diff --git a/Jenkinsfile b/Jenkinsfile
index 7e78227..61d545a 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -31,5 +31,37 @@ pipeline {
 			checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[credentialsId: 's444356', url: 'https://git.wmi.amu.edu.pl/s444356/ium_444356.git']]])
 		}
 	}
+
+	stage('Script'){
+		steps {
+			sh './download.sh'
+		}
+	}
+
+	stage('Preparation') { 
+     properties([
+         parameters([
+             string(
+                 defaultValue: 'maciejczajka',
+                 description: 'Kaggle username',
+                 name: 'KAGGLE_USERNAME',
+                 trim: false
+             ),
+             password(
+                 defaultValue: '',
+                 description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
+                 name: 'KAGGLE_KEY'
+             )
+         ])
+     ])
+ }
+ stage('Build') {
+     // Run the maven build
+     withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
+              "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
+         sh 'echo KAGGLE_USERNAME: $KAGGLE_USERNAME'
+         sh 'kaggle datasets list'
+     }
+ }
    }
 }
\ No newline at end of file
diff --git a/download.sh b/download.sh
new file mode 100755
index 0000000..a63e1ff
--- /dev/null
+++ b/download.sh
@@ -0,0 +1,12 @@
+dataset_operation() {
+    cat all_games.csv | gshuf > all_games.csv.shuf
+    head -n 1880 all_games.csv.shuf > all_games.csv.test
+    head -n 3760 all_games.csv.shuf | tail -n 1880 > all_games.csv.dev
+    tail -n +3761 all_games.csv.shuf > all_games.csv.train
+    rm all_games.csv.shuf
+    wc -l all_games.csv.*
+}
+
+kaggle datasets download -d deepcontractor/top-video-games-19952021-metacritic
+unzip top-video-games-19952021-metacritic.zip
+dataset_operation
\ No newline at end of file