You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@datasketches.apache.org by al...@apache.org on 2024/09/18 03:11:58 UTC
(datasketches-bigquery) branch cpc_defaults updated: adjusted CPC tests
This is an automated email from the ASF dual-hosted git repository.
alsay pushed a commit to branch cpc_defaults
in repository https://gitbox.apache.org/repos/asf/datasketches-bigquery.git
The following commit(s) were added to refs/heads/cpc_defaults by this push:
new 9eb9f60 adjusted CPC tests
9eb9f60 is described below
commit 9eb9f6036842a90e114e78d36f07e17b31f6ce06
Author: AlexanderSaydakov <Al...@users.noreply.github.com>
AuthorDate: Tue Sep 17 20:11:45 2024 -0700
adjusted CPC tests
---
cpc/test/cpc_sketch_test.sql | 59 ++++++++++++++++++++++++++++++++++----------
1 file changed, 46 insertions(+), 13 deletions(-)
diff --git a/cpc/test/cpc_sketch_test.sql b/cpc/test/cpc_sketch_test.sql
index 6769ba3..d9c88b8 100644
--- a/cpc/test/cpc_sketch_test.sql
+++ b/cpc/test/cpc_sketch_test.sql
@@ -17,36 +17,69 @@
* under the License.
*/
+# using defaults
# expected 5
select $BQ_DATASET.cpc_sketch_get_estimate(
- $BQ_DATASET.cpc_sketch_scalar_union(
- (select $BQ_DATASET.cpc_sketch_agg_string(str, struct<int, int>(null, null)) from unnest(["a", "b", "c"]) as str),
- (select $BQ_DATASET.cpc_sketch_agg_string(str, struct<int, int>(null, null)) from unnest(["c", "d", "e"]) as str),
- null,
- null
+ $BQ_DATASET.cpc_sketch_union(
+ (select $BQ_DATASET.cpc_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str),
+ (select $BQ_DATASET.cpc_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str)
+ )
+);
+
+# using full signatures
+# expected 5
+select $BQ_DATASET.cpc_sketch_get_estimate_seed(
+ $BQ_DATASET.cpc_sketch_union_lgk_seed(
+ (select $BQ_DATASET.cpc_sketch_agg_string_lgk_seed(str, struct<byteint, int64>(10, 111)) from unnest(["a", "b", "c"]) as str),
+ (select $BQ_DATASET.cpc_sketch_agg_string_lgk_seed(str, struct<byteint, int64>(10, 111)) from unnest(["c", "d", "e"]) as str),
+ 10,
+ 111
),
- null
+ 111
);
+# using defaults
create or replace table $BQ_DATASET.cpc_sketch(sketch bytes);
insert into $BQ_DATASET.cpc_sketch
-(select $BQ_DATASET.cpc_sketch_agg_string(cast(value as string), struct<int, int>(null, null)) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value);
+(select $BQ_DATASET.cpc_sketch_agg_string(cast(value as string)) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value);
insert into $BQ_DATASET.cpc_sketch
-(select $BQ_DATASET.cpc_sketch_agg_string(cast(value as string), struct<int, int>(null, null)) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value);
+(select $BQ_DATASET.cpc_sketch_agg_string(cast(value as string)) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value);
-select $BQ_DATASET.cpc_sketch_to_string(sketch, null) from $BQ_DATASET.cpc_sketch;
+select $BQ_DATASET.cpc_sketch_to_string(sketch) from $BQ_DATASET.cpc_sketch;
# expected about 20000
select $BQ_DATASET.cpc_sketch_get_estimate(
- $BQ_DATASET.cpc_sketch_agg_union(sketch, struct<int, int>(null, null)),
- null
+ $BQ_DATASET.cpc_sketch_agg_union(sketch)
) from $BQ_DATASET.cpc_sketch;
select $BQ_DATASET.cpc_sketch_get_estimate_and_bounds(
- $BQ_DATASET.cpc_sketch_agg_union(sketch, struct<int, int>(14, null)),
+ $BQ_DATASET.cpc_sketch_agg_union(sketch),
+ 3
+) from $BQ_DATASET.cpc_sketch;
+
+drop table $BQ_DATASET.cpc_sketch;
+
+# using full signatures
+create or replace table $BQ_DATASET.cpc_sketch(sketch bytes);
+
+insert into $BQ_DATASET.cpc_sketch
+(select $BQ_DATASET.cpc_sketch_agg_string_lgk_seed(cast(value as string), struct<byteint, int64>(10, 111)) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value);
+insert into $BQ_DATASET.cpc_sketch
+(select $BQ_DATASET.cpc_sketch_agg_string_lgk_seed(cast(value as string), struct<byteint, int64>(10, 111)) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value);
+
+select $BQ_DATASET.cpc_sketch_to_string_seed(sketch, 111) from $BQ_DATASET.cpc_sketch;
+
+# expected about 20000
+select $BQ_DATASET.cpc_sketch_get_estimate_seed(
+ $BQ_DATASET.cpc_sketch_agg_union_lgk_seed(sketch, struct<byteint, int64>(10, 111)),
+ 111
+) from $BQ_DATASET.cpc_sketch;
+
+select $BQ_DATASET.cpc_sketch_get_estimate_and_bounds_seed(
+ $BQ_DATASET.cpc_sketch_agg_union_lgk_seed(sketch, struct<byteint, int64>(10, 111)),
3,
- null
+ 111
) from $BQ_DATASET.cpc_sketch;
drop table $BQ_DATASET.cpc_sketch;
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datasketches.apache.org
For additional commands, e-mail: commits-help@datasketches.apache.org