From 0cda5fe099bf1d300bff4c698fe840522a808880 Mon Sep 17 00:00:00 2001
From: s464953 <micgul1@st.amu.edu.pl>
Date: Sat, 23 Mar 2024 20:11:47 +0100
Subject: [PATCH] Added download script

---
 Jenkinsfile         | 50 +++++++++++++++++++++------------------------
 download_dataset.sh | 46 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+), 27 deletions(-)
 create mode 100644 download_dataset.sh

diff --git a/Jenkinsfile b/Jenkinsfile
index ab8c194..1692276 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -1,27 +1,23 @@
-node {
- stage('Preparation') { 
-     properties([
-         parameters([
-             string(
-                 defaultValue: 'tomaszzitkiewicz',
-                 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'
-             )
-         ])
-     ])
- }
- stage('Build') {
-     // Run the maven build
-     withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
-              "KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
-         sh 'echo KAGGLE_USERNAME: $KAGGLE_USERNAME'
-         sh 'kaggle datasets list'
-     }
- }
-}
\ No newline at end of file
+pipeline {
+    agent any
+    
+    stages {
+        stage('Clone Repository') {
+            steps {
+                git 'https://git.wmi.amu.edu.pl/s464953/ium_464953.git'
+            }
+        }
+        stage('Run Script') {
+            steps {
+                script {
+                    sh 'bash download_dataset.sh $KAGGLE_USERNAME $KAGGLE_KEY'
+                }
+            }
+        }
+        stage('Archive Artifacts') {
+            steps {
+                archiveArtifacts artifacts: 'artifacts/*', onlyIfSuccessful: true
+            }
+        }
+    }
+}
diff --git a/download_dataset.sh b/download_dataset.sh
new file mode 100644
index 0000000..664f76c
--- /dev/null
+++ b/download_dataset.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+
+pip install kaggle --upgrade
+
+kaggle_username=$1
+kaggle_key=$2
+
+# Ustawienie zmiennych środowiskowych
+export KAGGLE_USERNAME=$kaggle_username
+export KAGGLE_KEY=$kaggle_key
+
+kaggle datasets download brunoalercon123/top-200-spotify-songs-dataset
+
+unzip top-200-spotify-songs-dataset.zip
+
+shuf Spotify-200-Songs.csv -o shuffled_spotify.csv
+
+head -n 100 shuffled_spotify.csv > subset1.csv
+tail -n 100 shuffled_spotify.csv > subset2.csv
+
+cut -d ',' -f 1,2,3 shuffled_spotify.csv > trimmed_spotify.csv
+
+cut -d ',' -f 1,2,4,5,6 shuffled_spotify.csv > processed_spotify.csv
+
+echo "Shuffled dataset:" > results.txt
+head shuffled_spotify.csv >> results.txt
+echo "" >> results.txt
+
+echo "Subset 1:" >> results.txt
+head subset1.csv >> results.txt
+echo "" >> results.txt
+
+echo "Subset 2:" >> results.txt
+head subset2.csv >> results.txt
+echo "" >> results.txt
+
+echo "Trimmed dataset:" >> results.txt
+head trimmed_spotify.csv >> results.txt
+echo "" >> results.txt
+
+echo "Processed dataset:" >> results.txt
+head processed_spotify.csv >> results.txt
+echo "" >> results.txt
+
+mkdir -p artifacts
+mv shuffled_spotify.csv subset1.csv subset2.csv trimmed_spotify.csv processed_spotify.csv results.txt artifacts/