mirror of
https://github.com/IBM/ai-privacy-toolkit.git
synced 2026-04-25 04:46:21 +02:00
Data and Model wrappers (#26)
* Squashed commit of wrappers:
Wrapper minimizer
* apply dataset wrapper on minimizer
* apply changes on minimization notebook
* add black_box_access and unlimited_queries params
Dataset wrapper anonymizer
Add features_names to ArrayDataset
and allow providing features names in QI and Cat features not just indexes
update notebooks
categorical features and QI passed by indexes
dataset include feature names and is_pandas param
add pytorch Dataset
Remove redundant code.
Use data wrappers in model wrapper APIs.
add generic dataset components
Create initial version of wrappers for models
* Fix handling of categorical features
This commit is contained in:
abigailgold
GitHub
parent
d53818644e
commit
2b2dab6bef
17 changed files with 1340 additions and 752 deletions
|
|
@ -29,198 +29,15 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 61,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>parents</th>\n",
|
||||
" <th>has_nurs</th>\n",
|
||||
" <th>form</th>\n",
|
||||
" <th>children</th>\n",
|
||||
" <th>housing</th>\n",
|
||||
" <th>finance</th>\n",
|
||||
" <th>social</th>\n",
|
||||
" <th>health</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>8450</th>\n",
|
||||
" <td>pretentious</td>\n",
|
||||
" <td>very_crit</td>\n",
|
||||
" <td>foster</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>12147</th>\n",
|
||||
" <td>great_pret</td>\n",
|
||||
" <td>very_crit</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>inconv</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>recommended</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2780</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>11924</th>\n",
|
||||
" <td>great_pret</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>foster</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>59</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>proper</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>2</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>...</th>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>5193</th>\n",
|
||||
" <td>pretentious</td>\n",
|
||||
" <td>less_proper</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>inconv</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>recommended</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1375</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>less_proper</td>\n",
|
||||
" <td>incomplete</td>\n",
|
||||
" <td>2</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>priority</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>10318</th>\n",
|
||||
" <td>great_pret</td>\n",
|
||||
" <td>less_proper</td>\n",
|
||||
" <td>foster</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>priority</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6396</th>\n",
|
||||
" <td>pretentious</td>\n",
|
||||
" <td>improper</td>\n",
|
||||
" <td>completed</td>\n",
|
||||
" <td>3</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>recommended</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>485</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>proper</td>\n",
|
||||
" <td>incomplete</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>inconv</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>10366 rows × 8 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" parents has_nurs form children housing finance \\\n",
|
||||
"8450 pretentious very_crit foster 1 less_conv convenient \n",
|
||||
"12147 great_pret very_crit complete 1 critical inconv \n",
|
||||
"2780 usual critical complete 4 less_conv convenient \n",
|
||||
"11924 great_pret critical foster 1 critical convenient \n",
|
||||
"59 usual proper complete 2 convenient convenient \n",
|
||||
"... ... ... ... ... ... ... \n",
|
||||
"5193 pretentious less_proper complete 1 convenient inconv \n",
|
||||
"1375 usual less_proper incomplete 2 less_conv convenient \n",
|
||||
"10318 great_pret less_proper foster 4 convenient convenient \n",
|
||||
"6396 pretentious improper completed 3 less_conv convenient \n",
|
||||
"485 usual proper incomplete 1 critical inconv \n",
|
||||
"\n",
|
||||
" social health \n",
|
||||
"8450 1 not_recom \n",
|
||||
"12147 1 recommended \n",
|
||||
"2780 1 not_recom \n",
|
||||
"11924 1 not_recom \n",
|
||||
"59 0 not_recom \n",
|
||||
"... ... ... \n",
|
||||
"5193 0 recommended \n",
|
||||
"1375 1 priority \n",
|
||||
"10318 0 priority \n",
|
||||
"6396 1 recommended \n",
|
||||
"485 1 not_recom \n",
|
||||
"\n",
|
||||
"[10366 rows x 8 columns]"
|
||||
]
|
||||
"text/plain": " parents has_nurs form children housing finance \\\n8450 pretentious very_crit foster 1 less_conv convenient \n12147 great_pret very_crit complete 1 critical inconv \n2780 usual critical complete 4 less_conv convenient \n11924 great_pret critical foster 1 critical convenient \n59 usual proper complete 2 convenient convenient \n... ... ... ... ... ... ... \n5193 pretentious less_proper complete 1 convenient inconv \n1375 usual less_proper incomplete 2 less_conv convenient \n10318 great_pret less_proper foster 4 convenient convenient \n6396 pretentious improper completed 3 less_conv convenient \n485 usual proper incomplete 1 critical inconv \n\n social health \n8450 1 not_recom \n12147 1 recommended \n2780 1 not_recom \n11924 1 not_recom \n59 0 not_recom \n... ... ... \n5193 0 recommended \n1375 1 priority \n10318 0 priority \n6396 1 recommended \n485 1 not_recom \n\n[10366 rows x 8 columns]",
|
||||
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>parents</th>\n <th>has_nurs</th>\n <th>form</th>\n <th>children</th>\n <th>housing</th>\n <th>finance</th>\n <th>social</th>\n <th>health</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>8450</th>\n <td>pretentious</td>\n <td>very_crit</td>\n <td>foster</td>\n <td>1</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>1</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>12147</th>\n <td>great_pret</td>\n <td>very_crit</td>\n <td>complete</td>\n <td>1</td>\n <td>critical</td>\n <td>inconv</td>\n <td>1</td>\n <td>recommended</td>\n </tr>\n <tr>\n <th>2780</th>\n <td>usual</td>\n <td>critical</td>\n <td>complete</td>\n <td>4</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>1</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>11924</th>\n <td>great_pret</td>\n <td>critical</td>\n <td>foster</td>\n <td>1</td>\n <td>critical</td>\n <td>convenient</td>\n <td>1</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>59</th>\n <td>usual</td>\n <td>proper</td>\n <td>complete</td>\n <td>2</td>\n <td>convenient</td>\n <td>convenient</td>\n <td>0</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>5193</th>\n <td>pretentious</td>\n <td>less_proper</td>\n <td>complete</td>\n <td>1</td>\n <td>convenient</td>\n <td>inconv</td>\n <td>0</td>\n <td>recommended</td>\n </tr>\n <tr>\n <th>1375</th>\n <td>usual</td>\n <td>less_proper</td>\n <td>incomplete</td>\n <td>2</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>1</td>\n <td>priority</td>\n </tr>\n <tr>\n <th>10318</th>\n <td>great_pret</td>\n <td>less_proper</td>\n <td>foster</td>\n <td>4</td>\n <td>convenient</td>\n <td>convenient</td>\n <td>0</td>\n <td>priority</td>\n </tr>\n <tr>\n <th>6396</th>\n <td>pretentious</td>\n <td>improper</td>\n <td>completed</td>\n <td>3</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>1</td>\n <td>recommended</td>\n </tr>\n <tr>\n <th>485</th>\n <td>usual</td>\n <td>proper</td>\n <td>incomplete</td>\n <td>1</td>\n <td>critical</td>\n <td>inconv</td>\n <td>1</td>\n <td>not_recom</td>\n </tr>\n </tbody>\n</table>\n<p>10366 rows × 8 columns</p>\n</div>"
|
||||
},
|
||||
"execution_count": 61,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -230,7 +47,7 @@
|
|||
"import sys\n",
|
||||
"sys.path.insert(0, os.path.abspath('..'))\n",
|
||||
"\n",
|
||||
"from apt.utils import get_nursery_dataset\n",
|
||||
"from apt.utils.dataset_utils import get_nursery_dataset\n",
|
||||
"\n",
|
||||
"(x_train, y_train), (x_test, y_test) = get_nursery_dataset(transform_social=True)\n",
|
||||
"\n",
|
||||
|
|
@ -246,7 +63,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 62,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -263,9 +80,9 @@
|
|||
"from sklearn.preprocessing import OneHotEncoder\n",
|
||||
"\n",
|
||||
"x_train_str = x_train.astype(str)\n",
|
||||
"train_encoded = OneHotEncoder(sparse=False, drop='if_binary').fit_transform(x_train_str)\n",
|
||||
"train_encoded = OneHotEncoder(sparse=False).fit_transform(x_train_str)\n",
|
||||
"x_test_str = x_test.astype(str)\n",
|
||||
"test_encoded = OneHotEncoder(sparse=False, drop='if_binary').fit_transform(x_test_str)\n",
|
||||
"test_encoded = OneHotEncoder(sparse=False).fit_transform(x_test_str)\n",
|
||||
" \n",
|
||||
"model = DecisionTreeClassifier()\n",
|
||||
"model.fit(train_encoded, y_train)\n",
|
||||
|
|
@ -287,7 +104,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 91,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -323,14 +140,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 96,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6430638626278217\n"
|
||||
"1.0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -361,14 +178,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 55,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6980513216284006\n"
|
||||
"0.5122515917422342\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -408,224 +225,43 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 97,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>parents</th>\n",
|
||||
" <th>has_nurs</th>\n",
|
||||
" <th>form</th>\n",
|
||||
" <th>children</th>\n",
|
||||
" <th>housing</th>\n",
|
||||
" <th>finance</th>\n",
|
||||
" <th>social</th>\n",
|
||||
" <th>health</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>8450</th>\n",
|
||||
" <td>pretentious</td>\n",
|
||||
" <td>very_crit</td>\n",
|
||||
" <td>foster</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>12147</th>\n",
|
||||
" <td>great_pret</td>\n",
|
||||
" <td>very_crit</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>inconv</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>recommended</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2780</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>11924</th>\n",
|
||||
" <td>great_pret</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>foster</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>59</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>proper</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>2</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>...</th>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>5193</th>\n",
|
||||
" <td>pretentious</td>\n",
|
||||
" <td>less_proper</td>\n",
|
||||
" <td>complete</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>inconv</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>recommended</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1375</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>less_proper</td>\n",
|
||||
" <td>incomplete</td>\n",
|
||||
" <td>2</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>priority</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>10318</th>\n",
|
||||
" <td>great_pret</td>\n",
|
||||
" <td>less_proper</td>\n",
|
||||
" <td>foster</td>\n",
|
||||
" <td>4</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>priority</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6396</th>\n",
|
||||
" <td>pretentious</td>\n",
|
||||
" <td>improper</td>\n",
|
||||
" <td>completed</td>\n",
|
||||
" <td>3</td>\n",
|
||||
" <td>less_conv</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>recommended</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>485</th>\n",
|
||||
" <td>usual</td>\n",
|
||||
" <td>proper</td>\n",
|
||||
" <td>incomplete</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>critical</td>\n",
|
||||
" <td>convenient</td>\n",
|
||||
" <td>0</td>\n",
|
||||
" <td>not_recom</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>10366 rows × 8 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" parents has_nurs form children housing finance \\\n",
|
||||
"8450 pretentious very_crit foster 1 less_conv convenient \n",
|
||||
"12147 great_pret very_crit complete 1 critical inconv \n",
|
||||
"2780 usual critical complete 4 less_conv convenient \n",
|
||||
"11924 great_pret critical foster 1 critical convenient \n",
|
||||
"59 usual proper complete 2 convenient convenient \n",
|
||||
"... ... ... ... ... ... ... \n",
|
||||
"5193 pretentious less_proper complete 1 convenient inconv \n",
|
||||
"1375 usual less_proper incomplete 2 less_conv convenient \n",
|
||||
"10318 great_pret less_proper foster 4 convenient convenient \n",
|
||||
"6396 pretentious improper completed 3 less_conv convenient \n",
|
||||
"485 usual proper incomplete 1 critical convenient \n",
|
||||
"\n",
|
||||
" social health \n",
|
||||
"8450 0 not_recom \n",
|
||||
"12147 1 recommended \n",
|
||||
"2780 0 not_recom \n",
|
||||
"11924 0 not_recom \n",
|
||||
"59 0 not_recom \n",
|
||||
"... ... ... \n",
|
||||
"5193 0 recommended \n",
|
||||
"1375 1 priority \n",
|
||||
"10318 0 priority \n",
|
||||
"6396 1 recommended \n",
|
||||
"485 0 not_recom \n",
|
||||
"\n",
|
||||
"[10366 rows x 8 columns]"
|
||||
]
|
||||
"text/plain": " parents has_nurs form children housing finance \\\n0 pretentious very_crit foster 1 less_conv convenient \n1 great_pret very_crit complete 1 critical inconv \n2 usual critical complete 4 less_conv convenient \n3 great_pret critical foster 1 critical convenient \n4 usual proper complete 2 convenient convenient \n... ... ... ... ... ... ... \n10361 pretentious less_proper complete 1 convenient inconv \n10362 usual less_proper incomplete 2 less_conv convenient \n10363 great_pret less_proper foster 4 convenient convenient \n10364 pretentious improper completed 3 less_conv convenient \n10365 usual proper incomplete 1 critical convenient \n\n social health \n0 0 not_recom \n1 1 recommended \n2 0 not_recom \n3 0 not_recom \n4 0 not_recom \n... ... ... \n10361 0 recommended \n10362 1 priority \n10363 0 priority \n10364 1 recommended \n10365 0 not_recom \n\n[10366 rows x 8 columns]",
|
||||
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>parents</th>\n <th>has_nurs</th>\n <th>form</th>\n <th>children</th>\n <th>housing</th>\n <th>finance</th>\n <th>social</th>\n <th>health</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>pretentious</td>\n <td>very_crit</td>\n <td>foster</td>\n <td>1</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>0</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>1</th>\n <td>great_pret</td>\n <td>very_crit</td>\n <td>complete</td>\n <td>1</td>\n <td>critical</td>\n <td>inconv</td>\n <td>1</td>\n <td>recommended</td>\n </tr>\n <tr>\n <th>2</th>\n <td>usual</td>\n <td>critical</td>\n <td>complete</td>\n <td>4</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>0</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>3</th>\n <td>great_pret</td>\n <td>critical</td>\n <td>foster</td>\n <td>1</td>\n <td>critical</td>\n <td>convenient</td>\n <td>0</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>4</th>\n <td>usual</td>\n <td>proper</td>\n <td>complete</td>\n <td>2</td>\n <td>convenient</td>\n <td>convenient</td>\n <td>0</td>\n <td>not_recom</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>10361</th>\n <td>pretentious</td>\n <td>less_proper</td>\n <td>complete</td>\n <td>1</td>\n <td>convenient</td>\n <td>inconv</td>\n <td>0</td>\n <td>recommended</td>\n </tr>\n <tr>\n <th>10362</th>\n <td>usual</td>\n <td>less_proper</td>\n <td>incomplete</td>\n <td>2</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>1</td>\n <td>priority</td>\n </tr>\n <tr>\n <th>10363</th>\n <td>great_pret</td>\n <td>less_proper</td>\n <td>foster</td>\n <td>4</td>\n <td>convenient</td>\n <td>convenient</td>\n <td>0</td>\n <td>priority</td>\n </tr>\n <tr>\n <th>10364</th>\n <td>pretentious</td>\n <td>improper</td>\n <td>completed</td>\n <td>3</td>\n <td>less_conv</td>\n <td>convenient</td>\n <td>1</td>\n <td>recommended</td>\n </tr>\n <tr>\n <th>10365</th>\n <td>usual</td>\n <td>proper</td>\n <td>incomplete</td>\n <td>1</td>\n <td>critical</td>\n <td>convenient</td>\n <td>0</td>\n <td>not_recom</td>\n </tr>\n </tbody>\n</table>\n<p>10366 rows × 8 columns</p>\n</div>"
|
||||
},
|
||||
"execution_count": 97,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from apt.utils.datasets import ArrayDataset\n",
|
||||
"from apt.anonymization import Anonymize\n",
|
||||
"\n",
|
||||
"features = x_train.columns\n",
|
||||
"QI = [\"finance\", \"social\", \"health\"]\n",
|
||||
"categorical_features = [\"parents\", \"has_nurs\", \"form\", \"housing\", \"finance\", \"health\", 'children']\n",
|
||||
"anonymizer = Anonymize(100, QI, categorical_features=categorical_features)\n",
|
||||
"anon = anonymizer.anonymize(x_train, x_train_predictions)\n",
|
||||
"anon"
|
||||
"QI_indexes = [i for i, v in enumerate(features) if v in QI]\n",
|
||||
"categorical_features_indexes = [i for i, v in enumerate(features) if v in categorical_features]\n",
|
||||
"anonymizer = Anonymize(100, QI_indexes, categorical_features=categorical_features_indexes)\n",
|
||||
"anon = anonymizer.anonymize(ArrayDataset(x_train, x_train_predictions))\n",
|
||||
"anon\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 64,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"7585"
|
||||
]
|
||||
"text/plain": "7585"
|
||||
},
|
||||
"execution_count": 64,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -637,16 +273,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 65,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"5766"
|
||||
]
|
||||
"text/plain": "5766"
|
||||
},
|
||||
"execution_count": 65,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -665,7 +299,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 66,
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -678,7 +312,7 @@
|
|||
],
|
||||
"source": [
|
||||
"anon_str = anon.astype(str)\n",
|
||||
"anon_encoded = OneHotEncoder(sparse=False, drop='if_binary').fit_transform(anon_str)\n",
|
||||
"anon_encoded = OneHotEncoder(sparse=False).fit_transform(anon_str)\n",
|
||||
"\n",
|
||||
"anon_model = DecisionTreeClassifier()\n",
|
||||
"anon_model.fit(anon_encoded, y_train)\n",
|
||||
|
|
@ -698,14 +332,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 98,
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6471155701331275\n"
|
||||
"1.0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -734,14 +368,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 69,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6982442600810341\n"
|
||||
"0.5245996527107852\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -765,15 +399,15 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 87,
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(0.33056202194878614, 0.2888695146759663)\n",
|
||||
"(0.34112301200908796, 0.3054344667247893)\n"
|
||||
"(0.49415432579890883, 0.48976438779451525)\n",
|
||||
"(0.49415432579890883, 0.48976438779451525)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -810,15 +444,15 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 88,
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(0.6457357075913777, 0.2002324905550712)\n",
|
||||
"(0.6472248353715898, 0.1999418773612322)\n"
|
||||
"(1.0, 0.019204655674102813)\n",
|
||||
"(0.9829787234042553, 0.04481086323957323)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -849,26 +483,24 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 74,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"anonymizer2 = Anonymize(1000, QI, categorical_features=categorical_features)\n",
|
||||
"anon2 = anonymizer2.anonymize(x_train, x_train_predictions)"
|
||||
"anonymizer2 = Anonymize(1000, QI_indexes, categorical_features=categorical_features_indexes)\n",
|
||||
"anon2 = anonymizer2.anonymize(ArrayDataset(x_train, x_train_predictions))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 75,
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"4226"
|
||||
]
|
||||
"text/plain": "4226"
|
||||
},
|
||||
"execution_count": 75,
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -887,7 +519,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 104,
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -900,7 +532,7 @@
|
|||
],
|
||||
"source": [
|
||||
"anon2_str = anon2.astype(str)\n",
|
||||
"anon2_encoded = OneHotEncoder(sparse=False, drop='if_binary').fit_transform(anon2_str)\n",
|
||||
"anon2_encoded = OneHotEncoder(sparse=False).fit_transform(anon2_str)\n",
|
||||
"\n",
|
||||
"anon2_model = DecisionTreeClassifier()\n",
|
||||
"anon2_model.fit(anon2_encoded, y_train)\n",
|
||||
|
|
@ -920,14 +552,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 105,
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6266640941539648\n"
|
||||
"1.0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -956,14 +588,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 106,
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6944819602546788\n"
|
||||
"0.515820953115956\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -980,17 +612,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 107,
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(0.35793357933579334, 0.17037470725995316)\n",
|
||||
"(0.3360655737704918, 0.1680327868852459)\n",
|
||||
"(0.6457357075913777, 0.2002324905550712)\n",
|
||||
"(0.6327519379844961, 0.1897704155768672)\n"
|
||||
"(0.49415432579890883, 0.48976438779451525)\n",
|
||||
"(0.49415432579890883, 0.48976438779451525)\n",
|
||||
"(1.0, 0.019204655674102813)\n",
|
||||
"(1.0, 0.026382153249272552)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -1023,27 +655,26 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 111,
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"QI2 = [\"parents\", \"has_nurs\", \"form\", \"children\", \"housing\", \"finance\", \"social\", \"health\"]\n",
|
||||
"anonymizer3 = Anonymize(100, QI2, categorical_features=categorical_features)\n",
|
||||
"anon3 = anonymizer3.anonymize(x_train, x_train_predictions)"
|
||||
"QI2_indexes = [i for i, v in enumerate(features) if v in QI2]\n",
|
||||
"anonymizer3 = Anonymize(100, QI2_indexes, categorical_features=categorical_features_indexes)\n",
|
||||
"anon3 = anonymizer3.anonymize(ArrayDataset(x_train, x_train_predictions))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 112,
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"39"
|
||||
]
|
||||
"text/plain": "39"
|
||||
},
|
||||
"execution_count": 112,
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -1055,22 +686,22 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 113,
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Anonymized model accuracy: 0.7723765432098766\n",
|
||||
"BB attack accuracy: 0.5792012348060969\n",
|
||||
"WB attack accuracy: 0.6680493922438742\n"
|
||||
"Anonymized model accuracy: 0.751929012345679\n",
|
||||
"BB attack accuracy: 1.0\n",
|
||||
"WB attack accuracy: 0.5187150299054601\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"anon3_str = anon3.astype(str)\n",
|
||||
"anon3_encoded = OneHotEncoder(sparse=False, drop='if_binary').fit_transform(anon3_str)\n",
|
||||
"anon3_encoded = OneHotEncoder(sparse=False).fit_transform(anon3_str)\n",
|
||||
"\n",
|
||||
"anon3_model = DecisionTreeClassifier()\n",
|
||||
"anon3_model.fit(anon3_encoded, y_train)\n",
|
||||
|
|
@ -1105,17 +736,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 114,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(0.35793357933579334, 0.17037470725995316)\n",
|
||||
"(0.3393939393939394, 0.13114754098360656)\n",
|
||||
"(0.6457357075913777, 0.2002324905550712)\n",
|
||||
"(1, 0.0)\n"
|
||||
"(0.49415432579890883, 0.48976438779451525)\n",
|
||||
"(0.49415432579890883, 0.48976438779451525)\n",
|
||||
"(1.0, 0.019204655674102813)\n",
|
||||
"(1.0, 0.032201745877788554)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -1162,4 +793,4 @@
|
|||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue