ium_444452/Jenkinsfile.create_dataset

node {
    docker.image('s444452/ium:1.2').inside {
        stage('Preparation') {
            properties([
                parameters([
                string(
                 defaultValue: 'adamosiowy',
                 description: 'Kaggle username',
                 name: 'KAGGLE_USERNAME',
                 trim: false
                ),
                password(
                 defaultValue: '',
                 description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
                 name: 'KAGGLE_KEY'
                ),
                string(
                 defaultValue: "10000",
                 description: 'Determine the size of dataset',
                 name: 'CUTOFF'
                )
                ])
            ])
        }
        stage('Clone repository') {
            checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[credentialsId: '5e0a58a0-03ad-41dd-beff-7b8a07c7fe0c', url: 'https://git.wmi.amu.edu.pl/s444452/ium_444452.git']]])
        }
        stage('Run script') {
            withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                "KAGGLE_KEY=${params.KAGGLE_KEY}","CUTOFF=${params.CUTOFF}"]) {
                sh "rm real-or-fake-fake-jobposting-prediction.zip"
                sh "ls"
                sh "python3 download_dataset.py '.' 'dataset.csv'"
            }
        }
        stage('Archive artifacts') {
            archiveArtifacts 'dataset.csv' 'train_data.csv' 'test_data.csv' 'dev_data.csv'
        }
    }
}