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

Jump to bottom

Histogram order fix #5746

Merged
merged 1 commit into from
Sep 30, 2024
Merged

Histogram order fix #5746

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
29 changes: 15 additions & 14 deletions runtime/queries/column_rug_histogram.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ func (q *ColumnRugHistogram) Resolve(ctx context.Context, rt *runtime.Runtime, i
}

sanitizedColumnName := safeName(q.ColumnName)
outlierPseudoBucketSize := 500
outlierPseudoBucketCount := 500
selectColumn := fmt.Sprintf("%s::DOUBLE", sanitizedColumnName)

rugSQL := fmt.Sprintf(
Expand All @@ -87,15 +87,15 @@ func (q *ColumnRugHistogram) Resolve(ctx context.Context, rt *runtime.Runtime, i
WHERE %[2]s IS NOT NULL
), buckets AS (
SELECT
`+rangeNumbersCol(olap.Dialect())+`::FLOAT as bucket,
(bucket) * (%[7]v) / %[4]v + (%[5]v) AS low,
(bucket + 1) * (%[7]v) / %[4]v + (%[5]v) AS high
FROM `+rangeNumbers(olap.Dialect())+`(0, %[4]v)
`+rangeNumbersCol(olap.Dialect())+`::FLOAT as bucket, -- range
(bucket) * (%[7]v) / %[4]v + (%[5]v) AS low, -- bucket * (max-min) / bucketCount + min
(bucket + 1) * (%[7]v) / %[4]v + (%[5]v) AS high -- (bucket+1) * (max-min) / bucketCount + min
FROM `+rangeNumbers(olap.Dialect())+`(0, %[4]v) -- range(0,bucketCount)
),
-- bin the values
binned_data AS (
SELECT
FLOOR((value - (%[5]v)) / (%[7]v) * %[4]v) as bucket
FLOOR((value - (%[5]v)) / (%[7]v) * %[4]v) as bucket -- floor((value - min) / (max-min) * bucketCount)
from values
),
-- join the bucket set with the binned values to generate the histogram
Expand All @@ -113,7 +113,7 @@ func (q *ColumnRugHistogram) Resolve(ctx context.Context, rt *runtime.Runtime, i
-- calculate the right edge, sine in histogram_stage we don't look at the values that
-- might be the largest.
right_edge AS (
SELECT count(*) as c from values WHERE value = (%[6]v)
SELECT count(*) as c from values WHERE value = (%[6]v) -- value = max
), histrogram_with_edge AS (
SELECT
bucket,
Expand All @@ -131,14 +131,15 @@ func (q *ColumnRugHistogram) Resolve(ctx context.Context, rt *runtime.Runtime, i
ifNull(count, 0)
FROM histrogram_with_edge
WHERE present=true
ORDER BY bucket
`,
selectColumn,
sanitizedColumnName,
olap.Dialect().EscapeTable(q.Database, q.DatabaseSchema, q.TableName),
outlierPseudoBucketSize,
*minVal,
*maxVal,
*rng,
selectColumn, // 1
sanitizedColumnName, // 2
olap.Dialect().EscapeTable(q.Database, q.DatabaseSchema, q.TableName), // 3
outlierPseudoBucketCount, // 4
*minVal, // 5
*maxVal, // 6
*rng, // 7
)

outlierResults, err := olap.Execute(ctx, &drivers.Statement{
Expand Down
Loading