s444463/ium_444463
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

r

Browse Source
This commit is contained in:
Mikołaj Pokrywka 2022-04-03 15:40:56 +02:00
parent 9700a1349d
commit d83a35ed0e
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
download_data_and_process.py
View File

@ -5,7 +5,7 @@ import numpy as np
# kaggle.api.authenticate()
# kaggle.api.dataset_download_files('shivamb/real-or-fake-fake-jobposting-prediction', path='fake_job_postings.csv', unzip=True)
data=pd.read_csv('fake_job_postings.csv')
data=pd.read_csv('/data/fake_job_postings.csv')
data = data.replace(np.nan, '', regex=True)
print("="*20)

1
process_data.sh
View File

@ -3,6 +3,7 @@ echo "Download data from kaggle"
echo $KAGGLE_USERNAME
kaggle datasets download -d shivamb/real-or-fake-fake-jobposting-prediction
unzip -o real-or-fake-fake-jobposting-prediction.zip
cp fake_job_postings.csv.csv /data/fake_job_postings.csv
echo "Save column titles"
head -n 1 fake_job_postings.csv > column_titles.csv
tail -n +2 fake_job_postings.csv > data_not_shuf.csv