how many geographic locations are present in NMDC Biosamples?

[turbomam]

[
  {
    "$match": {
      "geo_loc_name_has_raw_value": { "$exists": true, "$ne": null, "$ne": "" }
    }
  },
  {
    "$unwind": {
      "path": "$geo_loc_name_has_raw_value",
      "preserveNullAndEmptyArrays": false
    }
  },
  {
    "$group": {
      "_id": "$geo_loc_name_has_raw_value",
      "count": { "$sum": 1 }
    }
  },
  {
    "$project": {
      "_id": 0,
      "geo_loc_name_has_raw_value": "$_id",
      "count": 1
    }
  },
  { "$sort": { "count": -1 } }
]

[turbomam]

411

~ 320 with a count > 1