def test_copy():
sd = StructuredDataset(df=df, label_names=['label'], protected_attribute_names=['two'])
sd2 = sd.copy()
sd3 = sd.copy(True)
sd.features[0] = 999
assert np.all(sd2.features[0] == 999)
assert not np.any(sd3.features[0] == 999)
def test_eq():
sd = StructuredDataset(df=df, label_names=['label'], protected_attribute_names=['two'])
sd2 = sd.copy()
sd3 = sd.copy(True)
sd4 = StructuredDataset(df=df, label_names=['label'], protected_attribute_names=['one', 'three'])
assert sd == sd2
assert sd == sd3
assert sd2 == sd3
assert sd != sd4
def test_temporarily_ignore():
sd = StructuredDataset(df=df, label_names=['label'], protected_attribute_names=['one', 'three'])
modified = sd.copy()
modified.labels = sd.labels + 1
assert sd != modified
with sd.temporarily_ignore('labels'):
assert sd == modified
assert 'labels' not in sd.ignore_fields
from aif360.datasets import StructuredDataset
from aif360.metrics import SampleDistortionMetric
data = np.arange(12).reshape((3, 4)).T
cols = ['one', 'two', 'three', 'label']
labs = np.ones((4, 1))
df = pd.DataFrame(data=np.concatenate((data, labs), axis=1), columns=cols)
sd = StructuredDataset(df=df,
label_names=['label'],
protected_attribute_names=['one', 'three'])
distorted = data + 1
sd_distorted = sd.copy(True)
sd_distorted.features = distorted
rand = np.random.randint(0, 10, (4, 4))
rand2 = np.random.randint(0, 10, (4, 3))
df_rand = pd.DataFrame(data=rand, columns=cols)
sd_rand = StructuredDataset(df=df_rand,
label_names=['label'],
protected_attribute_names=['one', 'three'])
sd_rand2 = sd_rand.copy(True)
sd_rand2.features = rand2
priv = [{'one': 1}]
unpriv = [{'one': 2}]