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

Update CHANGES.md

Browse Source
This commit is contained in:
Tianqi Chen 2016-01-14 15:58:02 -08:00
parent 98d8a8b871
commit 0dc68b1aef
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
CHANGES.md
View File

@ -2,17 +2,17 @@ Change Log
========== ==========
xgboost-0.1 xgboost-0.1
=========== -----------
* Initial release * Initial release
xgboost-0.2x xgboost-0.2x
============ ------------
* Python module * Python module
* Weighted samples instances * Weighted samples instances
* Initial version of pairwise rank * Initial version of pairwise rank
xgboost-0.3 xgboost-0.3
=========== -----------
* Faster tree construction module * Faster tree construction module
- Allows subsample columns during tree construction via ```bst:col_samplebytree=ratio``` - Allows subsample columns during tree construction via ```bst:col_samplebytree=ratio```
* Support for boosting from initial predictions * Support for boosting from initial predictions
@ -22,7 +22,7 @@ xgboost-0.3
* Add R module * Add R module
xgboost-0.4 xgboost-0.4
=========== -----------
* Distributed version of xgboost that runs on YARN, scales to billions of examples * Distributed version of xgboost that runs on YARN, scales to billions of examples
* Direct save/load data and model from/to S3 and HDFS * Direct save/load data and model from/to S3 and HDFS
* Feature importance visualization in R module, by Michael Benesty * Feature importance visualization in R module, by Michael Benesty
@ -35,8 +35,8 @@ xgboost-0.4
* sklearn wrapper is supported in python module * sklearn wrapper is supported in python module
* Experimental External memory version * Experimental External memory version
on going at master xgboost-0.47
================== ------------
* Changes in R library * Changes in R library
- fixed possible problem of poisson regression. - fixed possible problem of poisson regression.
- switched from 0 to NA for missing values. - switched from 0 to NA for missing values.
@ -56,3 +56,6 @@ on going at master
- added best_ntree_limit attribute, in addition to best_score and best_iteration. - added best_ntree_limit attribute, in addition to best_score and best_iteration.
* Java api is ready for use * Java api is ready for use
* Added more test cases and continuous integration to make each build more robust. * Added more test cases and continuous integration to make each build more robust.
on going at master
------------------