electricsheepafrica/africa-mrt-settlements

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- geodata
- populated-places-settlements
- mrt
pretty_name: "Mauritania: Settlements"
dataset_info:
splits:
- name: train
num_examples: 8840
- name: test
num_examples: 2210
---

# Mauritania: Settlements

**Publisher:** OCHA West and Central Africa (ROWCA) · **Source:** [HDX](https://data.humdata.org/dataset/mrt-settlements) · **License:** `cc-by-igo` · **Updated:** 2025-04-25

---

## Abstract

Admin COD datasets for Mauritania endorsed by RO on October 2015; see metadata for description of cleaning and processing performed by ITOS.

Each row in this dataset represents tabular records. Data was last updated on HDX on 2025-04-25. Geographic scope: **MRT**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 11,051 |
| **Columns** | 7 (0 numeric, 7 categorical, 0 datetime) |
| **Train split** | 8,840 rows |
| **Test split** | 2,210 rows |
| **Geographic scope** | MRT |
| **Publisher** | OCHA West and Central Africa (ROWCA) |
| **HDX last updated** | 2025-04-25 |

---

## Variables

**Identifier / Metadata** — `unnamed_0` (Adrar, Tiris-Zemmour, Hodh Ech Chargi), `unnamed_1` (F'Derik, Atar, Ouadane), `unnamed_2` (Fderik 2, Ouadane 2, Oualata 2), `unnamed_3` (El Mabrouk, El Mraifig, Bou Derga), `unnamed_4` (<Null>, Admin2 Capital, Admin1 Capital) and 2 others.

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `unnamed_0` | object | 0.0% | Adrar, Tiris-Zemmour, Hodh Ech Chargi |
| `unnamed_1` | object | 0.0% | F'Derik, Atar, Ouadane |
| `unnamed_2` | object | 0.0% | Fderik 2, Ouadane 2, Oualata 2 |
| `unnamed_3` | object | 0.0% | El Mabrouk, El Mraifig, Bou Derga |
| `unnamed_4` | object | 0.0% | <Null>, Admin2 Capital, Admin1 Capital |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-17 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
_No numeric columns._

---

## 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.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/mrt-settlements) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_mrt_settlements,
title = {Mauritania: Settlements},
author = {OCHA West and Central Africa (ROWCA)},
year = {2025},
url = {https://data.humdata.org/dataset/mrt-settlements},
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.*