GetTrainingPredictionsForModel: Get training predictions for a particular model.

Description Usage Arguments Examples

View source: R/TrainingPredictions.R

Description

Training predictions are the internal out-of-fold predictions for data that was used to train the model. These predictions are especially useful for creating stacked models or blenders.

Usage

1
GetTrainingPredictionsForModel(model, dataSubset = "all", maxWait = 600)

Arguments

model

dataRobotModel. The model to get training predictions for.

dataSubset

character. What data subset would you like to predict on? Possible options are included in DataSubset. Possible options are:

  • DataSubset$All will use all available data.

  • DataSubset$ValidationAndHoldout will use all data except the training set.

  • DataSubset$Holdout will use only holdout data.

maxWait

integer. The maximum time (in seconds) to wait for the model job to complete.

Examples

1
2
3
4
5
6
7
## Not run: 
  projectId <- "59a5af20c80891534e3c2bde"
  modelId <- "5996f820af07fc605e81ead4"
  model <- GetModel(projectId, modelId)
  trainingPredictions <- GetTrainingPredictionsFromModel(model)

## End(Not run)

datarobot documentation built on June 2, 2021, 9:06 a.m.