HLRC: Add ML Get Buckets API #33056
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,214 @@ | ||
| /* | ||
| * Licensed to Elasticsearch under one or more contributor | ||
| * license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright | ||
| * ownership. Elasticsearch 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. | ||
| */ | ||
| package org.elasticsearch.client; | ||
|
|
||
| import org.elasticsearch.action.bulk.BulkRequest; | ||
| import org.elasticsearch.action.index.IndexRequest; | ||
| import org.elasticsearch.action.support.WriteRequest; | ||
| import org.elasticsearch.common.xcontent.XContentType; | ||
| import org.elasticsearch.protocol.xpack.ml.GetBucketsRequest; | ||
| import org.elasticsearch.protocol.xpack.ml.GetBucketsResponse; | ||
| import org.elasticsearch.protocol.xpack.ml.PutJobRequest; | ||
| import org.elasticsearch.protocol.xpack.ml.job.config.Job; | ||
| import org.elasticsearch.protocol.xpack.ml.job.results.Bucket; | ||
| import org.elasticsearch.protocol.xpack.ml.job.util.PageParams; | ||
| import org.junit.After; | ||
| import org.junit.Before; | ||
|
|
||
| import java.io.IOException; | ||
|
|
||
| import static org.hamcrest.Matchers.equalTo; | ||
| import static org.hamcrest.Matchers.is; | ||
| import static org.hamcrest.Matchers.lessThanOrEqualTo; | ||
|
|
||
| public class MachineLearningGetResultsIT extends ESRestHighLevelClientTestCase { | ||
|
|
||
| private static final String RESULTS_INDEX = ".ml-anomalies-shared"; | ||
| private static final String DOC = "doc"; | ||
|
|
||
| private static final String JOB_ID = "get-results-it-job"; | ||
|
|
||
| private BucketStats bucketStats = new BucketStats(); | ||
|
|
||
| @Before | ||
| public void createJobAndIndexResults() throws IOException { | ||
| MachineLearningClient machineLearningClient = highLevelClient().machineLearning(); | ||
| Job job = MachineLearningIT.buildJob(JOB_ID); | ||
| machineLearningClient.putJob(new PutJobRequest(job), RequestOptions.DEFAULT); | ||
|
|
||
| BulkRequest bulkRequest = new BulkRequest(); | ||
| bulkRequest.setRefreshPolicy(WriteRequest.RefreshPolicy.IMMEDIATE); | ||
|
|
||
| long time = 1533081600000L; // 2018-08-01T00:00:00Z | ||
| long endTime = time + 3600000L * 24 * 10; // 10 days of hourly buckets | ||
| while (time < endTime) { | ||
| addBucketIndexRequest(time, false, bulkRequest); | ||
| addRecordIndexRequests(time, false, bulkRequest); | ||
| time += 3600000L; | ||
| } | ||
|
|
||
| // Also index an interim bucket | ||
| addBucketIndexRequest(time, true, bulkRequest); | ||
| addRecordIndexRequests(time, true, bulkRequest); | ||
|
|
||
| highLevelClient().bulk(bulkRequest, RequestOptions.DEFAULT); | ||
| } | ||
|
|
||
| private void addBucketIndexRequest(long timestamp, boolean isInterim, BulkRequest bulkRequest) { | ||
| IndexRequest indexRequest = new IndexRequest(RESULTS_INDEX, DOC); | ||
| double bucketScore = randomDoubleBetween(0.0, 100.0, true); | ||
| bucketStats.report(bucketScore); | ||
| indexRequest.source("{\"job_id\":\"" + JOB_ID + "\", \"result_type\":\"bucket\", \"timestamp\": " + timestamp + "," + | ||
|
There was a problem hiding this comment. Any reason why you prefer to build the string representation rather than constructing a Bucket object converting it to a ByteReference and use the overload of There was a problem hiding this comment. The constructor and setter methods of |
||
| "\"bucket_span\": 3600,\"is_interim\": " + isInterim + ", \"anomaly_score\": " + bucketScore + | ||
| ", \"bucket_influencers\":[{\"job_id\": \"" + JOB_ID + "\", \"result_type\":\"bucket_influencer\", " + | ||
| "\"influencer_field_name\": \"bucket_time\", \"timestamp\": " + timestamp + ", \"bucket_span\": 3600, " + | ||
| "\"is_interim\": " + isInterim + "}]}", XContentType.JSON); | ||
| bulkRequest.add(indexRequest); | ||
| } | ||
|
|
||
| private void addRecordIndexRequests(long timestamp, boolean isInterim, BulkRequest bulkRequest) { | ||
| if (randomBoolean()) { | ||
| return; | ||
| } | ||
| int recordCount = randomIntBetween(1, 3); | ||
| for (int i = 0; i < recordCount; ++i) { | ||
| IndexRequest indexRequest = new IndexRequest(RESULTS_INDEX, DOC); | ||
| double recordScore = randomDoubleBetween(0.0, 100.0, true); | ||
| double p = randomDoubleBetween(0.0, 0.05, false); | ||
| indexRequest.source("{\"job_id\":\"" + JOB_ID + "\", \"result_type\":\"record\", \"timestamp\": " + timestamp + "," + | ||
| "\"bucket_span\": 3600,\"is_interim\": " + isInterim + ", \"record_score\": " + recordScore + ", \"probability\": " | ||
| + p + "}", XContentType.JSON); | ||
| bulkRequest.add(indexRequest); | ||
| } | ||
| } | ||
|
|
||
| @After | ||
| public void deleteJob() throws IOException { | ||
| new MlRestTestStateCleaner(logger, client()).clearMlMetadata(); | ||
| } | ||
|
|
||
| public void testGetBuckets() throws IOException { | ||
| MachineLearningClient machineLearningClient = highLevelClient().machineLearning(); | ||
|
|
||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.count(), equalTo(241L)); | ||
| assertThat(response.buckets().size(), equalTo(100)); | ||
| assertThat(response.buckets().get(0).getTimestamp().getTime(), equalTo(1533081600000L)); | ||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| request.setTimestamp("1533081600000"); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.count(), equalTo(1L)); | ||
| assertThat(response.buckets().size(), equalTo(1)); | ||
| assertThat(response.buckets().get(0).getTimestamp().getTime(), equalTo(1533081600000L)); | ||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| request.setAnomalyScore(75.0); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.count(), equalTo(bucketStats.criticalCount)); | ||
| assertThat(response.buckets().size(), equalTo((int) Math.min(100, bucketStats.criticalCount))); | ||
| assertThat(response.buckets().stream().anyMatch(b -> b.getAnomalyScore() < 75.0), is(false)); | ||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| request.setExcludeInterim(true); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.count(), equalTo(240L)); | ||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| request.setStart("1533081600000"); | ||
| request.setEnd("1533092400000"); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.count(), equalTo(3L)); | ||
| assertThat(response.buckets().get(0).getTimestamp().getTime(), equalTo(1533081600000L)); | ||
|
There was a problem hiding this comment. Nit: extract 1533081600000L to a constant FIRST_BUCKET_TIME as the literal is used several times |
||
| assertThat(response.buckets().get(1).getTimestamp().getTime(), equalTo(1533081600000L + 3600000L)); | ||
| assertThat(response.buckets().get(2).getTimestamp().getTime(), equalTo(1533081600000L + 2 * + 3600000L)); | ||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| request.setPageParams(new PageParams(3, 3)); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.buckets().size(), equalTo(3)); | ||
| assertThat(response.buckets().get(0).getTimestamp().getTime(), equalTo(1533081600000L + 3 * 3600000L)); | ||
| assertThat(response.buckets().get(1).getTimestamp().getTime(), equalTo(1533081600000L + 4 * 3600000L)); | ||
| assertThat(response.buckets().get(2).getTimestamp().getTime(), equalTo(1533081600000L + 5 * + 3600000L)); | ||
|
There was a problem hiding this comment. nit: extra plus in |
||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| request.setSort("anomaly_score"); | ||
| request.setDescending(true); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| double previousScore = 100.0; | ||
| for (Bucket bucket : response.buckets()) { | ||
| assertThat(bucket.getAnomalyScore(), lessThanOrEqualTo(previousScore)); | ||
| previousScore = bucket.getAnomalyScore(); | ||
| } | ||
| } | ||
| { | ||
| GetBucketsRequest request = new GetBucketsRequest(JOB_ID); | ||
| // Make sure we get all buckets | ||
| request.setPageParams(new PageParams(0, 10000)); | ||
| request.setExpand(true); | ||
|
|
||
| GetBucketsResponse response = execute(request, machineLearningClient::getBuckets, machineLearningClient::getBucketsAsync); | ||
|
|
||
| assertThat(response.buckets().stream().anyMatch(b -> b.getRecords().size() > 0), is(true)); | ||
| } | ||
| } | ||
|
|
||
| private static class BucketStats { | ||
| // score < 50.0 | ||
| private long minorCount; | ||
|
|
||
| // score < 75.0 | ||
| private long majorCount; | ||
|
|
||
| // score > 75.0 | ||
| private long criticalCount; | ||
|
|
||
| private void report(double anomalyScore) { | ||
| if (anomalyScore < 50.0) { | ||
| minorCount++; | ||
| } else if (anomalyScore < 75.0) { | ||
| majorCount++; | ||
| } else { | ||
| criticalCount++; | ||
| } | ||
| } | ||
| } | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: capitalise 'The'. Same in the comment for
getBucketsAsyncThere was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actually reviewing further down the lower case start of the parameter description is more consistent. If that is the preferred style change 'Additional' on the line below and in the async version comments
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
it's just vastly inconsistent :-(
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I like capitalized as it separates better from the param name. I'll capitalize and cross my fingers.