change creating datasets
This commit is contained in:
parent
81c0a9a7dd
commit
4aae76c38b
1
Jenkinsfile
vendored
1
Jenkinsfile
vendored
@ -25,7 +25,6 @@ pipeline{
|
||||
steps{
|
||||
withEnv(["CUTOFF=${params.CUTOFF}"]) {
|
||||
sh "chmod 777 ./data.sh"
|
||||
sh "./data.sh"
|
||||
}
|
||||
}}
|
||||
stage('Archive artifacts'){
|
||||
|
3
stats.py
3
stats.py
@ -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)
|
||||
|
Loading…
Reference in New Issue
Block a user