change creating datasets
Some checks failed
s434804-training/pipeline/head This commit looks good
s434804-evaluation/pipeline/head There was a failure building this commit

This commit is contained in:
Dawid 2021-05-14 22:48:23 +02:00
parent 81c0a9a7dd
commit 4aae76c38b
2 changed files with 3 additions and 1 deletions

1
Jenkinsfile vendored
View File

@ -25,7 +25,6 @@ pipeline{
steps{
withEnv(["CUTOFF=${params.CUTOFF}"]) {
sh "chmod 777 ./data.sh"
sh "./data.sh"
}
}}
stage('Archive artifacts'){

View File

@ -11,6 +11,9 @@ df = pd.read_csv('country_vaccinations.csv')
# podział danych na train/validate/test (6:2:2) za pomocą biblioteki numpy i pandas
train, validate, test = np.split(df.sample(frac=1), [int(.6*len(df)), int(.8*len(df))])
train.to_csv("train.csv")
validate.to_csv("validate.csv")
test.to_csv("test.csv")
# Wypisanie ilości elementów w poszczególnych ramkach danych
print("Whole set size".ljust(20), df.size)
print("Train set size: ".ljust(20), train.size)