separate repo for lab4

lab4/Dockerfile

@@ -0,0 +1,12 @@
+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 ./lego_sets.csv ./
+COPY ./process_dataset.py ./

lab4/Jenkinsfile

@@ -0,0 +1,15 @@
+pipeline {
+    agent {
+        dockerfile true
+        }
+    stages {
+        stage('Stage 1') {
+            steps {
+				    sh 'chmod u+x ./process_dataset.py'
+                    echo 'Processing dataset...'
+                    sh 'python3 process_dataset.py'
+					echo 'Dataset processed'
+				}
+            }
+        }		
+}

lab4/Jenkinsfile1

@@ -0,0 +1,15 @@
+pipeline {
+    agent {
+        docker { image 's449288/ium:2.0' }
+        }
+    stages {
+        stage('Stage 1') {
+            steps {
+				    sh 'chmod u+x ./process_dataset.py'
+                    echo 'Processing dataset...'
+                    sh 'python3 process_dataset.py'
+					echo 'Dataset processed'
+				}
+            }
+        }		
+}

lab4/process_dataset.py

@@ -0,0 +1,30 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+
+# usuwamy przy okazji puste pola
+lego = pd.read_csv('lego_sets.csv', encoding='utf-8').dropna()
+
+# list_price moze byc do dwoch miejsc po przecinku
+lego['list_price'] = lego['list_price'].round(2)
+
+# num_reviews, piece_count i prod_id moga byc wartosciami calkowitymi
+lego['num_reviews'] = lego['num_reviews'].apply(np.int64)
+lego['piece_count'] = lego['piece_count'].apply(np.int64)
+lego['prod_id'] = lego['prod_id'].apply(np.int64)
+
+# wglad, statystyki
+print(lego)
+print(lego.describe(include='all'))
+
+# pierwszy podzial, wydzielamy zbior treningowy
+lego_train, lego_rem = train_test_split(lego, train_size=0.8, random_state=1)
+
+# drugi podział, wydzielamy walidacyjny i testowy
+lego_valid, lego_test = train_test_split(lego_rem, test_size=0.5, random_state=1)
+
+# zapis
+lego.to_csv('lego_sets_clean.csv', index=None, header=True)
+lego_train.to_csv('lego_sets_clean_train.csv', index=None, header=True)
+lego_valid.to_csv('lego_sets_clean_valid.csv', index=None, header=True)
+lego_test.to_csv('lego_sets_clean_test.csv', index=None, header=True)