From 8a6ab2c57ae7f335e142319e920ddeab6b349688 Mon Sep 17 00:00:00 2001 From: Mateusz Date: Mon, 1 Apr 2024 15:27:29 +0200 Subject: [PATCH] Dockerfile --- create-dataset.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/create-dataset.py b/create-dataset.py index c736b8a..a09e03c 100644 --- a/create-dataset.py +++ b/create-dataset.py @@ -1,4 +1,5 @@ import os +from kaggle.api.kaggle_api_extended import KaggleApi import pandas as pd import numpy as np @@ -8,9 +9,10 @@ from sklearn.model_selection import train_test_split def download_kaggle_dataset(): - os.system("kaggle datasets download -d mlg-ulb/creditcardfraud") - os.system("unzip creditcardfraud.zip") - os.system("rm creditcardfraud.zip") + os.system("pwd") + kaggle = KaggleApi() + kaggle.authenticate() + kaggle.dataset_download_files("mlg-ulb/creditcardfraud", path="./", unzip=True) def load_data(name):