{
  "@context": {
    "@language": "en",
    "@vocab": "https://schema.org/",
    "citeAs": "cr:citeAs",
    "column": "cr:column",
    "conformsTo": "dct:conformsTo",
    "cr": "http://mlcommons.org/croissant/",
    "data": {
      "@id": "cr:data",
      "@type": "@json"
    },
    "dataType": {
      "@id": "cr:dataType",
      "@type": "@vocab"
    },
    "dct": "http://purl.org/dc/terms/",
    "extract": "cr:extract",
    "field": "cr:field",
    "fileObject": "cr:fileObject",
    "fileProperty": "cr:fileProperty",
    "format": "cr:format",
    "includes": "cr:includes",
    "isLiveDataset": "cr:isLiveDataset",
    "key": "cr:key",
    "md5": "cr:md5",
    "parentField": "cr:parentField",
    "path": "cr:path",
    "recordSet": "cr:recordSet",
    "references": "cr:references",
    "repeated": "cr:repeated",
    "sc": "https://schema.org/",
    "sha256": "sha256",
    "source": "cr:source",
    "subField": "cr:subField"
  },
  "@type": "sc:Dataset",
  "citeAs": null,
  "conformsTo": "http://mlcommons.org/croissant/1.0",
  "creator": [],
  "description": "Harvard Dataverse NIR spectra of Plasmodium falciparum infected Anopheles gambiae. Origin database composed from 2 standardized v2.0 leaves: 1 spectral source(s), 1 declared target(s). Auto-generated from dataset_card.json (verify before publication).\n\nOpen tier: freely usable and redistributable under the stated license.",
  "distribution": [
    {
      "@id": "file/X.parquet",
      "@type": "cr:FileObject",
      "encodingFormat": "application/vnd.apache.parquet",
      "name": "malaria_nir",
      "sha256": "63a5380ef99c4557431f14374eae2cb46c5a59e7bea70a542dbe77cce8404109"
    },
    {
      "@id": "file/variables.parquet",
      "@type": "cr:FileObject",
      "encodingFormat": "application/vnd.apache.parquet",
      "name": "variables",
      "sha256": "5ddef04fd28a11913c0904cf1eb86fa73f5aa33b43067d7d4ffebd5f6522570a"
    }
  ],
  "keywords": [
    "nir",
    "v2",
    "harvard"
  ],
  "license": "CC-BY-4.0",
  "name": "harvard_dataverse_malaria_anopheles_gambiae_nir",
  "recordSet": [
    {
      "@id": "X",
      "@type": "cr:RecordSet",
      "description": "Spectra from source 'malaria_nir' (562 observations x 2151 wavelengths).",
      "field": [
        {
          "@id": "X/observation_id",
          "@type": "cr:Field",
          "dataType": "sc:Text",
          "description": "Unique acquisition identity within this spectral source.",
          "name": "observation_id",
          "source": {
            "extract": {
              "column": "observation_id"
            },
            "fileObject": {
              "@id": "file/X.parquet"
            }
          }
        },
        {
          "@id": "X/sample_id",
          "@type": "cr:Field",
          "dataType": "sc:Text",
          "description": "Source-unit grouping (may repeat; availability documented in the card).",
          "name": "sample_id",
          "source": {
            "extract": {
              "column": "sample_id"
            },
            "fileObject": {
              "@id": "file/X.parquet"
            }
          }
        },
        {
          "@id": "X/spectrum",
          "@type": "cr:Field",
          "dataType": "sc:Float",
          "description": "Spectral intensities across the none axis.",
          "name": "spectrum",
          "repeated": true,
          "source": {
            "fileObject": {
              "@id": "file/X.parquet"
            }
          }
        }
      ],
      "key": {
        "@id": "X/observation_id"
      },
      "name": "X"
    },
    {
      "@id": "variables",
      "@type": "cr:RecordSet",
      "description": "Target and metadata variables keyed by sample_id.",
      "field": [
        {
          "@id": "variables/sample_id",
          "@type": "cr:Field",
          "dataType": "sc:Text",
          "description": "Sample identity (join key).",
          "name": "sample_id",
          "source": {
            "extract": {
              "column": "sample_id"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/parasite_load",
          "@type": "cr:Field",
          "dataType": "sc:Float",
          "description": "Variable 'parasite_load' (role target, type numeric).",
          "name": "parasite_load",
          "source": {
            "extract": {
              "column": "parasite_load"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/ID1",
          "@type": "cr:Field",
          "dataType": "sc:Integer",
          "description": "Variable 'ID1' (role metadata, type categorical).",
          "name": "ID1",
          "source": {
            "extract": {
              "column": "ID1"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/ID2",
          "@type": "cr:Field",
          "dataType": "sc:Float",
          "description": "Variable 'ID2' (role metadata, type numeric).",
          "name": "ID2",
          "source": {
            "extract": {
              "column": "ID2"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/ID",
          "@type": "cr:Field",
          "dataType": "sc:Integer",
          "description": "Variable 'ID' (role metadata, type categorical).",
          "name": "ID",
          "source": {
            "extract": {
              "column": "ID"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/Oocytes",
          "@type": "cr:Field",
          "dataType": "sc:Float",
          "description": "Variable 'Oocytes' (role metadata, type numeric).",
          "name": "Oocytes",
          "source": {
            "extract": {
              "column": "Oocytes"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/active_status",
          "@type": "cr:Field",
          "dataType": "sc:Integer",
          "description": "Variable 'active_status' (role metadata, type categorical).",
          "name": "active_status",
          "source": {
            "extract": {
              "column": "active_status"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/replaces_dataset_id",
          "@type": "cr:Field",
          "dataType": "sc:Integer",
          "description": "Variable 'replaces_dataset_id' (role metadata, type categorical).",
          "name": "replaces_dataset_id",
          "source": {
            "extract": {
              "column": "replaces_dataset_id"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/active_replacement_source_note",
          "@type": "cr:Field",
          "dataType": "sc:Integer",
          "description": "Variable 'active_replacement_source_note' (role metadata, type categorical).",
          "name": "active_replacement_source_note",
          "source": {
            "extract": {
              "column": "active_replacement_source_note"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        },
        {
          "@id": "variables/infection_stage",
          "@type": "cr:Field",
          "dataType": "sc:Integer",
          "description": "Variable 'infection_stage' (role metadata, type categorical).",
          "name": "infection_stage",
          "source": {
            "extract": {
              "column": "infection_stage"
            },
            "fileObject": {
              "@id": "file/variables.parquet"
            }
          }
        }
      ],
      "key": {
        "@id": "variables/sample_id"
      },
      "name": "variables"
    }
  ],
  "sameAs": [
    "10.7910/DVN/YD34OX"
  ],
  "url": "https://entrepot.recherche.data.gouv.fr",
  "version": "1.1.0"
}