@@ -24,7 +24,7 @@ def test_join_big(small_client, memory_multiplier):
24
24
df2_big = df2_big .astype ({"predicate" : "int" })
25
25
26
26
join = df1_big .merge (df2_big , on = "predicate" , how = "inner" )
27
- # dask-expr will drop all columns except the Index for size
27
+ # dask.dataframe will drop all columns except the Index for size
28
28
# computations, which will optimize itself through merges, e.g.
29
29
# shuffling a lot less data than what we want to test
30
30
# map_partitions blocks those optimizations
@@ -55,7 +55,7 @@ def test_join_big_small(small_client, memory_multiplier, configure_shuffling):
55
55
df_small_pd = df_small .astype ({"predicate" : "int" }).compute ()
56
56
57
57
join = df_big .merge (df_small_pd , on = "predicate" , how = "inner" )
58
- # dask-expr will drop all columns except the Index for size
58
+ # dask.dataframe will drop all columns except the Index for size
59
59
# computations, which will optimize itself through merges, e.g.
60
60
# shuffling a lot less data than what we want to test
61
61
# map_partitions blocks those optimizations
@@ -77,7 +77,7 @@ def test_set_index(small_client, persist, memory_multiplier):
77
77
if persist :
78
78
df_big = df_big .persist ()
79
79
df_indexed = df_big .set_index ("0" )
80
- # dask-expr will drop all columns except the Index for size
80
+ # dask.dataframe will drop all columns except the Index for size
81
81
# computations, which will optimize itself through set_index, e.g.
82
82
# shuffling a lot less data than what we want to test
83
83
# map_partitions blocks those optimizations
0 commit comments