Skip to content

Commit fbc3e58

Browse files
committed
run.sh
1 parent 48b0de7 commit fbc3e58

File tree

2 files changed

+14
-22
lines changed

2 files changed

+14
-22
lines changed
Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
mkdir data
2+
mkdir data/whole_data && mkdir data/whole_data/train && mkdir data/whole_data/test
3+
tar zxvf data/sample_train.tar.gz -C data
4+
tar zxvf data/sample_test.tar.gz -C data
5+
python process_public_data.py
6+
mv data/ctr_cvr.train data/whole_data/train
7+
mv data/ctr_cvr.test data/whole_data/test

datasets/ali-cpp_aitm/run.sh

Lines changed: 7 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -1,22 +1,7 @@
1-
mkdir data
2-
mkdir data/whole_data && mkdir data/whole_data/train && mkdir data/whole_data/test
3-
train_source_path="./data/sample_train.tar.gz"
4-
train_target_path="train_data"
5-
test_source_path="./data/sample_test.tar.gz"
6-
test_target_path="test_data"
7-
cd data
8-
echo "downloading sample_train.tar.gz......"
9-
curl -# 'http://jupter-oss.oss-cn-hangzhou.aliyuncs.com/file/opensearch/documents/408/sample_train.tar.gz?Expires=1586435769&OSSAccessKeyId=LTAIGx40tjZWxj6q&Signature=ahUDqhvKT1cGjC4%2FIER2EWtq7o4%3D&response-content-disposition=attachment%3B%20' -H 'Proxy-Connection: keep-alive' -H 'Upgrade-Insecure-Requests: 1' -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9' -H 'Accept-Language: zh-CN,zh;q=0.9' --compressed --insecure -o sample_train.tar.gz
10-
cd ..
11-
echo "unzipping sample_train.tar.gz......"
12-
tar -xzvf ${train_source_path} -C data && rm -rf ${train_source_path}
13-
cd data
14-
echo "downloading sample_test.tar.gz......"
15-
curl -# 'http://jupter-oss.oss-cn-hangzhou.aliyuncs.com/file/opensearch/documents/408/sample_test.tar.gz?Expires=1586435821&OSSAccessKeyId=LTAIGx40tjZWxj6q&Signature=OwLMPjt1agByQtRVi8pazsAliNk%3D&response-content-disposition=attachment%3B%20' -H 'Proxy-Connection: keep-alive' -H 'Upgrade-Insecure-Requests: 1' -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9' -H 'Accept-Language: zh-CN,zh;q=0.9' --compressed --insecure -o sample_test.tar.gz
16-
cd ..
17-
echo "unzipping sample_test.tar.gz......"
18-
tar -xzvf ${test_source_path} -C data && rm -rf ${test_source_path}
19-
echo "preprocessing data......"
20-
python process_public_data.py
21-
mv data/ctr_cvr.train data/whole_data/train
22-
mv data/ctr_cvr.test data/whole_data/test
1+
mkdir whole_data
2+
mkdir whole_data/train && mkdir whole_data/test
3+
cd whole_data/train
4+
wget https://paddlerec.bj.bcebos.com/datasets/aitm/ctr_cvr.train
5+
cd ../test
6+
wget https://paddlerec.bj.bcebos.com/datasets/aitm/ctr_cvr.test
7+
cd ../../

0 commit comments

Comments
 (0)