Add Feature Importance Plot Function (#328)

R-package/NAMESPACE

@@ -20,6 +20,7 @@ export(lgb.importance)
 export(lgb.interprete)
 export(lgb.load)
 export(lgb.model.dt.tree)
+export(lgb.plot.importance)
 export(lgb.save)
 export(lgb.train)
 export(lightgbm)

R-package/R/lgb.plot.importance.R

@@ -0,0 +1,50 @@
+#' Plot feature importance as a bar graph
+#'
+#' Plot previously calculated feature importance: Gain, Cover and Frequency, as a bar graph.
+#'
+#' @param tree_imp a \code{data.table} returned by \code{\link{lgb.importance}}.
+#' @param top_n maximal number of top features to include into the plot.
+#' @param measure the name of importance measure to plot, can be "Gain", "Cover" or "Frequency".
+#' @param left_margin (base R barplot) allows to adjust the left margin size to fit feature names.
+#' @param cex (base R barplot) passed as \code{cex.names} parameter to \code{barplot}.
+#'
+#' @details
+#' The graph represents each feature as a horizontal bar of length proportional to the defined importance of a feature.
+#' Features are shown ranked in a decreasing importance order.
+#'
+#' @return
+#' The \code{lgb.plot.importance} function creates a \code{barplot}
+#' and silently returns a processed data.table with \code{top_n} features sorted by defined importance.
+#'
+#' @examples
+#'
+#' data(agaricus.train, package = 'lightgbm')
+#' train <- agaricus.train
+#' dtrain <- lgb.Dataset(train$data, label = train$label)
+#'
+#' params = list(objective = "binary",
+#'               learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+#'               min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+#'               model <- lgb.train(params, dtrain, 20)
+#' model <- lgb.train(params, dtrain, 20)
+#'
+#' tree_imp <- lgb.importance(model, percentage = TRUE)
+#' lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain")
+#'
+#' @export
+
+lgb.plot.importance <- function(tree_imp, top_n = 10, measure = "Gain", left_margin = 10, cex = NULL) {
+  measure <- match.arg(measure, choices = c("Gain", "Cover", "Frequency"), several.ok = FALSE)
+  top_n <- min(top_n, nrow(tree_imp))
+  tree_imp <- tree_imp[order(abs(get(measure)), decreasing = TRUE),][1:top_n,]
+  if (is.null(cex)) {
+    cex <- 2.5 / log2(1 + top_n)
+  }
+  op <- par(no.readonly = TRUE)
+  on.exit(par(op))
+  par(mar = op$mar %>% magrittr::inset(., 2, left_margin))
+  tree_imp[.N:1,
+           barplot(height = get(measure), names.arg = Feature, horiz = TRUE,
+                   main = "Feature Importance", xlab = measure, cex.names = cex, las = 1)]
+  invisible(tree_imp)
+}

R-package/man/lgb.plot.importance.Rd

@@ -0,0 +1,48 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.plot.importance.R
+\name{lgb.plot.importance}
+\alias{lgb.plot.importance}
+\title{Plot feature importance as a bar graph}
+\usage{
+lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain",
+  left_margin = 10, cex = NULL)
+}
+\arguments{
+\item{tree_imp}{a \code{data.table} returned by \code{\link{lgb.importance}}.}
+
+\item{top_n}{maximal number of top features to include into the plot.}
+
+\item{measure}{the name of importance measure to plot, can be "Gain", "Cover" or "Frequency".}
+
+\item{left_margin}{(base R barplot) allows to adjust the left margin size to fit feature names.}
+
+\item{cex}{(base R barplot) passed as \code{cex.names} parameter to \code{barplot}.}
+}
+\value{
+The \code{lgb.plot.importance} function creates a \code{barplot}
+and silently returns a processed data.table with \code{top_n} features sorted by defined importance.
+}
+\description{
+Plot previously calculated feature importance: Gain, Cover and Frequency, as a bar graph.
+}
+\details{
+The graph represents each feature as a horizontal bar of length proportional to the defined importance of a feature.
+Features are shown ranked in a decreasing importance order.
+}
+\examples{
+
+data(agaricus.train, package = 'lightgbm')
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+
+params = list(objective = "binary",
+              learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+              min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+              model <- lgb.train(params, dtrain, 20)
+model <- lgb.train(params, dtrain, 20)
+
+tree_imp <- lgb.importance(model, percentage = TRUE)
+lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain")
+
+}
+