Cross Validation

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

Type: command Aliases: CV Namespace: Microsoft.ML.Runtime.Data Assembly: Microsoft.ML.Data.dll Microsoft Documentation: Cross Validation



Name Short name Default Description
cacheData cache   Whether we should cache input training data
calibrator cali Microsoft. ML. Runtime. Internal. Calibration. PlattCalibratorTrainerFactory Output calibrator
collateMetrics collate True Whether we should collate metrics or store them in per-folds files
continueTrain cont False Whether we should load predictor from input model and use it as the initial model state
customColumn col   Columns with custom kinds declared through key assignments, for example, col[Kind]=Name to assign column named ‘Name’ kind ‘Kind’
dataFile data   The data file
evaluator eval   Evaluator to use
featureColumn feat Features Column to use for features
groupColumn group GroupId Column to use for grouping
inputModelFile in   Model file to load
labelColumn lab Label Column to use for labels
loadTransforms loadTrans   Load transforms from model file?
loader     The data loader
maxCalibrationExamples numcali 1000000000 Number of instances to train the calibrator
nameColumn name Name Name column name
normalizeFeatures norm Auto Normalize option for the feature column
numFolds k 2 Number of folds in k-fold cross-validation
outputDataFile dout   File to save per-instance predictions and metrics to
outputExampleFoldIndex opf False Print the run/fold index in per-instance output
outputModelFile out   Model file to save
parallel n   Desired degree of parallelism in the data pipeline
preTransform prexf   Transforms to apply prior to splitting the data into folds
randomSeed seed   Random seed
scorer     Scorer to use
server     The web server to publish the RESTful API
stratificationColumn strat   Column to use for stratification
summaryFilename sf   Results summary filename
trainer tr   Trainer to use
transform xf   Transform
useThreads threads True Use threads
validationFile valid   The validation data file
verbose v   Verbose?
weightColumn weight Weight Column to use for example weight