def main() -> None:
"""Load data from feather files, pass it to `train_and_transform` and then save the result."""
args = BeutelArgs().parse_args()
if args.mode == "run":
assert args.train is not None
assert args.new_train is not None
assert args.test is not None
assert args.new_test is not None
train, test = load_data_from_flags(args)
save_transformations(train_and_transform(train, test, args), args)
elif args.mode == "fit":
assert args.model is not None
assert args.train is not None
assert args.new_train is not None
train = DataTuple.from_npz(Path(args.train))
transformed_train, enc = fit(train, args)
transformed_train.to_npz(Path(args.new_train))
dump(enc, Path(args.model))
elif args.mode == "transform":
assert args.model is not None
assert args.test is not None
assert args.new_test is not None
test = DataTuple.from_npz(Path(args.test))
model = load(Path(args.model))
transformed_test = transform(test, model, args)
transformed_test.to_npz(Path(args.new_test))
def main() -> None:
"""Main method to run model."""
args = VfaeArgs(explicit_bool=True).parse_args()
set_seed(args.seed)
if args.mode == "run":
assert args.train is not None
assert args.new_train is not None
assert args.test is not None
assert args.new_test is not None
train, test = load_data_from_flags(args)
save_transformations(train_and_transform(train, test, args), args)
elif args.mode == "fit":
assert args.model is not None
assert args.train is not None
assert args.new_train is not None
train = DataTuple.from_npz(Path(args.train))
enc = fit(train, args)
transformed_train = transform(enc, train, args)
transformed_train.to_npz(Path(args.new_train))
dump(enc, Path(args.model))
elif args.mode == "transform":
assert args.model is not None
assert args.test is not None
assert args.new_test is not None
test = DataTuple.from_npz(Path(args.test))
model = load(Path(args.model))
transformed_test = transform(model, test, args)
transformed_test.to_npz(Path(args.new_test))
def main() -> None:
"""LFR Model.
Learning fair representations is a pre-processing technique that finds a
latent representation which encodes the data well but obfuscates information
about protected attributes [2]_.
References:
.. [2] R. Zemel, Y. Wu, K. Swersky, T. Pitassi, and C. Dwork, "Learning
Fair Representations." International Conference on Machine Learning,
2013.
Based on code from https://github.com/zjelveh/learning-fair-representations
Which in turn, we've got from AIF360
"""
args = ZemelArgs()
args.parse_args()
if args.mode == "run":
assert args.train is not None
assert args.new_train is not None
assert args.test is not None
assert args.new_test is not None
train, test = load_data_from_flags(args)
save_transformations(train_and_transform(train, test, args), args)
elif args.mode == "fit":
assert args.model is not None
assert args.train is not None
assert args.new_train is not None
train = DataTuple.from_npz(Path(args.train))
model = fit(train, args)
sens_col = train.s.columns[0]
training_sensitive = train.x.loc[train.s[sens_col] == 0].to_numpy()
training_nonsensitive = train.x.loc[train.s[sens_col] == 1].to_numpy()
train_transformed = trans(model.prototypes, model.w,
training_nonsensitive, training_sensitive,
train)
data = DataTuple(x=train_transformed,
s=train.s,
y=train.y,
name=train.name)
data.to_npz(Path(args.new_train))
dump(model, Path(args.model))
elif args.mode == "transform":
assert args.model is not None
assert args.test is not None
assert args.new_test is not None
test = DataTuple.from_npz(Path(args.test))
model = load(Path(args.model))
transformed_test = transform(test, model.prototypes, model.w)
transformed_test.to_npz(Path(args.new_test))
def main():
"""This function runs the Agarwal model as a standalone program."""
args: AgarwalArgs = AgarwalArgs().parse_args()
train, test = DataTuple.from_npz(Path(args.train)), TestTuple.from_npz(
Path(args.test))
Prediction(hard=train_and_predict(train, test, args)["preds"]).to_npz(
Path(args.predictions))
def fit(self, train: DataTuple) -> Tuple[PreAlgorithm, DataTuple]:
"""Generate fair features with the given data asynchronously.
Args:
train: training data
test: test data
Returns:
a tuple of the pre-processed training data and the test data
"""
self.model_path = self.model_dir / f"model_{self.name}.joblib"
with TemporaryDirectory() as tmpdir:
tmp_path = Path(tmpdir)
# ================================ write data to files ================================
train_path, test_path = tmp_path / "train.npz", tmp_path / "test.npz"
train.to_npz(train_path)
# ========================== generate commandline arguments ===========================
transformed_train_path = tmp_path / "transformed_train.npz"
cmd = self._fit_script_command(train_path, transformed_train_path, self.model_path)
# ============================= run the generated command =============================
self._call_script(cmd + ["--mode", "fit"])
# ================================== load results =====================================
transformed_train = DataTuple.from_npz(transformed_train_path)
# prefix the name of the algorithm to the dataset name
transformed_train = transformed_train.replace(
name=None if train.name is None else f"{self.name}: {train.name}"
)
return self, transformed_train
def main() -> None:
"""This function runs the Agarwal model as a standalone program."""
args: AgarwalArgs = AgarwalArgs().parse_args()
random.seed(args.seed)
np.random.seed(args.seed)
try:
import cloudpickle
# Need to install cloudpickle for now. See https://github.com/fairlearn/fairlearn/issues/569
except ImportError as e:
raise RuntimeError(
"In order to use Agarwal, install fairlearn and cloudpickle."
) from e
if args.mode == "run":
assert args.train is not None
assert args.test is not None
assert args.predictions is not None
train, test = DataTuple.from_npz(Path(args.train)), TestTuple.from_npz(
Path(args.test))
Prediction(hard=train_and_predict(train, test, args)["preds"]).to_npz(
Path(args.predictions))
elif args.mode == "fit":
assert args.train is not None
assert args.model is not None
data = DataTuple.from_npz(Path(args.train))
model = fit(data, args)
with working_dir(Path(args.model)):
model_file = cloudpickle.dumps(model)
dump(model_file, Path(args.model))
elif args.mode == "predict":
assert args.model is not None
assert args.predictions is not None
assert args.test is not None
data = TestTuple.from_npz(Path(args.test))
model_file = load(Path(args.model))
with working_dir(Path(args.model)):
model = cloudpickle.loads(model_file)
Prediction(hard=predict(model, data)["preds"]).to_npz(
Path(args.predictions))
else:
raise RuntimeError(f"Unknown mode: {args.mode}")
def main() -> None:
"""This function runs the FWD model as a standalone program on tabular data."""
args = DroArgs().parse_args()
if args.mode == "run":
assert args.train is not None
assert args.test is not None
assert args.predictions is not None
train, test = load_data_from_flags(args)
train_and_predict(train, test, args).to_npz(Path(args.predictions))
elif args.mode == "fit":
assert args.train is not None
assert args.model is not None
data = DataTuple.from_npz(Path(args.train))
model = fit(data, args)
dump(model, Path(args.model))
elif args.mode == "predict":
assert args.model is not None
assert args.predictions is not None
assert args.test is not None
data = TestTuple.from_npz(Path(args.test))
model = load(Path(args.model))
predict(model, data, args).to_npz(Path(args.predictions))
async def run_async(self, train: DataTuple,
test: TestTuple) -> Tuple[DataTuple, TestTuple]:
"""Generate fair features with the given data asynchronously.
Args:
train: training data
test: test data
Returns:
a tuple of the pre-processed training data and the test data
"""
with TemporaryDirectory() as tmpdir:
tmp_path = Path(tmpdir)
# ================================ write data to files ================================
train_path, test_path = tmp_path / "train.npz", tmp_path / "test.npz"
train.to_npz(train_path)
test.to_npz(test_path)
# ========================== generate commandline arguments ===========================
transformed_train_path = tmp_path / "transformed_train.npz"
transformed_test_path = tmp_path / "transformed_test.npz"
cmd = self._script_command(train_path, test_path,
transformed_train_path,
transformed_test_path)
# ============================= run the generated command =============================
await self._call_script(cmd)
# ================================== load results =====================================
transformed_train = DataTuple.from_npz(transformed_train_path)
transformed_test = TestTuple.from_npz(transformed_test_path)
# prefix the name of the algorithm to the dataset name
transformed_train = transformed_train.replace(
name=None if train.name is None else f"{self.name}: {train.name}")
transformed_test = transformed_test.replace(
name=None if test.name is None else f"{self.name}: {test.name}")
return transformed_train, transformed_test
def load_data_from_flags(args: AlgoArgs) -> Tuple[DataTuple, TestTuple]:
"""Load data from the paths specified in the flags."""
return DataTuple.from_npz(Path(args.train)), TestTuple.from_npz(
Path(args.test))