electricsheepafrica/africa-health-facilities-uganda

---
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
- uga
pretty_name: "Uganda Healthsites"
dataset_info:
splits:
- name: train
num_examples: 6404
- name: test
num_examples: 1601
---

# Uganda Healthsites

**Publisher:** Global Healthsites Mapping Project · **Source:** [HDX](https://data.humdata.org/dataset/uganda-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: **UGA**.

*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)** | 8,005 |
| **Columns** | 14 (6 numeric, 7 categorical, 0 datetime) |
| **Train split** | 6,404 rows |
| **Test split** | 1,601 rows |
| **Geographic scope** | UGA |
| **Publisher** | Global Healthsites Mapping Project |
| **HDX last updated** | 2025-10-15 |

---

## Variables

**Geographic** — `x` (range 29.5836–34.9951), `y` (range -1.4585–3.8747), `osm_type` (node, way), `loc_amenity` (clinic, hospital, doctors).

**Temporal** — `changeset_timestamp`.

**Identifier / Metadata** — `osm_id` (range 44507617.0–13234094864.0), `loc_name` (HEALTH CENTRE II, HEALTH CENTRE III, HEALTH CENTRE), `changeset_id` (range 3085046.0–173307262.0), `meta_id` (b1921e5556de4f58a65a8ef207213762, f478e113ebf640b0a4b831b355e88488, e4c9f2dc48db4c5090524d04cf24172d), `esa_source` (HDX) and 1 others.

**Other** — `completeness` (range 6.25–50.0), `geo_bounds_url` (Uganda Bureau of Statistics, Makerere University, Department of Geography, HOT-Uganda), `changeset_version` (range 1.0–19.0).

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `x` | float64 | 6.5% | 29.5836 – 34.9951 (mean 32.1522) |
| `y` | float64 | 6.5% | -1.4585 – 3.8747 (mean 0.9736) |
| `osm_id` | int64 | 0.0% | 44507617.0 – 13234094864.0 (mean 7980362365.6266) |
| `osm_type` | object | 0.0% | node, way |
| `completeness` | float64 | 0.0% | 6.25 – 50.0 (mean 14.1607) |
| `loc_amenity` | object | 0.5% | clinic, hospital, doctors |
| `loc_name` | object | 6.1% | HEALTH CENTRE II, HEALTH CENTRE III, HEALTH CENTRE |
| `geo_bounds_url` | object | 77.3% | Uganda Bureau of Statistics, Makerere University, Department of Geography, HOT-Uganda |
| `changeset_id` | int64 | 0.0% | 3085046.0 – 173307262.0 (mean 109400246.9284) |
| `changeset_version` | int64 | 0.0% | 1.0 – 19.0 (mean 1.5919) |
| `changeset_timestamp` | datetime64[ns, UTC] | 0.0% | |
| `meta_id` | object | 0.0% | b1921e5556de4f58a65a8ef207213762, f478e113ebf640b0a4b831b355e88488, e4c9f2dc48db4c5090524d04cf24172d |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-20 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `x` | 29.5836 | 34.9951 | 32.1522 | 32.5253 |
| `y` | -1.4585 | 3.8747 | 0.9736 | 0.5407 |
| `osm_id` | 44507617.0 | 13234094864.0 | 7980362365.6266 | 9909142405.0 |
| `completeness` | 6.25 | 50.0 | 14.1607 | 12.5 |
| `changeset_id` | 3085046.0 | 173307262.0 | 109400246.9284 | 132580931.0 |
| `changeset_version` | 1.0 | 19.0 | 1.5919 | 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`. 23 column(s) with >80% missing values were removed: `meta_healthcare`, `meta_operator`, `meta_speciality`, `meta_operator_type`, `contact_phone`, `status_operational_status`.... 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: `geo_bounds_url`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/uganda-healthsites) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_health_facilities_uganda,
title = {Uganda Healthsites},
author = {Global Healthsites Mapping Project},
year = {2025},
url = {https://data.humdata.org/dataset/uganda-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.*