Add second pipeline with .py file

Jenkinsfile_create_dataset

@@ -1,10 +1,8 @@
 pipeline {
    agent  any
-
-   //Definijuemy parametry, które będzie można podać podczas wywoływania zadania
          parameters{
              string(
-                 defaultValue: 'mikaleta',
+                 defaultValue: 'kalkam',
                  description: 'Kaggle username',
                  name: 'KAGGLE_USERNAME',
                  trim: false
@@ -22,7 +20,7 @@ pipeline {
              )
          }
     stages {
-      stage('clear_before') {
+      stage('Clear directory before executing') {
          steps {
             sh 'rm -rf *'
          }
@@ -34,7 +32,7 @@ pipeline {
          }
       }
 
-      stage('Build') {
+      stage('Download dataset') {
          steps {
          withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                   "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {

Jenkinsfile_dataset_stats

@@ -0,0 +1,46 @@
+pipeline {
+   agent any
+   parameters{
+      choice(
+         choices: ['lastSuccessful()', 'lastCompleted()', 'latestSavedBuild()'],
+         description: 'Which build to use for copying artifacts',
+         name: 'BUILD_SELECTOR'
+      )}
+    stages {
+      stage('Clear directory') {
+         steps {
+            sh 'rm -rf *'
+         }
+      }
+      stage('Clone project from repo') {
+         steps {
+            sh 'git clone https://git.wmi.amu.edu.pl/s486867/ium_z486867'
+         }
+      }
+      stage('Copy artifacts from previous build') {
+         steps {
+            copyArtifacts filter: 'X_test.csv,X_dev.csv,X_train.csv', fingerprintArtifacts: true, projectName: 'z-s486867-create-dataset', selector: workspace()
+         }
+      }
+      stage('Docker') {
+         agent {
+            dockerfile {
+               filename 'Dockerfile'
+               dir      'ium_z486867'
+               reuseNode true
+            }
+         }
+         steps {
+                  sh 'python ./ium_z486867/dataset-stats.py'
+                  archiveArtifacts 'X_test.csv'
+                  archiveArtifacts 'X_dev.csv'
+                  archiveArtifacts 'X_train.csv'
+         }
+      }
+      stage('Clear directory') {
+         steps {
+            sh 'rm -rf *'
+         }
+      }
+   }
+}

dataset-stats.py

@@ -0,0 +1,18 @@
+import pandas
+
+X_train = pandas.read_csv('X_train.csv',
+                          engine='python',
+                          encoding='ISO-8859-1',
+                          sep=',')
+X_dev = pandas.read_csv('X_dev.csv',
+                          engine='python',
+                          encoding='ISO-8859-1',
+                          sep=',')
+X_test = pandas.read_csv('X_test.csv',
+                          engine='python',
+                          encoding='ISO-8859-1',
+                          sep=',')
+
+X_train.describe(include='all').to_csv('X_train_stats.csv', index=True)
+X_dev.describe(include='all').to_csv('X_dev_stats.csv', index=True)
+X_test.describe(include='all').to_csv('X_test_stats.csv', index=True)