Closed lzhw520110 closed 6 years ago
I don't know what happened. But it's obvious that recently xgboost-0.7 is released but I haven't upgrade my package. Switch your xgboost to 0.6, it will be OK. I will update it to 0.7 work with new version of xgboost when I'm free. Good luck!
I've encounterd the same issue. I've made PR https://github.com/bigdong89/xgboostExtension/pull/5 for the upgrade to V0.7.
The reason for the error lies in the fact that the get_xgb_params function uses the init signature to get the parameters. Since this signature has changed in XGBoost v0.7 this error was raised.
Thanks, Floris! Codes are merged for 0.7!
win7 py2.7 xgboost 0.7 when run xgbranker_example, I get error as this I add 'n_jobs' and 'random_state' to class XGBRanker.init(), This error dispeared, but I get a new error as this
Traceback (most recent call last): File "", line 1, in
dtrain.handle))
File "C:\Users\Lenovo\Anaconda2\lib\site-packages\xgboost-0.7-py2.7.egg\xgboost\core.py", line 130, in _check_call
raise XGBoostError(_LIB.XGBGetLastError())
xgboost.core.XGBoostError: Invalid Parameter format for seed expect int but value='None'
When I set seed=0 in class XGBRanker.init() and run xgbranker_example again, get a new error as this:
[11:10:29] dmlc-core/include/dmlc/./logging.h:300: [11:10:29] src/tree/updater_colmaker.cc:657: Check failed: param.colsample_bylevel > 0U (0 vs. 0) colsample_bylevel cannot be zero. Traceback (most recent call last): File "", line 1, in
xgb_model=xgb_model, callbacks=callbacks)
File "C:\Users\Lenovo\Anaconda2\lib\site-packages\xgboost-0.7-py2.7.egg\xgboost\training.py", line 74, in _train_internal
bst.update(dtrain, i, obj)
File "C:\Users\Lenovo\Anaconda2\lib\site-packages\xgboost-0.7-py2.7.egg\xgboost\core.py", line 898, in update
dtrain.handle))
File "C:\Users\Lenovo\Anaconda2\lib\site-packages\xgboost-0.7-py2.7.egg\xgboost\core.py", line 130, in _check_call
raise XGBoostError(_LIB.XGBGetLastError())
xgboost.core.XGBoostError: [11:10:29] src/tree/updater_colmaker.cc:657: Check failed: param.colsample_bylevel > 0U (0 vs. 0) colsample_bylevel cannot be zero.
I have no idea about this error!