Edit Jenkinsfile, datasetScript.sh

Jenkinsfile

@@ -12,6 +12,12 @@ pipeline {
          description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
          name: 'KAGGLE_KEY'
       )
+      string(
+            defaultValue: '50',
+            description: 'dataset cutoff',
+            name: 'CUTOFF',
+            trim: false
+         )
    }
    stages {
       stage('Run sh file') {

datasetScript.sh

@@ -4,4 +4,4 @@ kaggle datasets download -d rishikeshkonapure/home-loan-approval
 unzip -o home-loan-approval.zip
 cat loan_sanction_test.csv loan_sanction_train.csv > loan_sanction.csv
 head -n 5 loan_sanction.csv
-{ head -n 1 loan_sanction.csv && tail -n +2 loan_sanction.csv | shuf; } > loan_sanction_shuffled.csv
+{ head -n 1 loan_sanction.csv && tail -n +2 loan_sanction.csv | shuf; } | tail -n +2 | head -n $(($CUTOFF+1)) > loan_sanction_shuffled.csv