Dockerfile

Jenkinsfile

@@ -1,5 +1,10 @@
 pipeline {
-  agent any
+  agent { 
+    dockerfile {
+      filename 'Dockerfile'
+      args '-u root'
+    }
+  }
   
   parameters {
     string (
@@ -15,39 +20,16 @@ pipeline {
     )
   }
 
+  environment {
+    KAGGLE_USERNAME = "${params.KAGGLE_USERNAME}"
+    KAGGLE_KEY = "${params.KAGGLE_KEY}"
+  }
+
   stages {
-    stage('Clone Repository') {
-      steps {
-        git branch: 'main', url: 'https://git.wmi.amu.edu.pl/s464913/ium_464913.git'
-      }
-    }
-
-    stage('Download dataset') {
-      steps {
-        withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
-          sh 'kaggle datasets download -d mlg-ulb/creditcardfraud'
-          sh 'unzip -o creditcardfraud.zip'
-          sh 'rm creditcardfraud.zip'
-        }
-      }
-    }
-
     stage('Run create-dataset script') {
-        agent {
-          dockerfile {
-            reuseNode true
-        }
-      }
-
       steps {
         sh 'chmod +x create-dataset.py'
-        sh 'python3 ./create-dataset.py'
-      }
-    }
-
-    stage('Archive Artifacts') {
-      steps {
-        archiveArtifacts artifacts: 'data/*', onlyIfSuccessful: true
+        sh 'python3 ./create-dataset.py $KAGGLE_USERNAME'
       }
     }
   }

create-dataset.py

@@ -91,26 +91,10 @@ def main():
     # download_kaggle_dataset()
     os.makedirs("data", exist_ok=True)
 
-    os.system("ls -al")
     os.system("pwd")
+    os.system("rm -rf /var/lib/jenkins/workspace/z-s464913-create-dataset-1/data/")
 
-    df = load_data("creditcard.csv")
-    df = normalize_data(df)
-
-    undersample_data, X_undersample, y_undersample = create_undersample_data(df)
-    X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = (
-        split_undersample_data(X_undersample, y_undersample)
-    )
-    save_undersample_data(
-        undersample_data,
-        X_train_undersample,
-        X_test_undersample,
-        y_train_undersample,
-        y_test_undersample,
-    )
-
-    X_train, X_test, y_train, y_test = split_whole_data(df)
-    save_whole_data(df, X_train, X_test, y_train, y_test)
+    os.system("ls -l /var/lib/jenkins/workspace/z-s464913-create-dataset-1/")
 
 
 if __name__ == "__main__":