Xtra-Computing / thundergbm

ThunderGBM: Fast GBDTs and Random Forests on GPUs
Apache License 2.0
695 stars 88 forks source link

how to use the random forest to train and predict? #42

Open xinsuinizhuan opened 4 years ago

Kurt-Liuhf commented 4 years ago

Hi, you can refer to the parameters document of ThunderGBM here. You need to set four key parameters namely, bagging = 1 and n_trees=1, n_parallel_trees to the number of trees of your random forest, column_sampling_rate to set the proportion of features to use, if you want to use the random forest. Thank you.