electricsheepafrica/africa-health-facilities-sudan

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- health-facilities
- hxl
- sdn
pretty_name: "Sudan Healthsites"
dataset_info:
splits:
- name: train
num_examples: 1140
- name: test
num_examples: 285
---

# Sudan Healthsites

**Publisher:** Global Healthsites Mapping Project · **Source:** [HDX](https://data.humdata.org/dataset/sudan-healthsites) · **License:** `ODbL` · **Updated:** 2025-10-15

---

## Abstract

This dataset shows the list of operating health facilities. Attributes included: Name,Nature of Facility, Activities, Lat, Long

Each row in this dataset represents tabular records. Data was last updated on HDX on 2025-10-15. Geographic scope: **SDN**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 1,425 |
| **Columns** | 15 (6 numeric, 8 categorical, 0 datetime) |
| **Train split** | 1,140 rows |
| **Test split** | 285 rows |
| **Geographic scope** | SDN |
| **Publisher** | Global Healthsites Mapping Project |
| **HDX last updated** | 2025-10-15 |

---

## Variables

**Geographic** — `x` (range 22.1589–37.2254), `y` (range 9.9746–20.7487), `osm_type` (node, way), `amenity` (pharmacy, hospital, clinic).

**Temporal** — `changeset_timestamp`.

**Identifier / Metadata** — `osm_id` (range 5773443.0–13186644832.0), `name` (صيدلية علياء, المركز الصحي, صيدلية الاول), `changeset_id` (range 15833692.0–173157154.0), `uuid` (87ceb4cfc61c4a01829fb323b0a4f63f, 9b52124e8d4244f2b645a065a8d677f1, 956454c5449842519512f6fc5724dce5), `esa_source` (HDX) and 1 others.

**Other** — `completeness` (range 6.25–31.25), `healthcare` (pharmacy, hospital, clinic), `dispensing` (yes, no), `changeset_version` (range 1.0–10.0).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-health-facilities-sudan")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `x` | float64 | 21.3% | 22.1589 – 37.2254 (mean 32.3614) |
| `y` | float64 | 21.3% | 9.9746 – 20.7487 (mean 15.4739) |
| `osm_id` | int64 | 0.0% | 5773443.0 – 13186644832.0 (mean 5609771368.5242) |
| `osm_type` | object | 0.0% | node, way |
| `completeness` | float64 | 0.0% | 6.25 – 31.25 (mean 12.7697) |
| `amenity` | object | 0.9% | pharmacy, hospital, clinic |
| `healthcare` | object | 38.7% | pharmacy, hospital, clinic |
| `name` | object | 5.3% | صيدلية علياء, المركز الصحي, صيدلية الاول |
| `dispensing` | object | 77.4% | yes, no |
| `changeset_id` | int64 | 0.0% | 15833692.0 – 173157154.0 (mean 99357921.047) |
| `changeset_version` | int64 | 0.0% | 1.0 – 10.0 (mean 1.7361) |
| `changeset_timestamp` | datetime64[ns, UTC] | 0.0% | |
| `uuid` | object | 0.0% | 87ceb4cfc61c4a01829fb323b0a4f63f, 9b52124e8d4244f2b645a065a8d677f1, 956454c5449842519512f6fc5724dce5 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-20 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `x` | 22.1589 | 37.2254 | 32.3614 | 32.5302 |
| `y` | 9.9746 | 20.7487 | 15.4739 | 15.5989 |
| `osm_id` | 5773443.0 | 13186644832.0 | 5609771368.5242 | 6833721514.0 |
| `completeness` | 6.25 | 31.25 | 12.7697 | 12.5 |
| `changeset_id` | 15833692.0 | 173157154.0 | 99357921.047 | 80090679.0 |
| `changeset_version` | 1.0 | 10.0 | 1.7361 | 1.0 |

---

## 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`. 22 column(s) with >80% missing values were removed: `operator`, `source`, `speciality`, `operator_type`, `operational_status`, `opening_hours`.... 1 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 Global Healthsites Mapping Project 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: `x`, `y`, `healthcare`, `dispensing`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/sudan-healthsites) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_health_facilities_sudan,
title = {Sudan Healthsites},
author = {Global Healthsites Mapping Project},
year = {2025},
url = {https://data.humdata.org/dataset/sudan-healthsites},
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.*