mammoth-io Generate Profile API

openapi: 3.2.0
info:
  title: Mammoth Io Generate Profile API
  version: 0.1.0
  contact:
    name: Mammoth Analytics
    url: https://mammoth.io
    email: support@mammoth.io
  description: 'Operations tagged Generate Profile across 2 of this provider''s published API definitions: app.mammoth.io-openapi.json, mammoth-io-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: /api/v2
security:
- bearerAuth: []
- apiKey: []
  apiSecret: []
  workspaceId: []
tags:
- name: Generate Profile
paths:
  /workspaces/{workspace_id}/projects/{project_id}/datasets/{dataset_id}/dataviews/{dataview_id}/profile_generation:
    post:
      tags:
      - Generate Profile
      summary: Generate or Update Dataset Profile
      description: Triggers AI-based profiling for a given dataview.
      operationId: GenerateProfile
      parameters:
      - name: workspace_id
        in: path
        schema:
          type: integer
          minimum: 1.0
          title: Workspace ID
          description: Workspace refers to a collection of projects. Workspace ID is unique identifier for workspace.
          examples:
          - 4
        description: Workspace refers to a collection of projects. Workspace ID is unique identifier for workspace.
        required: true
        deprecated: false
        examples:
          workspace_id-example-1:
            summary: Sample workspace ID
            value: 4
      - name: project_id
        in: path
        schema:
          type: integer
          minimum: 1.0
          title: Project ID
          description: Project ID of the workspace
          examples:
          - 4
        description: Project ID of the workspace
        required: true
        deprecated: false
        examples:
          project_id-example-1:
            summary: Sample project ID
            value: 4
      - name: dataset_id
        in: path
        schema:
          type: integer
          minimum: 0.0
          title: Dataset ID
          description: Id of the dataset
          examples:
          - 121
        description: Id of the dataset
        required: true
        deprecated: false
        examples:
          dataset_id-example-1:
            summary: Sample dataset ID
            value: 121
      - name: dataview_id
        in: path
        schema:
          type: integer
          minimum: 1.0
          title: Dataview ID
          description: Dataview ID of the dataset
          examples:
          - 4
        description: Dataview ID of the dataset
        required: true
        deprecated: false
        examples:
          dataview_id-example-1:
            summary: Sample dataview ID
            value: 4
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ProfileGenerationSpec'
        required: true
      responses:
        '201':
          description: Document created, URL follows
          headers: {}
          content:
            application/json:
              schema:
                oneOf:
                - $ref: '#/components/schemas/ProfileGeneration'
                - $ref: '#/components/schemas/ObjectJobSchema'
        '400':
          description: Bad request syntax or unsupported method
          content:
            application/json:
              schema:
                oneOf:
                - properties:
                    status_code:
                      type: integer
                    detail:
                      type: string
                    extra:
                      additionalProperties: {}
                      type:
                      - 'null'
                      - object
                      - array
                  type: object
                  required:
                  - detail
                  - status_code
                  description: Client Error
                  examples:
                  - status_code: 400
                    detail: Bad Request
                    extra: {}
                - properties:
                    status_code:
                      type: integer
                    detail:
                      type: string
                    extra:
                      additionalProperties: {}
                      type:
                      - 'null'
                      - object
                      - array
                  type: object
                  required:
                  - detail
                  - status_code
                  description: Validation Exception
                  examples:
                  - status_code: 400
                    detail: Bad Request
                    extra: {}
        '403':
          description: Request forbidden -- authorization will not help
          content:
            application/json:
              schema:
                properties:
                  status_code:
                    type: integer
                  detail:
                    type: string
                  extra:
                    additionalProperties: {}
                    type:
                    - 'null'
                    - object
                    - array
                type: object
                required:
                - detail
                - status_code
                description: Authorization Exception
                examples:
                - status_code: 403
                  detail: Forbidden
                  extra: {}
        '202':
          description: Successfully Submitted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
      deprecated: false
    servers:
    - url: /api/v2
components:
  schemas:
    NumericColumnStats:
      properties:
        column_name:
          type: string
          description: Name of the numeric column
          default: ''
        schema_analysis:
          $ref: '#/components/schemas/SchemaAnalysis'
        statistical_summary:
          $ref: '#/components/schemas/NumericStatisticalSummary'
        quality_metrics:
          $ref: '#/components/schemas/NumericQualityMetrics'
        performance_metadata:
          $ref: '#/components/schemas/PerformanceMetadata'
      type: object
      required: []
      title: NumericColumnStats
    PrimaryKeyInfo:
      properties:
        name:
          type: string
        type:
          type: string
          enum:
          - TEXT
          - NUMERIC
          - DATE
        ds_name:
          type: string
        display_name:
          type: string
      type: object
      required:
      - display_name
      - ds_name
      - name
      - type
      title: PrimaryKeyInfo
    DatePerformanceMetadata:
      properties:
        total_rows:
          type: integer
          description: Total number of rows in the dataset
          default: 0
        non_null_count:
          type: integer
          description: Number of rows with non-null values
          default: 0
        missing_count:
          type: integer
          description: Number of rows with null/missing values
          default: 0
        data_freshness_days:
          oneOf:
          - type: integer
          - type: 'null'
          description: Days since the most recent date
      type: object
      required: []
      title: DatePerformanceMetadata
    TextQualityMetrics:
      properties:
        completeness_rate:
          type: number
          description: Percentage of non-null values
          default: 0.0
        missing_percentage:
          type: number
          description: Percentage of missing/null values
          default: 0.0
        empty_string_count:
          type: integer
          description: Number of empty strings (after trimming)
          default: 0
        numeric_strings_count:
          type: integer
          description: Number of text values containing only numbers
          default: 0
        email_like_count:
          type: integer
          description: Number of values matching email pattern
          default: 0
        phone_like_count:
          type: integer
          description: Number of values matching phone number pattern
          default: 0
      type: object
      required: []
      title: TextQualityMetrics
    ProfileGenerationSpec:
      properties:
        params:
          $ref: '#/components/schemas/ProfileGenerationParams'
      type: object
      required:
      - params
      title: ProfileGenerationSpec
      description: Parameters required for profile generation
      examples:
      - params:
          action: stats
    SchemaAnalysis:
      properties:
        column_type:
          type: string
          enum:
          - TEXT
          - NUMERIC
          - DATE
          description: Data type of the column
          default: TEXT
        is_nullable:
          type: boolean
          description: Whether the column allows null values
          default: false
        num_unique:
          type: integer
          description: Number of distinct/unique values
          default: 0
        uniqueness_percentage:
          oneOf:
          - type: number
          - type: 'null'
          description: Percentage of unique values
      type: object
      required: []
      title: SchemaAnalysis
    PerformanceMetadata:
      properties:
        total_rows:
          type: integer
          description: Total number of rows in the dataset
          default: 0
        non_null_count:
          type: integer
          description: Number of rows with non-null values
          default: 0
        missing_count:
          type: integer
          description: Number of rows with null/missing values
          default: 0
      type: object
      required: []
      title: PerformanceMetadata
    JobResponse:
      properties:
        job:
          $ref: '#/components/schemas/JobSchema'
      type: object
      required:
      - job
      title: JobResponse
    JoinSuggestion:
      properties:
        root:
          items:
            $ref: '#/components/schemas/JoinSuggestionItem'
          type: array
      type: object
      required:
      - root
      title: JoinSuggestion
    DateStatisticalSummary:
      properties:
        cardinality:
          type: integer
          description: Number of distinct values (same as num_unique)
          default: 0
        data_sample:
          items:
            $ref: '#/components/schemas/DataSampleItem'
          type: array
          description: Top 30 most frequent values with counts and percentages
          default: []
        min_date:
          oneOf:
          - type: string
          - type: 'null'
          description: Earliest date
        max_date:
          oneOf:
          - type: string
          - type: 'null'
          description: Latest date
        date_range_days:
          oneOf:
          - type: integer
          - type: 'null'
          description: Number of days between earliest and latest dates
        unique_years:
          oneOf:
          - type: integer
          - type: 'null'
          description: Number of distinct years
        unique_months:
          oneOf:
          - type: integer
          - type: 'null'
          description: Number of distinct months
        unique_days:
          oneOf:
          - type: integer
          - type: 'null'
          description: Number of distinct days
        unique_weekdays:
          oneOf:
          - type: integer
          - type: 'null'
          description: Number of distinct weekdays
      type: object
      required: []
      title: DateStatisticalSummary
    ColumnStats:
      properties:
        root:
          additionalProperties:
            oneOf:
            - $ref: '#/components/schemas/TextColumnStats'
            - $ref: '#/components/schemas/NumericColumnStats'
            - $ref: '#/components/schemas/DateColumnStats'
          type: object
      type: object
      required:
      - root
      title: ColumnStats
    DateColumnStats:
      properties:
        column_name:
          type: string
          description: Name of the date column
          default: ''
        schema_analysis:
          $ref: '#/components/schemas/SchemaAnalysis'
        statistical_summary:
          $ref: '#/components/schemas/DateStatisticalSummary'
        quality_metrics:
          $ref: '#/components/schemas/DateQualityMetrics'
        performance_metadata:
          $ref: '#/components/schemas/DatePerformanceMetadata'
      type: object
      required: []
      title: DateColumnStats
    KeyInfo:
      properties:
        name:
          type: string
        type:
          type: string
          enum:
          - TEXT
          - NUMERIC
          - DATE
        display_name:
          type: string
      type: object
      required:
      - display_name
      - name
      - type
      title: KeyInfo
    DataSampleItem:
      properties:
        value:
          type: string
          description: The actual value
          default: ''
        count:
          type: integer
          description: Frequency of this value
          default: 0
        percentage:
          type: number
          description: Percentage of total non-null values
          default: 0.0
      type: object
      required: []
      title: DataSampleItem
    DateQualityMetrics:
      properties:
        completeness_rate:
          type: number
          description: Percentage of non-null values
          default: 0.0
        missing_percentage:
          type: number
          description: Percentage of missing/null values
          default: 0.0
        future_dates_count:
          type: integer
          description: Number of dates in the future
          default: 0
        very_old_dates_count:
          type: integer
          description: Number of dates before 1900-01-01
          default: 0
        weekend_dates_count:
          type: integer
          description: Number of dates falling on weekends
          default: 0
      type: object
      required: []
      title: DateQualityMetrics
    NumericStatisticalSummary:
      properties:
        cardinality:
          type: integer
          description: Number of distinct values (same as num_unique)
          default: 0
        data_sample:
          items:
            $ref: '#/components/schemas/DataSampleItem'
          type: array
          description: Top 30 most frequent values with counts and percentages
          default: []
        col_min:
          oneOf:
          - type: number
          - type: 'null'
          description: Minimum value
        col_max:
          oneOf:
          - type: number
          - type: 'null'
          description: Maximum value
        col_avg:
          oneOf:
          - type: number
          - type: 'null'
          description: Mean/average value
        col_median:
          oneOf:
          - type: number
          - type: 'null'
          description: Median value
        col_sum:
          oneOf:
          - type: number
          - type: 'null'
          description: Sum of all values
        col_stddev:
          oneOf:
          - type: number
          - type: 'null'
          description: Standard deviation
        col_variance:
          oneOf:
          - type: number
          - type: 'null'
          description: Variance
        col_range:
          oneOf:
          - type: number
          - type: 'null'
          description: Range (max - min)
        q1:
          oneOf:
          - type: number
          - type: 'null'
          description: First quartile (25th percentile)
        q3:
          oneOf:
          - type: number
          - type: 'null'
          description: Third quartile (75th percentile)
        iqr:
          oneOf:
          - type: number
          - type: 'null'
          description: Interquartile range (Q3 - Q1)
        p5:
          oneOf:
          - type: number
          - type: 'null'
          description: 5th percentile
        p95:
          oneOf:
          - type: number
          - type: 'null'
          description: 95th percentile
      type: object
      required: []
      title: NumericStatisticalSummary
    JoinSuggestionItem:
      properties:
        foreign_key:
          $ref: '#/components/schemas/KeyInfo'
        primary_key:
          $ref: '#/components/schemas/PrimaryKeyInfo'
        foreign_table:
          type: string
        primary_table:
          type: string
        foreign_dataview_id:
          type: integer
        foreign_metadata:
          items:
            type: object
          type: array
        foreign_dataview_name:
          type: string
        foreign_datasource_name:
          type: string
        cardinality:
          type: integer
      type: object
      required:
      - cardinality
      - foreign_datasource_name
      - foreign_dataview_id
      - foreign_dataview_name
      - foreign_key
      - foreign_metadata
      - foreign_table
      - primary_key
      - primary_table
      title: JoinSuggestionItem
    ObjectJobSchema:
      properties:
        status_code:
          oneOf:
          - type: integer
          - type: 'null'
          title: Status code
          examples:
          - value:
              status_code: 200
        job_id:
          oneOf:
          - type: integer
          - type: 'null'
          title: Job id
          description: Created job id
        failure_reason:
          oneOf:
          - type: string
          - type: 'null'
          title: Failure reason
          description: Failure reason if status is failure
          examples:
          - value:
              failure_reason: Some reason
      type: object
      required: []
      title: ObjectJobSchema
    JobSchema:
      properties:
        id:
          type: integer
          minimum: 0.0
          title: Job id
          examples:
          - value:
              id: 10
        status:
          type: string
          enum:
          - success
          - failure
          - processing
          - error
          title: Job status
          description: Job status can be success, failure or processing
          examples:
          - value:
              status: success
        response:
          oneOf:
          - type: object
          - type: array
          description: Result of async task is stored in response
          examples:
          - value:
              response:
                object: some object
        last_updated_at:
          type: string
          format: date-time
          title: Job last updated at
          description: Job last updated at is the time when Job status was last updated
          examples:
          - value:
              last_updated_at: '2021-08-10T10:00:00'
        created_at:
          type: string
          format: date-time
          title: Job created at
          description: Create at is time when async task was created
          examples:
          - value:
              created_at: '2021-08-10T10:00:00'
        path:
          type: string
          title: Job path
          description: API request path of the Job operation
          examples:
          - value:
              path: /api/v2/dataviews/1
        operation:
          type: string
          title: Job operation
          description: Operation is async task name which Job is tracking
          examples:
          - value:
              operation: post_modification_pipeline_execution
      type: object
      required:
      - created_at
      - id
      - last_updated_at
      - operation
      - path
      - response
      - status
      title: JobSchema
    ProfileGenerationParams:
      properties:
        action:
          type: string
          enum:
          - stats
          - insights
          - data_quality
          - join_recommendation
          description: 'Specifies the action to perform: ''stats'' to fetch stats or ''profile'' to fetch profile.'
      type: object
      required:
      - action
      title: ProfileGenerationParams
      description: Encapsulated profile generation parameters
    TextStatisticalSummary:
      properties:
        cardinality:
          type: integer
          description: Number of distinct values (same as num_unique)
          default: 0
        data_sample:
          items:
            $ref: '#/components/schemas/DataSampleItem'
          type: array
          description: Top 30 most frequent values with counts and percentages
          default: []
        min_length:
          oneOf:
          - type: integer
          - type: 'null'
          description: Minimum string length
        max_length:
          oneOf:
          - type: integer
          - type: 'null'
          description: Maximum string length
        avg_length:
          oneOf:
          - type: number
          - type: 'null'
          description: Average string length
      type: object
      required: []
      title: TextStatisticalSummary
    NumericQualityMetrics:
      properties:
        completeness_rate:
          type: number
          description: Percentage of non-null values
          default: 0.0
        missing_percentage:
          type: number
          description: Percentage of missing/null values
          default: 0.0
        negative_count:
          type: integer
          description: Number of negative values
          default: 0
        zero_count:
          type: integer
          description: Number of zero values
          default: 0
        positive_count:
          type: integer
          description: Number of positive values
          default: 0
      type: object
      required: []
      title: NumericQualityMetrics
    TextColumnStats:
      properties:
        column_name:
          type: string
          description: Name of the text column
          default: ''
        schema_analysis:
          $ref: '#/components/schemas/SchemaAnalysis'
        statistical_summary:
          $ref: '#/components/schemas/TextStatisticalSummary'
        quality_metrics:
          $ref: '#/components/schemas/TextQualityMetrics'
        performance_metadata:
          $ref: '#/components/schemas/PerformanceMetadata'
      type: object
      required: []
      title: TextColumnStats
    ProfileGeneration:
      properties:
        profile:
          $ref: '#/components/schemas/ColumnStats'
        join_suggestions:
          $ref: '#/components/schemas/JoinSuggestion'
      type: object
      required:
      - join_suggestions
      - profile
      title: ProfileGeneration
  securitySchemes:
    bearerAuth:
      type: http
      description: 'Primary credential. Authorization: Bearer mm_<token>. The token is issued server-side and shown once at creation.'
      scheme: bearer
    apiKey:
      type: apiKey
      description: Deprecated — use bearerAuth.
      name: X-API-KEY
      in: header
    apiSecret:
      type: apiKey
      description: Deprecated — use bearerAuth.
      name: X-API-SECRET
      in: header
    workspaceId:
      type: apiKey
      description: Required with X-API-KEY and X-API-SECRET. Deprecated with them — use bearerAuth.
      name: X-WORKSPACE-ID
      in: header
x-refined-from:
- app.mammoth.io-openapi.json
- mammoth-io-openapi.json