def export(output: str = typer.Argument(".", help="Location to export")):
"""
Export previosly trained AutoML instance.
"""
model = AutoML.folder_load(Path("."))
model.export_portable(output)
def automl_predict(
input: Path,
output: Path = Path("output.csv"),
model: Path = Path("."),
ignore_cols: List[int] = typer.Option([]),
format: str = None,
):
"""
🔮 Predict with a previously trained AutoML instance.
"""
try:
dataset = _load_dataset(format, input, ignore_cols)
except ValueError as e:
logger.error(f"⚠️ Error: {str(e)}")
return
try:
automl = AutoML.folder_load(model)
except TypeError as e:
logger.error(f"⚠️ Error: {str(e)}")
return
console.print(f"🔮 Predicting {len(dataset)} items with the pipeline:")
console.print(repr(automl.best_pipeline_))
X = dataset.values
y = automl.predict(X)
with output.open("wt") as fp:
df = pd.DataFrame(y, columns=["y"])
df.to_csv(fp)
console.print(f"💾 Predictions saved to [blue]{output.absolute()}[/]")
def automl_server(
path: str = typer.Argument(".", help="Autogoal serialized model"),
ip: str = typer.Argument(
"0.0.0.0", help="Interface ip to be used by the HTTP API"),
port: int = typer.Argument(8000, help="Port to be bind by the server"),
):
console.print(f"Loading model from folder: {path}")
model = AutoML.folder_load(Path(path))
run(model, ip, port)