r

Jenkinsfile

@@ -34,7 +34,6 @@ pipeline {
                 withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                          "KAGGLE_KEY=${params.KAGGLE_KEY}",
                          "CUTOFF=${params.CUTOFF}"]) {
-                            sh "./process_data.sh"
                             sh 'python3 ./download_data_and_process.py'
                             archiveArtifacts artifacts: "data_test.csv, data_dev.csv, data_train.csv, column_titles.csv"
                 }

download_data_and_process.py

@@ -1,6 +1,10 @@
 import subprocess
 import pandas as pd
 import numpy as np
+import kaggle
+
+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 = data.replace(np.nan, '', regex=True)