apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-05-02 16:22:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

using dataset wrapper on anonymizer

Browse source
This commit is contained in:
olasaadi 2022-03-01 02:28:41 +02:00
parent f2df2fcc8c
commit 1280b849f4
3 changed files with 64 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

31
apt/utils/dataset_utils.py
View file

@ -5,6 +5,8 @@ import ssl
from os import path, mkdir
from six.moves.urllib.request import urlretrieve
from apt.utils.datasets import BaseDataset, Data
def _load_iris(test_set_size: float = 0.3):
iris = datasets.load_iris()
@ -14,8 +16,10 @@ def _load_iris(test_set_size: float = 0.3):
# Split training and test sets
x_train, x_test, y_train, y_test = model_selection.train_test_split(data, labels, test_size=test_set_size,
random_state=18, stratify=labels)
return (x_train, y_train), (x_test, y_test)
train_dataset = BaseDataset(x_train, y_train)
test_dataset = BaseDataset(x_test, y_test)
dataset = Data(train_dataset, test_dataset)
return dataset
def get_iris_dataset():
@ -37,7 +41,10 @@ def _load_diabetes(test_set_size: float = 0.3):
x_train, x_test, y_train, y_test = model_selection.train_test_split(data, labels, test_size=test_set_size,
random_state=18)
return (x_train, y_train), (x_test, y_test)
train_dataset = BaseDataset(x_train, y_train)
test_dataset = BaseDataset(x_test, y_test)
dataset = Data(train_dataset, test_dataset)
return dataset
def get_diabetes_dataset():
@ -97,7 +104,10 @@ def get_german_credit_dataset(test_set: float = 0.3):
x_test.reset_index(drop=True, inplace=True)
y_test.reset_index(drop=True, inplace=True)
return (x_train, y_train), (x_test, y_test)
train_dataset = BaseDataset(x_train, y_train)
test_dataset = BaseDataset(x_test, y_test)
dataset = Data(train_dataset, test_dataset)
return dataset
def _modify_german_dataset(data):
@ -156,8 +166,10 @@ def get_adult_dataset():
y_train = train.loc[:, 'label']
x_test = test.drop(['label'], axis=1)
y_test = test.loc[:, 'label']
return (x_train, y_train), (x_test, y_test)
train_dataset = BaseDataset(x_train, y_train)
test_dataset = BaseDataset(x_test, y_test)
dataset = Data(train_dataset, test_dataset)
return dataset
def _modify_adult_dataset(data):
@ -315,5 +327,10 @@ def get_nursery_dataset(raw: bool = True, test_set: float = 0.2, transform_socia
y_train = train.loc[:, "label"]
x_test = test.drop(["label"], axis=1)
y_test = test.loc[:, "label"]
x_train = x_train.astype(str)
x_test = x_test.astype(str)
return (x_train, y_train), (x_test, y_test)
train_dataset = BaseDataset(x_train, y_train)
test_dataset = BaseDataset(x_test, y_test)
dataset = Data(train_dataset, test_dataset)
return dataset