Dockerfile

Jenkinsfile

@@ -16,6 +16,12 @@ pipeline {
   }
 
   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}"]) {
@@ -35,7 +41,7 @@ pipeline {
 
       steps {
         sh 'chmod +x create-dataset.py'
-        sh 'python3 ./create-dataset.py $KAGGLE_USERNAME'
+        sh 'python3 ./create-dataset.py'
       }
     }
 

create-dataset.py

@@ -1,6 +1,4 @@
 import os
-import sys
-from kaggle.api.kaggle_api_extended import KaggleApi
 import pandas as pd
 import numpy as np
 
@@ -9,14 +7,6 @@ from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split
 
 
-def download_kaggle_dataset():
-    os.environ["KAGGLE_USERNAME"] = "vskyper"
-    os.environ["KAGGLE_KEY"] = sys.argv[1]
-    kaggle = KaggleApi()
-    kaggle.authenticate()
-    kaggle.dataset_download_files("mlg-ulb/creditcardfraud", path="./", unzip=True)
-
-
 def load_data(name):
     df = pd.read_csv(name)
     return df