a

Jenkinsfile

@@ -37,7 +37,7 @@ pipeline {
                             //  sh './process_data.sh'
                             sh 'ls'
                             sh 'python3 ./download_data_and_process.py'
-                            archiveArtifacts artifacts: "data_test.csv, data_dev.csv, data_train.csv, column_titles.csv, fake_job_postings.csv"
+                            archiveArtifacts artifacts: "data_test.csv, data_dev.csv, data_train.csv, column_titles.csv, data.csv"
                 }
             }
         }

download_data_and_process.py

@@ -5,7 +5,13 @@ 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.csv')
 data = data.replace(np.nan, '', regex=True)
 
 print("="*20)

process_data.sh

@@ -4,7 +4,6 @@ echo $KAGGLE_USERNAME
 kaggle datasets download -d shivamb/real-or-fake-fake-jobposting-prediction
 unzip -o real-or-fake-fake-jobposting-prediction.zip
 ls
-cat fake_job_postings.csv > data.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