search

fabsig / GPBoost

Combining tree-boosting with Gaussian process and mixed effects models
Other
574 stars 46 forks source link

Problem in running GPBOOST within last 8-10 days #98

Closed mpce-pal closed 1 year ago

mpce-pal commented 1 year ago

I was able to run GPBoost (Python) and got the results but while trying to run codes within last week, getting following error:

gpb = GPBoostRegressor().fit(x_train,y_train) score(gpb)

/usr/local/lib/python3.10/dist-packages/gpboost/basic.py in predict(self, data, start_iteration, num_iteration, pred_latent, pred_leaf, pred_contrib, data_has_header, is_reshape, group_data_pred, group_rand_coef_data_pred, gp_coords_pred, gp_rand_coef_data_pred, cluster_ids_pred, predict_cov_mat, predict_var, cov_pars, ignore_gp_model, raw_score, vecchia_pred_type, num_neighbors_pred, **kwargs) 3510 "Use the function 'set_prediction_data' to specify this") 3511 if num_neighbors_pred is not None: -> 3512 raise GPBoostError("The argument 'num_neighbors_pred' is discontinued. " 3513 "Use the function 'set_prediction_data' to specify this") 3514 predictor = self._to_predictor(deepcopy(kwargs))

GPBoostError: The argument 'num_neighbors_pred' is discontinued. Use the function 'set_prediction_data' to specify this

fabsig commented 1 year ago

Thanks a lot for reporting this!

Unfortunately, the Python API and also the scikit-learn API are currently not automatically tested. That's why bugs like this one can occur...

The just released version 1.2.1.1 fixes this.