From 00367909c236a7732af2e013b8d05f9022debe17 Mon Sep 17 00:00:00 2001
From: Alicja Szulecka <73056579+AliSzu@users.noreply.github.com>
Date: Tue, 2 Apr 2024 19:36:23 +0200
Subject: [PATCH] update

---
 IUM_2.py    |  7 -------
 Jenkinsfile | 10 ++++++++++
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/IUM_2.py b/IUM_2.py
index 6e5af93..5fa7a25 100644
--- a/IUM_2.py
+++ b/IUM_2.py
@@ -1,13 +1,7 @@
 import pandas as pd
-import kaggle
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
 
-def download_file():
-    kaggle.api.authenticate()
-    kaggle.api.dataset_download_files('nasa/meteorite-landings', path='.', unzip=True)
-    
-
 def split(data):
     meteorite_train, meteorite_test = train_test_split(data, test_size=0.2, random_state=1)
     meteorite_train, meteorite_val = train_test_split(meteorite_train, test_size=0.25, random_state=1)
@@ -28,7 +22,6 @@ def preprocessing(data):
     data.loc[(data['mass'].isnull()) & (data['name'].str.startswith('Österplana')), 'mass'] = 0
     return data
 
-download_file()
 data = pd.read_csv("meteorite-landings.csv")
 meteorite_train, meteorite_test, meteorite_val = split(data)
 
diff --git a/Jenkinsfile b/Jenkinsfile
index 401b4d8..c9f4481 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -11,6 +11,16 @@ pipeline {
                checkout scm
             }
         }
+         stage('Download dataset') {
+      steps {
+        withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}", "KAGGLE_KEY=${params.KAGGLE_KEY}"]) {
+          sh 'pip install kaggle'
+          sh 'kaggle datasets download -d nasa/meteorite-landings'
+          sh 'unzip -o meteorite-landings.zip'
+          sh 'rm meteorite-landings.zip'
+        }
+      }
+    }
      stage('Build') {
          steps {
             script {