diff --git a/Jenkinsfile b/Jenkinsfile
index ffd6cc0..e1f0c4c 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -1,10 +1,35 @@
 pipeline {
     agent any 
+    parameters {
+        string(
+            defaultValue: 'kamilab0bkowska',
+            description: '',
+            name: 'KAGGLE_USERNAME',
+            trim: false
+             ),
+        password(
+            defaultValue: '',
+            description: '',
+            name: 'KAGGLE_KEY'
+        )
+
+    }
     stages {
         stage('Stage 1') {
             steps {
                 echo 'Hello world!' 
             }
         }
+        stage('Get data save artifacts') {
+            steps {
+                withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
+                "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
+                    sh 'echo KAGGLE_USERNAME: $KAGGLE_USERNAME'
+                    sh 'data_prep.sh'
+                    archiveArtifacts artifacts: 'apps_train.csv, apps_test.csv, apps_validate.csv'
+                }
+            }
+        }
     }
-}
\ No newline at end of file
+}
+
diff --git a/data_prep.sh b/data_prep.sh
new file mode 100644
index 0000000..d8ace10
--- /dev/null
+++ b/data_prep.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+
+kaggle datasets download -d lava18/google-play-store-apps
+unzip -o google-play-store-apps.zip
+sed -i '1d' googleplaystore.csv
+shuf googleplaystore.csv > apps_shuf.csv
+#cp apps_shuf.csv apps_shuf_copy.csv
+head -n 6505 apps_shuf.csv > apps_train.csv
+sed -i '1,6505d' apps_shuf.csv
+head -n 2168 apps_shuf.csv > apps_test.csv
+sed -i '1,2168d' apps_shuf.csv
+head -n 2168 apps_shuf.csv > apps_validate.csv
\ No newline at end of file