specmine (version 4.0.0)

summary_var_importance: Summarise variable importance tables

Description

Keep the top rows of each variable-importance table produced during model comparison.

Usage

summary_var_importance(performances, number.rows)

Value

A list of truncated variable-importance tables, one per model.

Arguments

performances

A list returned by train_models_performance().

number.rows

Number of rows to keep from each variable-importance table.

Examples

performances <- list(
  vips = list(
    rf = data.frame(Mean = c(0.9, 0.7, 0.4), row.names = c("v1", "v2", "v3")),
    svm = data.frame(Mean = c(0.8, 0.6, 0.5), row.names = c("v1", "v2", "v3"))
  )
)
summary_var_importance(performances, 2)