electricsheepafrica/africa-sierra-leone-health-sites

---
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
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- health
- health-facilities
- sle
pretty_name: "Sierra Leone Healthsites"
dataset_info:
splits:
- name: train
num_examples: 1384
- name: test
num_examples: 346
---

# Sierra Leone Healthsites

**Publisher:** Global Healthsites Mapping Project · **Source:** [HDX](https://data.humdata.org/dataset/sierra-leone-health-sites) · **License:** `other-pd-nr` · **Updated:** 2025-04-25

---

## Abstract

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

Each row in this dataset represents facility or site records. Data was last updated on HDX on 2025-04-25. Geographic scope: **SLE**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Facility or site records |
| **Rows (total)** | 1,731 |
| **Columns** | 13 (2 numeric, 11 categorical, 0 datetime) |
| **Train split** | 1,384 rows |
| **Test split** | 346 rows |
| **Geographic scope** | SLE |
| **Publisher** | Global Healthsites Mapping Project |
| **HDX last updated** | 2025-04-25 |

---

## Variables

**Geographic** — `province` (Northern, Southern, Western), `district` (Western Urban, Bo, Kenema), `health_facility` (Foindu, Kpetema, Bendu), `nature_of_facility` (Health Post, Health Centre, Hospital), `lon` (range -13.2949–-10.3066) and 2 others.

**Identifier / Metadata** — `id` (HF0233, HF0001, HF1163), `source_of_info_name` (SL-MOH, MOHS DHIS, Yellow Pages, Cybo), `esa_source` (HDX), `esa_processed`.

**Other** — `address` (Cline Town, Kenema Town, Tongi Tingi), `activities` (Maternal and Child Health Post, Community Health Post, Community Health Centre).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sierra-leone-health-sites")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `id` | object | 0.0% | HF0233, HF0001, HF1163 |
| `province` | object | 0.1% | Northern, Southern, Western |
| `district` | object | 0.1% | Western Urban, Bo, Kenema |
| `address` | object | 76.7% | Cline Town, Kenema Town, Tongi Tingi |
| `health_facility` | object | 0.0% | Foindu, Kpetema, Bendu |
| `nature_of_facility` | object | 0.1% | Health Post, Health Centre, Hospital |
| `activities` | object | 6.6% | Maternal and Child Health Post, Community Health Post, Community Health Centre |
| `lon` | float64 | 5.4% | -13.2949 – -10.3066 (mean -12.1294) |
| `lat` | float64 | 5.4% | 6.9694 – 9.9745 (mean 8.3993) |
| `source_of_info_name` | object | 0.1% | SL-MOH, MOHS DHIS, Yellow Pages, Cybo |
| `raw_hdx_data_link` | object | 0.1% | https://data.humdata.org/dataset/sierra-leone-healthsites |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `lon` | -13.2949 | -10.3066 | -12.1294 | -12.0611 |
| `lat` | 6.9694 | 9.9745 | 8.3993 | 8.4725 |

---

## 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`. 8 column(s) with >80% missing values were removed: `scope_of_services`, `ancillary_services`, `inpatient_services`, `ownership`, `staff`, `tags`.... 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: `address`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/sierra-leone-health-sites) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_sierra_leone_health_sites,
title = {Sierra Leone Healthsites},
author = {Global Healthsites Mapping Project},
year = {2025},
url = {https://data.humdata.org/dataset/sierra-leone-health-sites},
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.*