Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Sort out testcases in aggregate.slt #14301

Closed
wants to merge 3 commits into from
Closed

Sort out testcases in aggregate.slt #14301

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
af04147
refactor aggregate
logan-keede Jan 25, 2025
9caf659
remove falsely generated code
logan-keede Jan 25, 2025
87205fd
fix: repetition and mislocation
logan-keede Jan 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6,205 changes: 0 additions & 6,205 deletions datafusion/sqllogictest/test_files/aggregate.slt
View file
Open in desktop

This file was deleted.

3,053 changes: 3,053 additions & 0 deletions datafusion/sqllogictest/test_files/aggregate/aggregate.slt
View file
Open in desktop

Large diffs are not rendered by default.

361 changes: 361 additions & 0 deletions datafusion/sqllogictest/test_files/aggregate/approx_percentile_cont.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,361 @@
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at

# http://www.apache.org/licenses/LICENSE-2.0

# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.

include ./init.slt.part

#######
# Error tests
#######

# https://github.com/apache/datafusion/issues/3353
statement error DataFusion error: Schema error: Schema contains duplicate unqualified field name "approx_distinct\(aggregate_test_100\.c9\)"
SELECT approx_distinct(c9) count_c9, approx_distinct(cast(c9 as varchar)) count_c9_str FROM aggregate_test_100

# csv_query_approx_percentile_cont_with_weight
statement error DataFusion error: Error during planning: Failed to coerce arguments to satisfy a call to approx_percentile_cont_with_weight function: coercion from \[Utf8, Int8, Float64\] to the signature OneOf(.*) failed(.|\n)*
SELECT approx_percentile_cont_with_weight(c1, c2, 0.95) FROM aggregate_test_100

statement error DataFusion error: Error during planning: Failed to coerce arguments to satisfy a call to approx_percentile_cont_with_weight function: coercion from \[Int16, Utf8, Float64\] to the signature OneOf(.*) failed(.|\n)*
SELECT approx_percentile_cont_with_weight(c3, c1, 0.95) FROM aggregate_test_100

statement error DataFusion error: Error during planning: Failed to coerce arguments to satisfy a call to approx_percentile_cont_with_weight function: coercion from \[Int16, Int8, Utf8\] to the signature OneOf(.*) failed(.|\n)*
SELECT approx_percentile_cont_with_weight(c3, c2, c1) FROM aggregate_test_100

# csv_query_approx_percentile_cont_with_histogram_bins
statement error DataFusion error: External error: This feature is not implemented: Tdigest max_size value for 'APPROX_PERCENTILE_CONT' must be UInt > 0 literal \(got data type Int64\)\.
SELECT c1, approx_percentile_cont(c3, 0.95, -1000) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1

statement error DataFusion error: Error during planning: Failed to coerce arguments to satisfy a call to approx_percentile_cont function: coercion from \[Int16, Float64, Utf8\] to the signature OneOf(.*) failed(.|\n)*
SELECT approx_percentile_cont(c3, 0.95, c1) FROM aggregate_test_100

statement error DataFusion error: Error during planning: Failed to coerce arguments to satisfy a call to approx_percentile_cont function: coercion from \[Int16, Float64, Float64\] to the signature OneOf(.*) failed(.|\n)*
SELECT approx_percentile_cont(c3, 0.95, 111.1) FROM aggregate_test_100

statement error DataFusion error: Error during planning: Failed to coerce arguments to satisfy a call to approx_percentile_cont function: coercion from \[Float64, Float64, Float64\] to the signature OneOf(.*) failed(.|\n)*
SELECT approx_percentile_cont(c12, 0.95, 111.1) FROM aggregate_test_100

statement error DataFusion error: This feature is not implemented: Percentile value for 'APPROX_PERCENTILE_CONT' must be a literal
SELECT approx_percentile_cont(c12, c12) FROM aggregate_test_100

statement error DataFusion error: This feature is not implemented: Tdigest max_size value for 'APPROX_PERCENTILE_CONT' must be a literal
SELECT approx_percentile_cont(c12, 0.95, c5) FROM aggregate_test_100

# Not supported over sliding windows
query error This feature is not implemented: Aggregate can not be used as a sliding accumulator because `retract_batch` is not implemented
SELECT approx_percentile_cont(c3, 0.5) OVER (ROWS BETWEEN 4 PRECEDING AND CURRENT ROW)
FROM aggregate_test_100

## This test executes the APPROX_PERCENTILE_CONT aggregation against the test
## data, asserting the estimated quantiles are ±5% their actual values.
##
## Actual quantiles calculated with:
##
## ```r
## read_csv("./testing/data/csv/aggregate_test_100.csv") |>
## select_if(is.numeric) |>
## summarise_all(~ quantile(., c(0.1, 0.5, 0.9)))
## ```
##
## Giving:
##
## ```text
## c2 c3 c4 c5 c6 c7 c8 c9 c10 c11 c12
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 -95.3 -22925. -1882606710 -7.25e18 18.9 2671. 472608672. 1.83e18 0.109 0.0714
## 2 3 15.5 4599 377164262 1.13e18 134. 30634 2365817608. 9.30e18 0.491 0.551
## 3 5 102. 25334. 1991374996. 7.37e18 231 57518. 3776538487. 1.61e19 0.834 0.946
## ```
##
## Column `c12` is omitted due to a large relative error (~10%) due to the small
## float values.

#csv_query_approx_percentile_cont (c2)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c2, 0.1) AS DOUBLE) / 1.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c2, 0.5) AS DOUBLE) / 3.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c2, 0.9) AS DOUBLE) / 5.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c3)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c3, 0.1) AS DOUBLE) / -95.3) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c3, 0.5) AS DOUBLE) / 15.5) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c3, 0.9) AS DOUBLE) / 102.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c4)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c4, 0.1) AS DOUBLE) / -22925.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c4, 0.5) AS DOUBLE) / 4599.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c4, 0.9) AS DOUBLE) / 25334.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c5)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c5, 0.1) AS DOUBLE) / -1882606710.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c5, 0.5) AS DOUBLE) / 377164262.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c5, 0.9) AS DOUBLE) / 1991374996.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c6)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c6, 0.1) AS DOUBLE) / -7250000000000000000) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c6, 0.5) AS DOUBLE) / 1130000000000000000) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c6, 0.9) AS DOUBLE) / 7370000000000000000) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c7)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c7, 0.1) AS DOUBLE) / 18.9) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c7, 0.5) AS DOUBLE) / 134.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c7, 0.9) AS DOUBLE) / 231.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c8)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c8, 0.1) AS DOUBLE) / 2671.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c8, 0.5) AS DOUBLE) / 30634.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c8, 0.9) AS DOUBLE) / 57518.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c9)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c9, 0.1) AS DOUBLE) / 472608672.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c9, 0.5) AS DOUBLE) / 2365817608.0) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c9, 0.9) AS DOUBLE) / 3776538487.0) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c10)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c10, 0.1) AS DOUBLE) / 1830000000000000000) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c10, 0.5) AS DOUBLE) / 9300000000000000000) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c10, 0.9) AS DOUBLE) / 16100000000000000000) < 0.05) AS q FROM aggregate_test_100
----
true

# csv_query_approx_percentile_cont (c11)
query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c11, 0.1) AS DOUBLE) / 0.109) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c11, 0.5) AS DOUBLE) / 0.491) < 0.05) AS q FROM aggregate_test_100
----
true

query B
SELECT (ABS(1 - CAST(approx_percentile_cont(c11, 0.9) AS DOUBLE) / 0.834) < 0.05) AS q FROM aggregate_test_100
----
true

# percentile_cont_with_nulls
query I
SELECT APPROX_PERCENTILE_CONT(v, 0.5) FROM (VALUES (1), (2), (3), (NULL), (NULL), (NULL)) as t (v);
----
2

# percentile_cont_with_nulls_only
query I
SELECT APPROX_PERCENTILE_CONT(v, 0.5) FROM (VALUES (CAST(NULL as INT))) as t (v);
----
NULL

#
# percentile_cont edge cases
#

statement ok
CREATE TABLE tmp_percentile_cont(v1 INT, v2 DOUBLE);

statement ok
INSERT INTO tmp_percentile_cont VALUES (1, 'NaN'::Double), (2, 'NaN'::Double), (3, 'NaN'::Double);

# ISSUE: https://github.com/apache/datafusion/issues/11871
# Note `approx_median()` is using the same implementation as `approx_percentile_cont()`
query R
select APPROX_MEDIAN(v2) from tmp_percentile_cont WHERE v1 = 1;
----
NaN

# ISSUE: https://github.com/apache/datafusion/issues/11870
query R
select APPROX_PERCENTILE_CONT(v2, 0.8) from tmp_percentile_cont;
----
NaN

# ISSUE: https://github.com/apache/datafusion/issues/11869
# Note: `approx_percentile_cont_with_weight()` uses the same implementation as `approx_percentile_cont()`
query R
SELECT APPROX_PERCENTILE_CONT_WITH_WEIGHT(
v2,
'+Inf'::Double,
0.9
)
FROM tmp_percentile_cont;
----
NaN

statement ok
DROP TABLE tmp_percentile_cont;

# Test for issue where approx_percentile_cont_with_weight

statement ok
CREATE TABLE t1(v1 BOOL);

statement ok
INSERT INTO t1 VALUES (TRUE);

# ISSUE: https://github.com/apache/datafusion/issues/12716
# This test verifies that approx_percentile_cont_with_weight does not panic when given 'NaN' and returns 'inf'
query R
SELECT approx_percentile_cont_with_weight('NaN'::DOUBLE, 0, 0) FROM t1 WHERE t1.v1;
----
Infinity

statement ok
DROP TABLE t1;

# csv_query_approx_percentile_cont_with_weight
query TI
SELECT c1, approx_percentile_cont(c3, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
----
a 73
b 68
c 122
d 124
e 115

# csv_query_approx_percentile_cont_with_weight (2)
query TI
SELECT c1, approx_percentile_cont_with_weight(c3, 1, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
----
a 73
b 68
c 122
d 124
e 115

# csv_query_approx_percentile_cont_with_histogram_bins
query TI
SELECT c1, approx_percentile_cont(c3, 0.95, 200) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
----
a 73
b 68
c 122
d 124
e 115

query TI
SELECT c1, approx_percentile_cont_with_weight(c3, c2, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
----
a 74
b 68
c 123
d 124
e 115

# test_approx_percentile_cont_decimal_support
query TI
SELECT c1, approx_percentile_cont(c2, cast(0.85 as decimal(10,2))) apc FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
----
a 4
b 5
c 4
d 4
e 4
Loading
Loading