electricsheepafrica/africa-west-and-central-africa-administrative-boundaries-levels

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- central-africa
- geodata
- populated-places-settlements
- west-africa
- ben
- bfa
- cpv
- cmr
- caf
pretty_name: "West and Central Africa - Administrative boundaries levels 0 - 2 and Settlements"
dataset_info:
splits:
- name: train
num_examples: 1884
- name: test
num_examples: 471
---

# West and Central Africa - Administrative boundaries levels 0 - 2 and Settlements

**Publisher:** OCHA West and Central Africa (ROWCA) · **Source:** [HDX](https://data.humdata.org/dataset/west-and-central-africa-administrative-boundaries-levels) · **License:** `cc-by` · **Updated:** 2025-05-05

---

## Abstract

West and Central Africa Administrative boundaries, administrative level 0 to 2. Notice: The boundaries and names shown and the designations used on these shapefiles do not imply official endorsement or acceptance by the United Nations.
West and Central Africa settlements with administrative capitals

Each row in this dataset represents subnational administrative unit observations. Temporal coverage is indicated by the `last_modif`, `date` column(s). Geographic scope: **BEN, BFA, CPV, CMR, CAF, TCD, COG, CIV, and 16 others**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 2,355 |
| **Columns** | 14 (3 numeric, 9 categorical, 2 datetime) |
| **Train split** | 1,884 rows |
| **Test split** | 471 rows |
| **Geographic scope** | BEN, BFA, CPV, CMR, CAF, TCD, COG, CIV, and 16 others |
| **Publisher** | OCHA West and Central Africa (ROWCA) |
| **HDX last updated** | 2025-05-05 |

---

## Variables

**Geographic** — `admin0name` (Nigeria, Ghana, Democratic Republic of Congo), `admin0pcod` (NG, GH, CD), `admin1name` (Kano, Ashanti, Eastern), `admin2name` (Sao Joao Baptista, Nossa Senhora Da Luz, Dagana), `admin1pcod` (NG20, GH02, NG21) and 1 others.

**Temporal** — `date`.

**Identifier / Metadata** — `objectid_1` (range 1.0–2356.0), `source` (OCHAfrom ctrylayers), `esa_source` (HDX), `esa_processed` (2026-04-08).

**Other** — `last_modif`, `shape_leng` (range 0.0462–26.1063), `shape_area` (range 0.0001–28.8161).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-west-and-central-africa-administrative-boundaries-levels")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `objectid_1` | int64 | 0.0% | 1.0 – 2356.0 (mean 1178.6025) |
| `admin0name` | object | 0.0% | Nigeria, Ghana, Democratic Republic of Congo |
| `admin0pcod` | object | 0.0% | NG, GH, CD |
| `admin1name` | object | 0.0% | Kano, Ashanti, Eastern |
| `admin2name` | object | 0.0% | Sao Joao Baptista, Nossa Senhora Da Luz, Dagana |
| `admin1pcod` | object | 0.0% | NG20, GH02, NG21 |
| `admin2pcod` | object | 0.0% | CD10, CI0903, LR0402 |
| `last_modif` | datetime64[ns] | 0.0% | |
| `source` | object | 0.0% | OCHAfrom ctrylayers |
| `date` | datetime64[ns] | 0.0% | |
| `shape_leng` | float64 | 0.0% | 0.0462 – 26.1063 (mean 2.5904) |
| `shape_area` | float64 | 0.0% | 0.0001 – 28.8161 (mean 0.4021) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `objectid_1` | 1.0 | 2356.0 | 1178.6025 | 1179.0 |
| `shape_leng` | 0.0462 | 26.1063 | 2.5904 | 1.777 |
| `shape_area` | 0.0001 | 28.8161 | 0.4021 | 0.1037 |

---

## 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`. 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 OCHA West and Central Africa (ROWCA) and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- This dataset spans 24 countries; geographic and methodological inconsistencies across national boundaries may affect cross-country comparability.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/west-and-central-africa-administrative-boundaries-levels) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_west_and_central_africa_administrative_boundaries_levels,
title = {West and Central Africa - Administrative boundaries levels 0 - 2 and Settlements},
author = {OCHA West and Central Africa (ROWCA)},
year = {2025},
url = {https://data.humdata.org/dataset/west-and-central-africa-administrative-boundaries-levels},
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.*