liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-10 22:56:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Better account for equal distances [skip ci]

Browse Source
This commit is contained in:
Andrew Kane
2024-04-11 21:34:46 -07:00
parent 70eee06e83
commit 5510ae5b8c
1 changed files with 27 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
test/t/032_ivfflat_halfvec_build_recall.pl
View File

@@ -32,18 +32,19 @@ sub test_recall
SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit; SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
)); ));
my @actual_ids = split("\n", $actual); my @actual_ids = split("\n", $actual);
my %actual_set = map { $_ => 1 } @actual_ids;
my @expected_ids = split("\n", $expected[$i]); my @expected_ids = split("\n", $expected[$i]);
my %expected_set = map { $_ => 1 } @expected_ids;
foreach (@expected_ids) foreach (@actual_ids)
{ {
if (exists($actual_set{$_})) if (exists($expected_set{$_}))
{ {
$correct++; $correct++;
} }
$total++;
} }
$total += $limit;
} }
cmp_ok($correct / $total, ">=", $min, $operator); cmp_ok($correct / $total, ">=", $min, $operator);
@@ -85,7 +86,12 @@ for my $i (0 .. $#operators)
@expected = (); @expected = ();
foreach (@queries) foreach (@queries)
{ {
my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;"); my $res = $node->safe_psql("postgres", qq(
WITH top AS (
SELECT v $operator '$_' AS distance FROM tst ORDER BY distance LIMIT $limit
)
SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
));
push(@expected, $res); push(@expected, $res);
} }
@@ -102,8 +108,14 @@ for my $i (0 .. $#operators)
test_recall(1, 0.35, $operator); test_recall(1, 0.35, $operator);
test_recall(10, 0.95, $operator); test_recall(10, 0.95, $operator);
} }
# Account for equal distances if ($operator eq "<=>")
test_recall(100, 0.985, $operator); {
test_recall(100, 0.985, $operator);
}
else
{
test_recall(100, 1.00, $operator);
}
$node->safe_psql("postgres", "DROP INDEX idx;"); $node->safe_psql("postgres", "DROP INDEX idx;");
@@ -123,8 +135,14 @@ for my $i (0 .. $#operators)
test_recall(1, 0.35, $operator); test_recall(1, 0.35, $operator);
test_recall(10, 0.95, $operator); test_recall(10, 0.95, $operator);
} }
# Account for equal distances if ($operator eq "<=>")
test_recall(100, 0.985, $operator); {
test_recall(100, 0.985, $operator);
}
else
{
test_recall(100, 1.00, $operator);
}
$node->safe_psql("postgres", "DROP INDEX idx;"); $node->safe_psql("postgres", "DROP INDEX idx;");
} }