Microsoft Purview Data Profiling API

openapi: 3.1.0
info:
  title: Microsoft Purview Account Accounts Data Profiling API
  description: APIs for managing Purview accounts, configurations, and administrative settings through Azure Resource Manager. Provides resource management operations for creating, updating, and deleting Purview accounts.
  version: 2021-12-01
  contact:
    name: Microsoft Purview Support
    url: https://learn.microsoft.com/en-us/purview/
  license:
    name: Microsoft API License
    url: https://azure.microsoft.com/en-us/support/legal/
servers:
- url: https://management.azure.com
  description: Azure Resource Manager endpoint
security:
- oauth2: []
tags:
- name: Data Profiling
  description: Operations for data profiling operations
paths:
  /dataquality/profiling/{assetId}:
    post:
      operationId: runDataProfiling
      summary: Microsoft Purview Run data profiling
      description: Initiate data profiling for a specific data asset.
      tags:
      - Data Profiling
      parameters:
      - name: assetId
        in: path
        required: true
        description: The data asset identifier
        schema:
          type: string
      - name: api-version
        in: query
        required: true
        schema:
          type: string
          default: 2024-03-01-preview
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ProfilingRequest'
      responses:
        '202':
          description: Data profiling initiated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProfilingResult'
        '401':
          description: Unauthorized
    get:
      operationId: getDataProfilingResult
      summary: Microsoft Purview Get data profiling result
      description: Get data profiling results for a specific data asset.
      tags:
      - Data Profiling
      parameters:
      - name: assetId
        in: path
        required: true
        schema:
          type: string
      - name: api-version
        in: query
        required: true
        schema:
          type: string
          default: 2024-03-01-preview
      responses:
        '200':
          description: Data profiling result retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProfilingResult'
        '401':
          description: Unauthorized
        '404':
          description: Not found
components:
  schemas:
    ColumnProfile:
      type: object
      properties:
        columnName:
          type: string
        dataType:
          type: string
        nullCount:
          type: integer
          format: int64
        nullPercentage:
          type: number
          format: float
        distinctCount:
          type: integer
          format: int64
        minValue:
          type: string
        maxValue:
          type: string
        meanValue:
          type: string
        standardDeviation:
          type: number
          format: double
        topValues:
          type: array
          items:
            type: object
            properties:
              value:
                type: string
              count:
                type: integer
                format: int64
    ProfilingRequest:
      type: object
      properties:
        columns:
          type: array
          items:
            type: string
        sampleSize:
          type: integer
          format: int32
    ProfilingResult:
      type: object
      properties:
        assetId:
          type: string
        status:
          type: string
          enum:
          - InProgress
          - Completed
          - Failed
        profiledAt:
          type: string
          format: date-time
        rowCount:
          type: integer
          format: int64
        columnProfiles:
          type: array
          items:
            $ref: '#/components/schemas/ColumnProfile'
  securitySchemes:
    oauth2:
      type: oauth2
      description: Azure Active Directory OAuth2 authentication
      flows:
        clientCredentials:
          tokenUrl: https://login.microsoftonline.com/{tenantId}/oauth2/v2.0/token
          scopes:
            https://management.azure.com/.default: Access Azure Resource Manager