electricsheepafrica/africa-ourairports-cog

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- aviation
- facilities-infrastructure
- geodata
- hxl
- transportation
- cog
pretty_name: "Airports in Congo-Brazzaville"
dataset_info:
splits:
- name: train
num_examples: 46
- name: test
num_examples: 11
---

# Airports in Congo-Brazzaville

**Publisher:** OurAirports · **Source:** [HDX](https://data.humdata.org/dataset/ourairports-cog) · **License:** `cc-by-igo` · **Updated:** 2026-02-01

---

## Abstract

List of airports in Congo-Brazzaville, with latitude and longitude. Unverified community data from http://ourairports.com/countries/CG/

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2026-02-01. Geographic scope: **COG**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 58 |
| **Columns** | 23 (7 numeric, 15 categorical, 0 datetime) |
| **Train split** | 46 rows |
| **Test split** | 11 rows |
| **Geographic scope** | COG |
| **Publisher** | OurAirports |
| **HDX last updated** | 2026-02-01 |

---

## Variables

**Geographic** — `type` (small_airport, medium_airport, large_airport), `latitude_deg` (range -4.816–3.2789), `longitude_deg` (range 11.3089–18.5144), `country_name` (Republic of the Congo, #country +name), `iso_country` (CG, #country +code +iso2) and 4 others.

**Temporal** — `last_updated`.

**Outcome / Measurement** — `score` (range 0.0–1000.0).

**Identifier / Metadata** — `id` (range 2868.0–595634.0), `ident` (#meta +code, CG-0003, LKC), `name` (#loc +airport +name, Mokabi Airport, Lekana Airport), `gps_code` (#loc +airport +code +gps, FCMR, FCMY), `icao_code` and 3 others.

**Other** — `elevation_ft` (range 39.0–2756.0), `continent` (AF, #region +continent +code), `scheduled_service` (range 0.0–1.0), `wikipedia_link`.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-ourairports-cog")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `id` | float64 | 1.7% | 2868.0 – 595634.0 (mean 75364.3509) |
| `ident` | object | 0.0% | #meta +code, CG-0003, LKC |
| `type` | object | 0.0% | small_airport, medium_airport, large_airport |
| `name` | object | 0.0% | #loc +airport +name, Mokabi Airport, Lekana Airport |
| `latitude_deg` | float64 | 1.7% | -4.816 – 3.2789 (mean -2.1287) |
| `longitude_deg` | float64 | 1.7% | 11.3089 – 18.5144 (mean 13.9512) |
| `elevation_ft` | float64 | 6.9% | 39.0 – 2756.0 (mean 1231.0185) |
| `continent` | object | 0.0% | AF, #region +continent +code |
| `country_name` | object | 0.0% | Republic of the Congo, #country +name |
| `iso_country` | object | 0.0% | CG, #country +code +iso2 |
| `region_name` | object | 0.0% | Niari Department, Cuvette Department, Likouala Department |
| `iso_region` | object | 0.0% | CG-9, CG-8, CG-7 |
| `local_region` | float64 | 1.7% | 2.0 – 14.0 (mean 8.8947) |
| `municipality` | object | 1.7% | #loc +municipality +name, Leganda, Loubetsi |
| `scheduled_service` | float64 | 1.7% | 0.0 – 1.0 (mean 0.0351) |
| `gps_code` | object | 13.8% | #loc +airport +code +gps, FCMR, FCMY |
| `icao_code` | object | 58.6% | |
| `iata_code` | object | 55.2% | |
| `wikipedia_link` | object | 56.9% | |
| `score` | float64 | 1.7% | 0.0 – 1000.0 (mean 100.8772) |
| `last_updated` | datetime64[ns, UTC] | 1.7% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 2868.0 | 595634.0 | 75364.3509 | 31096.0 |
| `latitude_deg` | -4.816 | 3.2789 | -2.1287 | -2.867 |
| `longitude_deg` | 11.3089 | 18.5144 | 13.9512 | 13.533 |
| `elevation_ft` | 39.0 | 2756.0 | 1231.0185 | 1195.5 |
| `local_region` | 2.0 | 14.0 | 8.8947 | 9.0 |
| `scheduled_service` | 0.0 | 1.0 | 0.0351 | 0.0 |
| `score` | 0.0 | 1000.0 | 100.8772 | 50.0 |

---

## Curation

Raw data was downloaded from HDX via the CKAN API and converted to Parquet. Column names were lowercased and standardised to snake_case. Common missing-value markers (`N/A`, `null`, `none`, `-`, `unknown`, `no data`, `#N/A`) were unified to `NaN`. 3 column(s) with >80% missing values were removed: `local_code`, `home_link`, `keywords`. 8 column(s) were cast from string to numeric or datetime based on parse-success rate (>85% threshold). The dataset was split 80/20 into train and test partitions using a fixed random seed (42) and saved as Snappy-compressed Parquet.

---

## Limitations

- Data originates from OurAirports and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- The following columns have >20% missing values and should be treated with caution in modelling: `icao_code`, `iata_code`, `wikipedia_link`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/ourairports-cog) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_ourairports_cog,
title = {Airports in Congo-Brazzaville},
author = {OurAirports},
year = {2026},
url = {https://data.humdata.org/dataset/ourairports-cog},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}
```

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — Africa's ML dataset infrastructure. Lagos, Nigeria.*