diff --git a/doc/BUILD b/doc/BUILD index 057760a991b7..91e55a71174f 100644 --- a/doc/BUILD +++ b/doc/BUILD @@ -458,7 +458,6 @@ doctest( "source/data/inspecting-data.rst", "source/data/loading-data.rst", "source/data/performance-tips.rst", - "source/data/saving-data.rst", "source/data/working-with-images.rst", "source/data/working-with-llms.rst", "source/data/working-with-pytorch.rst", diff --git a/doc/source/data/saving-data.rst b/doc/source/data/saving-data.rst index 258ac24a3897..8a7ced9ebf88 100644 --- a/doc/source/data/saving-data.rst +++ b/doc/source/data/saving-data.rst @@ -143,11 +143,11 @@ Changing the number of output files ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ When you call a write method, Ray Data writes your data to several files. To control the -number of output files, configure ``min_rows_per_write``. +number of output files, configure ``min_rows_per_file``. .. note:: - ``min_rows_per_write`` is a hint, not a strict limit. Ray Data might write more or + ``min_rows_per_file`` is a hint, not a strict limit. Ray Data might write more or fewer rows to each file. Under the hood, if the number of rows per block is larger than the specified value, Ray Data writes the number of rows per block to each file. @@ -159,7 +159,7 @@ number of output files, configure ``min_rows_per_write``. import ray ds = ray.data.read_csv("s3://anonymous@ray-example-data/iris.csv") - ds.write_csv("/tmp/few_files/", min_rows_per_write=75) + ds.write_csv("/tmp/few_files/", min_rows_per_file=75) print(os.listdir("/tmp/few_files/"))