def automl_fit(
input: Path,
output: Path = Path("automl.bin"),
target: str = None,
ignore_cols: List[int] = typer.Option([]),
evaluation_timeout: int = 5 * Min,
memory_limit: int = 4 * Gb,
search_timeout: int = 60 * 60,
pop_size: int = 20,
iterations: int = 100,
random_state: int = None,
format: str = None,
):
"""
🏃 Train an AutoML instance on a dataset.
"""
try:
dataset = _load_dataset(format, input, ignore_cols)
except ValueError as e:
logger.error(f"⚠️ Error: {str(e)}")
return
if target is None:
target = dataset.columns[-1]
columns = [c for c in dataset.columns if c != target]
X = dataset[columns].values
y = dataset[target].values
automl = AutoML(
output=VectorCategorical(),
search_kwargs=dict(
evaluation_timeout=evaluation_timeout,
memory_limit=memory_limit,
search_timeout=search_timeout,
pop_size=pop_size,
),
random_state=random_state,
search_iterations=iterations,
)
console.print(f"🏃 Training on {len(dataset)} items.")
automl.fit(X, y, logger=RichLogger())
with output.open("wb") as fp:
automl.save(fp)
console.print(f"💾 Saving model to [green]{output.absolute()}[/].")
def test_automl_save_load():
X, y = dummy.generate(seed=0)
automl = AutoML(search_iterations=3, registry=[DummyAlgorithm])
automl.fit(X, y)
pipe = automl.best_pipeline_
fp = BytesIO()
automl.save(fp)
fp.seek(0)
automl2 = AutoML.load(fp)
pipe2 = automl2.best_pipeline_
assert repr(pipe) == repr(pipe2)
def test_automl_save_load():
X, y = dummy.generate(seed=0)
automl = AutoML(
input=(MatrixContinuousDense, Supervised[VectorCategorical]),
output=VectorCategorical,
search_iterations=3,
registry=[DummyAlgorithm],
)
automl.fit(X, y)
pipe = automl.best_pipeline_
fp = BytesIO()
automl.save(fp)
fp.seek(0)
automl2 = AutoML.load(fp)
pipe2 = automl2.best_pipeline_
assert repr(pipe) == repr(pipe2)
# import high-level API
from autogoal.ml import AutoML
from autogoal.kb import MatrixContinuousDense, CategoricalVector
# load data
from autogoal.datasets import cars
X, y = cars.load()
# instantiate AutoML class
automl = AutoML(
input=MatrixContinuousDense(),
output=CategoricalVector(),
# ... other parameters and constraints
)
# fit the model
automl.fit(X, y)
# save the best model
with open("model.bin", "wb") as fp:
automl.save(fp)