Save PFA

The documentation is generated based on the sources available at dotnet/machinelearning and released under MIT License.

Type: command Aliases: SavePfa Namespace: Microsoft.ML.Runtime.Model.Pfa Assembly: Microsoft.ML.Data.dll Microsoft Documentation: Save PFA


Given a data model, write out the corresponding PFA.


Name Short name Default Description
allowSet set False Whether we should allow set operations.
dataFile data   The data file
formatting format Indented Format option for the JSON exporter.
inputModelFile in   Model file to load
inputsToDrop idrop   Comma delimited list of input column names to drop
keepInput input False Whether the inputs should also map to the outputs.
loadPredictor pred   Whether we should attempt to load the predictor and attach the scorer to the pipeline if one is present.
loadTransforms loadTrans   Load transforms from model file?
loader     The data loader
name     The ‘name’ property in the output PFA program. By default this will be the extension-less name
outputModelFile out   Model file to save
outputsToDrop odrop   Comma delimited list of output column names to drop
parallel n   Desired degree of parallelism in the data pipeline
pfa     The path to write the output PFA too. Leave empty for stdout.
randomSeed seed   Random seed
server     The web server to publish the RESTful API
transform xf   Transform
verbose v   Verbose?