{
  "@context": {
    "@language": "en",
    "@vocab": "https://schema.org/",
    "citeAs": "cr:citeAs",
    "column": "cr:column",
    "conformsTo": "dct:conformsTo",
    "cr": "http://mlcommons.org/croissant/",
    "rai": "http://mlcommons.org/croissant/RAI/",
    "data": {
      "@id": "cr:data",
      "@type": "@json"
    },
    "dataType": {
      "@id": "cr:dataType",
      "@type": "@vocab"
    },
    "dct": "http://purl.org/dc/terms/",
    "equivalentProperty": "cr:equivalentProperty",
    "examples": {
      "@id": "cr:examples",
      "@type": "@json"
    },
    "extract": "cr:extract",
    "field": "cr:field",
    "fileProperty": "cr:fileProperty",
    "fileObject": "cr:fileObject",
    "fileSet": "cr:fileSet",
    "format": "cr:format",
    "includes": "cr:includes",
    "isLiveDataset": "cr:isLiveDataset",
    "jsonPath": "cr:jsonPath",
    "key": "cr:key",
    "md5": "cr:md5",
    "parentField": "cr:parentField",
    "path": "cr:path",
    "recordSet": "cr:recordSet",
    "references": "cr:references",
    "regex": "cr:regex",
    "repeated": "cr:repeated",
    "replace": "cr:replace",
    "samplingRate": "cr:samplingRate",
    "sc": "https://schema.org/",
    "separator": "cr:separator",
    "source": "cr:source",
    "subField": "cr:subField",
    "transform": "cr:transform"
  },
  "@type": "sc:Dataset",
  "conformsTo": "http://mlcommons.org/croissant/1.0",
  "name": "LFS occupation coding (example)",
  "description": "Job descriptions from the labour force survey with ISCO-08 codes assigned by trained coders, for training and evaluating automatic occupation coders.",
  "url": "https://stats.example/datasets/lfs-occupation-ml",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "version": "1.0.0",
  "datePublished": "2026-10-09",
  "citeAs": "National Statistics Office (example). 2026. LFS occupation coding (example), version 1.0.0. https://stats.example/datasets/lfs-occupation-ml",
  "creator": {
    "@type": "Organization",
    "name": "National Statistics Office (example)"
  },
  "distribution": [
    {
      "@type": "cr:FileObject",
      "@id": "data-file",
      "name": "lfs_occupation_ml.csv",
      "description": "The data, one record per row.",
      "contentUrl": "lfs_occupation_ml.csv",
      "encodingFormat": "text/csv",
      "sha256": "e6b0b1fd6a3230680e3598208f4c08b1b25e41873cc0d050009bd6f858264972"
    },
    {
      "@type": "cr:FileObject",
      "@id": "splits-file",
      "name": "splits.csv",
      "description": "The split assignment, one row per record.",
      "contentUrl": "splits.csv",
      "encodingFormat": "text/csv",
      "sha256": "bbd83fc32f8f6d7fb90ae1195140e0cc934945e813c209153915736f80a08ce6"
    }
  ],
  "recordSet": [
    {
      "@type": "cr:RecordSet",
      "@id": "records",
      "name": "records",
      "description": "One record per row of lfs_occupation_ml.csv.",
      "key": {
        "@id": "records/record_id"
      },
      "field": [
        {
          "@type": "cr:Field",
          "@id": "records/record_id",
          "name": "records/record_id",
          "description": "Unique identifier of the record; no meaning Role: id.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "record_id"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/hhid",
          "name": "records/hhid",
          "description": "Identifier of the household the person belongs to; records of one household must stay in one split Role: group.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "hhid"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/region",
          "name": "records/region",
          "description": "Region of residence: R01 Northern, R02 Central, R03 Southern, R04 Eastern Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "region"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/urban",
          "name": "records/urban",
          "description": "1 urban, 0 rural Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "urban"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/sex",
          "name": "records/sex",
          "description": "1 male, 2 female Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "sex"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/age_group",
          "name": "records/age_group",
          "description": "15-24, 25-54, 55-64 Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "age_group"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/educ",
          "name": "records/educ",
          "description": "ISCED 2011 level 0 to 5 (6 and above collapsed into 5) Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "educ"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/job_title",
          "name": "records/job_title",
          "description": "The respondent's description of their main job, as recorded by the interviewer Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "job_title"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/industry_text",
          "name": "records/industry_text",
          "description": "The respondent's description of the activity of the establishment Role: feature.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "industry_text"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/isco_code",
          "name": "records/isco_code",
          "description": "ISCO-08 unit group (four digits) assigned by a trained coder; the label to predict Role: label.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "isco_code"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/isco_major",
          "name": "records/isco_major",
          "description": "First digit of isco_code; a coarser label Role: label.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "isco_major"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "records/weight",
          "name": "records/weight",
          "description": "Person weight calibrated to the population; use for population estimates, never as a training sample weight without a stated reason Role: weight.",
          "dataType": "sc:Float",
          "source": {
            "fileObject": {
              "@id": "data-file"
            },
            "extract": {
              "column": "weight"
            }
          }
        }
      ]
    },
    {
      "@type": "cr:RecordSet",
      "@id": "split_names",
      "name": "split_names",
      "description": "The named splits of the dataset.",
      "dataType": "cr:Split",
      "key": {
        "@id": "split_names/name"
      },
      "field": [
        {
          "@type": "cr:Field",
          "@id": "split_names/name",
          "name": "name",
          "description": "The split name.",
          "dataType": "sc:Text"
        }
      ],
      "data": [
        {
          "split_names/name": "test"
        },
        {
          "split_names/name": "train"
        },
        {
          "split_names/name": "validation"
        }
      ]
    },
    {
      "@type": "cr:RecordSet",
      "@id": "record_splits",
      "name": "record_splits",
      "description": "The split of each record, joined on the record identifier.",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "record_splits/record",
          "name": "record_splits/record",
          "description": "The record identifier.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "splits-file"
            },
            "extract": {
              "column": "record_id"
            }
          },
          "references": {
            "field": {
              "@id": "records/record_id"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "record_splits/split",
          "name": "record_splits/split",
          "description": "The split name.",
          "dataType": "sc:Text",
          "source": {
            "fileObject": {
              "@id": "splits-file"
            },
            "extract": {
              "column": "split"
            }
          },
          "references": {
            "field": {
              "@id": "split_names/name"
            }
          }
        }
      ]
    }
  ]
}