diff --git a/Jenkinsfile b/Jenkinsfile
index 8ba4342..98d64be 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -25,6 +25,9 @@ node {
               "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
          sh 'kaggle datasets download -d mssmartypants/water-quality > output.txt'
          sh 'unzip -o water-quality.zip >> output.txt'
+         sh 'mapfile -t lines < waterQuality1.csv'
+         sh 'shuf -e "${lines[@]}" | head -n 30 > temp.csv'
+         sh 'mv temp.csv waterQuality1.csv'
          sh 'python3 create_dataset.py >> output.txt'
          archiveArtifacts artifacts: 'waterQuality.csv, output.txt'
      }