Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Frequence to Frequency

Browse Source
This commit is contained in:
terrytangyuan 2015-11-20 20:25:29 -06:00
parent 77fab79d83
commit 51ee382517
4 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
R-package/R/xgb.importance.R
View File

@ -119,7 +119,7 @@ xgb.importance <- function(feature_names = NULL, filename_dump = NULL, model = N
treeDump <- function(feature_names, text, keepDetail){
if(keepDetail) groupBy <- c("Feature", "Split", "MissingNo") else groupBy <- "Feature"
result <- xgb.model.dt.tree(feature_names = feature_names, text = text)[,"MissingNo" := Missing == No ][Feature != "Leaf",.(Gain = sum(Quality), Cover = sum(Cover), Frequence = .N), by = groupBy, with = T][,`:=`(Gain = Gain / sum(Gain), Cover = Cover / sum(Cover), Frequence = Frequence / sum(Frequence))][order(Gain, decreasing = T)]
result <- xgb.model.dt.tree(feature_names = feature_names, text = text)[,"MissingNo" := Missing == No ][Feature != "Leaf",.(Gain = sum(Quality), Cover = sum(Cover), Frequency = .N), by = groupBy, with = T][,`:=`(Gain = Gain / sum(Gain), Cover = Cover / sum(Cover), Frequency = Frequency / sum(Frequency))][order(Gain, decreasing = T)]
result
}

2
R-package/R/xgb.model.dt.tree.R
View File

@ -166,4 +166,4 @@ xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model
# Avoid error messages during CRAN check.
# The reason is that these variables are never declared
# They are mainly column names inferred by Data.table...
globalVariables(c("ID", "Tree", "Yes", ".", ".N", "Feature", "Cover", "Quality", "No", "Gain", "Frequence"))
globalVariables(c("ID", "Tree", "Yes", ".", ".N", "Feature", "Cover", "Quality", "No", "Gain", "Frequency"))

2
R-package/tests/testthat/test_helpers.R
View File

@ -25,7 +25,7 @@ test_that("xgb.importance works", {
expect_true(xgb.dump(bst, 'xgb.model.dump', with.stats = T))
importance <- xgb.importance(sparse_matrix@Dimnames[[2]], 'xgb.model.dump')
expect_equal(dim(importance), c(7, 4))
expect_equal(colnames(importance), c("Feature", "Gain", "Cover", "Frequence"))
expect_equal(colnames(importance), c("Feature", "Gain", "Cover", "Frequency"))
})
test_that("xgb.plot.tree works", {

4
R-package/vignettes/discoverYourData.Rmd
View File

@ -202,7 +202,7 @@ head(importance)
`Cover` measures the relative quantity of observations concerned by a feature.
`Frequence` is a simpler way to measure the `Gain`. It just counts the number of times a feature is used in all generated trees. You should not use it (unless you know why you want to use it).
`Frequency` is a simpler way to measure the `Gain`. It just counts the number of times a feature is used in all generated trees. You should not use it (unless you know why you want to use it).
### Improvement in the interpretability of feature importance data.table
@ -216,7 +216,7 @@ For that purpose we will execute the same function as above but using two more p
importanceRaw <- xgb.importance(sparse_matrix@Dimnames[[2]], model = bst, data = sparse_matrix, label = output_vector)
# Cleaning for better display
importanceClean <- importanceRaw[,`:=`(Cover=NULL, Frequence=NULL)]
importanceClean <- importanceRaw[,`:=`(Cover=NULL, Frequency=NULL)]
head(importanceClean)
```