,0.06771811047853521,,,,
+37,170,,,,,,,,
+38,171,,,,,,,,
+39,172,a101003612395,惠普 HP PROBOOK 440G5（I3-8130U/4GB/1TB/2GB独显/WIN10PRO）笔记本,5580.0,-0.10691264725494555,,,5580.0,-0.10691264725494555
+40,173,,,,,,,,
+41,174,,,,,,,,
+42,175,,,,,,,,
+43,176,a101002212829,戴尔 DELL LATITUDE E3490（I5-8250U/8GB/500GB/集成显卡/DOS或LINUX）1年 笔记本,5599.0,-0.1340681362725451,5599.0,-0.1340681362725451,,
+44,177,a101002212865,戴尔 DELL LATITUDE E5290（I5-8250U/4GB/1TB/集成显卡/DOS或LINUX）3年 笔记本,6699.0,-0.34248496993987976,6699.0,-0.34248496993987976,,
+45,178,,,,,,,,
+46,179,a101002212829,戴尔 DELL LATITUDE E3490（I5-8250U/8GB/500GB/集成显卡/DOS或LINUX）1年 笔记本,5599.0,-0.1290901835594573,5599.0,-0.1290901835594573,,
+47,180,a101002212829,戴尔 DELL LATITUDE E3490（I5-8250U/8GB/500GB/集成显卡/DOS或LINUX）1年 笔记本,5599.0,-0.13157894736842105,5599.0,-0.13157894736842105,,
+48,181,a101002212646,戴尔 DELL LATITUDE E5490（I5-8250U/4GB/1TB/WIN10HB）3年 笔记本,4991.77,0.09075227686703088,5659.0,-0.030783242258652095,,
+49,182,a101002212829,戴尔 DELL LATITUDE E3490（I5-8250U/8GB/500GB/集成显卡/DOS或LINUX）1年 笔记本,5599.0,-0.07756852507924669,5599.0,-0.07756852507924669,,
+50,183,a101002212818,戴尔 DELL LATITUDE E3490（I5-8250U/4GB/500GB/2GB独显/DOS或LINUX）3年 笔记本,5599.0,-0.009990749306197965,5599.0,-0.009990749306197965,,
+51,184,a101002212646,戴尔 DELL LATITUDE E5490（I5-8250U/4GB/1TB/WIN10HB）3年 笔记本,4991.77,0.14661602671118523,5659.0,0.03522537562604341,,
+52,185,a101002212844,戴尔 DELL LATITUDE E3490（I5-8250U/8GB/256GB SSD/集成显卡/DOS或LINUX）3年 笔记本,6699.0,-0.1717684100052475,6699.0,-0.1717684100052475,,
+53,186,a101002212844,戴尔 DELL LATITUDE E3490（I5-8250U/8GB/256GB SSD/集成显卡/DOS或LINUX）3年 笔记本,6699.0,-0.1835689045936396,6699.0,-0.1835689045936396,,
+54,187,a101002212860,戴尔 DELL LATITUDE E5490（I5-8250U/4GB/500GB/2GB独显/DOS或LINUX）3年 笔记本,6699.0,-0.05685670261941449,6699.0,-0.05685670261941449,,
+55,188,a101002212847,戴尔 DELL LATITUDE E3490（I7-8550U/4GB/1TB/2GB独显/DOS或LINUX）1年 笔记本,6699.0,0.030084420567920184,6699.0,0.030084420567920184,,
+56,189,a101002212847,戴尔 DELL LATITUDE E3490（I7-8550U/4GB/1TB/2GB独显/DOS或LINUX）1年 笔记本,6699.0,0.0,6699.0,0.0,,
+57,190,,,,,,,,
+58,191,a101003612389,惠普 HP PROBOOK 348G4（I5-8250U/8GB/1TB+128GB SSD/2GB独显/DOS或LINUX）笔记本,5900.0,-0.07777097366809553,,,5900.0,-0.07777097366809553
+59,192,a101003612399,惠普 HP PROBOOK 430G5（I5-8250U/4GB/256GB SSD/集成显卡/DOS或LINUX）笔记本,5680.0,-0.20424084816963392,,,5680.0,-0.20424084816963392
+60,193,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,-0.12822564512902582,,,5800.0,-0.12822564512902582
+61,194,a101003612389,惠普 HP PROBOOK 348G4（I5-8250U/8GB/1TB+128GB SSD/2GB独显/DOS或LINUX）笔记本,5900.0,0.022041118725689944,,,5900.0,0.022041118725689944
+62,195,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,-0.02564102564102564,,,5800.0,-0.02564102564102564
+63,196,a101003612389,惠普 HP PROBOOK 348G4（I5-8250U/8GB/1TB+128GB SSD/2GB独显/DOS或LINUX）笔记本,5900.0,0.10493303949822004,,,5900.0,0.10493303949822004
+64,197,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,0.059843307217869644,,,5800.0,0.059843307217869644
+65,198,a101003612389,惠普 HP PROBOOK 348G4（I5-8250U/8GB/1TB+128GB SSD/2GB独显/DOS或LINUX）笔记本,5900.0,0.1748710736052508,,,5900.0,0.1748710736052508
+66,199,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,0.13217418064317588,,,5800.0,0.13217418064317588
+67,200,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,0.13217418064317588,,,5800.0,0.13217418064317588
+68,201,,,,,,,,
+69,202,a101003612235,惠普 HP PROBOOK 440G5（I5-8250U/4GB/1TB/2GB独显/WIN10HB）笔记本,4663.89,0.3336348049721388,,,6180.0,0.11701671667381054
+70,203,a101003612235,惠普 HP PROBOOK 440G5（I5-8250U/4GB/1TB/2GB独显/WIN10HB）笔记本,4663.89,0.32506215173596226,,,6180.0,0.10844406343763395
+71,204,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,0.059843307217869644,,,5800.0,0.059843307217869644
+72,205,a101003612234,惠普 HP PROBOOK 440G5（I5-8250U/4GB/256GB SSD/2GB独显/WIN10HB）笔记本,5800.0,-0.02564102564102564,,,5800.0,-0.02564102564102564
+73,206,,,,,,,,
+74,207,,,,,,,,
+75,208,,,,,,,,
+76,209,,,,,,,,
+77,210,,,,,,,,
+78,211,,,,,,,,

bijiben_hubie_fujian_rate.csv

+,id,url,产品型号,price2,rate
+0,133,,,,
+1,134,,,,
+2,135,,,,
+3,136,http://120.35.30.176/shopping/goods_2c9be5956ab05cbe016ac3db587c6fa5.htm,宏碁/acer TravelMate P249 7086 便携式计算机,5308.0,0.1904
+4,137,http://120.35.30.176/shopping/goods_2c9be5956a541f6a016a619a98c77235.htm,宏碁/acer TravelMate P2410 8282 便携式计算机,4900.0,0.108
+5,138,,,,
+6,139,,,,
+7,140,,,,
+8,141,,,,
+9,142,http://120.35.30.176/shopping/goods_2c9be5956ab05cbe016ac3db587c6fa5.htm,宏碁/acer TravelMate P249 7086 便携式计算机,5308.0,0.222
+10,143,,,,
+11,144,,,,
+12,145,http://120.35.30.176/shopping/goods_2c9be5956ab05cbe016ac3db587c6fa5.htm,宏碁/acer TravelMate P249 7086 便携式计算机,5308.0,0.2356923076923077
+13,146,,,,
+14,147,,,,
+15,148,,,,
+16,149,,,,
+17,150,,,,
+18,151,http://120.35.30.176/shopping/goods_2c9be5956c406d64016c6a06629a711f.htm,联想/Lenovo 昭阳K43c-80239 便携式计算机,5999.0,-0.5290064458768615
+19,152,,,,
+20,153,,,,
+21,154,,,,
+22,155,,,,
+23,156,,,,
+24,157,http://120.35.30.176/shopping/goods_2c9be595686e27a301687897ba6c3e54.htm,联想/Lenovo 昭阳K43c-80509 便携式计算机,6490.0,-0.09184864144024003
+25,160,http://120.35.30.176/shopping/goods_2c9be5956939539e0169478ddc3c2e5a.htm,联想/Lenovo 昭阳K43c-80508 便携式计算机,5990.0,0.0567779658408986
+26,162,,,,
+27,163,http://120.35.30.176/shopping/goods_2c9be5956c406d64016c89cf8c1e48b4.htm,联想/Lenovo ThinkPad L480-246 便携式计算机,5998.0,-0.22784556911382275
+28,164,,,,
+29,166,http://120.35.30.176/shopping/goods_2c9be5956c406d64016c89cf8c1e48b4.htm,联想/Lenovo ThinkPad L480-246 便携式计算机,5998.0,-0.11620294599018004
+30,167,http://120.35.30.176/shopping/goods_2c9be5956a2533d3016a29277c3c0121.htm,联想/Lenovo ThinkPad L480-247 便携式计算机,6999.0,-0.2100350058343057
+31,168,http://120.35.30.176/shopping/goods_2c9be5956c406d64016c89cf8c1e48b4.htm,联想/Lenovo ThinkPad L480-246 便携式计算机,5998.0,-0.06139406062471149
+32,169,,,,
+33,170,,,,
+34,171,,,,
+35,173,,,,
+36,174,,,,
+37,175,,,,
+38,176,,,,
+39,177,,,,
+40,178,,,,
+41,179,,,,
+42,180,,,,
+43,181,http://120.35.30.176/shopping/goods_7F3F0F4E0B2740CCE0531138A8C0688B.htm,戴尔/DELL Latitude 5490 230047 便携式计算机,9980.0,-0.7049180327868853
+44,182,,,,
+45,183,,,,
+46,184,http://120.35.30.176/shopping/goods_7F3F0F4E0B2740CCE0531138A8C0688B.htm,戴尔/DELL Latitude 5490 230047 便携式计算机,9980.0,-0.5826377295492488
+47,185,,,,
+48,186,,,,
+49,187,http://120.35.30.176/shopping/goods_7F3F0F4E0B2740CCE0531138A8C0688B.htm,戴尔/DELL Latitude 5490 230047 便携式计算机,9980.0,-0.5161787365177196
+50,188,http://120.35.30.176/shopping/goods_2c9be5956c406d64016c8a828d710e05.htm,戴尔/DELL Latitude 3490 230088 便携式计算机,6980.0,0.0422102839600921
+51,189,,,,
+52,190,,,,
+53,191,,,,
+54,194,,,,
+55,196,,,,
+56,198,,,,
+57,201,,,,
+58,206,,,,
+59,207,,,,
+60,208,,,,
+61,209,,,,
+62,210,,,,
+63,211,,,,

bijiben_hubie_jingdong_rate.csv

+,id,url,产品型号,price2,rate
+0,133,,,,
+1,134,,,,
+2,135,,,,
+3,137,,,,
+4,140,,,,
+5,144,,,,
+6,147,,,,
+7,148,,,,
+8,149,,,,
+9,150,,,,
+10,151,,,,
+11,152,,,,
+12,153,,,,
+13,154,,,,
+14,155,https://item.jd.com/100002727261.html,联想昭阳K43c-80(I5-8250U/4G/IT/集显/W10 Home/含鼠标/含三年上门/14寸)笔记本电脑第2档东电,6533.0,-0.06073831605746499
+15,156,https://item.jd.com/100002727261.html,联想昭阳K43c-80(I5-8250U/4G/IT/集显/W10 Home/含鼠标/含三年上门/14寸)笔记本电脑第2档东电,6533.0,-0.08256046553918894
+16,157,https://item.jd.com/100002727261.html,联想昭阳K43c-80(I5-8250U/4G/IT/集显/W10 Home/含鼠标/含三年上门/14寸)笔记本电脑第2档东电,,
+17,158,https://item.jd.com/100002727261.html,联想昭阳K43c-80(I5-8250U/4G/IT/集显/W10 Home/含鼠标/含三年上门/14寸)笔记本电脑第2档东电,,
+18,159,https://item.jd.com/100002727261.html,联想昭阳K43c-80(I5-8250U/4G/IT/集显/W10 Home/含鼠标/含三年上门/14寸)笔记本电脑第2档东电,6533.0,-0.023695953223572857
+19,160,https://item.jd.com/100002727261.html,联想昭阳K43c-80(I5-8250U/4G/IT/集显/W10 Home/含鼠标/含三年上门/14寸)笔记本电脑第2档东电,6533.0,-0.0698569010617018
+20,161,,,,
+21,162,,,,
+22,163,,,,
+23,164,,,,
+24,165,,,,
+25,166,,,,
+26,167,,,,
+27,168,,,,
+28,169,,,,
+29,170,,,,
+30,171,,,,
+31,172,,,,
+32,173,,,,
+33,174,,,,
+34,175,,,,
+35,176,https://item.jd.com/100000458671.html,戴尔（DELL）Latitude3490-i501（i5-8250U Win10 Home 4GB 500G 1年上门）,3799.0,0.24268537074148297
+36,177,https://item.jd.com/6492114.html,戴尔（DELL）Latitude 5290 12.5英寸商用笔记本(i5-8250U 8G 1TB HD Win10H 3年上门),4999.0,0.06232464929859719
+37,178,,,,
+38,179,https://item.jd.com/100000458671.html,戴尔（DELL）Latitude3490-i501（i5-8250U Win10 Home 4GB 500G 1年上门）,3799.0,0.2460095770151636
+39,180,https://item.jd.com/100000458671.html,戴尔（DELL）Latitude3490-i501（i5-8250U Win10 Home 4GB 500G 1年上门）,3799.0,0.24040364068064898
+40,181,,,,
+41,182,https://item.jd.com/6680729.html,戴尔（DELL）Latitude 3490 14英寸商用笔记本(i5-8250U 4G 1T HD 独显 Win10H 1年上门),3999.0,0.26925228416930824
+42,183,https://item.jd.com/6680729.html,戴尔（DELL）Latitude 3490 14英寸商用笔记本(i5-8250U 4G 1T HD 独显 Win10H 1年上门),3999.0,0.26382978723404255
+43,184,,,,
+44,185,https://item.jd.com/100002103029.html,戴尔 DELL Latitude 3490 14英寸商用笔记本(I5-8250U 4G 500G AMD独显 3C Win10Pro 1年上门),5299.0,0.080111946825258
+45,186,https://item.jd.com/100002103029.html,戴尔 DELL Latitude 3490 14英寸商用笔记本(I5-8250U 4G 500G AMD独显 3C Win10Pro 1年上门),5299.0,0.07084805653710248
+46,187,,,,
+47,188,,,,
+48,189,,,,
+49,190,,,,
+50,191,,,,
+51,192,,,,
+52,193,,,,
+53,194,,,,
+54,195,,,,
+55,196,,,,
+56,197,,,,
+57,198,,,,
+58,199,,,,
+59,200,,,,
+60,201,,,,
+61,202,,,,
+62,203,,,,
+63,204,,,,
+64,205,,,,
+65,206,,,,
+66,207,,,,
+67,208,,,,
+68,209,,,,
+69,210,,,,
+70,211,,,,

crow.py

+# -*- coding: utf-8 -*-
+"""
+Created on Thu Aug  8 09:53:14 2019
+
+@author: admin
+"""
+
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Oct 24 10:04:45 2018
+
+@author: luomin03
+"""
+
+
+
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+
+import pandas as pd
+import numpy as np
+
+chrome_options=Options()
+chrome_options.add_argument('--headless')
+driver=webdriver.Chrome('D:/lm/chromedriver')
+
+
+df=pd.read_excel('hubei.xlsx')
+
+serch_word=df['商品名称']
+
+basic_url = 'http://wssc.hubeigp.gov.cn'
+
+
+def get_key_value(search_word,basic_url):
+    url = basic_url + "/search?utf8=%E2%9C%93&sk=" + search_word
+    driver.get(url)
+    para=dict()
+    para['product_name']=search_word
+    para['flag']=True
+    try:
+       se='#content > div > div.clear > div > ul > li:nth-child(2) > div > div.img > a:nth-child(2) > img'
+    
+       data=driver.find_element_by_css_selector(se)
+       data.click()
+       se='#price_tag'
+       data=driver.find_element_by_css_selector(se)
+       para['price']=data.text
+       se='#tags > li:nth-child(2) > a'
+       data=driver.find_element_by_css_selector(se)
+       data.click()
+       se='#tagContent1 > div > table > tbody > tr > td'
+       data=driver.find_elements_by_css_selector(se)
+       info_array = [info_.text for info_ in data]
+       for i in range(0,len(info_array)):
+           if i%2==0:
+               para[info_array[i]]=info_array[i+1]
+    except:
+        para['flag']=False
+    
+    return para
+    
+    
+   
+    
+search_word = "台式计算机 宏碁/ACER Veriton D730 8160"
+
+#one=get_key_value(search_word,basic_url)
+
+

database.py

+# -*- coding: utf-8 -*-
+"""
+Created on Thu Aug  8 13:11:51 2019
+
+@author: admin
+"""
+
+import pymssql
+import numpy as np
+
+import pandas as pd
+
+import string
+
+punc='！“”：（）；'+string.punctuation
+
+df=pd.read_csv('all_data.csv')
+
+df=df[['product_name','CPU型号','显示器尺寸','内存','独立显卡','机械硬盘','原厂预装操作系统']]
+
+time='20190826'
+
+
+#从数据库里获取产品价格
+def connp():
+    connect=pymssql.connect('123.56.115.207','luomin','lm20190821','zdindex')
+    if connect:
+        print('ll')
+    return connect
+
+connp=connp()
+
+cursorp = connp.cursor() 
+def gen_price():
+    l='goods_id,goods_name,index_price,high_index_price,low_index_price,index_price_wave,entry_avg_price,electricity_avg_price,purchase_avg_price'
+    sql="select "+l+" from zdindex.dbo.zd_week_price where periods="+'\''+time+'\''
+    data=[]
+    try:
+        cursorp.execute(sql)
+        col_name_list = [tuple[0] for tuple in cursorp.description]
+        row=cursorp.fetchall()
+    
+    
+        for i in row:
+            data.append(i)
+        data=pd.DataFrame(data) 
+        data.columns=col_name_list
+    except:
+        print(1)
+        return data
+    return  data
+
+price_data=gen_price()
+connp.close()
+price_data.columns=['产品编码','产品名称','指数价','最高价','最低价','畅销价','实体平均价','电商平均价','政采平均价']
+price_data.to_csv('price_data_db.csv')
+price_data=pd.read_csv('price_data_db.csv').iloc[:,1:]
+
+
+#从数据库里获取产品参数
+def conn():
+    connect=pymssql.connect('123.56.115.207','zgcindex','jiayou2017+2018','ZI_DataBase')
+    if connect:
+        print('ll')
+    return connect
+
+conn=conn()
+
+cursor = conn.cursor() 
+def get_proc_data(pro_name):
+    
+    sql='execute '+ pro_name
+    cursor.execute(sql)
+    col_name_list = [tuple[0] for tuple in cursor.description]
+    row=cursor.fetchall()
+    data=[]
+    for i in row:
+        data.append(i)
+    data=pd.DataFrame(data) 
+    data.columns=col_name_list
+    return  data
+
+def get_view_data(name):
+    sql="select * from vw_productselect where subcategoryname="+'\''+name+'\''
+    sql=sql+" and state=1 and maximumprice is not null"
+    data=[]
+    try:
+        cursor.execute(sql)
+        col_name_list = [tuple[0] for tuple in cursor.description]
+        row=cursor.fetchall()
+    
+    
+        for i in row:
+            data.append(i)
+        data=pd.DataFrame(data) 
+        data.columns=col_name_list
+    except:
+        return data
+    return  data
+    
+    
+
+
+taishiji_data=get_proc_data("InfoSelect_ZC_Value_taishiji0102")
+taishiji_data.to_csv('taishi_config_db.csv')
+
+bijiben_data=get_proc_data("InfoSelect_ZC_Value_bijiben0101")
+bijiben_data.to_csv('bijiben_config_db.csv')
+#yiti_data=get_proc_data("InfoSelect_ZC_Value_yitidiannao0105")
+#yiti_data.to_csv('一体机_db.csv')
+''''
+other_list=['服务器','显示器','摄像机','激光打印机','喷墨打印机','投影机','复印机','速印机','传真机','扫描仪','针式打印机','空调','多功能一体机']
+other_lis1t=['服务器','液晶显示器','视频设备','激光打印机','喷墨打印机','投影仪','复印机','速印机','传真机','扫描仪','针式打印机','空调机','多功能一体机']
+for i in other_list:
+    data_i=get_view_data(i)
+    name=i+'_db.csv'
+    data_i.to_csv(name,encoding='utf-8')
+
+def get_CPU(cpu):
+    try:
+        split_list=cpu.split(" ")
+    except:
+        return cpu
+    a=''
+    for i in split_list:
+        if '\u4e00' <= i <= '\u9fff':
+            continue
+        else :
+            
+            u=i.upper()
+            if u != 'INTEL'and u != 'CORE' and u!='AMD':
+                if len(a)==0:
+                    a=a+u
+                else:
+                    a=a+" "+u
+    return a
+                
+
+def gen_type(name,pinmu,logo):
+    name=name.upper()
+    if '（' in name:
+        name=name.split('（')[0]
+    if '(' in name:
+        name=name.split('(')[0]
+    if '：' in name:
+        name=name.split('：')[0]
+    if pinmu in name:
+        if(len(name.split(pinmu)[0])==0):
+            name=name.split(pinmu)[1]
+        name=name.split(pinmu)[0]
+        
+    s_list=name.split(' ')
+    stype=''
+    index=0
+    for i in s_list:
+        if i in logo or i=='PRO':
+            continue
+        else:
+            
+            s=''
+            for c in i:
+                if '\u4e00' <= c <= '\u9fff' or (c in punc and c!='-') :
+                    continue
+                else :
+                    s=s+c
+            if len(s)>0:
+                
+                stype=stype+s+' '
+                index=index+1
+            if index==2:
+                break
+    return stype
+                
+
+                
+data=[]
+for i in other_list:
+    
+    f=open(i+'_db.csv','rb')
+    index=0
+    while True:
+                if index==209:
+                    a=1
+                line = f.readline()
+                if not line :
+                   
+                    break
+                else:
+                    index=index+1
+                    if index==1:
+                        continue
+                    
+                    try:
+#             print(line)
+#             print(line.decode('utf8'))
+                        line=line.decode('utf8')
+                        da=str(line).split(',')
+                        d=[]
+                       
+                        d=[da[3],da[5],da[7],da[8]]
+                        stype=gen_type(d[3],d[0],d[1])
+                        d.append(stype)
+                        data.append(d)
+            #为了暴露出错误，最好此处不print
+                    except:
+                        print(str(line))
+
+
+  
+data=pd.DataFrame(data)
+data.columns=['品目','品牌','商品编码','产品名称','型号']
+data.to_csv('other.csv')
+'''
+
+
+#匹配价格和参数
+def match_config_price(config,price):
+    columns=list(config.columns)+list(price.columns[1:])
+    config=np.array(config)
+    price=np.array(price)
+    data=[]
+    for i in config:
+        a=1
+        for j in price:
+           
+            if i[0]==j[0]:
+                data.append(list(i)+list(j[1:]))
+                a=0
+                break
+        if a==1:
+            data.append(list(i))
+    
+    data=pd.DataFrame(data)
+    data.columns=columns
+    return data           
+
+def gen_config_price():
+    
+    taishi=pd.read_csv('taishi_config_db.csv').iloc[:,1:] 
+    taishi_data=match_config_price(taishi,price_data)
+    taishi_data.to_csv('taishi_data_db.csv')
+    bijiben=pd.read_csv('bijiben_config_db.csv').iloc[:,1:] 
+    bijiben_data=match_config_price(bijiben,price_data)
+    bijiben_data.to_csv('bijiben_data_db.csv')
+    '''
+    other=pd.read_csv('other.csv').iloc[:,1:] 
+    other=other[['商品编码','品目', '品牌', '产品名称', '型号']]
+    other_data=match_config_price(other,price_data)
+    other_data.to_csv('other_data_db.csv')
+    #return taishi_data,bijiben_data,other_data
+    '''
+    return bijiben_data,bijiben_data,bijiben_data
+
+price_data=pd.read_csv('price_data_db.csv').iloc[:,1:]   
+a,b,c=gen_config_price()  
+
+
+
+'''
+#从数据库中获取型号字段
+def conn():
+    connect=pymssql.connect('123.56.115.207','zgcindex','jiayou2017+2018','ZI_DataBase')
+    if connect:
+        print('ll')
+    return connect
+
+conn=conn()
+
+cursor = conn.cursor() 
+
+
+def gen_other_data(name):
+    
+    sql="select a.productcode,b.subtitle '参数项',a.value '参数值' from info_productdetail a join vw_relation_property b on b.subtitleid=a.cfgid where b.subcategoryname="
+    sql=sql+'\''+name+'\''
+    cursor.execute(sql)
+
+    col_name_list = [tuple[0] for tuple in cursor.description]
+    row=cursor.fetchall()
+    data=[]
+    for i in row:
+        data.append(i)
+    
+    other_db=pd.DataFrame(data)
+    other_db.columns=col_name_list
+    other_db=other_db.groupby(by='参数项').get_group('产品型号')
+    return other_db
+
+
+other_list=['激光打印机','喷墨打印机','针式打印机','传真机','多功能一体机']
+
+other_db=pd.DataFrame()
+for i in other_list:
+    sub_db=gen_other_data(i)
+    other_db=pd.concat([other_db,sub_db])
+   
+    
+other_db.to_csv('other_xinghao.csv')    
+conn.close()
+
+#匹配产品型号参数
+other_db=pd.read_csv('other_xinghao.csv').iloc[:,1:]
+
+other_db=other_db.groupby(by='参数项').get_group('产品型号')
+other_db=other_db.rename(columns={"productcode": "商品编码"})
+other_data_db=pd.read_csv('other_data_db.csv').iloc[:,1:]
+#other_data_db=other_data_db.groupby(by='品目').get_group('激光打印机')
+
+new_data=pd.merge(other_db,other_data_db,on='商品编码',how='inner')
+new_data=new_data.rename(columns={"参数值": "产品型号"})
+new_data.to_csv('other_data_xinghao.csv')
+
+'''
\ No newline at end of file

new_wenti_data.csv

+,id,count,产品型号
+0,249,2,P9180
+1,262,1,C833dn
+2,279,2,630KⅡ
+3,280,1,720
+4,281,1,615
+5,282,2,715
+6,283,2,512K
+7,284,2,600
+8,285,2,635K
+9,286,1,650KIII
+10,287,1,750KII
+11,288,1,700KII
+12,289,1,690KIII
+13,290,2,880K
+14,295,1,富士通发票之星
+15,296,1,富士通发票之星
+16,297,1,富士通发票之星
+17,298,1,富士通发票之星
+18,300,1,富士通发票之星
+19,301,1,富士通发票之星
+20,306,1,560K
+21,306,1,560K
+22,308,1,700KII
+23,310,2,160H
+24,311,2,160P
+25,312,2,160S
+26,313,1,550K
+27,314,1,710K
+28,318,2,06KF
+29,403,0,302DNF

other_data_fujian.csv

+,id,mflag,price,price2,url,产品型号,品牌,品目,型号,序号
+0,243,1,1999.0,1860,http://120.35.30.176/shopping/goods_2c9be5956c048aa4016c288eebc52912.htm,佳能/Canon iP110 喷墨打印机,佳能/Canon,喷墨打印机,IP110,433
+1,247,1,799.0,750,http://120.35.30.176/shopping/goods_2c9be595695d740b01696ae327b66553.htm,震旦/AURORA AD200PS 激光打印机,震旦/AURORA,激光打印机,AD200PS,437
+2,249,0,1200.0,,,,中盈/ZONEWIN,激光打印机,P9180,439
+3,262,0,11999.0,,,,OKI,激光打印机,C833dn,452
+4,267,1,1150.0,980,http://120.35.30.176/shopping/goods_7F3F0F4DF74640CCE0531138A8C0688B.htm,联想/Lenovo LJ2405D 激光打印机,联想/lenovo,激光打印机,LJ2405D,457
+5,277,0,1200.0,,,,兄弟/BROTHER,激光打印机,B2000D,467
+6,278,0,1290.0,,,,中盈/ZONEWIN,针式打印机,650KII,468
+7,279,0,1050.0,,,,中盈/ZONEWIN,针式打印机,630KⅡ,469
+8,280,0,1300.0,,,,中盈/ZONEWIN,针式打印机,720,470
+9,281,0,970.0,,,,中盈/ZONEWIN,针式打印机,615,471
+10,282,0,965.0,,,,中盈/ZONEWIN,针式打印机,715,472
+11,283,0,990.0,,,,中盈/ZONEWIN,针式打印机,512K,473
+12,284,0,2480.0,,,,中盈/ZONEWIN,针式打印机,600,474
+13,285,0,980.0,,,,实达/start,针式打印机,635K,475
+14,286,0,1350.0,,,,实达/start,针式打印机,650KIII,476
+15,287,0,1420.0,,,,实达/start,针式打印机,750KII,477
+16,288,0,1480.0,,,,实达/start,针式打印机,700KII,478
+17,289,0,1980.0,,,,实达/start,针式打印机,690KIII,479
+18,290,0,2480.0,,,,实达/start,针式打印机,880K,480
+19,295,0,897.0,,,,富士通/FUJITSU,针式打印机,富士通发票之星,485
+20,296,0,998.0,,,,富士通/FUJITSU,针式打印机,富士通发票之星,486
+21,297,0,1450.0,,,,富士通/FUJITSU,针式打印机,富士通发票之星,487
+22,298,0,1460.0,,,,富士通/FUJITSU,针式打印机,富士通发票之星,488
+23,300,0,1980.0,,,,富士通/FUJITSU,针式打印机,富士通发票之星,490
+24,301,0,1880.0,,,,富士通/FUJITSU,针式打印机,富士通发票之星,491
+25,306,0,980.0,,,,映美/Jolimark,针式打印机,560K,496
+26,308,0,1950.0,,,,映美/Jolimark,针式打印机,700KII,498
+27,310,0,2300.0,,,,晟拓/SUNTAIK,针式打印机,160H,500
+28,311,0,2400.0,,,,晟拓/SUNTAIK,针式打印机,160P,501
+29,312,0,2500.0,,,,晟拓/SUNTAIK,针式打印机,160S,502
+30,313,0,999.0,,,,标拓/Biaotop,针式打印机,550K,503
+31,314,0,1428.0,,,,标拓/Biaotop,针式打印机,710K,504
+32,315,0,1498.0,,,,标拓/Biaotop,针式打印机,标拓BT735KII,505
+33,316,0,1468.0,,,,标拓/Biaotop,针式打印机,635KII,506
+34,317,0,2488.0,,,,标拓/Biaotop,针式打印机,标拓AR880K,507
+35,318,0,1999.0,,,,爱普生/EPSON,针式打印机,06KF,508
+36,401,0,2480.0,,,,利盟/Lexmark,多功能一体机,MX321adn,683
+37,402,0,1350.0,,,,东芝/TOSHIBA,多功能一体机,300D,684
+38,403,0,1980.0,,,,东芝/TOSHIBA,多功能一体机,302DNF,685
+39,408,0,1450.0,,,,联想/lenovo,多功能一体机,M7400,690
+40,413,1,1950.0,2000,http://120.35.30.176/shopping/goods_7F3F0F4DFA7740CCE0531138A8C0688B.htm,联想/Lenovo M7655DHF 多功能一体机,联想/lenovo,多功能一体机,M7655DHF,695
+41,414,0,1399.0,,,,奔图/PANTUM,多功能一体机,M6500,696
+42,418,1,1799.0,1999,http://120.35.30.176/shopping/goods_2c9be5956bd5f898016bdb2e0e664397.htm,奔图/PANTUM M6600NW 多功能一体机,奔图/PANTUM,多功能一体机,M6600,700
+43,419,1,1799.0,1999,http://120.35.30.176/shopping/goods_2c9be5956a9a80ac016aa140ed5d20c8.htm,奔图/PANTUM M6606NW 多功能一体机,奔图/PANTUM,多功能一体机,M6606,701
+44,419,1,1799.0,1969,http://120.35.30.176/shopping/goods_2c9be5956a9a80ac016aa0f937500227.htm,奔图/PANTUM M6606 多功能一体机,奔图/PANTUM,多功能一体机,M6606,701
+45,422,0,2499.0,,,,奔图/PANTUM,多功能一体机,M6863FDN,704
+46,427,0,1600.0,,,,兄弟/BROTHER,多功能一体机,B7500D,709
+47,433,0,2500.0,,,,兄弟/BROTHER,多功能一体机,7895DW,715

other_hubei_anhui_rate.csv

+,id,url,产品型号,price2,rate
+0,243,http://120.35.30.176/shopping/goods_2c9be5956c048aa4016c288eebc52912.htm,佳能/Canon iP110 喷墨打印机,1860.0,0.06953476738369184
+1,247,http://120.35.30.176/shopping/goods_2c9be595695d740b01696ae327b66553.htm,震旦/AURORA AD200PS 激光打印机,750.0,0.06132665832290363
+2,249,,,,
+3,262,,,,
+4,267,http://120.35.30.176/shopping/goods_7F3F0F4DF74640CCE0531138A8C0688B.htm,联想/Lenovo LJ2405D 激光打印机,980.0,0.14782608695652175
+5,277,,,,
+6,278,,,,
+7,279,,,,
+8,280,,,,
+9,281,,,,
+10,282,,,,
+11,283,,,,
+12,284,,,,
+13,285,,,,
+14,286,,,,
+15,287,,,,
+16,288,,,,
+17,289,,,,
+18,290,,,,
+19,295,,,,
+20,296,,,,
+21,297,,,,
+22,298,,,,
+23,300,,,,
+24,301,,,,
+25,306,,,,
+26,308,,,,
+27,310,,,,
+28,311,,,,
+29,312,,,,
+30,313,,,,
+31,314,,,,
+32,315,,,,
+33,316,,,,
+34,317,,,,
+35,318,,,,
+36,401,,,,
+37,402,,,,
+38,403,,,,
+39,408,,,,
+40,413,http://120.35.30.176/shopping/goods_7F3F0F4DFA7740CCE0531138A8C0688B.htm,联想/Lenovo M7655DHF 多功能一体机,2000.0,-0.02564102564102564
+41,414,,,,
+42,418,http://120.35.30.176/shopping/goods_2c9be5956bd5f898016bdb2e0e664397.htm,奔图/PANTUM M6600NW 多功能一体机,1999.0,-0.11117287381878821
+43,419,http://120.35.30.176/shopping/goods_2c9be5956a9a80ac016aa0f937500227.htm,奔图/PANTUM M6606 多功能一体机,1969.0,-0.09449694274596998
+44,422,,,,
+45,427,,,,
+46,433,,,,