From 81241038479a1fb4f2afbb613c382632936f0018 Mon Sep 17 00:00:00 2001
From: Daniel Porzucek <danpor@st.amu.edu.pl>
Date: Wed, 20 Mar 2024 17:02:31 +0100
Subject: [PATCH] added cutoff parameter + displaying only 5 first lines

---
 Jenkinsfile      |  6 ++++++
 data_download.sh | 13 ++++++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/Jenkinsfile b/Jenkinsfile
index a4ce9a4..3555c2d 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -7,6 +7,12 @@ pipeline {
         name: 'KAGGLE_USERNAME',
         trim: false
     )
+    string(
+        defaultValue: '6',
+        description: 'Take only first {CUTOFF} values from dataset',
+        name: 'CUTOFF',
+        trim: false
+    )
     password(
         defaultValue: '',
         description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
diff --git a/data_download.sh b/data_download.sh
index 096296b..5f096a1 100644
--- a/data_download.sh
+++ b/data_download.sh
@@ -1,5 +1,12 @@
 #!/bin/bash
+figlet "DOWNLOAD DATA"
 kaggle datasets download iabhishekofficial/mobile-price-classification --unzip --force
-cat test.csv
-sed 's/\([^,]*\),\(.*\)/\2/'  test.csv
-cat test.csv
+
+
+figlet "TESTSET BEFORE ID COLUMN CUT"
+head -n 5 test.csv
+cut -d',' -f2- test.csv > test_without_id_column.csv
+
+
+figlet "TESTSET AFTER ID COLUMN CUT"
+head -n 5 test_without_id_column.csv