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

[R] various R code maintenance (#1964)

Browse Source 
* [R] xgb.save must work when handle in nil but raw exists

* [R] print.xgb.Booster should still print other info when handle is nil

* [R] rename internal function xgb.Booster to xgb.Booster.handle to make its intent clear

* [R] rename xgb.Booster.check to xgb.Booster.complete and make it visible; more docs

* [R] storing evaluation_log should depend only on watchlist, not on verbose

* [R] reduce the excessive chattiness of unit tests

* [R] only disable some tests in windows when it's not 64-bit

* [R] clean-up xgb.DMatrix

* [R] test xgb.DMatrix loading from libsvm text file

* [R] store feature_names in xgb.Booster, use them from utility functions

* [R] remove non-functional co-occurence computation from xgb.importance

* [R] verbose=0 is enough without a callback

* [R] added forgotten xgb.Booster.complete.Rd; cran check fixes

* [R] update installation instructions
This commit is contained in:
Vadim Khotilovich
2017-01-21 13:22:46 -06:00
committed by Tianqi Chen
parent a073a2c3d4
commit 2b5b96d760
27 changed files with 561 additions and 327 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
R-package/tests/testthat/test_basic.R
View File

@@ -8,7 +8,9 @@ train <- agaricus.train
test <- agaricus.test
set.seed(1994)
windows_flag = grepl('Windows', Sys.info()[['sysname']])
# disable some tests for Win32
windows_flag = .Platform$OS.type == "windows" &&
.Machine$sizeof.pointer != 8
test_that("train and predict binary classification", {
nrounds = 2
@@ -109,7 +111,7 @@ test_that("train and predict RF with softprob", {
set.seed(11)
bst <- xgboost(data = as.matrix(iris[, -5]), label = lb,
max_depth = 3, eta = 0.9, nthread = 2, nrounds = nrounds,
objective = "multi:softprob", num_class=3,
objective = "multi:softprob", num_class=3, verbose = 0,
num_parallel_tree = 4, subsample = 0.5, colsample_bytree = 0.5)
expect_equal(bst$niter, 15)
expect_equal(xgb.ntree(bst), 15*3*4)
@@ -144,25 +146,25 @@ test_that("training continuation works", {
# for the reference, use 4 iterations at once:
set.seed(11)
bst <- xgb.train(param, dtrain, nrounds = 4, watchlist)
bst <- xgb.train(param, dtrain, nrounds = 4, watchlist, verbose = 0)
# first two iterations:
set.seed(11)
bst1 <- xgb.train(param, dtrain, nrounds = 2, watchlist)
bst1 <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0)
# continue for two more:
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = bst1)
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0, xgb_model = bst1)
if (!windows_flag)
expect_equal(bst$raw, bst2$raw)
expect_false(is.null(bst2$evaluation_log))
expect_equal(dim(bst2$evaluation_log), c(4, 2))
expect_equal(bst2$evaluation_log, bst$evaluation_log)
# test continuing from raw model data
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = bst1$raw)
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0, xgb_model = bst1$raw)
if (!windows_flag)
expect_equal(bst$raw, bst2$raw)
expect_equal(dim(bst2$evaluation_log), c(2, 2))
# test continuing from a model in file
xgb.save(bst1, "xgboost.model")
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = "xgboost.model")
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0, xgb_model = "xgboost.model")
if (!windows_flag)
expect_equal(bst$raw, bst2$raw)
expect_equal(dim(bst2$evaluation_log), c(2, 2))
@@ -171,9 +173,11 @@ test_that("training continuation works", {
test_that("xgb.cv works", {
set.seed(11)
cv <- xgb.cv(data = train$data, label = train$label, max_depth = 2, nfold = 5,
eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
verbose=TRUE)
expect_output(
cv <- xgb.cv(data = train$data, label = train$label, max_depth = 2, nfold = 5,
eta = 1., nthread = 2, nrounds = 2, objective = "binary:logistic",
verbose=TRUE)
, "train-error:")
expect_is(cv, 'xgb.cv.synchronous')
expect_false(is.null(cv$evaluation_log))
expect_lt(cv$evaluation_log[, min(test_error_mean)], 0.03)