Skip to content

Read the summary statistics through their accessors #88

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

Merged
estebanzimanyi merged 1 commit into from
Oct 25, 2026
Merged

Read the summary statistics through their accessors #88

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
23 changes: 16 additions & 7 deletions src/test/java/org/mobilitydb/spark/AggregatesCatalogTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,9 +70,14 @@ static void stopSpark() {
}
}

/** The query's first row. */
private static org.apache.spark.sql.Row row(String sql) {
return spark.sql(sql).collectAsList().get(0);
}

/** The value of the query's first row. */
private static Object value(String sql) {
return spark.sql(sql).collectAsList().get(0).get(0);
return row(sql).get(0);
}

private static String answer(String sql) {
Expand Down Expand Up @@ -926,23 +931,27 @@ Stream<DynamicTest> theOverloadAnswersWhatMobilityDBAnswers() {

/** Each overload of summaryStatsAgg: its query over the two rasters of the raster cases
* of #OVERLOADS and the six fields of the summarystats record MobilityDB answers, count,
* sum, mean, standard deviation, minimum and maximum, read here in the order of the
* record, as no SQL function of the surface reads a field of it. */
* sum, mean, standard deviation, minimum and maximum, each read by its accessor,
* summarystatsCount to summarystatsMax; and those of summaryStats over the first. */
private static final Object[][] SUMMARIES = {
{"summaryStatsAgg(raster, BOOLEAN)",
"SELECT summaryStatsAgg(v, true) FROM (SELECT /*+ REPARTITION(2) */ rasterFromHexWKB(s) AS v FROM VALUES ('0100000200000000000000F03F000000000000F0BF0000000000000000000000000000084000000000000000000000000000000000110F0000030003004A003C1CC60000803F000000400000404000008040003C1CC60000C0400000E04000000041000010410600000A0014001E00280032003C00460050005A00'), ('0100000200000000000000F03F000000000000F0BF0000000000000840000000000000084000000000000000000000000000000000110F0000030003004A003C1CC60000803F000000400000404000008040003C1CC60000C0400000E04000000041000010410600000A0014001E00280032003C00460050005A00') AS t(s))",
"SELECT summarystatsCount(s), summarystatsSum(s), summarystatsMean(s), summarystatsStddev(s), summarystatsMin(s), summarystatsMax(s) FROM (SELECT summaryStatsAgg(v, true) AS s FROM (SELECT /*+ REPARTITION(2) */ rasterFromHexWKB(s) AS v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t(s)))",
new double[] {16, 80, 5, 2.7386127875258306, 1, 9}},
{"summaryStatsAgg(raster, INT, BOOLEAN)",
"SELECT summaryStatsAgg(v, 2, true) FROM (SELECT /*+ REPARTITION(2) */ rasterFromHexWKB(s) AS v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t(s))",
new double[] {18, 900, 50, 25.81988897471611, 10, 90}}};
"SELECT summarystatsCount(s), summarystatsSum(s), summarystatsMean(s), summarystatsStddev(s), summarystatsMin(s), summarystatsMax(s) FROM (SELECT summaryStatsAgg(v, 2, true) AS s FROM (SELECT /*+ REPARTITION(2) */ rasterFromHexWKB(s) AS v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t(s)))",
new double[] {18, 900, 50, 25.81988897471611, 10, 90}},
{"summaryStats(raster)",
"SELECT summarystatsCount(s), summarystatsSum(s), summarystatsMean(s), summarystatsStddev(s), summarystatsMin(s), summarystatsMax(s) FROM (SELECT summaryStats(rasterFromHexWKB('0100000200000000000000F03F000000000000F0BF0000000000000000000000000000084000000000000000000000000000000000110F0000030003004A003C1CC60000803F000000400000404000008040003C1CC60000C0400000E04000000041000010410600000A0014001E00280032003C00460050005A00')) AS s)",
new double[] {8, 40, 5, 2.7386127875258306, 1, 9}}};

@TestFactory
Stream<DynamicTest> theSummaryAnswersWhatMobilityDBAnswers() {
return Stream.of(SUMMARIES)
.map(c -> DynamicTest.dynamicTest((String) c[0], () -> {
double[] expected = (double[]) c[2];
org.apache.spark.sql.Row got = row((String) c[1]);
for (int i = 0; i < expected.length; i++) {
assertEquals(expected[i], ((Number) ((org.apache.spark.sql.Row) value((String) c[1])).get(i)).doubleValue(), "field " + i);
assertEquals(expected[i], ((Number) got.get(i)).doubleValue(), "field " + i);
}
}));
}
Expand Down
Loading