[ML] Data Frame Analytics: Fix race condition and support for feature…

… influence legacy format. (#81123) - Fixes a race condition where searches for data grid results with different parameters would return in different order with the wrong results on display. Fix uses a pattern to cancel useEffect callback for getIndexData(). - Fixes identifying pre 7.10 feature influence format for outlier detection and will display a callout on the results page with information for a workaround. - To fix identifying the legacy format, some cleanup of other code relating to the old format had to be done. The ml results object field is no longer treated as a "special" field for outlier detection and is treated and retrieved in the same way as other fields. - Adds an error callout if no Kibana index pattern is available for source/dest index.
elastic · Oct 21, 2020 · 4ba2fdb · 4ba2fdb
1 parent b362ed1
commit 4ba2fdb
Show file tree

Hide file tree

Showing 11 changed files with 151 additions and 74 deletions.
diff --git a/x-pack/plugins/ml/common/types/data_frame_analytics.ts b/x-pack/plugins/ml/common/types/data_frame_analytics.ts
@@ -19,7 +19,9 @@ export type DataFrameAnalyticsId = string;
 export interface OutlierAnalysis {
   [key: string]: {};
 
-  outlier_detection: {};
+  outlier_detection: {
+    compute_feature_influence?: boolean;
+  };
 }
 
 interface Regression {

diff --git a/x-pack/plugins/ml/common/util/analytics_utils.ts b/x-pack/plugins/ml/common/util/analytics_utils.ts
@@ -13,16 +13,19 @@ import {
 import { ANALYSIS_CONFIG_TYPE } from '../../common/constants/data_frame_analytics';
 
 export const isOutlierAnalysis = (arg: any): arg is OutlierAnalysis => {
+  if (typeof arg !== 'object' || arg === null) return false;
   const keys = Object.keys(arg);
   return keys.length === 1 && keys[0] === ANALYSIS_CONFIG_TYPE.OUTLIER_DETECTION;
 };
 
 export const isRegressionAnalysis = (arg: any): arg is RegressionAnalysis => {
+  if (typeof arg !== 'object' || arg === null) return false;
   const keys = Object.keys(arg);
   return keys.length === 1 && keys[0] === ANALYSIS_CONFIG_TYPE.REGRESSION;
 };
 
 export const isClassificationAnalysis = (arg: any): arg is ClassificationAnalysis => {
+  if (typeof arg !== 'object' || arg === null) return false;
   const keys = Object.keys(arg);
   return keys.length === 1 && keys[0] === ANALYSIS_CONFIG_TYPE.CLASSIFICATION;
 };

diff --git a/x-pack/plugins/ml/public/application/components/data_grid/common.ts b/x-pack/plugins/ml/public/application/components/data_grid/common.ts
@@ -33,7 +33,6 @@ import {
 
 import {
   FEATURE_IMPORTANCE,
-  FEATURE_INFLUENCE,
   OUTLIER_SCORE,
   TOP_CLASSES,
 } from '../../data_frame_analytics/common/constants';
@@ -112,10 +111,7 @@ export const getDataGridSchemasFromFieldTypes = (fieldTypes: FieldTypes, results
         schema = NON_AGGREGATABLE;
     }
 
-    if (
-      field === `${resultsField}.${OUTLIER_SCORE}` ||
-      field.includes(`${resultsField}.${FEATURE_INFLUENCE}`)
-    ) {
+    if (field === `${resultsField}.${OUTLIER_SCORE}`) {
       schema = 'numeric';
     }
 
@@ -203,11 +199,6 @@ export const useRenderCellValue = (
       }
 
       function getCellValue(cId: string) {
-        if (cId.includes(`.${FEATURE_INFLUENCE}.`) && resultsField !== undefined) {
-          const results = getNestedProperty(tableItems[adjustedRowIndex], resultsField, null);
-          return results[cId.replace(`${resultsField}.`, '')];
-        }
-
         if (tableItems.hasOwnProperty(adjustedRowIndex)) {
           const item = tableItems[adjustedRowIndex];
 

diff --git a/x-pack/plugins/ml/public/application/data_frame_analytics/common/fields.ts b/x-pack/plugins/ml/public/application/data_frame_analytics/common/fields.ts
@@ -17,7 +17,7 @@ import {
 import { ES_FIELD_TYPES, KBN_FIELD_TYPES } from '../../../../../../../src/plugins/data/public';
 import { newJobCapsService } from '../../services/new_job_capabilities_service';
 
-import { FEATURE_IMPORTANCE, FEATURE_INFLUENCE, OUTLIER_SCORE, TOP_CLASSES } from './constants';
+import { FEATURE_IMPORTANCE, OUTLIER_SCORE, TOP_CLASSES } from './constants';
 import { DataFrameAnalyticsConfig } from '../../../../common/types/data_frame_analytics';
 
 export type EsId = string;
@@ -179,7 +179,6 @@ export const getDefaultFieldsFromJobCaps = (
   const resultsField = jobConfig.dest.results_field;
 
   const featureImportanceFields = [];
-  const featureInfluenceFields = [];
   const topClassesFields = [];
   const allFields: any = [];
   let type: ES_FIELD_TYPES | undefined;
@@ -193,16 +192,6 @@ export const getDefaultFieldsFromJobCaps = (
         name: `${resultsField}.${OUTLIER_SCORE}`,
         type: KBN_FIELD_TYPES.NUMBER,
       });
-
-      featureInfluenceFields.push(
-        ...fields
-          .filter((d) => !jobConfig.analyzed_fields.excludes.includes(d.id))
-          .map((d) => ({
-            id: `${resultsField}.${FEATURE_INFLUENCE}.${d.id}`,
-            name: `${resultsField}.${FEATURE_INFLUENCE}.${d.name}`,
-            type: KBN_FIELD_TYPES.NUMBER,
-          }))
-      );
     }
   }
 
@@ -247,12 +236,7 @@ export const getDefaultFieldsFromJobCaps = (
     }
   }
 
-  allFields.push(
-    ...fields,
-    ...featureImportanceFields,
-    ...featureInfluenceFields,
-    ...topClassesFields
-  );
+  allFields.push(...fields, ...featureImportanceFields, ...topClassesFields);
   allFields.sort(({ name: a }: { name: string }, { name: b }: { name: string }) =>
     sortExplorationResultsFields(a, b, jobConfig)
   );

diff --git a/x-pack/plugins/ml/public/application/data_frame_analytics/common/get_index_data.ts b/x-pack/plugins/ml/public/application/data_frame_analytics/common/get_index_data.ts
@@ -19,7 +19,8 @@ import { DataFrameAnalyticsConfig } from '../../../../common/types/data_frame_an
 export const getIndexData = async (
   jobConfig: DataFrameAnalyticsConfig | undefined,
   dataGrid: UseDataGridReturnType,
-  searchQuery: SavedSearchQuery
+  searchQuery: SavedSearchQuery,
+  options: { didCancel: boolean }
 ) => {
   if (jobConfig !== undefined) {
     const {
@@ -52,22 +53,19 @@ export const getIndexData = async (
         index: jobConfig.dest.index,
         body: {
           fields: ['*'],
-          _source: jobConfig.dest.results_field,
+          _source: [],
           query: searchQuery,
           from: pageIndex * pageSize,
           size: pageSize,
           ...(Object.keys(sort).length > 0 ? { sort } : {}),
         },
       });
 
-      setRowCount(resp.hits.total.value);
-      const docs = resp.hits.hits.map((d) => ({
-        ...getProcessedFields(d.fields),
-        [jobConfig.dest.results_field]: d._source[jobConfig.dest.results_field],
-      }));
-
-      setTableItems(docs);
-      setStatus(INDEX_STATUS.LOADED);
+      if (!options.didCancel) {
+        setRowCount(resp.hits.total.value);
+        setTableItems(resp.hits.hits.map((d) => getProcessedFields(d.fields)));
+        setStatus(INDEX_STATUS.LOADED);
+      }
     } catch (e) {
       setErrorMessage(extractErrorMessage(e));
       setStatus(INDEX_STATUS.ERROR);

diff --git a/x-pack/plugins/ml/public/application/data_frame_analytics/common/use_results_view_config.ts b/x-pack/plugins/ml/public/application/data_frame_analytics/common/use_results_view_config.ts
@@ -6,6 +6,8 @@
 
 import { useEffect, useState } from 'react';
 
+import { i18n } from '@kbn/i18n';
+
 import { IndexPattern } from '../../../../../../../src/plugins/data/public';
 
 import { extractErrorMessage } from '../../../../common/util/errors';
@@ -32,6 +34,9 @@ export const useResultsViewConfig = (jobId: string) => {
   const trainedModelsApiService = useTrainedModelsApiService();
 
   const [indexPattern, setIndexPattern] = useState<IndexPattern | undefined>(undefined);
+  const [indexPatternErrorMessage, setIndexPatternErrorMessage] = useState<undefined | string>(
+    undefined
+  );
   const [isInitialized, setIsInitialized] = useState<boolean>(false);
   const [needsDestIndexPattern, setNeedsDestIndexPattern] = useState<boolean>(false);
   const [isLoadingJobConfig, setIsLoadingJobConfig] = useState<boolean>(false);
@@ -105,7 +110,11 @@ export const useResultsViewConfig = (jobId: string) => {
               setNeedsDestIndexPattern(true);
               const sourceIndex = jobConfigUpdate.source.index[0];
               const sourceIndexPatternId = getIndexPatternIdFromName(sourceIndex) || sourceIndex;
-              indexP = await mlContext.indexPatterns.get(sourceIndexPatternId);
+              try {
+                indexP = await mlContext.indexPatterns.get(sourceIndexPatternId);
+              } catch (e) {
+                indexP = undefined;
+              }
             }
 
             if (indexP !== undefined) {
@@ -114,6 +123,16 @@ export const useResultsViewConfig = (jobId: string) => {
               setIndexPattern(indexP);
               setIsInitialized(true);
               setIsLoadingJobConfig(false);
+            } else {
+              setIndexPatternErrorMessage(
+                i18n.translate(
+                  'xpack.ml.dataframe.analytics.results.indexPatternsMissingErrorMessage',
+                  {
+                    defaultMessage:
+                      'To view this page, a Kibana index pattern is necessary for either the destination or source index of this analytics job.',
+                  }
+                )
+              );
             }
           } catch (e) {
             setJobCapsServiceErrorMessage(extractErrorMessage(e));
@@ -129,6 +148,7 @@ export const useResultsViewConfig = (jobId: string) => {
 
   return {
     indexPattern,
+    indexPatternErrorMessage,
     isInitialized,
     isLoadingJobConfig,
     jobCapsServiceErrorMessage,

diff --git a/...es/analytics_exploration/components/exploration_page_wrapper/exploration_page_wrapper.tsx b/...es/analytics_exploration/components/exploration_page_wrapper/exploration_page_wrapper.tsx
@@ -6,7 +6,7 @@
 
 import React, { FC, useEffect, useState } from 'react';
 
-import { EuiFlexGroup, EuiFlexItem, EuiSpacer, EuiText } from '@elastic/eui';
+import { EuiCallOut, EuiFlexGroup, EuiFlexItem, EuiPanel, EuiSpacer, EuiText } from '@elastic/eui';
 import { i18n } from '@kbn/i18n';
 
 import { useUrlState } from '../../../../../util/url_state';
@@ -70,6 +70,7 @@ export const ExplorationPageWrapper: FC<Props> = ({
 }) => {
   const {
     indexPattern,
+    indexPatternErrorMessage,
     isInitialized,
     isLoadingJobConfig,
     jobCapsServiceErrorMessage,
@@ -99,6 +100,22 @@ export const ExplorationPageWrapper: FC<Props> = ({
     }
   }, [jobConfig?.dest.results_field]);
 
+  if (indexPatternErrorMessage !== undefined) {
+    return (
+      <EuiPanel grow={false}>
+        <EuiCallOut
+          title={i18n.translate('xpack.ml.dataframe.analytics.exploration.indexError', {
+            defaultMessage: 'An error occurred loading the index data.',
+          })}
+          color="danger"
+          iconType="cross"
+        >
+          <p>{indexPatternErrorMessage}</p>
+        </EuiCallOut>
+      </EuiPanel>
+    );
+  }
+
   if (jobConfigErrorMessage !== undefined || jobCapsServiceErrorMessage !== undefined) {
     return (
       <JobConfigErrorCallout

diff --git a/...ges/analytics_exploration/components/exploration_results_table/use_exploration_results.ts b/...ges/analytics_exploration/components/exploration_results_table/use_exploration_results.ts
@@ -73,8 +73,15 @@ export const useExplorationResults = (
     dataGrid.resetPagination();
   }, [JSON.stringify(searchQuery)]);
 
+  // The pattern using `didCancel` allows us to abort out of date remote request.
+  // We wrap `didCancel` in a object so we can mutate the value as it's being
+  // passed on to `getIndexData`.
   useEffect(() => {
-    getIndexData(jobConfig, dataGrid, searchQuery);
+    const options = { didCancel: false };
+    getIndexData(jobConfig, dataGrid, searchQuery, options);
+    return () => {
+      options.didCancel = true;
+    };
     // custom comparison
   }, [jobConfig && jobConfig.id, dataGrid.pagination, searchQuery, dataGrid.sortingColumns]);
 

diff --git a/...data_frame_analytics/pages/analytics_exploration/components/outlier_exploration/common.ts b/...data_frame_analytics/pages/analytics_exploration/components/outlier_exploration/common.ts
@@ -19,11 +19,8 @@ export const getFeatureCount = (resultsField: string, tableItems: DataGridItem[]
 
   const fullItem = tableItems[0];
 
-  if (
-    fullItem[resultsField] !== undefined &&
-    Array.isArray(fullItem[resultsField][FEATURE_INFLUENCE])
-  ) {
-    return fullItem[resultsField][FEATURE_INFLUENCE].length;
+  if (Array.isArray(fullItem[`${resultsField}.${FEATURE_INFLUENCE}.feature_name`])) {
+    return fullItem[`${resultsField}.${FEATURE_INFLUENCE}.feature_name`].length;
   }
 
   return 0;

diff --git a/...lytics/pages/analytics_exploration/components/outlier_exploration/outlier_exploration.tsx b/...lytics/pages/analytics_exploration/components/outlier_exploration/outlier_exploration.tsx
@@ -6,7 +6,9 @@
 
 import React, { useState, FC } from 'react';
 
-import { EuiSpacer, EuiText } from '@elastic/eui';
+import { EuiCallOut, EuiPanel, EuiSpacer, EuiText } from '@elastic/eui';
+
+import { i18n } from '@kbn/i18n';
 
 import {
   useColorRange,
@@ -15,7 +17,8 @@ import {
 } from '../../../../../components/color_range_legend';
 import { SavedSearchQuery } from '../../../../../contexts/ml';
 
-import { defaultSearchQuery, useResultsViewConfig } from '../../../../common';
+import { defaultSearchQuery, isOutlierAnalysis, useResultsViewConfig } from '../../../../common';
+import { FEATURE_INFLUENCE } from '../../../../common/constants';
 
 import { ExpandableSectionAnalytics, ExpandableSectionResults } from '../expandable_section';
 import { ExplorationQueryBar } from '../exploration_query_bar';
@@ -30,17 +33,54 @@ interface ExplorationProps {
 }
 
 export const OutlierExploration: FC<ExplorationProps> = React.memo(({ jobId }) => {
-  const { indexPattern, jobConfig, needsDestIndexPattern } = useResultsViewConfig(jobId);
+  const {
+    indexPattern,
+    indexPatternErrorMessage,
+    jobConfig,
+    needsDestIndexPattern,
+  } = useResultsViewConfig(jobId);
   const [searchQuery, setSearchQuery] = useState<SavedSearchQuery>(defaultSearchQuery);
   const outlierData = useOutlierData(indexPattern, jobConfig, searchQuery);
 
   const { columnsWithCharts, tableItems } = outlierData;
 
-  const colorRange = useColorRange(
-    COLOR_RANGE.BLUE,
-    COLOR_RANGE_SCALE.INFLUENCER,
-    jobConfig !== undefined ? getFeatureCount(jobConfig.dest.results_field, tableItems) : 1
-  );
+  const featureCount = getFeatureCount(jobConfig?.dest?.results_field || '', tableItems);
+  const colorRange = useColorRange(COLOR_RANGE.BLUE, COLOR_RANGE_SCALE.INFLUENCER, featureCount);
+
+  // Show the color range only if feature influence is enabled and there's more than 0 features.
+  const showColorRange =
+    featureCount > 0 &&
+    isOutlierAnalysis(jobConfig?.analysis) &&
+    jobConfig?.analysis.outlier_detection.compute_feature_influence === true;
+
+  const resultsField = jobConfig?.dest.results_field ?? '';
+
+  // Identify if the results index has a legacy feature influence format.
+  // If feature influence was enabled for the legacy job we'll show a callout
+  // with some additional information for a workaround.
+  const showLegacyFeatureInfluenceFormatCallout =
+    !needsDestIndexPattern &&
+    isOutlierAnalysis(jobConfig?.analysis) &&
+    jobConfig?.analysis.outlier_detection.compute_feature_influence === true &&
+    columnsWithCharts.findIndex(
+      (d) => d.id === `${resultsField}.${FEATURE_INFLUENCE}.feature_name`
+    ) === -1;
+
+  if (indexPatternErrorMessage !== undefined) {
+    return (
+      <EuiPanel grow={false}>
+        <EuiCallOut
+          title={i18n.translate('xpack.ml.dataframe.analytics.exploration.indexError', {
+            defaultMessage: 'An error occurred loading the index data.',
+          })}
+          color="danger"
+          iconType="cross"
+        >
+          <p>{indexPatternErrorMessage}</p>
+        </EuiCallOut>
+      </EuiPanel>
+    );
+  }
 
   return (
     <>
@@ -58,8 +98,26 @@ export const OutlierExploration: FC<ExplorationProps> = React.memo(({ jobId }) =
           </>
         )}
       {typeof jobConfig?.id === 'string' && <ExpandableSectionAnalytics jobId={jobConfig?.id} />}
+      {showLegacyFeatureInfluenceFormatCallout && (
+        <>
+          <EuiCallOut
+            size="s"
+            title={i18n.translate(
+              'xpack.ml.dataframe.analytics.outlierExploration.legacyFeatureInfluenceFormatCalloutTitle',
+              {
+                defaultMessage:
+                  'Color coded table cells based on feature influence are not available because the results index uses an unsupported legacy format. Please clone and rerun the job.',
+              }
+            )}
+            iconType="pin"
+          />
+          <EuiSpacer size="m" />
+        </>
+      )}
       <ExpandableSectionResults
-        colorRange={colorRange}
+        colorRange={
+          showColorRange && !showLegacyFeatureInfluenceFormatCallout ? colorRange : undefined
+        }
         indexData={outlierData}
         indexPattern={indexPattern}
         jobConfig={jobConfig}