Added comment for sample_shift.

Author: KateBlueSky

sklbench/datasets/transformer.py

@@ -118,6 +118,10 @@ def split_and_transform_data(bench_case, data, data_description):
         from mpi4py import MPI
 
         rank = MPI.COMM_WORLD.Get_rank()
+        # This approach was chosen to shift the distribution of synthetic data on each rank
+        # for KMeans weak scaling tests. When testing with a large number of tiles, this method avoids duplication of data on each rank.
+        # For example, if there are 24,576 tiles being used, each data point in the 24,576th tile would be multiplied by 1.47.
+        # The factor 0.003 was chosen arbitrarily and can be fine-tuned for other datasets and algorithms if needed.
         adjust_number = (math.sqrt(rank) * 0.003) + 1
         x_test = x_test * adjust_number