BigML Resource

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/bigml/main/json-schema/bigml-resource.json",
  "title": "BigML Resource",
  "description": "Base schema for all BigML API resources.",
  "type": "object",
  "properties": {
    "resource": {
      "type": "string",
      "description": "Fully-qualified resource identifier, e.g. 'source/5f1a2b3c4d5e6f7890abcdef'.",
      "pattern": "^[a-z]+/[a-f0-9]{24}$"
    },
    "created": {
      "type": "string",
      "format": "date-time",
      "description": "ISO 8601 timestamp when the resource was created."
    },
    "updated": {
      "type": "string",
      "format": "date-time",
      "description": "ISO 8601 timestamp when the resource was last updated."
    },
    "name": {
      "type": "string",
      "description": "Human-readable name for the resource."
    },
    "private": {
      "type": "boolean",
      "description": "Whether the resource is private (true) or public/shared (false).",
      "default": true
    },
    "tags": {
      "type": "array",
      "description": "List of user-defined tags.",
      "items": {
        "type": "string"
      }
    },
    "status": {
      "$ref": "#/$defs/ResourceStatus"
    }
  },
  "required": ["resource", "created", "updated", "status"],
  "$defs": {
    "ResourceStatus": {
      "type": "object",
      "title": "ResourceStatus",
      "description": "Processing status of a BigML resource.",
      "properties": {
        "code": {
          "type": "integer",
          "description": "Status code: 1=queued, 2=started, 3=waiting, 4=processing, 5=finished, 0=unknown, -1=failed.",
          "enum": [-1, 0, 1, 2, 3, 4, 5]
        },
        "message": {
          "type": "string",
          "description": "Human-readable status message."
        },
        "elapsed": {
          "type": "number",
          "description": "Processing time in milliseconds.",
          "minimum": 0
        },
        "progress": {
          "type": "number",
          "description": "Processing progress from 0.0 to 1.0.",
          "minimum": 0,
          "maximum": 1
        }
      },
      "required": ["code", "message"]
    },
    "Source": {
      "allOf": [
        {"$ref": "#"},
        {
          "title": "Source",
          "description": "A BigML data source created from a file upload, URL, or inline data.",
          "properties": {
            "file_name": {
              "type": "string",
              "description": "Name of the uploaded file."
            },
            "size": {
              "type": "integer",
              "description": "File size in bytes.",
              "minimum": 0
            },
            "rows": {
              "type": "integer",
              "description": "Number of rows in the source.",
              "minimum": 0
            },
            "columns": {
              "type": "integer",
              "description": "Number of columns in the source.",
              "minimum": 0
            },
            "fields": {
              "type": "object",
              "description": "Map of field IDs to field metadata.",
              "additionalProperties": {
                "$ref": "#/$defs/FieldMetadata"
              }
            },
            "source_parser": {
              "type": "object",
              "description": "Parsing configuration (separator, header, encoding, etc.).",
              "properties": {
                "separator": {"type": "string"},
                "header": {"type": "boolean"},
                "encoding": {"type": "string"},
                "missing_tokens": {
                  "type": "array",
                  "items": {"type": "string"}
                }
              }
            }
          }
        }
      ]
    },
    "Dataset": {
      "allOf": [
        {"$ref": "#"},
        {
          "title": "Dataset",
          "description": "A BigML dataset derived from a source, suitable for training ML models.",
          "properties": {
            "source": {
              "type": "string",
              "description": "Source resource ID used to create this dataset.",
              "pattern": "^source/[a-f0-9]{24}$"
            },
            "rows": {
              "type": "integer",
              "description": "Number of rows in the dataset.",
              "minimum": 0
            },
            "columns": {
              "type": "integer",
              "description": "Number of columns.",
              "minimum": 0
            },
            "fields": {
              "type": "object",
              "additionalProperties": {
                "$ref": "#/$defs/FieldMetadata"
              }
            }
          }
        }
      ]
    },
    "FieldMetadata": {
      "type": "object",
      "title": "FieldMetadata",
      "description": "Metadata for a single field (column) in a source or dataset.",
      "properties": {
        "name": {
          "type": "string",
          "description": "Field name as it appears in the original data."
        },
        "optype": {
          "type": "string",
          "description": "Operational type of the field.",
          "enum": ["categorical", "numeric", "text", "items", "datetime", "image"]
        },
        "column_number": {
          "type": "integer",
          "description": "Zero-based column index."
        },
        "missing_count": {
          "type": "integer",
          "description": "Number of missing values.",
          "minimum": 0
        },
        "summary": {
          "type": "object",
          "description": "Statistical summary of the field (min, max, mean, median, etc.)."
        }
      },
      "required": ["name", "optype"]
    },
    "Prediction": {
      "allOf": [
        {"$ref": "#"},
        {
          "title": "Prediction",
          "description": "A single prediction generated by a BigML model.",
          "properties": {
            "model": {
              "type": "string",
              "description": "Resource ID of the model, ensemble, deepnet, or regression used."
            },
            "input_data": {
              "type": "object",
              "description": "Map of field names or IDs to input values."
            },
            "output": {
              "type": "string",
              "description": "Name of the predicted field."
            },
            "prediction": {
              "type": "object",
              "description": "Prediction result, keyed by field name, with confidence or probability."
            },
            "confidence": {
              "type": "number",
              "description": "Confidence score for the prediction (0.0–1.0).",
              "minimum": 0,
              "maximum": 1
            }
          }
        }
      ]
    },
    "ListResponse": {
      "type": "object",
      "title": "ListResponse",
      "description": "Paginated list response for any BigML resource collection.",
      "properties": {
        "meta": {
          "type": "object",
          "properties": {
            "limit": {
              "type": "integer",
              "description": "Number of resources per page."
            },
            "offset": {
              "type": "integer",
              "description": "Index of the first resource in this page."
            },
            "total_count": {
              "type": "integer",
              "description": "Total number of matching resources."
            },
            "previous": {
              "type": ["string", "null"],
              "description": "URL for the previous page, or null."
            },
            "next": {
              "type": ["string", "null"],
              "description": "URL for the next page, or null."
            }
          },
          "required": ["limit", "offset", "total_count"]
        },
        "objects": {
          "type": "array",
          "description": "Array of resource objects.",
          "items": {"$ref": "#"}
        }
      },
      "required": ["meta", "objects"]
    }
  }
}