apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-09 03:52:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix directory issue when running tests for first time

Browse source
This commit is contained in:
abigailt 2021-07-12 14:58:58 +03:00
parent bcc3d67ba4
commit 60d48ab388
2 changed files with 13 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

10
apt/utils.py
View file

@ -2,7 +2,7 @@ from sklearn import datasets, model_selection
import sklearn.preprocessing import sklearn.preprocessing
import pandas as pd import pandas as pd
import ssl import ssl
from os import path from os import path, mkdir
from six.moves.urllib.request import urlretrieve from six.moves.urllib.request import urlretrieve
@ -40,9 +40,13 @@ def get_adult_dataset():
'label'] 'label']
train_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data' train_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data'
test_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test' test_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test'
data_dir = '../datasets/adult'
train_file = '../datasets/adult/train' train_file = '../datasets/adult/train'
test_file = '../datasets/adult/test' test_file = '../datasets/adult/test'
if not path.exists(data_dir):
mkdir(data_dir)
ssl._create_default_https_context = ssl._create_unverified_context ssl._create_default_https_context = ssl._create_unverified_context
if not path.exists(train_file): if not path.exists(train_file):
urlretrieve(train_url, train_file) urlretrieve(train_url, train_file)
@ -139,8 +143,12 @@ def get_nursery_dataset(raw: bool = True, test_set: float = 0.2, transform_socia
:return: Dataset and labels as pandas dataframes. :return: Dataset and labels as pandas dataframes.
""" """
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/nursery/nursery.data' url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/nursery/nursery.data'
data_dir = '../datasets/nursery'
data_file = '../datasets/nursery/data' data_file = '../datasets/nursery/data'
if not path.exists(data_dir):
mkdir(data_dir)
ssl._create_default_https_context = ssl._create_unverified_context ssl._create_default_https_context = ssl._create_unverified_context
if not path.exists(data_file): if not path.exists(data_file):
urlretrieve(url, data_file) urlretrieve(url, data_file)

4
datasets/.gitignore vendored Normal file
View file

@ -0,0 +1,4 @@
# Ignore everything in this directory
*
# Except this file
!.gitignore