Repository: yanshengli/tianchi_bigdata
Branch: master
Commit: 36aa99234c93
Files: 11
Total size: 20.0 KB
Directory structure:
gitextract_wuij7jog/
├── README.md
├── classify_user_item.py
├── combine_feature_txt.py
├── cut_data_set.py
├── fetch_feature.py
├── fetch_negative_sample.py
├── fetch_sample.py
├── get_feature_vector_txt_4.py
├── get_recommend_result_6.py
├── global_feature.py
└── produt_test_data.py
================================================
FILE CONTENTS
================================================
================================================
FILE: README.md
================================================
# tianchi_bigdata
任务：
[详见天池大数据任务介绍](http://tianchi.aliyun.com/competition/information.htm?spm=0.0.0.0.y1LXeD&raceId=1)
特征（39维）：
user特征、item特征、user-item特征、全局比例特征
数据采样
采用移动窗口target（17、15、13、11、9）+移动窗口样本采样（1、3、7、全部）
训练数据
正样本：15000，负样本：130000
测试数据
同样采用移动窗口变换采样，取了3天、5天、9天的做实验，最优提交为9天的，测试样本大小：155万
结果划分
结果最终取置信度0.78,取470条结果(子集结果)，最终f1值：11.46%
排名:25/7200，队伍名：叮当
学习模型
RF
程序架构
combine_feature_txt:混合正负样本特征
cut_data_set.py:按照移动窗口方式，分割数据集
fetch_feature.py：提取特征
fetch_negative_sample:负样本抽样
fetch_sample:提取正、负样本
get_feature_vector_txt_4.py:提取特征向量，去掉用户-商品标示
get_recommend_result_6.py:对最后分类结果取置信度，并得到相应的推荐结果
global_feature.py:提取全局比例特征
product_test_data.py:产生测试数据
classify_user_item.py:训练学习特征，并预测
[大赛排名] (http://tianchi.aliyun.com/competition/rankingList.htm?spm=0.0.0.0.OyeBsu&season=0&raceId=1&pageIndex=2)
================================================
FILE: classify_user_item.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
import numpy as np
f = open("train_sample.txt")
f.readline()
data = np.loadtxt(f)
X = data[:, :-1] # select columns 1 through end
y = data[:, -1] # select column 0, the stock price
print X
print y
print 'start train'
clf2 = RandomForestClassifier(n_estimators=100)
#clf2=GradientBoostingClassifier()
clf2.fit(X,y)
#clf2 = LogisticRegression().fit(X, y)
print clf2.classes_
f1=open("test_data_9feature.txt")
data1=np.loadtxt(f1)
X_new=data1[:,:]
print 'testing data is ok'
result=clf2.predict_proba(X_new)
print 'output result'
print result
f_result=open('result9.txt','w')
for i in range(0,len(result)):
f_result.write(str(result[i])+'\n')
================================================
FILE: combine_feature_txt.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
i=9
f1=open('combine_txt_positive_feature.txt','wb')
while (i<18):
filename='2014-12-'+str(i)
filename=filename+'_positive_user_item_feature.txt'
f=open(filename,'r')
lines=f.readlines()
for line in lines:
f1.write(line)
i=i+1
================================================
FILE: cut_data_set.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
import csv
reader=csv.reader(file('filter_user.csv', 'rb'))
csvfile = file('9_1_data.csv', 'wb')
writer1=csv.writer(csvfile)
csvfile = file('9_3_data.csv', 'wb')
writer2=csv.writer(csvfile)
csvfile = file('9_7_data.csv', 'wb')
writer3=csv.writer(csvfile)
csvfile = file('9_all_data.csv', 'wb')
writer4=csv.writer(csvfile)
##############################################取样本子集,后三天的作为验证日期，正样本10000个，负样本取100000个，最后对样本子集空间进行预测######################################
#################################取的是样本全集#######################################################################
positive_user_item=set()
num=0
for line in reader:
if num==0:
num=num+1
continue
time_s=line[5].split(' ')
time_slot=time_s[0].split('-')
month=int(time_slot[1])
day=int(time_slot[2])
dis_day=(12-month)*30+(19-day)
if dis_day>=10 and dis_day<=11 :
writer1.writerow(line)
if dis_day>=10 and dis_day<=13:
writer2.writerow(line)
if dis_day>=10 and dis_day<=17:
writer3.writerow(line)
if dis_day>=10 :
writer4.writerow(line)
num=num+1
================================================
FILE: fetch_feature.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
##################抽取如下特征,浏览数、收藏数、购物车、购买数、平均活跃天数、最后活跃天数距离最终时间的天数,先不考虑平均活跃天数####
import csv
def fetch_feature(sample_filename,feature_filename,item_brand):
reader=csv.reader(file(sample_filename, 'rb'))
csvfile = file(feature_filename, 'wb')
writer=csv.writer(csvfile)
###################################定义统计变量###########################################
user_item_click=dict()#(u,i)点击次数
usr_item_hide=dict()#(u,i)收藏次数
usr_item_shop_basket=dict()#(u,i)购物车次数
num=0
user_item_pair=set()#(u,i)对
user_basket=dict()#（u）购物车件数
usr_item_shop=dict()#(用户-item购买次数)
item_num=dict()
item_user=dict()
item_click=dict()
item_basket=dict()
item_hide=dict()
user_buy_brand=dict()
user_buy_item_brand=dict()
user_item_num=dict()
user_brand=dict()
user_buy=dict()
user_click=dict()
user_hide=dict()
user_item_time=dict()
user_click_item_brand=dict()
user_basket_item_brand=dict()
catogery_buy=dict()
catogery_click=dict()
catogery_basket=dict()
catogery_hide=dict()
###################################初始化#############################
for line in reader:
if line[5].find('2014-12-17')<0:
item_brand[line[1]]=line[4]
user_hide[line[0]]=0
user_click[line[0]]=0
user_buy[line[0]]=0
user_brand[line[0]]=set()
user_item_num[line[0]]=set()
user_item_click[(line[0],line[1])]=0
usr_item_hide[(line[0],line[1])]=0
usr_item_shop_basket[(line[0],line[1])]=0
user_item_pair.add((line[0],line[1]))
usr_item_shop[(line[0],line[1])]=0
item_num[line[1]]=0
item_user[line[1]]=set()
item_click[line[1]]=0
item_basket[line[1]]=0
item_hide[line[1]]=0
user_buy_brand[line[0]]=set()
user_buy_item_brand[(line[0],item_brand[line[1]])]=0
user_click_item_brand[(line[0],item_brand[line[1]])]=0
user_basket_item_brand[(line[0],item_brand[line[1]])]=0
user_basket[line[0]]=0
catogery_buy[item_brand[line[1]]]=0
catogery_click[item_brand[line[1]]]=0
catogery_basket[item_brand[line[1]]]=0
catogery_hide[item_brand[line[1]]]=0
num=num+1
#####################################统计特征############################################
for line in csv.reader(file(sample_filename, 'rb')):
if line[5].find('2014-12-17')<0:
time_s=line[5].split(' ')
time_slot=time_s[0].split('-')
month=int(time_slot[1])
day=int(time_slot[2])
dis_day=(12-month)*30+(17-day)####间隔时间
if (line[0],line[1]) not in user_item_time:
user_item_time[line[0],line[1]]=set()
user_item_time[line[0],line[1]].add(dis_day)
else:
user_item_time[line[0],line[1]].add(dis_day)
if line[2]=='1':
#################用户对该商品的点击总数############################
if (line[0],line[1]) not in user_item_click:
user_item_click[(line[0],line[1])]=1
else:
user_item_click[(line[0],line[1])]=1+user_item_click[(line[0],line[1])]
####用户点击总数#######
user_click[line[0]]=user_click[line[0]]+1
###############统计点击次数###############################
#########################统计用户对该商品所对应类型的次数#######################
user_click_item_brand[(line[0],item_brand[line[1]])]=1+user_click_item_brand[(line[0],item_brand[line[1]])]
#########################商品对应的种类被点击的次数#############
catogery_click[item_brand[line[1]]]=catogery_click[item_brand[line[1]]]+1
###################商品被点击的总数####################
item_click[line[1]]=item_click[line[1]]+1
if line[2]=='2':
if (line[0],line[1]) not in usr_item_hide:
usr_item_hide[(line[0],line[1])]=1
else:
usr_item_hide[(line[0],line[1])]=1+usr_item_hide[(line[0],line[1])]
#############用户收藏总数################
user_hide[line[0]]=user_hide[line[0]]+1
################商品类型被收藏的次数############
catogery_hide[item_brand[line[1]]]=catogery_hide[item_brand[line[1]]]+1
################商品被加入收藏的次数############
item_hide[line[1]]=item_hide[line[1]]+1
if line[2]=='3':
################（u,i）加入购物车的次数##############
if (line[0],line[1]) not in usr_item_shop_basket:
usr_item_shop_basket[(line[0],line[1])]=1
else:
usr_item_shop_basket[(line[0],line[1])]=1+usr_item_shop_basket[(line[0],line[1])]
############用户加入购物车的总数#######################
user_basket[line[0]]=user_basket[line[0]]+1
#########################统计用户对该商品所对应类型的购物车次数###################
user_basket_item_brand[(line[0],item_brand[line[1]])]=1+user_basket_item_brand[(line[0],item_brand[line[1]])]
########################商品种类被加入购物车的次数#####################
catogery_basket[item_brand[line[1]]]=catogery_basket[item_brand[line[1]]]+1
################商品被加入购物车的次数############
item_basket[line[1]]=item_basket[line[1]]+1
if line[2]=='4':
##############################该用户购买该商品的次数############################
if (line[0],line[1]) not in usr_item_shop:
usr_item_shop[(line[0],line[1])]=1
else:
usr_item_shop[(line[0],line[1])]=usr_item_shop[(line[0],line[1])]+1
#############用户购买商品的总次数#########################
user_buy[line[0]]=user_buy[line[0]]+1
###########################统计该商品被购买的次数##############################
item_num[line[1]]=item_num[line[1]]+1
###############商品被多少人购买####################
item_user[line[1]].add((line[0]))
##########################种类被购买的次数######################
catogery_buy[item_brand[line[1]]]=catogery_buy[item_brand[line[1]]]+1
################用户购买商品类型的总数############
user_buy_brand[line[0]].add(item_brand[line[1]])
####################用户购买该类型商品种类的数目###########
user_buy_item_brand[(line[0],item_brand[line[1]])]=1+user_buy_item_brand[(line[0],item_brand[line[1]])]
#############################用户交互的商品数################
user_item_num[line[0]].add((line[1]))
############################用户交互的商品品牌数####################
user_brand[line[0]].add(item_brand[line[1]])
#####################################写结果##################################################################
for k in user_item_pair:
####################用户交互的商品数与购买的商品数之比######################
if user_buy[k[0]]!=0:
comm_item_ratio=float("%.2f"%(len(user_item_num[k[0]])/user_buy[k[0]]))
else:
comm_item_ratio=0
#################用户交互的商品品牌数与购买的商品品牌数之比##################
if len(user_buy_brand[k[0]])!=0:
comm_brand_buy_ratio=float("%.2f"%(len(user_brand[k[0]])/len(user_buy_brand[k[0]])))
else:
comm_brand_buy_ratio=0
###################该类型商品点击与购买的比例###############
if catogery_buy[item_brand[k[1]]]!=0:
catogry_click_buy=float("%.2f"%(catogery_click[item_brand[k[1]]]/catogery_buy[item_brand[k[1]]]))
else:
catogry_click_buy=0
###################该类型商品加入购物车与购买的比例###############
if catogery_buy[item_brand[k[1]]]!=0:
catogry_basket_buy=float("%.2f"%(catogery_basket[item_brand[k[1]]]/catogery_buy[item_brand[k[1]]]))
else:
catogry_basket_buy=0
####购买该商品所对应的类型占总的购买量的比例########################
if user_buy[k[0]]!=0:
buy_catogry_ratio=float("%.2f"%(user_buy_item_brand[(k[0],item_brand[k[1]])]/user_buy[k[0]]))
else:
buy_catogry_ratio=0
##########################################点击该商品所对应的类型占总的点击量的比例####################
if user_click[k[0]]!=0:
click_catogry_ratio=float("%.2f"%(user_click_item_brand[(k[0],item_brand[k[1]])]/user_click[k[0]]))
else:
click_catogry_ratio=0
#########################################购物车该商品所对应的类型占总的购物车的比例######################
if user_basket[k[0]]!=0:
basket_catogry_ratio=float("%.2f"%(user_basket_item_brand[(k[0],item_brand[k[1]])]/user_basket[k[0]]))
else:
basket_catogry_ratio=0
####用户点击购买比例###############
if user_buy[k[0]]!=0:
click_buy_user_ratio=float("%.2f"%(user_click[k[0]]/user_buy[k[0]]))
else:
click_buy_user_ratio=0
######用户-商品对购物车与购买的比例####################
if usr_item_shop[k]!=0:
basket_buy_ratio=float("%.2f"%(usr_item_shop_basket[k]/usr_item_shop[k]))
else:
basket_buy_ratio=0
##########用户-商品点击与购物车的比例######
if usr_item_shop_basket[k]!=0:
click_basket=float("%.2f"%(user_item_click[k]/usr_item_shop_basket[k]))
else:
click_basket=0
##################用户购物车与购买的比例#####################
if user_buy[k[0]]!=0:
basket_buy_user_ratio=float("%.2f"%(user_basket[k[0]]/user_buy[k[0]]))
else:
basket_buy_user_ratio=0
#################用户点击与购物车的比例###################
if user_basket[k[0]]!=0:
ratio_click_basket=float("%.2f"%(user_click[k[0]]/user_basket[k[0]]))
else:
ratio_click_basket=0
######################用户收藏与购物的比例#################
if user_buy[k[0]]!=0:
ratio_hide_buy=float("%.2f"%(user_hide[k[0]]/user_buy[k[0]]))
else:
ratio_hide_buy=0
######################该类型商品收藏与购买的比例#################
if catogery_buy[item_brand[k[1]]]!=0:
catogry_hide_buy=float("%.2f"%(catogery_hide[item_brand[k[1]]]/catogery_buy[item_brand[k[1]]]))
else:
catogry_hide_buy=0
###################用户最早接触该物品的时间以及最晚接触该物品的时间#####################
sort_user_item_time=list(user_item_time[k])
eraliest_time=sort_user_item_time[-1]
latest_time=sort_user_item_time[0]
writer.writerow((k[0],k[1],user_item_click[k],user_click[k[0]],usr_item_hide[k],user_hide[k[0]],\
usr_item_shop_basket[k],user_basket[k[0]],usr_item_shop[k],user_buy[k[0]],item_num[k[1]],len(item_user[k[1]]),\
len(user_buy_brand[k[0]]),user_buy_item_brand[(k[0],item_brand[k[1]])],len(user_item_num[k[0]]),len(user_brand[k[0]]),
user_click_item_brand[(k[0],item_brand[k[1]])],user_basket_item_brand[(k[0],item_brand[k[1]])],catogery_click[item_brand[k[1]]],
catogery_hide[item_brand[k[1]]],catogery_basket[item_brand[k[1]]],catogery_buy[item_brand[k[1]]],item_click[k[1]],
item_hide[k[1]],item_basket[k[1]],
buy_catogry_ratio,click_buy_user_ratio,basket_buy_ratio,click_basket,basket_buy_user_ratio,ratio_hide_buy,
ratio_click_basket,click_catogry_ratio,basket_catogry_ratio,catogry_click_buy,catogry_basket_buy,
catogry_hide_buy,comm_item_ratio,comm_brand_buy_ratio,eraliest_time,latest_time))
####################39维特征##################################
if __name__=='__main__':
item_brand=dict()
fetch_feature('./17/17_1_data.csv',\
'./17/17_1_data_feature.csv',item_brand)
================================================
FILE: fetch_negative_sample.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
import csv
import random
num=1
csvfile = file('sample_17_negative_user.csv', 'wb')
writer=csv.writer(csvfile)
for line in csv.reader(file('17_negative.csv','r')):
if num%200==0:
writer.writerow(line)
num=num+1
print num
================================================
FILE: fetch_sample.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
import csv
import os
buy=set()
for line in csv.reader(file('./17/17_1_data.csv','rb')):
if line[5].find('2014-12-17')>=0:
if line[2]=='4':
buy.add((line[0],line[1]))
csvfile = file('17_negative.csv', 'wb')
writer=csv.writer(csvfile)
files=os.listdir('./17/')
for filename in files:
if filename.find('feature')>=0:
for line in csv.reader(file('./17/'+filename,'rb')):
if (line[0],line[1]) not in buy:
writer.writerow(line)
================================================
FILE: get_feature_vector_txt_4.py
================================================
__author__ = 'LiGe'
#encoding:Utf-8
import csv
##########################加类标,去用户-商品名，取纯特征文档#############################
def put_on_label(feature_csv,feature_txt_label):
f=open(feature_txt_label,'w')
for line in csv.reader(file(feature_csv, 'rb')):
f.write(line[2]+' '+line[3]+' '+line[4]+' '+line[5]+' '+line[6]
+' '+line[7]+line[8]
+' '+line[9]
+' '+line[10]
+' '+line[11]
+' '+line[12]
+' '+line[13]
+' '+line[14]
+' '+line[15]
+' '+line[16]
+' '+line[17]
+' '+line[18]
+' '+line[19]
+' '+line[20]
+' '+line[21]
+' '+line[22]
+' '+line[23]
+' '+line[24]
+' '+line[25]
+' '+line[26]
+' '+line[27]
+' '+line[28]
+' '+line[29]
+' '+line[30]
+' '+line[31]
+' '+line[32]
+' '+line[33]
+' '+line[34]
+' '+line[35]
+' '+line[36]
+' '+line[37]
+' '+line[38]
+' '+line[39]
+' '+line[40]
+'\n')
if __name__=="__main__":
feature_csv='global_test_data_feature.csv'
feature_txt_lable='test_data_9feature.txt'
put_on_label(feature_csv,feature_txt_lable)
================================================
FILE: get_recommend_result_6.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
import csv
def get_result(input_source_result_txt,output_final_result_csv,test_sourc_file_csv):
result_line_num=set()
f=open(input_source_result_txt,'r')
lines=f.readlines()
num=1
for line in lines:
linedata=line[1:-2].strip()
data=linedata.split(' ')
#print data[1]
if float(data[1].strip())>0.78:
result_line_num.add(num)
num=num+1
print len(result_line_num)
csvfile = file(output_final_result_csv, 'wb')
writer=csv.writer(csvfile)
num=1
suspect_user_item=set()
for line in csv.reader(file(test_sourc_file_csv, 'rb')):
if num in result_line_num:
suspect_user_item.add((line[0],line[1]))
#writer.writerow((line[0],line[1]))
num=num+1
sub_item=set()
for line in csv.reader(file('tianchi_mobile_recommend_train_item.csv','rb')):
sub_item.add(line[0])
count=0
for k in suspect_user_item:
if k[1] in sub_item:
writer.writerow((k[0],k[1]))
count=count+1
print count
if __name__=='__main__':
input_source_result_txt='result9.txt'
output_final_result_csv='tianchi_mobile_recommendation_predict_9_434.csv'
test_sourc_file_csv='global_test_data_feature.csv'
get_result(input_source_result_txt,output_final_result_csv,test_sourc_file_csv)
================================================
FILE: global_feature.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
import csv
global_user_feature=dict()
for line in csv.reader(file('9_all_data.csv','rb')):
global_user_feature[(line[0],line[1])]=line[25:]
csvfile = file('gloabal_9_1_data.csv', 'wb')
writer=csv.writer(csvfile)
for line in csv.reader(file('9_1_data.csv','rb')):
k=global_user_feature[(line[0],line[1])]
writer.writerow((line[0],line[1],line[2],line[3],
line[4],line[5],line[6],line[7],
line[8],line[9],line[10],line[11],
line[12],line[13],line[14],line[15],
line[16],line[17],line[18],line[19],
line[20],line[21],line[22],line[23],
line[24],k[0],k[1],k[2],k[3],k[4],k[5],
k[6],k[7],k[8],k[9],k[10],k[11],k[12],
k[12],k[13],k[14],k[15]
))
================================================
FILE: produt_test_data.py
================================================
__author__ = 'LiGe'
#encoding:utf-8
import csv
num=0
csvfile = file('test_data_9.csv', 'wb')
writer=csv.writer(csvfile)
for line in csv.reader(file('tianchi_mobile_recommend_train_user.csv','rb')):
if num==0:
num=num+1
continue
time_s=line[5].split(' ')
time_slot=time_s[0].split('-')
month=int(time_slot[1])
day=int(time_slot[2])
dis_day=(12-month)*30+(19-day)
if dis_day<=9:
writer.writerow(line)
gitextract_wuij7jog/ ├── README.md ├── classify_user_item.py ├── combine_feature_txt.py ├── cut_data_set.py ├── fetch_feature.py ├── fetch_negative_sample.py ├── fetch_sample.py ├── get_feature_vector_txt_4.py ├── get_recommend_result_6.py ├── global_feature.py └── produt_test_data.py
SYMBOL INDEX (3 symbols across 3 files) FILE: fetch_feature.py function fetch_feature (line 6) | def fetch_feature(sample_filename,feature_filename,item_brand): FILE: get_feature_vector_txt_4.py function put_on_label (line 6) | def put_on_label(feature_csv,feature_txt_label): FILE: get_recommend_result_6.py function get_result (line 6) | def get_result(input_source_result_txt,output_final_result_csv,test_sour...
Condensed preview — 11 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (24K chars).
[
{
"path": "README.md",
"chars": 853,
"preview": "# tianchi_bigdata\n任务：\n\n[详见天池大数据任务介绍](http://tianchi.aliyun.com/competition/information.htm?spm=0.0.0.0.y1LXeD&raceId=1)\n"
},
{
"path": "classify_user_item.py",
"chars": 876,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nfrom sklearn.linear_model import LogisticRegression\r\nfrom sklearn.ensemble import "
},
{
"path": "combine_feature_txt.py",
"chars": 305,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\ni=9\r\nf1=open('combine_txt_positive_feature.txt','wb')\r\nwhile (i<18):\r\n filename"
},
{
"path": "cut_data_set.py",
"chars": 1166,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nimport csv\r\nreader=csv.reader(file('filter_user.csv', 'rb'))\r\ncsvfile = file('9_1_"
},
{
"path": "fetch_feature.py",
"chars": 12065,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\n##################抽取如下特征,浏览数、收藏数、购物车、购买数、平均活跃天数、最后活跃天数距离最终时间的天数,先不考虑平均活跃天数####\r\n\r\n"
},
{
"path": "fetch_negative_sample.py",
"chars": 284,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nimport csv\r\nimport random\r\n\r\nnum=1\r\ncsvfile = file('sample_17_negative_user.csv', "
},
{
"path": "fetch_sample.py",
"chars": 543,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nimport csv\r\nimport os\r\nbuy=set()\r\nfor line in csv.reader(file('./17/17_1_data.csv'"
},
{
"path": "get_feature_vector_txt_4.py",
"chars": 1565,
"preview": "__author__ = 'LiGe'\r\n#encoding:Utf-8\r\nimport csv\r\n##########################加类标,去用户-商品名，取纯特征文档##########################"
},
{
"path": "get_recommend_result_6.py",
"chars": 1432,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nimport csv\r\n\r\n\r\ndef get_result(input_source_result_txt,output_final_result_csv,tes"
},
{
"path": "global_feature.py",
"chars": 898,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nimport csv\r\nglobal_user_feature=dict()\r\n\r\nfor line in csv.reader(file('9_all_data."
},
{
"path": "produt_test_data.py",
"chars": 468,
"preview": "__author__ = 'LiGe'\r\n#encoding:utf-8\r\nimport csv\r\nnum=0\r\n\r\ncsvfile = file('test_data_9.csv', 'wb')\r\nwriter=csv.writer(cs"
}
]
About this extraction
This page contains the full source code of the yanshengli/tianchi_bigdata GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 11 files (20.0 KB), approximately 6.0k tokens, and a symbol index with 3 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.