diff --git a/CreateDataset.dockerfile b/CreateDataset.dockerfile
new file mode 100644
index 0000000..3f303bf
--- /dev/null
+++ b/CreateDataset.dockerfile
@@ -0,0 +1,9 @@
+FROM ubuntu:latest
+
+ADD get-data.sh /get-data.sh
+ADD prepare_dataset.py /prepare_dataset.py
+
+RUN apt-get update
+RUN apt-get install -y python3 python3-pip unzip
+RUN pip install pandas
+RUN pip install scikit-learn
diff --git a/DatasetStats.dockerfile b/DatasetStats.dockerfile
new file mode 100644
index 0000000..08ee655
--- /dev/null
+++ b/DatasetStats.dockerfile
@@ -0,0 +1 @@
+FROM ubuntu:latest
\ No newline at end of file
diff --git a/JenkinsfileCreateDataset b/JenkinsfileCreateDataset
index a6e03f3..fda2d04 100644
--- a/JenkinsfileCreateDataset
+++ b/JenkinsfileCreateDataset
@@ -21,22 +21,37 @@ pipeline {
       )
    }
    stages {
+      stage('Checkout') {
+         steps {
+            sh 'rm -rf ium_z487183'
+            sh 'git clone https://git.wmi.amu.edu.pl/s487183/ium_z487183.git'
+         }
+      }
       stage('Prepare data') {
          steps {
             withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
-               sh './get-data.sh'
-               sh 'python3 prepare_dataset.py'
+               sh 'ium_z487183/get-data.sh'
+               sh 'python3 ium_z487183/prepare_dataset.py'
             }
          }
       }
       stage('Archive artifacts') {
+         agent { 
+            dockerfile {
+               filename 'CreateDataset.dockerfile'
+               dir      'ium_z487183'
+               reuseNode true
+            }
+         }
          steps {
-            archiveArtifacts 'X_test.csv'
-            archiveArtifacts 'X_val.csv'
-            archiveArtifacts 'X_train.csv'
-            archiveArtifacts 'Y_test.csv'
-            archiveArtifacts 'Y_val.csv'
-            archiveArtifacts 'Y_train.csv'
+            withEnv(["CUTOFF=${params.CUTOFF}"]) {
+               archiveArtifacts 'X_test.csv'
+               archiveArtifacts 'X_val.csv'
+               archiveArtifacts 'X_train.csv'
+               archiveArtifacts 'Y_test.csv'
+               archiveArtifacts 'Y_val.csv'
+               archiveArtifacts 'Y_train.csv'
+            }
          }
       }
    }
diff --git a/JenkinsfileDatasetStats b/JenkinsfileDatasetStats
index b5da6cc..6bffb51 100644
--- a/JenkinsfileDatasetStats
+++ b/JenkinsfileDatasetStats
@@ -8,15 +8,24 @@ pipeline {
          )
       }
     stages {
-      stage('Copy artifacts') {
+      stage('Checkout') {
          steps {
-            copyArtifacts filter: 'X_test.csv,X_val.csv,X_train.csv,Y_test.csv,Y_val.csv,Y_train.csv', fingerprintArtifacts: true, projectName: 'z487183-create-dataset', selector: workspace()
+            sh 'rm -rf ium_z487183'
+            sh 'git clone https://git.wmi.amu.edu.pl/s487183/ium_z487183.git'
          }
       }
       stage('Prepare stats') {
+         agent { 
+            dockerfile {
+               filename 'DatasetStats.dockerfile'
+               dir      'ium_z487183'
+               reuseNode true
+            }
+         }
          steps {
-               sh './prepare-stats.sh'
-               archiveArtifacts 'stats.txt'
+            copyArtifacts filter: 'X_test.csv,X_val.csv,X_train.csv,Y_test.csv,Y_val.csv,Y_train.csv', fingerprintArtifacts: true, projectName: 'z487183-create-dataset', selector: workspace()
+            sh './prepare-stats.sh'
+            archiveArtifacts 'stats.txt'
          }
       }
    }
diff --git a/prepare-stats.sh b/prepare-stats.sh
index 6b7e054..14c05f9 100755
--- a/prepare-stats.sh
+++ b/prepare-stats.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+rm -f stats.txt
 touch stats.txt
 wc -l X_test.csv >> stats.txt
 wc -l X_val.csv >> stats.txt