diff --git a/Jenkinsfile b/Jenkinsfile
index 3d1ee47..c6ae97f 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -1,6 +1,14 @@
 pipeline {
     agent any
 
+    parameters {
+        string(
+            defaultValue: '100',
+            description: 'The number of examples to keep in the dataset',
+            name: 'CUTOFF'
+        )
+    }
+
     stages {
         stage('Preparation') { 
             when { expression { true } }
@@ -45,6 +53,10 @@ pipeline {
                                 unzip -o olympics-124-years-datasettill-2020.zip
 
                                 echo "Processed Data" > output.txt
+
+                                head -n ${params.CUTOFF} athlete_events.csv > athlete_events_cutoff.csv
+
+                                mv athlete_events_cutoff.csv athlete_events.csv
                             '''
                         }
                     } catch (err) {