def test_dataloader():
seed_everything()
X = np.random.rand(5, 2)
y = np.random.rand(5)
x_val = np.random.rand(2, 2)
y_val = np.random.rand(2)
x_test = np.random.rand(1, 2)
y_test = np.random.rand(1)
shuffled_X, shuffled_y = sk_shuffle(X, y, random_state=1234)
# -----------------------------
# train
# -----------------------------
loaders = SklearnDataModule(X=X, y=y, val_split=0.2, test_split=0.2, random_state=1234, drop_last=True)
train_loader = loaders.train_dataloader()
val_loader = loaders.val_dataloader()
test_loader = loaders.test_dataloader()
assert np.all(train_loader.dataset.X == shuffled_X[2:])
assert np.all(val_loader.dataset.X == shuffled_X[0])
assert np.all(test_loader.dataset.X == shuffled_X[1])
assert np.all(train_loader.dataset.Y == shuffled_y[2:])
# -----------------------------
# train + val
# -----------------------------
loaders = SklearnDataModule(X=X, y=y, x_val=x_val, y_val=y_val, test_split=0.2, random_state=1234, drop_last=True)
train_loader = loaders.train_dataloader()
val_loader = loaders.val_dataloader()
test_loader = loaders.test_dataloader()
assert np.all(train_loader.dataset.X == shuffled_X[1:])
assert np.all(val_loader.dataset.X == x_val)
assert np.all(test_loader.dataset.X == shuffled_X[0])
# -----------------------------
# train + test
# -----------------------------
loaders = SklearnDataModule(
X=X, y=y, x_test=x_test, y_test=y_test, val_split=0.2, random_state=1234, drop_last=True
)
train_loader = loaders.train_dataloader()
val_loader = loaders.val_dataloader()
test_loader = loaders.test_dataloader()
assert np.all(train_loader.dataset.X == shuffled_X[1:])
assert np.all(val_loader.dataset.X == shuffled_X[0])
assert np.all(test_loader.dataset.X == x_test)
# -----------------------------
# train + val + test
# -----------------------------
loaders = SklearnDataModule(X, y, x_val, y_val, x_test, y_test, random_state=1234, drop_last=True)
train_loader = loaders.train_dataloader()
val_loader = loaders.val_dataloader()
test_loader = loaders.test_dataloader()
assert np.all(train_loader.dataset.X == shuffled_X)
assert np.all(val_loader.dataset.X == x_val)
assert np.all(test_loader.dataset.X == x_test)
def cli_main():
from warnings import warn
pl.seed_everything(1234)
# Example: Iris dataset in Sklearn (4 features, 3 class labels)
try:
from sklearn.datasets import load_iris
except ImportError:
warn('You want to use `sklearn` which is not installed yet,' # pragma: no-cover
' install it with `pip install sklearn`.')
X, y = load_iris(return_X_y=True)
loaders = SklearnDataModule(X, y)
# args
parser = ArgumentParser()
parser = LogisticRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
# model = LogisticRegression(**vars(args))
model = LogisticRegression(input_dim=4, num_classes=3, l1_strength=0.01, learning_rate=0.01)
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, loaders.train_dataloader(args.batch_size), loaders.val_dataloader(args.batch_size))
def cli_main():
from pl_bolts.datamodules.sklearn_datamodule import SklearnDataModule
pl.seed_everything(1234)
# create dataset
try:
from sklearn.datasets import load_boston
except ModuleNotFoundError as err:
raise ModuleNotFoundError( # pragma: no-cover
'You want to use `sklearn` which is not installed yet, install it with `pip install sklearn`.'
) from err
X, y = load_boston(return_X_y=True) # these are numpy arrays
loaders = SklearnDataModule(X, y)
# args
parser = ArgumentParser()
parser = LinearRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
model = LinearRegression(input_dim=13, l1_strength=1, l2_strength=1)
# model = LinearRegression(**vars(args))
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, loaders.train_dataloader(args.batch_size),
loaders.val_dataloader(args.batch_size))
def cli_main():
from pl_bolts.datamodules.sklearn_datamodule import SklearnDataModule
from pl_bolts.utils import _SKLEARN_AVAILABLE
pl.seed_everything(1234)
# create dataset
if _SKLEARN_AVAILABLE:
from sklearn.datasets import load_diabetes
else: # pragma: no cover
raise ModuleNotFoundError(
'You want to use `sklearn` which is not installed yet, install it with `pip install sklearn`.'
)
# args
parser = ArgumentParser()
parser = LinearRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
model = LinearRegression(input_dim=10, l1_strength=1, l2_strength=1)
# model = LinearRegression(**vars(args))
# data
X, y = load_diabetes(return_X_y=True) # these are numpy arrays
loaders = SklearnDataModule(X, y, batch_size=args.batch_size)
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, train_dataloader=loaders.train_dataloader(), val_dataloaders=loaders.val_dataloader())
def cli_main():
from pl_bolts.datamodules.sklearn_datamodule import SklearnDataModule
from pl_bolts.utils import _SKLEARN_AVAILABLE
pl.seed_everything(1234)
# Example: Iris dataset in Sklearn (4 features, 3 class labels)
if _SKLEARN_AVAILABLE:
from sklearn.datasets import load_iris
else: # pragma: no cover
raise ModuleNotFoundError(
'You want to use `sklearn` which is not installed yet, install it with `pip install sklearn`.'
)
# args
parser = ArgumentParser()
parser = LogisticRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
# model = LogisticRegression(**vars(args))
model = LogisticRegression(input_dim=4, num_classes=3, l1_strength=0.01, learning_rate=0.01)
# data
X, y = load_iris(return_X_y=True)
loaders = SklearnDataModule(X, y, batch_size=args.batch_size, num_workers=0)
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, train_dataloader=loaders.train_dataloader(), val_dataloaders=loaders.val_dataloader())
def cli_main():
pl.seed_everything(1234)
# Example: Iris dataset in Sklearn (4 features, 3 class labels)
from sklearn.datasets import load_iris
X, y = load_iris(return_X_y=True)
loaders = SklearnDataModule(X, y)
# args
parser = ArgumentParser()
parser = LogisticRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
# model = LogisticRegression(**vars(args))
model = LogisticRegression(input_dim=4, num_classes=3, l1_strength=0.01, learning_rate=0.01)
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, loaders.train_dataloader(args.batch_size), loaders.val_dataloader(args.batch_size))
def cli_main():
pl.seed_everything(1234)
# create dataset
from sklearn.datasets import load_boston
X, y = load_boston(return_X_y=True) # these are numpy arrays
loaders = SklearnDataModule(X, y)
# args
parser = ArgumentParser()
parser = LinearRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
model = LinearRegression(input_dim=13, l1_strength=1, l2_strength=1)
# model = LinearRegression(**vars(args))
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, loaders.train_dataloader(args.batch_size),
loaders.val_dataloader(args.batch_size))
parser.add_argument('--input_dim', type=int, default=None)
parser.add_argument('--num_classes', type=int, default=None)
parser.add_argument('--bias', default='store_true')
parser.add_argument('--batch_size', type=int, default=16)
return parser
# todo: covert to CLI func and add test
if __name__ == '__main__': # pragma: no cover
from argparse import ArgumentParser
pl.seed_everything(1234)
# Example: Iris dataset in Sklearn (4 features, 3 class labels)
from sklearn.datasets import load_iris
X, y = load_iris(return_X_y=True)
loaders = SklearnDataModule(X, y)
# args
parser = ArgumentParser()
parser = LogisticRegression.add_model_specific_args(parser)
parser = pl.Trainer.add_argparse_args(parser)
args = parser.parse_args()
# model
# model = LogisticRegression(**vars(args))
model = LogisticRegression(input_dim=4, num_classes=3, l1_strength=0.01, learning_rate=0.01)
# train
trainer = pl.Trainer.from_argparse_args(args)
trainer.fit(model, loaders.train_dataloader(args.batch_size), loaders.val_dataloader(args.batch_size))