honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[7.x][ML] Adjust DF Analytics process phases (#56107) (#56177) 

As of elastic/ml-cpp#1179, the analytics process reports phases
depending on the analysis type. This commit adjusts the phases
of current analyses from `analyzing` to the following:

 - outlier_detection: [`computing_outlier`]
 - regression/classification: [`feature_selection`, `coarse_parameter_search`, `fine_tuning_parameters`, `final_training`]

Backport of #56107
This commit is contained in:
Dimitris Athanasiou 2020-05-05 15:00:07 +03:00 committed by GitHub
parent 75dadb7a6d
commit 2d7899c83c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 29 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
client/rest-high-level/src/test/java/org/elasticsearch/client/MachineLearningIT.java
View File

@ -1564,7 +1564,7 @@ public class MachineLearningIT extends ESRestHighLevelClientTestCase {
assertThat(progress.size(), equalTo(4));
assertThat(progress.get(0), equalTo(new PhaseProgress("reindexing", 0)));
assertThat(progress.get(1), equalTo(new PhaseProgress("loading_data", 0)));
assertThat(progress.get(2), equalTo(new PhaseProgress("analyzing", 0)));
assertThat(progress.get(2), equalTo(new PhaseProgress("computing_outliers", 0)));
assertThat(progress.get(3), equalTo(new PhaseProgress("writing_results", 0)));
assertThat(stats.getMemoryUsage().getPeakUsageBytes(), equalTo(0L));
assertThat(stats.getDataCounts(), equalTo(new DataCounts(0, 0, 0)));

12
x-pack/plugin/core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/Classification.java
View File

@ -20,6 +20,7 @@ import org.elasticsearch.xpack.core.ml.inference.trainedmodel.PredictionFieldTyp
import org.elasticsearch.xpack.core.ml.utils.ExceptionsHelper;
import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
@ -106,6 +107,15 @@ public class Classification implements DataFrameAnalysis {
*/
private static final int DEFAULT_NUM_TOP_CLASSES = 2;
private static final List<String> PROGRESS_PHASES = Collections.unmodifiableList(
Arrays.asList(
"feature_selection",
"coarse_parameter_search",
"fine_tuning_parameters",
"final_training"
)
);
private final String dependentVariable;
private final BoostedTreeParams boostedTreeParams;
private final String predictionFieldName;
@ -350,7 +360,7 @@ public class Classification implements DataFrameAnalysis {
@Override
public List<String> getProgressPhases() {
return Collections.singletonList("analyzing");
return PROGRESS_PHASES;
}
public static String extractJobIdFromStateDoc(String stateDocId) {

4
x-pack/plugin/core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/OutlierDetection.java
View File

@ -58,6 +58,8 @@ public class OutlierDetection implements DataFrameAnalysis {
return ignoreUnknownFields ? LENIENT_PARSER.apply(parser, null).build() : STRICT_PARSER.apply(parser, null).build();
}
private static final List<String> PROGRESS_PHASES = Collections.singletonList("computing_outliers");
/**
* The number of neighbors. Leave unspecified for dynamic detection.
*/
@ -251,7 +253,7 @@ public class OutlierDetection implements DataFrameAnalysis {
@Override
public List<String> getProgressPhases() {
return Collections.singletonList("analyzing");
return PROGRESS_PHASES;
}
public enum Method {

12
x-pack/plugin/core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/Regression.java
View File

@ -19,6 +19,7 @@ import org.elasticsearch.index.mapper.NumberFieldMapper;
import org.elasticsearch.xpack.core.ml.utils.ExceptionsHelper;
import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
@ -77,6 +78,15 @@ public class Regression implements DataFrameAnalysis {
return ignoreUnknownFields ? LENIENT_PARSER.apply(parser, null) : STRICT_PARSER.apply(parser, null);
}
private static final List<String> PROGRESS_PHASES = Collections.unmodifiableList(
Arrays.asList(
"feature_selection",
"coarse_parameter_search",
"fine_tuning_parameters",
"final_training"
)
);
private final String dependentVariable;
private final BoostedTreeParams boostedTreeParams;
private final String predictionFieldName;
@ -266,7 +276,7 @@ public class Regression implements DataFrameAnalysis {
@Override
public List<String> getProgressPhases() {
return Collections.singletonList("analyzing");
return PROGRESS_PHASES;
}
public static String extractJobIdFromStateDoc(String stateDocId) {

6
x-pack/plugin/src/test/resources/rest-api-spec/test/ml/data_frame_analytics_cat_apis.yml
View File

@ -81,6 +81,6 @@ setup:
- match:
$body: |
/^ id \s+ t \s+ s \s+ p \s+ source_index \s+ dest_index \n
(dfa\-classification\-job \s+ classification \s+ stopped \s+ reindexing:0,loading_data:0,analyzing:0,writing_results:0 \s+ index-source \s+ index-dest-c \n)+
(dfa\-outlier\-detection\-job \s+ outlier_detection \s+ stopped \s+ reindexing:0,loading_data:0,analyzing:0,writing_results:0 \s+ index-source \s+ index-dest-od \n)+
(dfa\-regression\-job \s+ regression \s+ stopped \s+ reindexing:0,loading_data:0,analyzing:0,writing_results:0 \s+ index-source \s+ index-dest-r \n)+ $/
(dfa\-classification\-job \s+ classification \s+ stopped \s+ reindexing:0,loading_data:0,feature_selection:0,coarse_parameter_search:0,fine_tuning_parameters:0,final_training:0,writing_results:0 \s+ index-source \s+ index-dest-c \n)+
(dfa\-outlier\-detection\-job \s+ outlier_detection \s+ stopped \s+ reindexing:0,loading_data:0,computing_outliers:0,writing_results:0 \s+ index-source \s+ index-dest-od \n)+
(dfa\-regression\-job \s+ regression \s+ stopped \s+ reindexing:0,loading_data:0,feature_selection:0,coarse_parameter_search:0,fine_tuning_parameters:0,final_training:0,writing_results:0 \s+ index-source \s+ index-dest-r \n)+ $/