Loading dataset script update

Jenkinsfile

@@ -1,34 +1,22 @@
 node {
-    // stage('Preparation') {
+    stage('checkout: Check out from version control') {
-    //     properties ([
+        git 'https://git.wmi.amu.edu.pl/s478841/ium_478841.git'
-    //         parameters([
+    }
-    //             string(
-    //                 defaultValue:'mateuszogrodowczyk',
-    //                 description: 'Kaggle username',
-    //                 name: 'KAGGLE_USERNAME',
-    //                 trim: false
-    //             ),
-    //             password(
-    //                 description: 'Kaggle access token retrieved from kaggle.json file - https://github.com/Kaggle/kaggle-api#api-credentials',
-    //                 name: 'KAGGLE_KEY'
-    //             )
-    //         ])
-    //     ])
-    // }
-
     stage('Install depends.') {
         sh 'pip install --user -r requirements.txt'
     }
-    stage('Prepare dataset') {
+    stage('sh: Shell script') {
         withEnv([
             "KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
             "KAGGLE_KEY=${params.KAGGLE_KEY}"
         ]) {
-            sh 'echo Welcome: $KAGGLE_USERNAME'
-            sh 'kaggle datasets list'
-        }
-
             sh 'chmod u+x ./load_data.sh'
             sh './load_data.sh'
         }
+    }
+    post {
+        always {
+            archiveArtifacts artifacts: 'avocado.data*', onlyIfSuccessful: true
+        }
+    }
 }

load_data.sh

@@ -1 +1,13 @@
-figlet "Load data"
+figlet "Welcome $KAGGLE_USERNAME"
+
+rm -r avocado.data*
+
+kaggle datasets download -d neuromusic/avocado-prices
+unzip -o avocado-prices.zip
+
+tail -n +2 avocado.csv | shuf > avocado_shuf.csv
+head -n 14000 avocado_shuf.csv > avocado.data.train
+tail -n +14001 avocado_shuf.csv | head -n 2249 > avocado.data.valid
+tail -n 2000 avocado_shuf.csv > avocado.data.test
+
+wc -l avocado.data* > results.txt