Encode pandas categorical data automatically. (#7231)

2021-09-17 11:09:55 +08:00
parent 32e0858501
commit 22d56cebf1
3 changed files with 40 additions and 16 deletions
--- a/src/tree/updater_gpu_hist.cu
+++ b/src/tree/updater_gpu_hist.cu
@@ -582,6 +582,8 @@ struct GPUHistMakerDevice {

    auto is_cat = candidate.split.is_cat;
    if (is_cat) {
+      CHECK_LT(candidate.split.fvalue, std::numeric_limits<bst_cat_t>::max())
+          << "Categorical feature value too large.";
      auto cat = common::AsCat(candidate.split.fvalue);
      std::vector<uint32_t> split_cats(LBitField32::ComputeStorageSize(std::max(cat+1, 1)), 0);
      LBitField32 cats_bits(split_cats);