datafair.cloud

{
  "type": "object",
  "properties": {
    "datasetId": {
      "type": "string",
      "description": "The exact dataset ID from the \"id\" field in list_datasets results. Do not use the title or slug."
    },
    "fieldKey": {
      "type": "string",
      "description": "The column key to calculate the metric on (use keys from describe_dataset)"
    },
    "metric": {
      "type": "string",
      "description": "Metric to calculate. Available: avg, sum, min, max (for numbers); min, max, cardinality, value_count (for strings); value_count (for others); stats returns count/min/max/avg/sum; percentiles returns distribution."
    },
    "percents": {
      "type": "string",
      "description": "Comma-separated percentages for percentiles metric (default: \"1,5,25,50,75,95,99\"). Only used when metric is \"percentiles\"."
    },
    "filters": {
      "type": "object",
      "description": "Column filters as key-value pairs: column_key + suffix, all values strings. Example: { \"ville_eq\": \"Paris\", \"age_lte\": \"30\", \"nom_search\": \"Jean\" }. Suffixes include _eq, _in, _gt/_lt, _search and more; if one is rejected the 400 error lists what the column supports. Never _c_-prefix a column filter (use ville_eq, not _c_ville_eq).",
      "properties": {}
    },
    "bbox": {
      "type": "string",
      "description": "Bounding box \"lonMin,latMin,lonMax,latMax\" (lon before lat), e.g. \"-2.5,43,3,47\". Geolocalized datasets only."
    },
    "geoDistance": {
      "type": "string",
      "description": "Proximity filter \"lon,lat,distance\" (lon first), e.g. \"2.35,48.85,10km\"; distance \"0\" = point-in-polygon. Geolocalized datasets only."
    },
    "dateMatch": {
      "type": "string",
      "description": "Date \"YYYY-MM-DD\" (single day) or \"YYYY-MM-DD,YYYY-MM-DD\" (range), e.g. \"2023-11-21\". Temporal datasets only."
    }
  },
  "required": [
    "datasetId",
    "fieldKey",
    "metric"
  ]
}