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

Add dump_format=json option (#1726)

Browse Source 
* Add format to the params accepted by DumpModel

Currently, only the test format is supported when trying to dump
a model. The plan is to add more such formats like JSON which are
easy to read and/or parse by machines. And to make the interface
for this even more generic to allow other formats to be added.

Hence, we make some modifications to make these function generic
and accept a new parameter "format" which signifies the format of
the dump to be created.

* Fix typos and errors in docs

* plugin: Mention all the register macros available

Document the register macros currently available to the plugin
writers so they know what exactly can be extended using hooks.

* sparce_page_source: Use same arg name in .h and .cc

* gbm: Add JSON dump

The dump_format argument can be used to specify what type
of dump file should be created. Add functionality to dump
gblinear and gbtree into a JSON file.

The JSON file has an array, each item is a JSON object for the tree.
For gblinear:
 - The item is the bias and weights vectors
For gbtree:
 - The item is the root node. The root node has a attribute "children"
   which holds the children nodes. This happens recursively.

* core.py: Add arg dump_format for get_dump()
This commit is contained in:
AbdealiJK
2016-11-04 22:25:25 +05:30
committed by Tianqi Chen
parent 9c693f0f5f
commit b94fcab4dc
16 changed files with 320 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
src/c_api/c_api.cc
View File

@@ -662,13 +662,14 @@ inline void XGBoostDumpModelImpl(
BoosterHandle handle,
const FeatureMap& fmap,
int with_stats,
const char *format,
xgboost::bst_ulong* len,
const char*** out_models) {
std::vector<std::string>& str_vecs = XGBAPIThreadLocalStore::Get()->ret_vec_str;
std::vector<const char*>& charp_vecs = XGBAPIThreadLocalStore::Get()->ret_vec_charp;
Booster *bst = static_cast<Booster*>(handle);
bst->LazyInit();
str_vecs = bst->learner()->Dump2Text(fmap, with_stats != 0);
str_vecs = bst->learner()->DumpModel(fmap, with_stats != 0, format);
charp_vecs.resize(str_vecs.size());
for (size_t i = 0; i < str_vecs.size(); ++i) {
charp_vecs[i] = str_vecs[i].c_str();
@@ -681,6 +682,14 @@ XGB_DLL int XGBoosterDumpModel(BoosterHandle handle,
int with_stats,
xgboost::bst_ulong* len,
const char*** out_models) {
XGBoosterDumpModelEx(handle, fmap, with_stats, "text", len, out_models);
}
XGB_DLL int XGBoosterDumpModelEx(BoosterHandle handle,
const char* fmap,
int with_stats,
const char *format,
xgboost::bst_ulong* len,
const char*** out_models) {
API_BEGIN();
FeatureMap featmap;
if (strlen(fmap) != 0) {
@@ -689,7 +698,7 @@ XGB_DLL int XGBoosterDumpModel(BoosterHandle handle,
dmlc::istream is(fs.get());
featmap.LoadText(is);
}
XGBoostDumpModelImpl(handle, featmap, with_stats, len, out_models);
XGBoostDumpModelImpl(handle, featmap, with_stats, format, len, out_models);
API_END();
}
@@ -700,12 +709,23 @@ XGB_DLL int XGBoosterDumpModelWithFeatures(BoosterHandle handle,
int with_stats,
xgboost::bst_ulong* len,
const char*** out_models) {
XGBoosterDumpModelExWithFeatures(handle, fnum, fname, ftype, with_stats,
"text", len, out_models);
}
XGB_DLL int XGBoosterDumpModelExWithFeatures(BoosterHandle handle,
int fnum,
const char** fname,
const char** ftype,
int with_stats,
const char *format,
xgboost::bst_ulong* len,
const char*** out_models) {
API_BEGIN();
FeatureMap featmap;
for (int i = 0; i < fnum; ++i) {
featmap.PushBack(i, fname[i], ftype[i]);
}
XGBoostDumpModelImpl(handle, featmap, with_stats, len, out_models);
XGBoostDumpModelImpl(handle, featmap, with_stats, format, len, out_models);
API_END();
}