BigML Datasets API

openapi: 3.0.3
info:
  title: BigML REST Anomaly Detection Datasets API
  description: 'The BigML REST API provides programmatic access to the full BigML machine learning platform. Create and manage sources, datasets, models, ensembles, clusters, anomaly detectors, topic models, time series forecasters, deepnets, linear and logistic regression models, PCA, and generate predictions — both individual and batch — over HTTPS using username and API key authentication.

    '
  version: 1.0.0
  contact:
    name: BigML Support
    url: https://support.bigml.com/
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
  x-api-id: bigml:bigml-api
  x-provider: https://bigml.com/
servers:
- url: https://bigml.io/andromeda
  description: BigML production API (use username/api_key query params)
security:
- ApiKeyAuth: []
tags:
- name: Datasets
  description: Create and manage training datasets from sources
paths:
  /dataset:
    get:
      summary: List Datasets
      operationId: listDatasets
      tags:
      - Datasets
      parameters:
      - $ref: '#/components/parameters/username'
      - $ref: '#/components/parameters/apiKey'
      - $ref: '#/components/parameters/limit'
      - $ref: '#/components/parameters/offset'
      responses:
        '200':
          description: List of datasets
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListResponse'
    post:
      summary: Create a Dataset
      operationId: createDataset
      tags:
      - Datasets
      parameters:
      - $ref: '#/components/parameters/username'
      - $ref: '#/components/parameters/apiKey'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - source
              properties:
                source:
                  type: string
                  description: Source resource ID.
                name:
                  type: string
                size:
                  type: integer
                  description: Maximum number of rows.
      responses:
        '201':
          description: Dataset created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
  /dataset/{resource_id}:
    parameters:
    - $ref: '#/components/parameters/resourceId'
    - $ref: '#/components/parameters/username'
    - $ref: '#/components/parameters/apiKey'
    get:
      summary: Get a Dataset
      operationId: getDataset
      tags:
      - Datasets
      responses:
        '200':
          description: Dataset details
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
    put:
      summary: Update a Dataset
      operationId: updateDataset
      tags:
      - Datasets
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
      responses:
        '200':
          description: Dataset updated
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
    delete:
      summary: Delete a Dataset
      operationId: deleteDataset
      tags:
      - Datasets
      responses:
        '204':
          description: Dataset deleted
components:
  schemas:
    ResourceStatus:
      type: object
      properties:
        code:
          type: integer
          description: HTTP-style status code (1=queued,2=started,3=waiting,4=processing,5=finished,0=unknown,-1=failed)
        message:
          type: string
        elapsed:
          type: number
          description: Processing time in milliseconds.
    Dataset:
      allOf:
      - $ref: '#/components/schemas/ResourceBase'
      - type: object
        properties:
          source:
            type: string
            description: Source resource ID used to create this dataset.
          rows:
            type: integer
          columns:
            type: integer
          fields:
            type: object
            additionalProperties:
              type: object
    ResourceBase:
      type: object
      properties:
        resource:
          type: string
          description: Resource identifier (e.g., source/5f1a2b3c4d5e6f7890abcdef)
        created:
          type: string
          format: date-time
        updated:
          type: string
          format: date-time
        status:
          $ref: '#/components/schemas/ResourceStatus'
        name:
          type: string
        tags:
          type: array
          items:
            type: string
        private:
          type: boolean
    ListResponse:
      type: object
      properties:
        meta:
          type: object
          properties:
            limit:
              type: integer
            offset:
              type: integer
            total_count:
              type: integer
            previous:
              type: string
              nullable: true
            next:
              type: string
              nullable: true
        objects:
          type: array
          items:
            $ref: '#/components/schemas/ResourceBase'
  parameters:
    apiKey:
      name: api_key
      in: query
      required: true
      schema:
        type: string
      description: BigML API key.
    username:
      name: username
      in: query
      required: true
      schema:
        type: string
      description: BigML username.
    resourceId:
      name: resource_id
      in: path
      required: true
      schema:
        type: string
        pattern: ^[a-f0-9]{24}$
      description: The 24-character hexadecimal resource identifier.
    limit:
      name: limit
      in: query
      required: false
      schema:
        type: integer
        default: 20
        maximum: 1000
      description: Number of resources to return.
    offset:
      name: offset
      in: query
      required: false
      schema:
        type: integer
        default: 0
      description: Index of the first resource to return.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: query
      name: username
      description: 'Authenticate with username and api_key as query parameters. Example: ?username=myuser&api_key=a1b2c3...

        '
x-tagGroups:
- name: Data Management
  tags:
  - Sources
  - Datasets
  - Projects
  - Data Connectors
- name: Supervised Learning
  tags:
  - Models
  - Ensembles
  - Supervised Learning
  - Evaluations
  - Predictions
- name: Unsupervised Learning
  tags:
  - Clustering
  - Anomaly Detection
  - Unsupervised Learning
  - Time Series
- name: Batch Operations
  tags:
  - Batch Operations
- name: Automation
  tags:
  - WhizzML Scripting