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

17
R-package/tests/testthat/test_update.R
View File

@@ -9,24 +9,23 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
test_that("updating the model works", {
watchlist = list(train = dtrain, test = dtest)
cb = list(cb.evaluation.log()) # to run silent, but store eval. log
# no-subsampling
p1 <- list(objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = 2)
set.seed(11)
bst1 <- xgb.train(p1, dtrain, nrounds = 10, watchlist, verbose = 0, callbacks = cb)
bst1 <- xgb.train(p1, dtrain, nrounds = 10, watchlist, verbose = 0)
tr1 <- xgb.model.dt.tree(model = bst1)
# with subsampling
p2 <- modifyList(p1, list(subsample = 0.1))
set.seed(11)
bst2 <- xgb.train(p2, dtrain, nrounds = 10, watchlist, verbose = 0, callbacks = cb)
bst2 <- xgb.train(p2, dtrain, nrounds = 10, watchlist, verbose = 0)
tr2 <- xgb.model.dt.tree(model = bst2)
# the same no-subsampling boosting with an extra 'refresh' updater:
p1r <- modifyList(p1, list(updater = 'grow_colmaker,prune,refresh', refresh_leaf = FALSE))
set.seed(11)
bst1r <- xgb.train(p1r, dtrain, nrounds = 10, watchlist, verbose = 0, callbacks = cb)
bst1r <- xgb.train(p1r, dtrain, nrounds = 10, watchlist, verbose = 0)
tr1r <- xgb.model.dt.tree(model = bst1r)
# all should be the same when no subsampling
expect_equal(bst1$evaluation_log, bst1r$evaluation_log)
@@ -35,7 +34,7 @@ test_that("updating the model works", {
# the same boosting with subsampling with an extra 'refresh' updater:
p2r <- modifyList(p2, list(updater = 'grow_colmaker,prune,refresh', refresh_leaf = FALSE))
set.seed(11)
bst2r <- xgb.train(p2r, dtrain, nrounds = 10, watchlist, verbose = 0, callbacks = cb)
bst2r <- xgb.train(p2r, dtrain, nrounds = 10, watchlist, verbose = 0)
tr2r <- xgb.model.dt.tree(model = bst2r)
# should be the same evaluation but different gains and larger cover
expect_equal(bst2$evaluation_log, bst2r$evaluation_log)
@@ -45,7 +44,7 @@ test_that("updating the model works", {
# process type 'update' for no-subsampling model, refreshing the tree stats AND leaves from training data:
p1u <- modifyList(p1, list(process_type = 'update', updater = 'refresh', refresh_leaf = TRUE))
bst1u <- xgb.train(p1u, dtrain, nrounds = 10, watchlist, verbose = 0, callbacks = cb, xgb_model = bst1)
bst1u <- xgb.train(p1u, dtrain, nrounds = 10, watchlist, verbose = 0, xgb_model = bst1)
tr1u <- xgb.model.dt.tree(model = bst1u)
# all should be the same when no subsampling
expect_equal(bst1$evaluation_log, bst1u$evaluation_log)
@@ -53,7 +52,7 @@ test_that("updating the model works", {
# process type 'update' for model with subsampling, refreshing only the tree stats from training data:
p2u <- modifyList(p2, list(process_type = 'update', updater = 'refresh', refresh_leaf = FALSE))
bst2u <- xgb.train(p2u, dtrain, nrounds = 10, watchlist, verbose = 0, callbacks = cb, xgb_model = bst2)
bst2u <- xgb.train(p2u, dtrain, nrounds = 10, watchlist, verbose = 0, xgb_model = bst2)
tr2u <- xgb.model.dt.tree(model = bst2u)
# should be the same evaluation but different gains and larger cover
expect_equal(bst2$evaluation_log, bst2u$evaluation_log)
@@ -66,7 +65,7 @@ test_that("updating the model works", {
# process type 'update' for no-subsampling model, refreshing only the tree stats from TEST data:
p1ut <- modifyList(p1, list(process_type = 'update', updater = 'refresh', refresh_leaf = FALSE))
bst1ut <- xgb.train(p1ut, dtest, nrounds = 10, watchlist, verbose = 0, callbacks = cb, xgb_model = bst1)
bst1ut <- xgb.train(p1ut, dtest, nrounds = 10, watchlist, verbose = 0, xgb_model = bst1)
tr1ut <- xgb.model.dt.tree(model = bst1ut)
# should be the same evaluations but different gains and smaller cover (test data is smaller)
expect_equal(bst1$evaluation_log, bst1ut$evaluation_log)