From 4aae76c38bdd70667df0753af524e67199f06ad6 Mon Sep 17 00:00:00 2001
From: Dawid <dawid.wietrzych@gmail.com>
Date: Fri, 14 May 2021 22:48:23 +0200
Subject: [PATCH] change creating datasets

---
 Jenkinsfile | 1 -
 stats.py    | 3 +++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/Jenkinsfile b/Jenkinsfile
index ef7d8a4..418a3ce 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -25,7 +25,6 @@ pipeline{
             steps{
             withEnv(["CUTOFF=${params.CUTOFF}"]) {
                 sh "chmod 777 ./data.sh"
-                sh "./data.sh"
             }
         }}
         stage('Archive artifacts'){
diff --git a/stats.py b/stats.py
index 36bfa79..cfdbde0 100644
--- a/stats.py
+++ b/stats.py
@@ -11,6 +11,9 @@ df = pd.read_csv('country_vaccinations.csv')
 # podział danych na train/validate/test (6:2:2) za pomocą biblioteki numpy i pandas
 train, validate, test = np.split(df.sample(frac=1), [int(.6*len(df)), int(.8*len(df))])
 
+train.to_csv("train.csv")
+validate.to_csv("validate.csv")
+test.to_csv("test.csv")
 # Wypisanie ilości elementów w poszczególnych ramkach danych
 print("Whole set size".ljust(20), df.size)
 print("Train set size: ".ljust(20), train.size)