Make each analysis report desired field mappings to be copied (elasti…

…c#50219)
przemekwitek · Dec 20, 2019 · d7f17c9 · d7f17c9
1 parent a383778
commit d7f17c9
Show file tree

Hide file tree

Showing 18 changed files with 439 additions and 248 deletions.
diff --git a/...core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/Classification.java b/...core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/Classification.java
@@ -248,6 +248,14 @@ public Map<String, Long> getFieldCardinalityLimits() {
         return Collections.singletonMap(dependentVariable, 2L);
     }
 
+    @Override
+    public Map<String, String> getExplicitlyMappedFields(String resultsFieldName) {
+        return new HashMap<>() {{
+            put(resultsFieldName + "." + predictionFieldName, dependentVariable);
+            put(resultsFieldName + ".top_classes.class_name", dependentVariable);
+        }};
+    }
+
     @Override
     public boolean supportsMissingValues() {
         return true;

diff --git a/...e/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/DataFrameAnalysis.java b/...e/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/DataFrameAnalysis.java
@@ -41,6 +41,17 @@ public interface DataFrameAnalysis extends ToXContentObject, NamedWriteable {
      */
     Map<String, Long> getFieldCardinalityLimits();
 
+    /**
+     * Returns fields for which the mappings should be copied from source index to destination index.
+     * Each entry of the returned {@link Map} is of the form:
+     *   key   - field path in the destination index
+     *   value - field path in the source index from which the mapping should be taken
+     *
+     * @param resultsFieldName name of the results field under which all the results are stored
+     * @return {@link Map} containing fields for which the mappings should be copied from source index to destination index
+     */
+    Map<String, String> getExplicitlyMappedFields(String resultsFieldName);
+
     /**
      * @return {@code true} if this analysis supports data frame rows with missing values
      */

diff --git a/...re/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/OutlierDetection.java b/...re/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/OutlierDetection.java
@@ -229,6 +229,11 @@ public Map<String, Long> getFieldCardinalityLimits() {
         return Collections.emptyMap();
     }
 
+    @Override
+    public Map<String, String> getExplicitlyMappedFields(String resultsFieldName) {
+        return Collections.emptyMap();
+    }
+
     @Override
     public boolean supportsMissingValues() {
         return false;

diff --git a/...gin/core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/Regression.java b/...gin/core/src/main/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/Regression.java
@@ -186,6 +186,11 @@ public Map<String, Long> getFieldCardinalityLimits() {
         return Collections.emptyMap();
     }
 
+    @Override
+    public Map<String, String> getExplicitlyMappedFields(String resultsFieldName) {
+        return Collections.singletonMap(resultsFieldName + "." + predictionFieldName, dependentVariable);
+    }
+
     @Override
     public boolean supportsMissingValues() {
         return true;

diff --git a/...src/test/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/ClassificationTests.java b/...src/test/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/ClassificationTests.java
@@ -25,7 +25,9 @@
 import java.util.Map;
 import java.util.Set;
 
+import static org.hamcrest.Matchers.anEmptyMap;
 import static org.hamcrest.Matchers.containsString;
+import static org.hamcrest.Matchers.empty;
 import static org.hamcrest.Matchers.equalTo;
 import static org.hamcrest.Matchers.hasEntry;
 import static org.hamcrest.Matchers.is;
@@ -161,8 +163,16 @@ public void testGetParams() {
                 hasEntry("prediction_field_type", "string")));
     }
 
-    public void testFieldCardinalityLimitsIsNonNull() {
-        assertThat(createTestInstance().getFieldCardinalityLimits(), is(not(nullValue())));
+    public void testRequiredFieldsIsNonEmpty() {
+        assertThat(createTestInstance().getRequiredFields(), is(not(empty())));
+    }
+
+    public void testFieldCardinalityLimitsIsNonEmpty() {
+        assertThat(createTestInstance().getFieldCardinalityLimits(), is(not(anEmptyMap())));
+    }
+
+    public void testFieldMappingsToCopyIsNonEmpty() {
+        assertThat(createTestInstance().getExplicitlyMappedFields(""), is(not(anEmptyMap())));
     }
 
     public void testToXContent_GivenVersionBeforeRandomizeSeedWasIntroduced() throws IOException {

diff --git a/...c/test/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/OutlierDetectionTests.java b/...c/test/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/OutlierDetectionTests.java
@@ -12,11 +12,11 @@
 import java.io.IOException;
 import java.util.Map;
 
+import static org.hamcrest.Matchers.anEmptyMap;
 import static org.hamcrest.Matchers.closeTo;
+import static org.hamcrest.Matchers.empty;
 import static org.hamcrest.Matchers.equalTo;
 import static org.hamcrest.Matchers.is;
-import static org.hamcrest.Matchers.not;
-import static org.hamcrest.Matchers.nullValue;
 
 public class OutlierDetectionTests extends AbstractSerializingTestCase<OutlierDetection> {
 
@@ -84,8 +84,16 @@ public void testGetParams_GivenExplicitValues() {
         assertThat(params.get(OutlierDetection.STANDARDIZATION_ENABLED.getPreferredName()), is(false));
     }
 
-    public void testFieldCardinalityLimitsIsNonNull() {
-        assertThat(createTestInstance().getFieldCardinalityLimits(), is(not(nullValue())));
+    public void testRequiredFieldsIsEmpty() {
+        assertThat(createTestInstance().getRequiredFields(), is(empty()));
+    }
+
+    public void testFieldCardinalityLimitsIsEmpty() {
+        assertThat(createTestInstance().getFieldCardinalityLimits(), is(anEmptyMap()));
+    }
+
+    public void testFieldMappingsToCopyIsEmpty() {
+        assertThat(createTestInstance().getExplicitlyMappedFields(""), is(anEmptyMap()));
     }
 
     public void testGetStateDocId() {

diff --git a/...ore/src/test/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/RegressionTests.java b/...ore/src/test/java/org/elasticsearch/xpack/core/ml/dataframe/analyses/RegressionTests.java
@@ -19,7 +19,9 @@
 import java.util.Collections;
 
 import static org.hamcrest.Matchers.allOf;
+import static org.hamcrest.Matchers.anEmptyMap;
 import static org.hamcrest.Matchers.containsString;
+import static org.hamcrest.Matchers.empty;
 import static org.hamcrest.Matchers.equalTo;
 import static org.hamcrest.Matchers.hasEntry;
 import static org.hamcrest.Matchers.is;
@@ -100,8 +102,16 @@ public void testGetParams() {
             allOf(hasEntry("dependent_variable", "foo"), hasEntry("prediction_field_name", "foo_prediction")));
     }
 
-    public void testFieldCardinalityLimitsIsNonNull() {
-        assertThat(createTestInstance().getFieldCardinalityLimits(), is(not(nullValue())));
+    public void testRequiredFieldsIsNonEmpty() {
+        assertThat(createTestInstance().getRequiredFields(), is(not(empty())));
+    }
+
+    public void testFieldCardinalityLimitsIsEmpty() {
+        assertThat(createTestInstance().getFieldCardinalityLimits(), is(anEmptyMap()));
+    }
+
+    public void testFieldMappingsToCopyIsNonEmpty() {
+        assertThat(createTestInstance().getExplicitlyMappedFields(""), is(not(anEmptyMap())));
     }
 
     public void testGetStateDocId() {