From e75c417504a20ec241f666f7a3c479c8f7cdc5d0 Mon Sep 17 00:00:00 2001
From: piotrwrzodak <piotrwrzodakk@gmail.com>
Date: Thu, 11 May 2023 22:58:08 +0200
Subject: [PATCH] 4.3.1 v8

---
 Dockerfile                        | 7 +++++++
 Jenkinsfile-create-dataset-docker | 7 +------
 create-dataset.py                 | 8 ++++----
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 804a083..4c47d7e 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -4,3 +4,10 @@ RUN apt-get update && \
     apt-get install -y python3 python3-pip
 
 RUN pip3 install pandas numpy
+
+WORKDIR /app
+
+COPY create-dataset.py /app
+COPY data/barcelona_weekends.csv /app
+
+CMD ["python3", "create-dataset.py"]
\ No newline at end of file
diff --git a/Jenkinsfile-create-dataset-docker b/Jenkinsfile-create-dataset-docker
index cc07fd6..5a3ec4c 100644
--- a/Jenkinsfile-create-dataset-docker
+++ b/Jenkinsfile-create-dataset-docker
@@ -44,12 +44,7 @@ pipeline {
                 dockerfile true
             }
             steps {
-                sh 'python3 create-dataset.py'
-            }
-        }
-        stage('Archive') {
-            steps {
-                archiveArtifacts artifacts: 'data/barcelona_weekends.train.csv, data/barcelona_weekends.dev.csv, data/barcelona_weekends.test.csv', fingerprint: true
+                archiveArtifacts artifacts: 'barcelona_weekends.train.csv, barcelona_weekends.dev.csv, barcelona_weekends.test.csv', fingerprint: true
             }
         }
    }
diff --git a/create-dataset.py b/create-dataset.py
index 281d1be..d93da1e 100644
--- a/create-dataset.py
+++ b/create-dataset.py
@@ -5,16 +5,16 @@ import numpy as np
 
 cutoff = 10
 
-data = pd.read_csv('./data/barcelona_weekends.csv')
+data = pd.read_csv('./barcelona_weekends.csv')
 data = data.sample(cutoff)
 data = data.iloc[:, 1:]
 
 train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42),
                                         [int(.6 * len(data)), int(.8 * len(data))])
 
-train_set.to_csv('data/barcelona_weekends.train.csv', index=False)
-dev_set.to_csv('data/barcelona_weekends.dev.csv', index=False)
-test_set.to_csv('data/barcelona_weekends.test.csv', index=False)
+train_set.to_csv('barcelona_weekends.train.csv', index=False)
+dev_set.to_csv('barcelona_weekends.dev.csv', index=False)
+test_set.to_csv('barcelona_weekends.test.csv', index=False)
 
 
 check = pd.read_csv('./train.csv')