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

fix online prediction function in learner.h (#2010)

Browse Source 
I use the online prediction function(`inline void Predict(const SparseBatch::Inst &inst, ... ) const;`), the results obtained are different from the results of the batch prediction function(`  virtual void Predict(DMatrix* data, ...) const = 0`). After the investigation found that the online prediction function using the `base_score_` parameters, and the batch prediction function is not used in this parameter. It is found that the `base_score_` values are different when the same model file is loaded many times.

```
1st times：base_score_: 6.69023e-21
2nd times：base_score_: -3.7668e+19
3rd times：base_score_: 5.40507e+07
```
 Online prediction results are affected by `base_score_` parameters. After deleting the if condition(`if (out_preds->size() == 1)`) , the online prediction is consistent with the batch prediction results, and the xgboost prediction results are consistent with python version.  Therefore, it is likely that the online prediction function is bug
This commit is contained in:
ZhouYong 2017-03-17 01:35:52 +08:00 committed by Tianqi Chen
parent 4a63f4ab43
commit fee1181803
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
include/xgboost/learner.h
View File

@ -188,9 +188,6 @@ inline void Learner::Predict(const SparseBatch::Inst& inst,
std::vector<bst_float>* out_preds,
unsigned ntree_limit) const {
gbm_->Predict(inst, out_preds, ntree_limit);
if (out_preds->size() == 1) {
(*out_preds)[0] += base_score_;
}
if (!output_margin) {
obj_->PredTransform(out_preds);
}