Marginal plots of fitted gbm objects

Plots the marginal effect of the selected variables by "integrating" out the other variables.

Usage

# S3 method for class 'GBMFit'
plot(
  x,
  var_index = 1,
  num_trees = gbm_fit_obj$params$num_trees,
  continuous_resolution = 100,
  grid_levels = NULL,
  return_grid = FALSE,
  type = "link",
  ...
)

Arguments

x: a GBMFit object fitted using a call to gbmt
var_index: a vector of indices or the names of the variables to plot. If using indices, the variables are indexed in the same order that they appear in the initial gbmt formula. If length(var_index) is between 1 and 3 then plot.GBMFit produces the plots. Otherwise, plot.GBMFit returns only the grid of evaluation points and their average predictions
num_trees: the number of trees used to generate the plot. Only the first num_trees trees will be used
continuous_resolution: The number of equally space points at which to evaluate continuous predictors
grid_levels: A list containing the points at which to evaluate each predictor in var_index (in the same order as var_index). For continuous predictors this is usually a regular sequence of values within the range of the variable. For categorical predictors, the points are the levels of the factor. When length(var_index) is one, the values can be provided directly, outside a list. This is NULL by default and generated automatically from the data, using continuous_resolution for continuous predictors. Forcing the values can be useful to evaluate two models on the same exact range
return_grid: if TRUE then plot.GBMFit produces no graphics and only returns the grid of evaluation points and their average predictions. This is useful for customizing the graphics for special variable types or for dimensions greater than 3
type: the type of prediction to plot on the vertical axis. See predict_gmt
...: other arguments passed to the plot function

Value

Nothing unless return_grid is true then plot.GBMFit produces no graphics and only returns the grid of evaluation points and their average predictions.

Details

plot.GBMFit produces low dimensional projections of the GBMFit object, see gbmt, by integrating out the variables not included in the var_index argument. The function selects a grid of points and uses the weighted tree traversal method described in Friedman (2001) to do the integration. Based on the variable types included in the projection, plot_gbmt selects an appropriate display choosing amongst line plots, contour plots, and lattice plots. If the default graphics are not sufficient the user may set return.grid=TRUE, store the result of the function, and develop another graphic display more appropriate to the particular example.

References

J.H. Friedman (2001). "Greedy Function Approximation: A Gradient Boosting Machine," Annals of Statistics 29(4).