p12346870
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

clean codedex warning

This commit is contained in:
hanjun996 2020-07-01 11:44:10 +08:00
parent 7b5b4837ff
commit 83c5505727
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
model_zoo/wide_and_deep/src/preprocess_data.py
View File

@ -17,6 +17,8 @@ import os
import pickle
import collections
import argparse
import urllib.request
import tarfile
import numpy as np
from mindspore.mindrecord import FileWriter
@ -257,10 +259,15 @@ if __name__ == '__main__':
download_data_path = data_path + "origin_data/"
mkdir_path(download_data_path)
os.system(
"wget -P {} -c https://s3-eu-west-1.amazonaws.com/kaggle-display-advertising-challenge-dataset/dac.tar.gz --no-check-certificate".format(
download_data_path))
os.system("tar -zxvf {}dac.tar.gz".format(download_data_path))
url = "https://s3-eu-west-1.amazonaws.com/kaggle-display-advertising-challenge-dataset/dac.tar.gz"
file_name = download_data_path + '/' + url.split('/')[-1]
urllib.request.urlretrieve(url, filename=file_name)
tar = tarfile.open(file_name)
names = tar.getnames()
for name in names:
tar.extract(name, path=download_data_path)
tar.close()
criteo_stats = CriteoStatsDict()
data_file_path = data_path + "origin_data/train.txt"