From ab20b9c0de2b0041872c92aea0b57007ea15ee6a Mon Sep 17 00:00:00 2001 From: Mateusz Date: Mon, 1 Apr 2024 16:20:48 +0200 Subject: [PATCH] Dockerfile --- Jenkinsfile | 2 +- create-dataset.py | 22 +++++++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/Jenkinsfile b/Jenkinsfile index a83cf3f..91a827c 100644 --- a/Jenkinsfile +++ b/Jenkinsfile @@ -2,7 +2,7 @@ pipeline { agent { dockerfile { filename 'Dockerfile' - args '-u root -v $HOME:/app' + args '-u root' } } diff --git a/create-dataset.py b/create-dataset.py index 00ea4e0..e307f24 100644 --- a/create-dataset.py +++ b/create-dataset.py @@ -69,11 +69,11 @@ def save_undersample_data( y_train_undersample, y_test_undersample, ): - undersample_data.to_csv("/data/undersample_data.csv", index=False) - X_train_undersample.to_csv("/data/X_train_undersample.csv", index=False) - X_test_undersample.to_csv("/data/X_test_undersample.csv", index=False) - y_train_undersample.to_csv("/data/y_train_undersample.csv", index=False) - y_test_undersample.to_csv("/data/y_test_undersample.csv", index=False) + undersample_data.to_csv("data/undersample_data.csv", index=False) + X_train_undersample.to_csv("data/X_train_undersample.csv", index=False) + X_test_undersample.to_csv("data/X_test_undersample.csv", index=False) + y_train_undersample.to_csv("data/y_train_undersample.csv", index=False) + y_test_undersample.to_csv("data/y_test_undersample.csv", index=False) def split_whole_data(df): @@ -87,16 +87,16 @@ def split_whole_data(df): def save_whole_data(df, X_train, X_test, y_train, y_test): - df.to_csv("/data/creditcard.csv", index=False) - X_train.to_csv("/data/X_train.csv", index=False) - X_test.to_csv("/data/X_test.csv", index=False) - y_train.to_csv("/data/y_train.csv", index=False) - y_test.to_csv("/data/y_test.csv", index=False) + df.to_csv("data/creditcard.csv", index=False) + X_train.to_csv("data/X_train.csv", index=False) + X_test.to_csv("data/X_test.csv", index=False) + y_train.to_csv("data/y_train.csv", index=False) + y_test.to_csv("data/y_test.csv", index=False) def main(): download_kaggle_dataset() - os.makedirs("/data", exist_ok=True) + os.makedirs("data", exist_ok=True) df = load_data("creditcard.csv") df = normalize_data(df)