This is an automated email from the ASF dual-hosted git repository. alsay pushed a commit to branch runable_examples in repository https://gitbox.apache.org/repos/asf/datasketches-bigquery.git
commit 95698fd31a4b0a109c0452414dc6e2b11067b680 Author: AlexanderSaydakov <[email protected]> AuthorDate: Fri Feb 7 14:01:52 2025 -0800 render examples with bqutil.datasketches prefix in function calls --- cpc/README.md | 68 ++++++++++----------- fi/README.md | 16 ++--- hll/README.md | 62 +++++++++---------- kll/README.md | 48 +++++++-------- readme_generator.py | 3 + req/README.md | 44 ++++++------- tdigest/README.md | 28 ++++----- theta/README.md | 132 +++++++++++++++++++-------------------- tuple/README.md | 173 ++++++++++++++++++++++++++-------------------------- 9 files changed, 288 insertions(+), 286 deletions(-) diff --git a/cpc/README.md b/cpc/README.md index 6567779..b55e9a3 100644 --- a/cpc/README.md +++ b/cpc/README.md @@ -60,19 +60,19 @@ page for how to contact us. # using defaults # expected 5 -select `$BQ_DATASET`.cpc_sketch_get_estimate( - `$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) +select bqutil.datasketches.cpc_sketch_get_estimate( + bqutil.datasketches.cpc_sketch_union( + (select bqutil.datasketches.cpc_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.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), +select bqutil.datasketches.cpc_sketch_get_estimate_seed( + bqutil.datasketches.cpc_sketch_union_lgk_seed( + (select bqutil.datasketches.cpc_sketch_agg_string_lgk_seed(str, struct<byteint, int64>(10, 111)) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.cpc_sketch_agg_string_lgk_seed(str, struct<byteint, int64>(10, 111)) from unnest(["c", "d", "e"]) as str), 10, 111 ), @@ -80,48 +80,48 @@ select `$BQ_DATASET`.cpc_sketch_get_estimate_seed( ); # using defaults -create or replace table `$BQ_DATASET`.cpc_sketch(sketch bytes); +create or replace temp table cpc_sketch(sketch bytes); -insert into `$BQ_DATASET`.cpc_sketch -(select `$BQ_DATASET`.cpc_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.cpc_sketch -(select `$BQ_DATASET`.cpc_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into cpc_sketch +(select bqutil.datasketches.cpc_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into cpc_sketch +(select bqutil.datasketches.cpc_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); -select `$BQ_DATASET`.cpc_sketch_to_string(sketch) from `$BQ_DATASET`.cpc_sketch; +select bqutil.datasketches.cpc_sketch_to_string(sketch) from cpc_sketch; # expected about 20000 -select `$BQ_DATASET`.cpc_sketch_get_estimate( - `$BQ_DATASET`.cpc_sketch_agg_union(sketch) -) from `$BQ_DATASET`.cpc_sketch; +select bqutil.datasketches.cpc_sketch_get_estimate( + bqutil.datasketches.cpc_sketch_agg_union(sketch) +) from cpc_sketch; -select `$BQ_DATASET`.cpc_sketch_get_estimate_and_bounds( - `$BQ_DATASET`.cpc_sketch_agg_union(sketch), +select bqutil.datasketches.cpc_sketch_get_estimate_and_bounds( + bqutil.datasketches.cpc_sketch_agg_union(sketch), 3 -) from `$BQ_DATASET`.cpc_sketch; +) from cpc_sketch; -drop table `$BQ_DATASET`.cpc_sketch; +drop table cpc_sketch; # using full signatures -create or replace table `$BQ_DATASET`.cpc_sketch(sketch bytes); +create or replace temp table cpc_sketch(sketch bytes); -insert into `$BQ_DATASET`.cpc_sketch -(select `$BQ_DATASET`.cpc_sketch_agg_int64_lgk_seed(value, 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_int64_lgk_seed(value, struct<byteint, int64>(10, 111)) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into cpc_sketch +(select bqutil.datasketches.cpc_sketch_agg_int64_lgk_seed(value, struct<byteint, int64>(10, 111)) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into cpc_sketch +(select bqutil.datasketches.cpc_sketch_agg_int64_lgk_seed(value, 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; +select bqutil.datasketches.cpc_sketch_to_string_seed(sketch, 111) from 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)), +select bqutil.datasketches.cpc_sketch_get_estimate_seed( + bqutil.datasketches.cpc_sketch_agg_union_lgk_seed(sketch, struct<byteint, int64>(10, 111)), 111 -) from `$BQ_DATASET`.cpc_sketch; +) from cpc_sketch; -select `$BQ_DATASET`.cpc_sketch_get_estimate_and_bounds_seed( - `$BQ_DATASET`.cpc_sketch_agg_union_lgk_seed(sketch, struct<byteint, int64>(10, 111)), +select bqutil.datasketches.cpc_sketch_get_estimate_and_bounds_seed( + bqutil.datasketches.cpc_sketch_agg_union_lgk_seed(sketch, struct<byteint, int64>(10, 111)), 3, 111 -) from `$BQ_DATASET`.cpc_sketch; +) from cpc_sketch; -drop table `$BQ_DATASET`.cpc_sketch; +drop table cpc_sketch; ``` diff --git a/fi/README.md b/fi/README.md index 11a1f5d..3a51be0 100644 --- a/fi/README.md +++ b/fi/README.md @@ -47,17 +47,17 @@ page for how to contact us. ```sql -select `$BQ_DATASET`.frequent_strings_sketch_to_string(`$BQ_DATASET`.frequent_strings_sketch_build(str, 1, 5)) from unnest(["a", "b", "c"]) as str; +select bqutil.datasketches.frequent_strings_sketch_to_string(bqutil.datasketches.frequent_strings_sketch_build(str, 1, 5)) from unnest(["a", "b", "c"]) as str; -create or replace table `$BQ_DATASET`.fs_sketch(sketch bytes); +create or replace temp table fs_sketch(sketch bytes); -insert into `$BQ_DATASET`.fs_sketch -(select `$BQ_DATASET`.frequent_strings_sketch_build(str, 1, 5) from unnest(["a", "b", "c", "d"]) as str); +insert into fs_sketch +(select bqutil.datasketches.frequent_strings_sketch_build(str, 1, 5) from unnest(["a", "b", "c", "d"]) as str); -insert into `$BQ_DATASET`.fs_sketch -(select `$BQ_DATASET`.frequent_strings_sketch_build(str, 1, 5) from unnest(["a", "a", "c"]) as str); +insert into fs_sketch +(select bqutil.datasketches.frequent_strings_sketch_build(str, 1, 5) from unnest(["a", "a", "c"]) as str); -select `$BQ_DATASET`.frequent_strings_sketch_get_result(`$BQ_DATASET`.frequent_strings_sketch_merge(sketch, 5), "NO_FALSE_NEGATIVES", null) from `$BQ_DATASET`.fs_sketch; +select bqutil.datasketches.frequent_strings_sketch_get_result(bqutil.datasketches.frequent_strings_sketch_merge(sketch, 5), "NO_FALSE_NEGATIVES", null) from fs_sketch; -drop table `$BQ_DATASET`.fs_sketch; +drop table fs_sketch; ``` diff --git a/hll/README.md b/hll/README.md index 03dc49e..127a88e 100644 --- a/hll/README.md +++ b/hll/README.md @@ -54,59 +54,59 @@ page for how to contact us. ```sql # expected 3 -select `$BQ_DATASET`.hll_sketch_get_estimate(`$BQ_DATASET`.hll_sketch_agg_string(s)) from unnest(["a", "b", "c"]) as s; +select bqutil.datasketches.hll_sketch_get_estimate(bqutil.datasketches.hll_sketch_agg_string(s)) from unnest(["a", "b", "c"]) as s; -select `$BQ_DATASET`.hll_sketch_to_string(`$BQ_DATASET`.hll_sketch_agg_string(s)) from unnest(["a", "b", "c"]) as s; +select bqutil.datasketches.hll_sketch_to_string(bqutil.datasketches.hll_sketch_agg_string(s)) from unnest(["a", "b", "c"]) as s; # expected 5 -select `$BQ_DATASET`.hll_sketch_get_estimate_and_bounds( - `$BQ_DATASET`.hll_sketch_union_lgk_type( - (select `$BQ_DATASET`.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.hll_sketch_get_estimate_and_bounds( + bqutil.datasketches.hll_sketch_union_lgk_type( + (select bqutil.datasketches.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["c", "d", "e"]) as str), 10, "HLL_8" ), 2 ); -select `$BQ_DATASET`.hll_sketch_to_string( - `$BQ_DATASET`.hll_sketch_union_lgk_type( - (select `$BQ_DATASET`.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.hll_sketch_to_string( + bqutil.datasketches.hll_sketch_union_lgk_type( + (select bqutil.datasketches.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.hll_sketch_agg_string_lgk_type(str, struct<byteint, string>(10, "HLL_8")) from unnest(["c", "d", "e"]) as str), 10, "HLL_8" ) ); -create or replace table `$BQ_DATASET`.hll_sketch(sketch bytes); +create or replace temp table hll_sketch(sketch bytes); -insert into `$BQ_DATASET`.hll_sketch -(select `$BQ_DATASET`.hll_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.hll_sketch -(select `$BQ_DATASET`.hll_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into hll_sketch +(select bqutil.datasketches.hll_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into hll_sketch +(select bqutil.datasketches.hll_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); # expected estimate about 20000 -select `$BQ_DATASET`.hll_sketch_to_string( - `$BQ_DATASET`.hll_sketch_agg_union(sketch) -) from `$BQ_DATASET`.hll_sketch; +select bqutil.datasketches.hll_sketch_to_string( + bqutil.datasketches.hll_sketch_agg_union(sketch) +) from hll_sketch; -select `$BQ_DATASET`.hll_sketch_to_string( - `$BQ_DATASET`.hll_sketch_agg_union_lgk_type(sketch, struct<byteint, string>(10, "HLL_6")) -) from `$BQ_DATASET`.hll_sketch; +select bqutil.datasketches.hll_sketch_to_string( + bqutil.datasketches.hll_sketch_agg_union_lgk_type(sketch, struct<byteint, string>(10, "HLL_6")) +) from hll_sketch; -drop table `$BQ_DATASET`.hll_sketch; +drop table hll_sketch; -create or replace table `$BQ_DATASET`.hll_sketch(sketch bytes); +create or replace temp table hll_sketch(sketch bytes); -insert into `$BQ_DATASET`.hll_sketch -(select `$BQ_DATASET`.hll_sketch_agg_int64_lgk_type(value, struct<int, string>(8, "HLL_6")) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.hll_sketch -(select `$BQ_DATASET`.hll_sketch_agg_int64_lgk_type(value, struct<int, string>(8, "HLL_6")) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into hll_sketch +(select bqutil.datasketches.hll_sketch_agg_int64_lgk_type(value, struct<int, string>(8, "HLL_6")) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into hll_sketch +(select bqutil.datasketches.hll_sketch_agg_int64_lgk_type(value, struct<int, string>(8, "HLL_6")) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); # expected estimate about 20000 -select `$BQ_DATASET`.hll_sketch_to_string( - `$BQ_DATASET`.hll_sketch_agg_union_lgk_type(sketch, struct<byteint, string>(8, "HLL_6")) -) from `$BQ_DATASET`.hll_sketch; +select bqutil.datasketches.hll_sketch_to_string( + bqutil.datasketches.hll_sketch_agg_union_lgk_type(sketch, struct<byteint, string>(8, "HLL_6")) +) from hll_sketch; -drop table `$BQ_DATASET`.hll_sketch; +drop table hll_sketch; ``` diff --git a/kll/README.md b/kll/README.md index 1a5571d..30a707d 100644 --- a/kll/README.md +++ b/kll/README.md @@ -57,63 +57,63 @@ page for how to contact us. ```sql -create or replace table `$BQ_DATASET`.kll_sketch(sketch bytes); +create or replace temp table kll_sketch(sketch bytes); # using default -insert into `$BQ_DATASET`.kll_sketch -(select `$BQ_DATASET`.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); +insert into kll_sketch +(select bqutil.datasketches.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); # using full signature -insert into `$BQ_DATASET`.kll_sketch -(select `$BQ_DATASET`.kll_sketch_float_build_k(value, 100) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); +insert into kll_sketch +(select bqutil.datasketches.kll_sketch_float_build_k(value, 100) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); -select `$BQ_DATASET`.kll_sketch_float_to_string(sketch) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_to_string(sketch) from kll_sketch; # using default -select `$BQ_DATASET`.kll_sketch_float_to_string(`$BQ_DATASET`.kll_sketch_float_merge(sketch)) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_to_string(bqutil.datasketches.kll_sketch_float_merge(sketch)) from kll_sketch; # using full signature -select `$BQ_DATASET`.kll_sketch_float_to_string(`$BQ_DATASET`.kll_sketch_float_merge_k(sketch, 100)) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_to_string(bqutil.datasketches.kll_sketch_float_merge_k(sketch, 100)) from kll_sketch; # expected 0.5 -select `$BQ_DATASET`.kll_sketch_float_get_rank(`$BQ_DATASET`.kll_sketch_float_merge(sketch), 10, true) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_rank(bqutil.datasketches.kll_sketch_float_merge(sketch), 10, true) from kll_sketch; # expected 10 -select `$BQ_DATASET`.kll_sketch_float_get_quantile(`$BQ_DATASET`.kll_sketch_float_merge(sketch), 0.5, true) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_quantile(bqutil.datasketches.kll_sketch_float_merge(sketch), 0.5, true) from kll_sketch; # expected 20 -select `$BQ_DATASET`.kll_sketch_float_get_n(`$BQ_DATASET`.kll_sketch_float_merge(sketch)) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_n(bqutil.datasketches.kll_sketch_float_merge(sketch)) from kll_sketch; # expected 0.5, 0.5 -select `$BQ_DATASET`.kll_sketch_float_get_pmf(`$BQ_DATASET`.kll_sketch_float_merge(sketch), [10.0], true) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_pmf(bqutil.datasketches.kll_sketch_float_merge(sketch), [10.0], true) from kll_sketch; # expected 0.5, 1 -select `$BQ_DATASET`.kll_sketch_float_get_cdf(`$BQ_DATASET`.kll_sketch_float_merge(sketch), [10.0], true) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_cdf(bqutil.datasketches.kll_sketch_float_merge(sketch), [10.0], true) from kll_sketch; # expected 1 -select `$BQ_DATASET`.kll_sketch_float_get_min_value(`$BQ_DATASET`.kll_sketch_float_merge(sketch)) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_min_value(bqutil.datasketches.kll_sketch_float_merge(sketch)) from kll_sketch; # expected 20 -select `$BQ_DATASET`.kll_sketch_float_get_max_value(`$BQ_DATASET`.kll_sketch_float_merge(sketch)) from `$BQ_DATASET`.kll_sketch; +select bqutil.datasketches.kll_sketch_float_get_max_value(bqutil.datasketches.kll_sketch_float_merge(sketch)) from kll_sketch; -drop table `$BQ_DATASET`.kll_sketch; +drop table kll_sketch; # expected about 1.3% -select `$BQ_DATASET`.kll_sketch_float_get_normalized_rank_error(`$BQ_DATASET`.kll_sketch_float_build(value), false) from unnest(generate_array(1, 10000)) as value; +select bqutil.datasketches.kll_sketch_float_get_normalized_rank_error(bqutil.datasketches.kll_sketch_float_build(value), false) from unnest(generate_array(1, 10000)) as value; -select `$BQ_DATASET`.kll_sketch_float_get_num_retained(`$BQ_DATASET`.kll_sketch_float_build(value)) from unnest(generate_array(1, 10000)) as value; +select bqutil.datasketches.kll_sketch_float_get_num_retained(bqutil.datasketches.kll_sketch_float_build(value)) from unnest(generate_array(1, 10000)) as value; # expected false -select `$BQ_DATASET`.kll_sketch_float_kolmogorov_smirnov( - (select `$BQ_DATASET`.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value), - (select `$BQ_DATASET`.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value), +select bqutil.datasketches.kll_sketch_float_kolmogorov_smirnov( + (select bqutil.datasketches.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value), + (select bqutil.datasketches.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value), 0.05 ); # expected true -select `$BQ_DATASET`.kll_sketch_float_kolmogorov_smirnov( - (select `$BQ_DATASET`.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value), - (select `$BQ_DATASET`.kll_sketch_float_build(value) from unnest([11,12,13,14,15,16,17,18,19,20]) as value), +select bqutil.datasketches.kll_sketch_float_kolmogorov_smirnov( + (select bqutil.datasketches.kll_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value), + (select bqutil.datasketches.kll_sketch_float_build(value) from unnest([11,12,13,14,15,16,17,18,19,20]) as value), 0.05 ); ``` diff --git a/readme_generator.py b/readme_generator.py index 10bffbd..4029422 100644 --- a/readme_generator.py +++ b/readme_generator.py @@ -155,6 +155,9 @@ def generate_readme(template_path: str, function_index: dict, examples_path: str break sql_code_without_license = "\n".join(sql_code_lines[start_index:]) + # add project and dataset available in BQ + sql_code_without_license = sql_code_without_license.replace('`$BQ_DATASET`', 'bqutil.datasketches') + # Add the SQL code in a code block output_lines.append(f"```sql\n{sql_code_without_license}\n```\n") diff --git a/req/README.md b/req/README.md index 5b21953..66dfafe 100644 --- a/req/README.md +++ b/req/README.md @@ -61,53 +61,53 @@ page for how to contact us. # using defaults -create or replace table `$BQ_DATASET`.req_sketch(sketch bytes); +create or replace temp table req_sketch(sketch bytes); -insert into `$BQ_DATASET`.req_sketch -(select `$BQ_DATASET`.req_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); +insert into req_sketch +(select bqutil.datasketches.req_sketch_float_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); -insert into `$BQ_DATASET`.req_sketch -(select `$BQ_DATASET`.req_sketch_float_build(value) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); +insert into req_sketch +(select bqutil.datasketches.req_sketch_float_build(value) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); -select `$BQ_DATASET`.req_sketch_float_to_string(`$BQ_DATASET`.req_sketch_float_merge(sketch)) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_to_string(bqutil.datasketches.req_sketch_float_merge(sketch)) from req_sketch; # expected 0.5 -select `$BQ_DATASET`.req_sketch_float_get_rank(`$BQ_DATASET`.req_sketch_float_merge(sketch), 10, true) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_rank(bqutil.datasketches.req_sketch_float_merge(sketch), 10, true) from req_sketch; # expected 10 -select `$BQ_DATASET`.req_sketch_float_get_quantile(`$BQ_DATASET`.req_sketch_float_merge(sketch), 0.5, true) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_quantile(bqutil.datasketches.req_sketch_float_merge(sketch), 0.5, true) from req_sketch; # expected 0.5, 0.5 -select `$BQ_DATASET`.req_sketch_float_get_pmf(`$BQ_DATASET`.req_sketch_float_merge(sketch), [10.0], true) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_pmf(bqutil.datasketches.req_sketch_float_merge(sketch), [10.0], true) from req_sketch; # expected 0.5, 1 -select `$BQ_DATASET`.req_sketch_float_get_cdf(`$BQ_DATASET`.req_sketch_float_merge(sketch), [10.0], true) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_cdf(bqutil.datasketches.req_sketch_float_merge(sketch), [10.0], true) from req_sketch; # expected 1 -select `$BQ_DATASET`.req_sketch_float_get_min_value(`$BQ_DATASET`.req_sketch_float_merge(sketch)) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_min_value(bqutil.datasketches.req_sketch_float_merge(sketch)) from req_sketch; # expected 20 -select `$BQ_DATASET`.req_sketch_float_get_max_value(`$BQ_DATASET`.req_sketch_float_merge(sketch)) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_max_value(bqutil.datasketches.req_sketch_float_merge(sketch)) from req_sketch; # expected 20 -select `$BQ_DATASET`.req_sketch_float_get_n(`$BQ_DATASET`.req_sketch_float_merge(sketch)) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_n(bqutil.datasketches.req_sketch_float_merge(sketch)) from req_sketch; # expected 20 -select `$BQ_DATASET`.req_sketch_float_get_num_retained(`$BQ_DATASET`.req_sketch_float_merge(sketch)) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_get_num_retained(bqutil.datasketches.req_sketch_float_merge(sketch)) from req_sketch; -drop table `$BQ_DATASET`.req_sketch; +drop table req_sketch; # using full signatures -create or replace table `$BQ_DATASET`.req_sketch(sketch bytes); +create or replace temp table req_sketch(sketch bytes); -insert into `$BQ_DATASET`.req_sketch -(select `$BQ_DATASET`.req_sketch_float_build_k_hra(value, struct<int, bool>(10, false)) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); +insert into req_sketch +(select bqutil.datasketches.req_sketch_float_build_k_hra(value, struct<int, bool>(10, false)) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); -insert into `$BQ_DATASET`.req_sketch -(select `$BQ_DATASET`.req_sketch_float_build_k_hra(value, struct<int, bool>(10, false)) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); +insert into req_sketch +(select bqutil.datasketches.req_sketch_float_build_k_hra(value, struct<int, bool>(10, false)) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); -select `$BQ_DATASET`.req_sketch_float_to_string(`$BQ_DATASET`.req_sketch_float_merge_k_hra(sketch, struct<int, bool>(10, false))) from `$BQ_DATASET`.req_sketch; +select bqutil.datasketches.req_sketch_float_to_string(bqutil.datasketches.req_sketch_float_merge_k_hra(sketch, struct<int, bool>(10, false))) from req_sketch; -drop table `$BQ_DATASET`.req_sketch; +drop table req_sketch; ``` diff --git a/tdigest/README.md b/tdigest/README.md index 6b5a6b6..efb6bee 100644 --- a/tdigest/README.md +++ b/tdigest/README.md @@ -51,38 +51,38 @@ page for how to contact us. ```sql -create or replace table `$BQ_DATASET`.tdigest_double(sketch bytes); +create or replace temp table tdigest_double(sketch bytes); # using default -insert into `$BQ_DATASET`.tdigest_double -(select `$BQ_DATASET`.tdigest_double_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); +insert into tdigest_double +(select bqutil.datasketches.tdigest_double_build(value) from unnest([1,2,3,4,5,6,7,8,9,10]) as value); # using full signature -insert into `$BQ_DATASET`.tdigest_double -(select `$BQ_DATASET`.tdigest_double_build_k(value, 100) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); +insert into tdigest_double +(select bqutil.datasketches.tdigest_double_build_k(value, 100) from unnest([11,12,13,14,15,16,17,18,19,20]) as value); -select `$BQ_DATASET`.tdigest_double_to_string(sketch) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_to_string(sketch) from tdigest_double; # using default -select `$BQ_DATASET`.tdigest_double_to_string(`$BQ_DATASET`.tdigest_double_merge(sketch)) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_to_string(bqutil.datasketches.tdigest_double_merge(sketch)) from tdigest_double; # using full signature -select `$BQ_DATASET`.tdigest_double_to_string(`$BQ_DATASET`.tdigest_double_merge_k(sketch, 100)) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_to_string(bqutil.datasketches.tdigest_double_merge_k(sketch, 100)) from tdigest_double; # expected 0.5 -select `$BQ_DATASET`.tdigest_double_get_rank(`$BQ_DATASET`.tdigest_double_merge(sketch), 10) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_get_rank(bqutil.datasketches.tdigest_double_merge(sketch), 10) from tdigest_double; # expected 10 -select `$BQ_DATASET`.tdigest_double_get_quantile(`$BQ_DATASET`.tdigest_double_merge(sketch), 0.5) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_get_quantile(bqutil.datasketches.tdigest_double_merge(sketch), 0.5) from tdigest_double; # expected 20 -select `$BQ_DATASET`.tdigest_double_get_total_weight(`$BQ_DATASET`.tdigest_double_merge(sketch)) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_get_total_weight(bqutil.datasketches.tdigest_double_merge(sketch)) from tdigest_double; # expected 1 -select `$BQ_DATASET`.tdigest_double_get_min_value(`$BQ_DATASET`.tdigest_double_merge(sketch)) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_get_min_value(bqutil.datasketches.tdigest_double_merge(sketch)) from tdigest_double; # expected 20 -select `$BQ_DATASET`.tdigest_double_get_max_value(`$BQ_DATASET`.tdigest_double_merge(sketch)) from `$BQ_DATASET`.tdigest_double; +select bqutil.datasketches.tdigest_double_get_max_value(bqutil.datasketches.tdigest_double_merge(sketch)) from tdigest_double; -drop table `$BQ_DATASET`.tdigest_double; +drop table tdigest_double; ``` diff --git a/theta/README.md b/theta/README.md index feaa1db..cef3a08 100644 --- a/theta/README.md +++ b/theta/README.md @@ -68,82 +68,82 @@ page for how to contact us. ```sql # using defaults -create or replace table `$BQ_DATASET`.theta_sketch(sketch bytes); +create or replace temp table theta_sketch(sketch bytes); -insert into `$BQ_DATASET`.theta_sketch -(select `$BQ_DATASET`.theta_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.theta_sketch -(select `$BQ_DATASET`.theta_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into theta_sketch +(select bqutil.datasketches.theta_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into theta_sketch +(select bqutil.datasketches.theta_sketch_agg_int64(value) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); # expected about 20000 -select `$BQ_DATASET`.theta_sketch_get_estimate_and_bounds( - `$BQ_DATASET`.theta_sketch_agg_union(sketch), +select bqutil.datasketches.theta_sketch_get_estimate_and_bounds( + bqutil.datasketches.theta_sketch_agg_union(sketch), 2 -) from `$BQ_DATASET`.theta_sketch; +) from theta_sketch; # expected estimate about 20000 -select `$BQ_DATASET`.theta_sketch_to_string( - `$BQ_DATASET`.theta_sketch_agg_union(sketch) -) from `$BQ_DATASET`.theta_sketch; +select bqutil.datasketches.theta_sketch_to_string( + bqutil.datasketches.theta_sketch_agg_union(sketch) +) from theta_sketch; -select `$BQ_DATASET`.theta_sketch_get_theta( - `$BQ_DATASET`.theta_sketch_agg_union(sketch) -) from `$BQ_DATASET`.theta_sketch; +select bqutil.datasketches.theta_sketch_get_theta( + bqutil.datasketches.theta_sketch_agg_union(sketch) +) from theta_sketch; -select `$BQ_DATASET`.theta_sketch_get_num_retained( - `$BQ_DATASET`.theta_sketch_agg_union(sketch) -) from `$BQ_DATASET`.theta_sketch; +select bqutil.datasketches.theta_sketch_get_num_retained( + bqutil.datasketches.theta_sketch_agg_union(sketch) +) from theta_sketch; -drop table `$BQ_DATASET`.theta_sketch; +drop table theta_sketch; # using full signatures -create or replace table `$BQ_DATASET`.theta_sketch(sketch bytes); +create or replace temp table theta_sketch(sketch bytes); -insert into `$BQ_DATASET`.theta_sketch -(select `$BQ_DATASET`.theta_sketch_agg_int64_lgk_seed_p(value, struct<int, int, float64>(14, 111, 0.9)) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.theta_sketch -(select `$BQ_DATASET`.theta_sketch_agg_int64_lgk_seed_p(value, struct<int, int, float64>(14, 111, 0.9)) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into theta_sketch +(select bqutil.datasketches.theta_sketch_agg_int64_lgk_seed_p(value, struct<int, int, float64>(14, 111, 0.9)) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into theta_sketch +(select bqutil.datasketches.theta_sketch_agg_int64_lgk_seed_p(value, struct<int, int, float64>(14, 111, 0.9)) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); # expected about 20000 -select `$BQ_DATASET`.theta_sketch_get_estimate_and_bounds_seed( - `$BQ_DATASET`.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), +select bqutil.datasketches.theta_sketch_get_estimate_and_bounds_seed( + bqutil.datasketches.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), 2, 111 -) from `$BQ_DATASET`.theta_sketch; +) from theta_sketch; # expected estimate about 20000 -select `$BQ_DATASET`.theta_sketch_to_string_seed( - `$BQ_DATASET`.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), +select bqutil.datasketches.theta_sketch_to_string_seed( + bqutil.datasketches.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), 111 -) from `$BQ_DATASET`.theta_sketch; +) from theta_sketch; -select `$BQ_DATASET`.theta_sketch_get_theta_seed( - `$BQ_DATASET`.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), +select bqutil.datasketches.theta_sketch_get_theta_seed( + bqutil.datasketches.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), 111 -) from `$BQ_DATASET`.theta_sketch; +) from theta_sketch; -select `$BQ_DATASET`.theta_sketch_get_num_retained_seed( - `$BQ_DATASET`.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), +select bqutil.datasketches.theta_sketch_get_num_retained_seed( + bqutil.datasketches.theta_sketch_agg_union_lgk_seed(sketch, struct<int, int>(10, 111)), 111 -) from `$BQ_DATASET`.theta_sketch; +) from theta_sketch; -drop table `$BQ_DATASET`.theta_sketch; +drop table theta_sketch; # using defaults # expected 5 -select `$BQ_DATASET`.theta_sketch_get_estimate( - `$BQ_DATASET`.theta_sketch_union( - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.theta_sketch_get_estimate( + bqutil.datasketches.theta_sketch_union( + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) ) ); # full signatures # expected 5 -select `$BQ_DATASET`.theta_sketch_get_estimate_seed( - `$BQ_DATASET`.theta_sketch_union_lgk_seed( - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.theta_sketch_get_estimate_seed( + bqutil.datasketches.theta_sketch_union_lgk_seed( + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), 10, 111 ), @@ -152,19 +152,19 @@ select `$BQ_DATASET`.theta_sketch_get_estimate_seed( # using defaults # expected 1 -select `$BQ_DATASET`.theta_sketch_get_estimate( - `$BQ_DATASET`.theta_sketch_intersection( - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.theta_sketch_get_estimate( + bqutil.datasketches.theta_sketch_intersection( + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) ) ); # full signatures # expected 1 -select `$BQ_DATASET`.theta_sketch_get_estimate_seed( - `$BQ_DATASET`.theta_sketch_intersection_seed( - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.theta_sketch_get_estimate_seed( + bqutil.datasketches.theta_sketch_intersection_seed( + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), 111 ), 111 @@ -172,19 +172,19 @@ select `$BQ_DATASET`.theta_sketch_get_estimate_seed( # using defaults # expected 2 -select `$BQ_DATASET`.theta_sketch_get_estimate( - `$BQ_DATASET`.theta_sketch_a_not_b( - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.theta_sketch_get_estimate( + bqutil.datasketches.theta_sketch_a_not_b( + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) ) ); # full signatures # expected 2 -select `$BQ_DATASET`.theta_sketch_get_estimate_seed( - `$BQ_DATASET`.theta_sketch_a_not_b_seed( - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.theta_sketch_get_estimate_seed( + bqutil.datasketches.theta_sketch_a_not_b_seed( + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), 111 ), 111 @@ -192,16 +192,16 @@ select `$BQ_DATASET`.theta_sketch_get_estimate_seed( # using defaults # expected 0.2 -select `$BQ_DATASET`.theta_sketch_jaccard_similarity( - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.theta_sketch_jaccard_similarity( + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string(str) from unnest(["c", "d", "e"]) as str) ); # using full signatures # expected 0.2 -select `$BQ_DATASET`.theta_sketch_jaccard_similarity_seed( - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.theta_sketch_jaccard_similarity_seed( + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(str, struct<int, int, float64>(10, 111, 0.999)) from unnest(["c", "d", "e"]) as str), 111 ); ``` diff --git a/tuple/README.md b/tuple/README.md index 4ded83a..85a2e03 100644 --- a/tuple/README.md +++ b/tuple/README.md @@ -74,111 +74,110 @@ page for how to contact us. ```sql # using defaults -create or replace table `$BQ_DATASET`.tuple_sketch(sketch bytes); +create or replace temp table tuple_sketch(sketch bytes); -insert into `$BQ_DATASET`.tuple_sketch -(select `$BQ_DATASET`.tuple_sketch_int64_from_theta_sketch(`$BQ_DATASET`.theta_sketch_agg_string(cast(value as string)), 1) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.tuple_sketch -(select `$BQ_DATASET`.tuple_sketch_int64_from_theta_sketch(`$BQ_DATASET`.theta_sketch_agg_string(cast(value as string)), 1) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); +insert into tuple_sketch +(select bqutil.datasketches.tuple_sketch_int64_from_theta_sketch(bqutil.datasketches.theta_sketch_agg_string(cast(value as string)), 1) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); +insert into tuple_sketch +(select bqutil.datasketches.tuple_sketch_int64_from_theta_sketch(bqutil.datasketches.theta_sketch_agg_string(cast(value as string)), 1) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); # expected about 20000 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate( - `$BQ_DATASET`.tuple_sketch_int64_agg_union(sketch) -) from `$BQ_DATASET`.tuple_sketch; +select bqutil.datasketches.tuple_sketch_int64_get_estimate( + bqutil.datasketches.tuple_sketch_int64_agg_union(sketch) +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_and_bounds( - `$BQ_DATASET`.tuple_sketch_int64_agg_union(sketch), +select bqutil.datasketches.tuple_sketch_int64_get_estimate_and_bounds( + bqutil.datasketches.tuple_sketch_int64_agg_union(sketch), 2 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_sum_estimate_and_bounds( - `$BQ_DATASET`.tuple_sketch_int64_agg_union(sketch), +select bqutil.datasketches.tuple_sketch_int64_get_sum_estimate_and_bounds( + bqutil.datasketches.tuple_sketch_int64_agg_union(sketch), 2 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; # expected estimate about 20000 -select `$BQ_DATASET`.tuple_sketch_int64_to_string( - `$BQ_DATASET`.tuple_sketch_int64_agg_union(sketch) -) from `$BQ_DATASET`.tuple_sketch; +select bqutil.datasketches.tuple_sketch_int64_to_string( + bqutil.datasketches.tuple_sketch_int64_agg_union(sketch) +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_theta( - `$BQ_DATASET`.tuple_sketch_int64_agg_union(sketch) -) from `$BQ_DATASET`.tuple_sketch; +select bqutil.datasketches.tuple_sketch_int64_get_theta( + bqutil.datasketches.tuple_sketch_int64_agg_union(sketch) +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_num_retained( - `$BQ_DATASET`.tuple_sketch_int64_agg_union(sketch) -) from `$BQ_DATASET`.tuple_sketch; +select bqutil.datasketches.tuple_sketch_int64_get_num_retained( + bqutil.datasketches.tuple_sketch_int64_agg_union(sketch) +) from tuple_sketch; -drop table `$BQ_DATASET`.tuple_sketch; +drop table tuple_sketch; # using full signatures -create or replace table `$BQ_DATASET`.tuple_sketch(sketch bytes); +create or replace temp table tuple_sketch(sketch bytes); -insert into `$BQ_DATASET`.tuple_sketch -(select `$BQ_DATASET`.tuple_sketch_int64_from_theta_sketch_seed( - `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(cast(value as string), STRUCT<BYTEINT, INT64, FLOAT64>(10, 111, 0.999)), +insert into tuple_sketch +(select bqutil.datasketches.tuple_sketch_int64_from_theta_sketch_seed( + bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(cast(value as string), STRUCT<BYTEINT, INT64, FLOAT64>(10, 111, 0.999)), 1, 111 ) from unnest(GENERATE_ARRAY(1, 10000, 1)) as value); -insert into `$BQ_DATASET`.tuple_sketch -(select `$BQ_DATASET`.tuple_sketch_int64_from_theta_sketch_seed( - `$BQ_DATASET`.theta_sketch_agg_string_lgk_seed_p(cast(value as string), STRUCT<BYTEINT, INT64, FLOAT64>(10, 111, 0.999)), +insert into tuple_sketch +(select bqutil.datasketches.tuple_sketch_int64_from_theta_sketch_seed( + bqutil.datasketches.theta_sketch_agg_string_lgk_seed_p(cast(value as string), STRUCT<BYTEINT, INT64, FLOAT64>(10, 111, 0.999)), 1, 111 ) from unnest(GENERATE_ARRAY(100000, 110000, 1)) as value); # expected about 20000 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), +select bqutil.datasketches.tuple_sketch_int64_get_estimate_seed( + bqutil.datasketches.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), 111 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_and_bounds_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), +select bqutil.datasketches.tuple_sketch_int64_get_estimate_and_bounds_seed( + bqutil.datasketches.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), 2, 111 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_sum_estimate_and_bounds_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), +select bqutil.datasketches.tuple_sketch_int64_get_sum_estimate_and_bounds_seed( + bqutil.datasketches.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), 2, 111 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; # expected estimate about 20000 -select `$BQ_DATASET`.tuple_sketch_int64_to_string_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), +select bqutil.datasketches.tuple_sketch_int64_to_string_seed( + bqutil.datasketches.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), 111 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_theta_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), +select bqutil.datasketches.tuple_sketch_int64_get_theta_seed( + bqutil.datasketches.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), 111 -) from `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; -select `$BQ_DATASET`.tuple_sketch_int64_get_num_retained_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), +select bqutil.datasketches.tuple_sketch_int64_get_num_retained_seed( + bqutil.datasketches.tuple_sketch_int64_agg_union_lgk_seed_mode(sketch, STRUCT<BYTEINT, INT64, STRING>(10, 111, "NOP")), 111 -) from `$BQ_DATASET`.tuple_sketch; - -drop table `$BQ_DATASET`.tuple_sketch; +) from tuple_sketch; +drop table tuple_sketch; # using defaults # expected 5 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate( - `$BQ_DATASET`.tuple_sketch_int64_union( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_int64(key, 1) from unnest([1, 2, 3]) as key), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_int64(key, 1) from unnest([3, 4, 5]) as key) +select bqutil.datasketches.tuple_sketch_int64_get_estimate( + bqutil.datasketches.tuple_sketch_int64_union( + (select bqutil.datasketches.tuple_sketch_int64_agg_int64(key, 1) from unnest([1, 2, 3]) as key), + (select bqutil.datasketches.tuple_sketch_int64_agg_int64(key, 1) from unnest([3, 4, 5]) as key) ) ); # using full signatures # expected 5 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( - `$BQ_DATASET`.tuple_sketch_int64_union_lgk_seed_mode( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_int64_lgk_seed_p_mode(key, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest([1, 2, 3]) as key), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_int64_lgk_seed_p_mode(key, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest([3, 4, 5]) as key), +select bqutil.datasketches.tuple_sketch_int64_get_estimate_seed( + bqutil.datasketches.tuple_sketch_int64_union_lgk_seed_mode( + (select bqutil.datasketches.tuple_sketch_int64_agg_int64_lgk_seed_p_mode(key, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest([1, 2, 3]) as key), + (select bqutil.datasketches.tuple_sketch_int64_agg_int64_lgk_seed_p_mode(key, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest([3, 4, 5]) as key), 10, 111, "MIN" @@ -188,19 +187,19 @@ select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( # using defaults # expected 1 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate( - `$BQ_DATASET`.tuple_sketch_int64_intersection( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string(str, 1) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string(str, 1) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.tuple_sketch_int64_get_estimate( + bqutil.datasketches.tuple_sketch_int64_intersection( + (select bqutil.datasketches.tuple_sketch_int64_agg_string(str, 1) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.tuple_sketch_int64_agg_string(str, 1) from unnest(["c", "d", "e"]) as str) ) ); # using full signatures # expected 1 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( - `$BQ_DATASET`.tuple_sketch_int64_intersection_seed_mode( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.tuple_sketch_int64_get_estimate_seed( + bqutil.datasketches.tuple_sketch_int64_intersection_seed_mode( + (select bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["c", "d", "e"]) as str), 111, "MIN" ), @@ -209,19 +208,19 @@ select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( # using defaults # expected 2 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate( - `$BQ_DATASET`.tuple_sketch_int64_a_not_b( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string(str, 1) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string(str, 1) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.tuple_sketch_int64_get_estimate( + bqutil.datasketches.tuple_sketch_int64_a_not_b( + (select bqutil.datasketches.tuple_sketch_int64_agg_string(str, 1) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.tuple_sketch_int64_agg_string(str, 1) from unnest(["c", "d", "e"]) as str) ) ); # using full signatures # expected 2 -select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( - `$BQ_DATASET`.tuple_sketch_int64_a_not_b_seed( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.tuple_sketch_int64_get_estimate_seed( + bqutil.datasketches.tuple_sketch_int64_a_not_b_seed( + (select bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "MIN")) from unnest(["c", "d", "e"]) as str), 111 ), 111 @@ -229,24 +228,24 @@ select `$BQ_DATASET`.tuple_sketch_int64_get_estimate_seed( # using defaults # expected 0.2 -select `$BQ_DATASET`.tuple_sketch_int64_jaccard_similarity( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string(str, 1) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string(str, 1) from unnest(["c", "d", "e"]) as str) +select bqutil.datasketches.tuple_sketch_int64_jaccard_similarity( + (select bqutil.datasketches.tuple_sketch_int64_agg_string(str, 1) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.tuple_sketch_int64_agg_string(str, 1) from unnest(["c", "d", "e"]) as str) ); # using full signatures # expected 0.2 -select `$BQ_DATASET`.tuple_sketch_int64_jaccard_similarity_seed( - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "NOP")) from unnest(["a", "b", "c"]) as str), - (select `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "NOP")) from unnest(["c", "d", "e"]) as str), +select bqutil.datasketches.tuple_sketch_int64_jaccard_similarity_seed( + (select bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "NOP")) from unnest(["a", "b", "c"]) as str), + (select bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(str, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "NOP")) from unnest(["c", "d", "e"]) as str), 111 ); # using defaults # expected 1 entry -select `$BQ_DATASET`.tuple_sketch_int64_to_string( - `$BQ_DATASET`.tuple_sketch_int64_filter_low_high( - `$BQ_DATASET`.tuple_sketch_int64_agg_string(key, 1), +select bqutil.datasketches.tuple_sketch_int64_to_string( + bqutil.datasketches.tuple_sketch_int64_filter_low_high( + bqutil.datasketches.tuple_sketch_int64_agg_string(key, 1), 2, 2 ) @@ -254,9 +253,9 @@ select `$BQ_DATASET`.tuple_sketch_int64_to_string( # using full signatures # expected 1 entry -select `$BQ_DATASET`.tuple_sketch_int64_to_string_seed( - `$BQ_DATASET`.tuple_sketch_int64_filter_low_high_seed( - `$BQ_DATASET`.tuple_sketch_int64_agg_string_lgk_seed_p_mode(key, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "SUM")), +select bqutil.datasketches.tuple_sketch_int64_to_string_seed( + bqutil.datasketches.tuple_sketch_int64_filter_low_high_seed( + bqutil.datasketches.tuple_sketch_int64_agg_string_lgk_seed_p_mode(key, 1, STRUCT<BYTEINT, INT64, FLOAT64, STRING>(10, 111, 0.999, "SUM")), 2, 2, 111 --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
