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.

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

Added standard deviation / variance sampling to extended stats #49782

Merged
merged 5 commits into from
Jun 10, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ GET /exams/_search

The above aggregation computes the grades statistics over all documents. The aggregation type is `extended_stats` and the `field` setting defines the numeric field of the documents the stats will be computed on. The above will return the following:

The `std_deviation` and `variance` are calculated as population metrics so they are always the same as `std_deviation_population` and `variance_population` respectively.

[source,console-result]
--------------------------------------------------
Expand All @@ -36,10 +37,18 @@ The above aggregation computes the grades statistics over all documents. The agg
"sum": 150.0,
"sum_of_squares": 12500.0,
"variance": 625.0,
"variance_population": 625.0,
"variance_sampling": 1250.0,
"std_deviation": 25.0,
"std_deviation_population": 25.0,
"std_deviation_sampling": 35.35533905932738,
"std_deviation_bounds": {
"upper": 125.0,
"lower": 25.0
"lower": 25.0,
"upper_population" : 125.0,
"lower_population" : 25.0,
"upper_sampling" : 145.71067811865476,
"lower_sampling" : 4.289321881345245
}
}
}
Expand Down Expand Up @@ -75,6 +84,9 @@ GET /exams/_search
`sigma` can be any non-negative double, meaning you can request non-integer values such as `1.5`. A value of `0` is valid, but will simply
return the average for both `upper` and `lower` bounds.

The `upper` and `lower` bounds are calculated as population metrics so they are always the same as `upper_population` and
`lower_population` respectively.

.Standard Deviation and Bounds require normality
[NOTE]
=====
Expand All @@ -93,9 +105,9 @@ GET /exams/_search
{
"size": 0,
"aggs" : {
"grades_stats" : {
"extended_stats" : {
"script" : {
"grades_stats" : {
"extended_stats" : {
"script" : {
"source" : "doc['grade'].value",
"lang" : "painless"
}
Expand All @@ -114,8 +126,8 @@ GET /exams/_search
{
"size": 0,
"aggs" : {
"grades_stats" : {
"extended_stats" : {
"grades_stats" : {
"extended_stats" : {
"script" : {
"id": "my_script",
"params": {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -113,10 +113,18 @@ And the following may be the response:
"sum": 985.0,
"sum_of_squares": 446725.0,
"variance": 41105.55555555556,
"variance_population": 41105.55555555556,
"variance_sampling": 61658.33333333334,
"std_deviation": 202.74505063146563,
"std_deviation_population": 202.74505063146563,
"std_deviation_sampling": 248.3109609609156,
"std_deviation_bounds": {
"upper": 733.8234345962646,
"lower": -77.15676792959795
"lower": -77.15676792959795,
"upper_population" : 733.8234345962646,
"lower_population" : -77.15676792959795,
"upper_sampling" : 824.9552552551645,
"lower_sampling" : -168.28858858849787
}
}
}
Expand Down

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
* 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
* 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
Expand All @@ -29,25 +29,55 @@ public interface ExtendedStats extends Stats {
double getSumOfSquares();

/**
* The variance of the collected values.
* The population variance of the collected values.
*/
double getVariance();

/**
* The standard deviation of the collected values.
* The population variance of the collected values.
*/
double getVariancePopulation();

/**
* The sampling variance of the collected values.
*/
double getVarianceSampling();

/**
* The population standard deviation of the collected values.
*/
double getStdDeviation();

/**
* The population standard deviation of the collected values.
*/
double getStdDeviationPopulation();

/**
* The sampling standard deviation of the collected values.
*/
double getStdDeviationSampling();

/**
* The upper or lower bounds of the stdDeviation
*/
double getStdDeviationBound(Bounds bound);

/**
* The standard deviation of the collected values as a String.
* The population standard deviation of the collected values as a String.
*/
String getStdDeviationAsString();

/**
* The population standard deviation of the collected values as a String.
*/
String getStdDeviationPopulationAsString();

/**
* The sampling standard deviation of the collected values as a String.
*/
String getStdDeviationSamplingAsString();

/**
* The upper or lower bounds of stdDev of the collected values as a String.
*/
Expand All @@ -60,13 +90,22 @@ public interface ExtendedStats extends Stats {
String getSumOfSquaresAsString();

/**
* The variance of the collected values as a String.
* The population variance of the collected values as a String.
*/
String getVarianceAsString();

/**
* The population variance of the collected values as a String.
*/
String getVariancePopulationAsString();

/**
* The sampling variance of the collected values as a String.
*/
String getVarianceSamplingAsString();

enum Bounds {
UPPER, LOWER
UPPER, LOWER, UPPER_POPULATION, LOWER_POPULATION, UPPER_SAMPLING, LOWER_SAMPLING
}

}
Original file line number Diff line number Diff line change
Expand Up @@ -162,7 +162,11 @@ public double metric(String name, long owningBucketOrd) {
case avg: return Double.NaN;
case sum_of_squares: return 0;
case variance: return Double.NaN;
case variance_population: return Double.NaN;
case variance_sampling: return Double.NaN;
case std_deviation: return Double.NaN;
case std_deviation_population: return Double.NaN;
case std_deviation_sampling: return Double.NaN;
case std_upper: return Double.NaN;
case std_lower: return Double.NaN;
default:
Expand All @@ -177,7 +181,11 @@ public double metric(String name, long owningBucketOrd) {
case avg: return sums.get(owningBucketOrd) / counts.get(owningBucketOrd);
case sum_of_squares: return sumOfSqrs.get(owningBucketOrd);
case variance: return variance(owningBucketOrd);
case variance_population: return variancePopulation(owningBucketOrd);
case variance_sampling: return varianceSampling(owningBucketOrd);
case std_deviation: return Math.sqrt(variance(owningBucketOrd));
case std_deviation_population: return Math.sqrt(variance(owningBucketOrd));
case std_deviation_sampling: return Math.sqrt(varianceSampling(owningBucketOrd));
case std_upper:
return (sums.get(owningBucketOrd) / counts.get(owningBucketOrd)) + (Math.sqrt(variance(owningBucketOrd)) * this.sigma);
case std_lower:
Expand All @@ -188,12 +196,23 @@ public double metric(String name, long owningBucketOrd) {
}

private double variance(long owningBucketOrd) {
return variancePopulation(owningBucketOrd);
}

private double variancePopulation(long owningBucketOrd) {
double sum = sums.get(owningBucketOrd);
long count = counts.get(owningBucketOrd);
double variance = (sumOfSqrs.get(owningBucketOrd) - ((sum * sum) / count)) / count;
return variance < 0 ? 0 : variance;
}

private double varianceSampling(long owningBucketOrd) {
double sum = sums.get(owningBucketOrd);
long count = counts.get(owningBucketOrd);
double variance = (sumOfSqrs.get(owningBucketOrd) - ((sum * sum) / count)) / (count - 1);
return variance < 0 ? 0 : variance;
}

@Override
public InternalAggregation buildAggregation(long bucket) {
if (valuesSource == null || bucket >= counts.size()) {
Expand Down
Loading