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

Distributed Fast Histogram Algorithm (#4011)

Browse Source 
* add back train method but mark as deprecated

* add back train method but mark as deprecated

* add back train method but mark as deprecated

* fix scalastyle error

* fix scalastyle error

* fix scalastyle error

* fix scalastyle error

* init

* allow hist algo

* more changes

* temp

* update

* remove hist sync

* udpate rabit

* change hist size

* change the histogram

* update kfactor

* sync per node stats

* temp

* update

* final

* code clean

* update rabit

* more cleanup

* fix errors

* fix failed tests

* enforce c++11

* fix lint issue

* broadcast subsampled feature correctly

* revert some changes

* fix lint issue

* enable monotone and interaction constraints

* don't specify default for monotone and interactions

* update docs
This commit is contained in:
Nan Zhu
2019-02-05 05:12:53 -08:00
committed by GitHub
parent 8905df4a18
commit ae3bb9c2d5
16 changed files with 169 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/learner.cc
View File

@@ -598,8 +598,8 @@ class LearnerImpl : public Learner {
}
const TreeMethod current_tree_method = tparam_.tree_method;
if (rabit::IsDistributed()) {
/* Choose tree_method='approx' when distributed training is activated */
CHECK(tparam_.dsplit != DataSplitMode::kAuto)
<< "Precondition violated; dsplit cannot be 'auto' in distributed mode";
if (tparam_.dsplit == DataSplitMode::kCol) {
@@ -614,14 +614,13 @@ class LearnerImpl : public Learner {
"for distributed training.";
break;
case TreeMethod::kApprox:
case TreeMethod::kHist:
// things are okay, do nothing
break;
case TreeMethod::kExact:
case TreeMethod::kHist:
LOG(WARNING) << "Tree method was set to be '"
<< (current_tree_method == TreeMethod::kExact ?
"exact" : "hist")
<< "', but only 'approx' is available for distributed "
LOG(CONSOLE) << "Tree method was set to be "
<< "exact"
<< "', but only 'approx' and 'hist' is available for distributed "
"training. The `tree_method` parameter is now being "
"changed to 'approx'";
break;
@@ -633,7 +632,15 @@ class LearnerImpl : public Learner {
LOG(FATAL) << "Unknown tree_method ("
<< static_cast<int>(current_tree_method) << ") detected";
}
tparam_.tree_method = TreeMethod::kApprox;
if (current_tree_method != TreeMethod::kHist) {
LOG(CONSOLE) << "Tree method is automatically selected to be 'approx'"
" for distributed training.";
tparam_.tree_method = TreeMethod::kApprox;
} else {
LOG(CONSOLE) << "Tree method is specified to be 'hist'"
" for distributed training.";
tparam_.tree_method = TreeMethod::kHist;
}
} else if (!p_train->SingleColBlock()) {
/* Some tree methods are not available for external-memory DMatrix */
switch (current_tree_method) {