[ML] Clone analytics job (#59791) (#60228)

* [ML] clone analytics job

* [ML] flyout clone header

* [ML] improve clone action context menu item

* [ML] support advanced job cloning

* [ML] extractCloningConfig

* [ML] fix isAdvancedSetting condition, add test

* [ML] clone job header

* [ML] job description placeholder

* [ML] setEstimatedModelMemoryLimit on source index change

* [ML] Fix types.

* [ML] useUpdateEffect in create_analytics_form.tsx

* [ML] setJobClone action

* [ML] remove CreateAnalyticsFlyoutWrapper instance from the create_analytics_button.tsx

* [ML] fix types

* [ML] hack to align Clone button with the other actions

* [ML] unknown props lead to advanced editor

* [ML] rename maximum_number_trees ot max_trees

* [ML] fix forceInput

* [ML] populate excludesOptions on the first update, skip setting mml on the fist update

* [ML] init functional test for cloning analytics jobs

* [ML] functional tests

* [ML] fix functional tests imports

* [ML] fix indices names for functional tests

* [ML] functional tests for outlier detection and regression jobs cloning

* [ML] delete james tag

* [ML] fix tests arrangement

Co-authored-by: Walter Rafelsberger <walter@elastic.co>

Co-authored-by: Walter Rafelsberger <walter@elastic.co>

Author: darnautov

x-pack/plugins/ml/__mocks__/shared_imports.ts

@@ -4,4 +4,4 @@
  * you may not use this file except in compliance with the Elastic License.
  */
 
-export function XJsonMode() {}
+export const XJsonMode = jest.fn();

x-pack/plugins/ml/public/application/data_frame_analytics/common/analytics.ts

@@ -19,25 +19,36 @@ export type IndexName = string;
 export type IndexPattern = string;
 export type DataFrameAnalyticsId = string;
 
+export enum ANALYSIS_CONFIG_TYPE {
+  OUTLIER_DETECTION = 'outlier_detection',
+  REGRESSION = 'regression',
+  CLASSIFICATION = 'classification',
+}
+
 interface OutlierAnalysis {
+  [key: string]: {};
   outlier_detection: {};
 }
 
-interface RegressionAnalysis {
-  regression: {
-    dependent_variable: string;
-    training_percent?: number;
-    prediction_field_name?: string;
-  };
+interface Regression {
+  dependent_variable: string;
+  training_percent?: number;
+  prediction_field_name?: string;
+}
+export interface RegressionAnalysis {
+  [key: string]: Regression;
+  regression: Regression;
 }
 
-interface ClassificationAnalysis {
-  classification: {
-    dependent_variable: string;
-    training_percent?: number;
-    num_top_classes?: string;
-    prediction_field_name?: string;
-  };
+interface Classification {
+  dependent_variable: string;
+  training_percent?: number;
+  num_top_classes?: string;
+  prediction_field_name?: string;
+}
+export interface ClassificationAnalysis {
+  [key: string]: Classification;
+  classification: Classification;
 }
 
 export interface LoadExploreDataArg {
@@ -136,21 +147,14 @@ type AnalysisConfig =
   | ClassificationAnalysis
   | GenericAnalysis;
 
-export enum ANALYSIS_CONFIG_TYPE {
-  OUTLIER_DETECTION = 'outlier_detection',
-  REGRESSION = 'regression',
-  CLASSIFICATION = 'classification',
-  UNKNOWN = 'unknown',
-}
-
 export const getAnalysisType = (analysis: AnalysisConfig) => {
   const keys = Object.keys(analysis);
 
   if (keys.length === 1) {
     return keys[0];
   }
 
-  return ANALYSIS_CONFIG_TYPE.UNKNOWN;
+  return 'unknown';
 };
 
 export const getDependentVar = (analysis: AnalysisConfig) => {
@@ -245,6 +249,7 @@ export interface DataFrameAnalyticsConfig {
   };
   source: {
     index: IndexName | IndexName[];
+    query?: any;
   };
   analysis: AnalysisConfig;
   analyzed_fields: {
@@ -254,6 +259,7 @@ export interface DataFrameAnalyticsConfig {
   model_memory_limit: string;
   create_time: number;
   version: string;
+  allow_lazy_start?: boolean;
 }
 
 export enum REFRESH_ANALYTICS_LIST_STATE {

x-pack/plugins/ml/public/application/data_frame_analytics/pages/analytics_management/components/analytics_list/action_clone.test.ts

@@ -0,0 +1,254 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License;
+ * you may not use this file except in compliance with the Elastic License.
+ */
+
+import { isAdvancedConfig } from './action_clone';
+
+describe('Analytics job clone action', () => {
+  describe('isAdvancedConfig', () => {
+    test('should detect a classification job created with the form', () => {
+      const formCreatedClassificationJob = {
+        description: "Classification job with 'bank-marketing' dataset",
+        source: {
+          index: ['bank-marketing'],
+          query: {
+            match_all: {},
+          },
+        },
+        dest: {
+          index: 'dest_bank_1',
+          results_field: 'ml',
+        },
+        analysis: {
+          classification: {
+            dependent_variable: 'y',
+            num_top_classes: 2,
+            prediction_field_name: 'y_prediction',
+            training_percent: 2,
+            randomize_seed: 6233212276062807000,
+          },
+        },
+        analyzed_fields: {
+          includes: [],
+          excludes: [],
+        },
+        model_memory_limit: '350mb',
+        allow_lazy_start: false,
+      };
+
+      expect(isAdvancedConfig(formCreatedClassificationJob)).toBe(false);
+    });
+
+    test('should detect a outlier_detection job created with the form', () => {
+      const formCreatedOutlierDetectionJob = {
+        description: "Outlier detection job with 'glass' dataset",
+        source: {
+          index: ['glass_withoutdupl_norm'],
+          query: {
+            match_all: {},
+          },
+        },
+        dest: {
+          index: 'dest_glass_1',
+          results_field: 'ml',
+        },
+        analysis: {
+          outlier_detection: {
+            compute_feature_influence: true,
+            outlier_fraction: 0.05,
+            standardization_enabled: true,
+          },
+        },
+        analyzed_fields: {
+          includes: [],
+          excludes: ['id', 'outlier'],
+        },
+        model_memory_limit: '1mb',
+        allow_lazy_start: false,
+      };
+      expect(isAdvancedConfig(formCreatedOutlierDetectionJob)).toBe(false);
+    });
+
+    test('should detect a regression job created with the form', () => {
+      const formCreatedRegressionJob = {
+        description: "Regression job with 'electrical-grid-stability' dataset",
+        source: {
+          index: ['electrical-grid-stability'],
+          query: {
+            match_all: {},
+          },
+        },
+        dest: {
+          index: 'dest_grid_1',
+          results_field: 'ml',
+        },
+        analysis: {
+          regression: {
+            dependent_variable: 'stab',
+            prediction_field_name: 'stab_prediction',
+            training_percent: 20,
+            randomize_seed: -2228827740028660200,
+          },
+        },
+        analyzed_fields: {
+          includes: [],
+          excludes: [],
+        },
+        model_memory_limit: '150mb',
+        allow_lazy_start: false,
+      };
+
+      expect(isAdvancedConfig(formCreatedRegressionJob)).toBe(false);
+    });
+
+    test('should detect advanced classification job', () => {
+      const advancedClassificationJob = {
+        description: "Classification job with 'bank-marketing' dataset",
+        source: {
+          index: ['bank-marketing'],
+          query: {
+            match_all: {},
+          },
+        },
+        dest: {
+          index: 'dest_bank_1',
+          results_field: 'CUSTOM_RESULT_FIELD',
+        },
+        analysis: {
+          classification: {
+            dependent_variable: 'y',
+            num_top_classes: 2,
+            prediction_field_name: 'y_prediction',
+            training_percent: 2,
+            randomize_seed: 6233212276062807000,
+          },
+        },
+        analyzed_fields: {
+          includes: [],
+          excludes: [],
+        },
+        model_memory_limit: '350mb',
+        allow_lazy_start: false,
+      };
+
+      expect(isAdvancedConfig(advancedClassificationJob)).toBe(true);
+    });
+
+    test('should detect advanced outlier_detection job', () => {
+      const advancedOutlierDetectionJob = {
+        description: "Outlier detection job with 'glass' dataset",
+        source: {
+          index: ['glass_withoutdupl_norm'],
+          query: {
+            // TODO check default for `match`
+            match_all: {},
+          },
+        },
+        dest: {
+          index: 'dest_glass_1',
+          results_field: 'ml',
+        },
+        analysis: {
+          outlier_detection: {
+            compute_feature_influence: false,
+            outlier_fraction: 0.05,
+            standardization_enabled: true,
+          },
+        },
+        analyzed_fields: {
+          includes: [],
+          excludes: ['id', 'outlier'],
+        },
+        model_memory_limit: '1mb',
+        allow_lazy_start: false,
+      };
+      expect(isAdvancedConfig(advancedOutlierDetectionJob)).toBe(true);
+    });
+
+    test('should detect a custom query', () => {
+      const advancedRegressionJob = {
+        description: "Regression job with 'electrical-grid-stability' dataset",
+        source: {
+          index: ['electrical-grid-stability'],
+          query: {
+            match: {
+              custom_field: 'custom_match',
+            },
+          },
+        },
+        dest: {
+          index: 'dest_grid_1',
+          results_field: 'ml',
+        },
+        analysis: {
+          regression: {
+            dependent_variable: 'stab',
+            prediction_field_name: 'stab_prediction',
+            training_percent: 20,
+            randomize_seed: -2228827740028660200,
+          },
+        },
+        analyzed_fields: {
+          includes: [],
+          excludes: [],
+        },
+        model_memory_limit: '150mb',
+        allow_lazy_start: false,
+      };
+
+      expect(isAdvancedConfig(advancedRegressionJob)).toBe(true);
+    });
+
+    test('should detect custom analysis settings', () => {
+      const config = {
+        description: "Classification clone with 'bank-marketing' dataset",
+        source: {
+          index: 'bank-marketing',
+        },
+        dest: {
+          index: 'bank_classification4',
+        },
+        analyzed_fields: {
+          excludes: [],
+        },
+        analysis: {
+          classification: {
+            dependent_variable: 'y',
+            training_percent: 71,
+            max_trees: 1500,
+          },
+        },
+        model_memory_limit: '400mb',
+      };
+
+      expect(isAdvancedConfig(config)).toBe(true);
+    });
+
+    test('should detect as advanced if the prop is unknown', () => {
+      const config = {
+        description: "Classification clone with 'bank-marketing' dataset",
+        source: {
+          index: 'bank-marketing',
+        },
+        dest: {
+          index: 'bank_classification4',
+        },
+        analyzed_fields: {
+          excludes: [],
+        },
+        analysis: {
+          classification: {
+            dependent_variable: 'y',
+            training_percent: 71,
+            maximum_number_trees: 1500,
+          },
+        },
+        model_memory_limit: '400mb',
+      };
+
+      expect(isAdvancedConfig(config)).toBe(true);
+    });
+  });
+});