def test_minimum_query_instances(self):
pytest.importorskip('sklearn')
backend = 'sklearn'
exp = self._get_exp(backend)
with pytest.raises(UserConfigValidationException):
query_instances = helpers.load_adult_income_dataset().drop("income", axis=1)[0:1]
exp.global_feature_importance(query_instances)
def _get_exp(self, backend, method="random"):
dataset = helpers.load_adult_income_dataset()
d = dice_ml.Data(dataframe=dataset, continuous_features=['age', 'hours_per_week'], outcome_name='income')
ML_modelpath = helpers.get_adult_income_modelpath(backend=backend)
m = dice_ml.Model(model_path=ML_modelpath, backend=backend)
exp = dice_ml.Dice(d, m, method=method)
return exp
def test_user_data_corruption(self):
dataset = helpers.load_adult_income_dataset()
dataset_copy = dataset.copy()
dice_ml.Data(dataframe=dataset, continuous_features=['age', 'hours_per_week'],
outcome_name='income', permitted_range={'age': [45, 60]},
continuous_features_precision={'hours_per_week': 2})
pd.testing.assert_frame_equal(dataset, dataset_copy)
def data_object():
dataset = helpers.load_adult_income_dataset()
return dice_ml.Data(dataframe=dataset,
continuous_features=['age', 'hours_per_week'],
outcome_name='income',
permitted_range={'age': [45, 60]},
continuous_features_precision={'hours_per_week': 2})
def _get_exp(self,
backend,
method="random",
is_public_data_interface=True):
if is_public_data_interface:
dataset = helpers.load_adult_income_dataset()
d = dice_ml.Data(dataframe=dataset,
continuous_features=['age', 'hours_per_week'],
outcome_name='income')
else:
d = dice_ml.Data(features={
'age': [17, 90],
'workclass':
['Government', 'Other/Unknown', 'Private', 'Self-Employed'],
'education': [
'Assoc', 'Bachelors', 'Doctorate', 'HS-grad', 'Masters',
'Prof-school', 'School', 'Some-college'
],
'marital_status':
['Divorced', 'Married', 'Separated', 'Single', 'Widowed'],
'occupation': [
'Blue-Collar', 'Other/Unknown', 'Professional', 'Sales',
'Service', 'White-Collar'
],
'race': ['Other', 'White'],
'gender': ['Female', 'Male'],
'hours_per_week': [1, 99]
},
outcome_name='income')
ML_modelpath = helpers.get_adult_income_modelpath(backend=backend)
m = dice_ml.Model(model_path=ML_modelpath, backend=backend)
exp = dice_ml.Dice(d, m, method=method)
return exp
def public_data_object():
"""
Returns a public data object for the adult income dataset
"""
dataset = helpers.load_adult_income_dataset()
return dice_ml.Data(dataframe=dataset,
continuous_features=['age', 'hours_per_week'],
outcome_name='income')
def pyt_exp_object():
backend = 'PYT'
dataset = helpers.load_adult_income_dataset()
d = dice_ml.Data(dataframe=dataset, continuous_features=['age', 'hours_per_week'], outcome_name='income')
ML_modelpath = helpers.get_adult_income_modelpath(backend=backend)
m = dice_ml.Model(model_path= ML_modelpath, backend=backend)
exp = dice_ml.Dice(d, m)
return exp
def create_adult_income_dataset():
dataset = helpers.load_adult_income_dataset()
continuous_features = ['age', 'hours_per_week']
target_name = 'income'
target = dataset[target_name]
classes = list(np.unique(target))
categorical_features = list(
set(dataset.columns) - set(continuous_features) - set([target_name]))
# Split data into train and test
data_train, data_test, y_train, y_test = train_test_split(dataset,
target,
test_size=5000,
random_state=7,
stratify=target)
return data_train, data_test, y_train, y_test, categorical_features, \
continuous_features, target_name, classes
@author: dtd
"""
import sys
sys.path.append('/home/dtd/Documents/interpretable_machine_learning/Source Code/DiCE-master')
from dice_ml.utils import helpers # helper functions
from dice_ml.data_interfaces import public_data_interface
import numpy as np
import tensorflow as tf
from dice_ml.model_interfaces import keras_tensorflow_model
from dice_ml.dice_interfaces import dice_tensorflow2
import sys
if __name__ == "__main__":
data = helpers.load_adult_income_dataset()
params = {}
params['dataframe'] = data
params['continuous_features'] = ['age', 'hours_per_week']
params['outcome_name'] = 'income'
data_inter = public_data_interface.PublicData(params)
model_path = helpers.get_adult_income_modelpath()
print("Loading model ")
model = keras_tensorflow_model.KerasTensorFlowModel(model_path=model_path)
print("Loading CE")
dice = dice_tensorflow2.DiceTensorFlow2(data_inter, model)
#
query_instance = {'age':22,
'workclass':'Private',
'education':'HS-grad',
