From 36f0ac9370230010e998121f7a26b35b80316c6f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Miko=C5=82aj=20Pokrywka?= <mp7961@gmail.com>
Date: Sun, 3 Apr 2022 15:16:37 +0200
Subject: [PATCH] r

---
 Jenkinsfile                  | 3 ++-
 download_data_and_process.py | 6 +++---
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/Jenkinsfile b/Jenkinsfile
index 016f19d..12bb502 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -32,7 +32,8 @@ pipeline {
                 withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
                          "KAGGLE_KEY=${params.KAGGLE_KEY}",
                          "CUTOFF=${params.CUTOFF}"]) {
-                            sh 'python3 ./download_data_and_process.py'
+                             sh './process_data.sh'
+                            // sh 'python3 ./download_data_and_process.py'
                             archiveArtifacts artifacts: "data_test.csv, data_dev.csv, data_train.csv, column_titles.csv"
                 }
             }
diff --git a/download_data_and_process.py b/download_data_and_process.py
index 9df15b5..cf9c33d 100644
--- a/download_data_and_process.py
+++ b/download_data_and_process.py
@@ -1,10 +1,10 @@
 import subprocess
 import pandas as pd
 import numpy as np
-import kaggle
+# import kaggle
 
-kaggle.api.authenticate()
-kaggle.api.dataset_download_files('shivamb/real-or-fake-fake-jobposting-prediction', path='fake_job_postings.csv', unzip=True)
+# kaggle.api.authenticate()
+# kaggle.api.dataset_download_files('shivamb/real-or-fake-fake-jobposting-prediction', path='fake_job_postings.csv', unzip=True)
 data=pd.read_csv('fake_job_postings.csv/fake_job_postings.csv')
 data = data.replace(np.nan, '', regex=True)