SOLVED - When using gridsearch, you need to pass the parameter dictionary as XGBClassifier(**param_dict)
Source
Original Post:
I’m receiving the following error when trying to run GridsearchCV. I’ve found similar questions online, and the solution is normally that the objective function is different in different versions of XGBoost. However, I am passing what appears to be an objective candidate for the version I’m running (1.3.3). I am using 'objective': 'binary:logistic' as a parameter. I tried removing the objective function altogether to use the default, but still receive this error.
XGBoostError: [08:46:30] /Users/travis/build/dmlc/xgboost/src/objective/objective.cc:26: Unknown objective function: {'n_estimators': 140, 'max_depth': 5, 'learning_rate': 0.1, 'objective': 'binary:logistic', 'min_child_weight': 1, 'gamma': 0, 'subsample': 0.8, 'colsample_bytree': 0.8, 'nthread': 4, 'scale_pos_weight': 1, 'seed': 42}
Objective candidate: survival:aft
Objective candidate: binary:hinge
Objective candidate: multi:softmax
Objective candidate: multi:softprob
Objective candidate: rank:pairwise
Objective candidate: rank:ndcg
Objective candidate: rank:map
Objective candidate: reg:squarederror
Objective candidate: reg:squaredlogerror
Objective candidate: reg:logistic
Objective candidate: reg:pseudohubererror
Objective candidate: binary:logistic
Objective candidate: binary:logitraw
Objective candidate: reg:linear
Objective candidate: count:poisson
Objective candidate: survival:cox
Objective candidate: reg:gamma
Objective candidate: reg:tweedie