datarobot (version 2.18.6)

GetFeatureImpactForModel: Retrieve completed Feature Impact results given a model

Description

This will only succeed if the Feature Impact computation has completed.

Usage

GetFeatureImpactForModel(model)

Value

A data frame with the following columns:

• featureName character. The name of the feature.

• impactNormalized numeric. The normalized impact score (largest value is 1).

• impactUnnormalized numeric. The unnormalized impact score.

• redundantWith character. A feature that makes this feature redundant, or NA if the feature is not redundant.

Arguments

model

character. The model for which you want to retrieve Feature Impact.

Details

Feature Impact is computed for each column by creating new data with that column randomly permuted (but the others left unchanged), and seeing how the error metric score for the predictions is affected. The 'impactUnnormalized' is how much worse the error metric score is when making predictions on this modified data. The 'impactNormalized' is normalized so that the largest value is 1. In both cases, larger values indicate more important features. Elsewhere this technique is sometimes called 'Permutation Importance'.

Feature impact also runs redundancy detection, which detects if some features are redundant with higher importance features. Note that some types of projects, like multiclass, do not run redundancy detection. This function will generate a warning if redundancy detection was not run.

Examples

if (FALSE) {
  model <- ListModels(project)[[1]]
  featureImpactJobId <- RequestFeatureImpact(model)
  # Note: This will only work after the feature impact job has completed. Use
  #       GetFeatureImpactFromJobId to automatically wait for the job.\
  featureImpact <- GetFeatureImpactForModel(model)
}