From 5a29b56c2723f8c28d094719a848d4fceefc1a31 Mon Sep 17 00:00:00 2001
From: szymonj98 <szymonj98@wp.pl>
Date: Sun, 3 Apr 2022 14:40:45 +0200
Subject: [PATCH] zadanie doker

---
 Dockerfile  | 22 ++++++++--------------
 Jenkinsfile | 41 ++++++++++-------------------------------
 kagle.py    |  4 ++--
 3 files changed, 20 insertions(+), 47 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 39d484a..a7bcc46 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,14 +1,8 @@
-FROM python:3.9
-
-
-RUN pip install --user kaggle
-RUN pip install --user pandas
-
-ADD . .
-ARG KAGGLE_USERNAME
-ARG KAGGLE_KEY
-
-RUN chmod a+x *.sh
-RUN ./dataset_download.sh
-
-CMD python kagle.py
\ No newline at end of file
+FROM ubuntu:latest
+WORKDIR /ium
+RUN apt update && apt install -y python3-pip
+RUN pip3 install pandas
+RUN pip3 install numpy
+RUN pip3 install sklearn
+COPY ./Steam-200k.csv ./
+COPY ./kagle.py ./
\ No newline at end of file
diff --git a/Jenkinsfile b/Jenkinsfile
index e39a7e1..a4d181c 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -1,34 +1,13 @@
 pipeline {
-    parameters {
-		string(
-			defaultValue: 'szymonjadczak',
-			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'
-		)
-	}
-	agent { 
-		dockerfile {
-            additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} -t s444386-create-dataset"
+    agent {
+        dockerfile true
         }
-	}
-	environment {
-		KAGGLE_USERNAME="$params.KAGGLE_USERNAME"
-		KAGGLE_KEY="$params.KAGGLE_KEY"
-		CUTOFF="$params.CUTOFF"
-	}
-	stages {
-		stage('Stage 1') {
-			steps {
-				echo 'Hello world!!!'
-				checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s444386/ium_444386']]])				
-				archiveArtifacts 'Steam-200k.csv'
-			}
-		}
-	}    
+    stages {
+        stage('Stage 1') {
+            steps {
+				    sh 'chmod u+x ./kagle.py'
+                    sh 'python3 kagle.py'
+				}
+            }
+        }		
 }
diff --git a/kagle.py b/kagle.py
index 1bf202e..7cb7eca 100644
--- a/kagle.py
+++ b/kagle.py
@@ -2,8 +2,8 @@ import os
 import pandas as pd
 from sklearn.model_selection import train_test_split
 
-os.system("kaggle datasets download -d tamber/steam-video-games")
-os.system("unzip -o steam-video-games.zip")
+#os.system("kaggle datasets download -d tamber/steam-video-games")
+#os.system("unzip -o steam-video-games.zip")
 
 steam=pd.read_csv('Steam-200k.csv',usecols=[0,1,2,3],names=['userId','game','behavior','hoursPlayed'])
 steam.isnull().values.any()