docker-v3

Jenkinsfile2

@@ -8,8 +8,7 @@ pipeline {
             steps {
                 copyArtifacts fingerprintArtifacts: true, projectName: 's434732-create-dataset', selector: buildParameter('BUILD_SELECTOR')
                 
-				sh "chmod 777 ./skrypt_zad2_stats.sh"
+				 sh 'python3 "./skrypt_stat.py" > stats.txt'
-                sh "./skrypt_zad2_stats.sh"
                 
 				archiveArtifacts "stats.txt"
             }

skrypt_stat.py

@@ -1,31 +1,12 @@
 import pandas as pd
-from sklearn.model_selection import train_test_split
-from sklearn import preprocessing
-import kaggle
 
-kaggle.api.authenticate()
+import pandas as pd
 
-kaggle.api.dataset_download_files('martj42/international-football-results-from-1872-to-2017', path='.', unzip=True)
+train = pd.read_csv('train.csv')
+test = pd.read_csv('test.csv')
+valid = pd.read_csv('valid.csv')
 
-results = pd.read_csv('results.csv')
-
-#brak wierszy z NaN
-results.dropna()
-
-#normalizacja itp
-for collumn in ['home_team', 'away_team', 'tournament', 'city', 'country']:
-    results[collumn] = results[collumn].str.lower()
-    
-# Podział zbioru 6:1:1
-train, test = train_test_split(results, test_size= 1 - 0.6)
-
-valid, test = train_test_split(test, test_size=0.5) 
-
-print("All data: ", results.size)
 print("Train size: ", train.size)
 print("Test size: ", test.size)
 print("Validate size: ", valid.size)
-print(results.describe(include='all'))
 
-# sprawdzenie czy cały dataset oraz podział na podzbiory jest równy
-print(train.size+test.size+valid.size)