Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[pyspark] support a list of feature column names (#8117)

Browse Source
This commit is contained in:
Bobby Wang
2022-08-08 17:05:27 +08:00
committed by GitHub
parent bcc8679a05
commit 03cc3b359c
11 changed files with 366 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/python/test_spark/test_data.py
View File

@@ -62,9 +62,11 @@ def run_dmatrix_ctor(is_dqm: bool) -> None:
kwargs = {"feature_types": feature_types}
if is_dqm:
cols = [f"feat-{i}" for i in range(n_features)]
train_Xy, valid_Xy = create_dmatrix_from_partitions(iter(dfs), cols, kwargs)
train_Xy, valid_Xy = create_dmatrix_from_partitions(iter(dfs), cols, 0, kwargs)
else:
train_Xy, valid_Xy = create_dmatrix_from_partitions(iter(dfs), None, kwargs)
train_Xy, valid_Xy = create_dmatrix_from_partitions(
iter(dfs), None, None, kwargs
)
assert valid_Xy is not None
assert valid_Xy.num_row() + train_Xy.num_row() == n_samples_per_batch * n_batches