electricsheepafrica/africa-south-sudan-health-facilities

---
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:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- facilities-infrastructure
- geodata
- health
- ssd
pretty_name: "South Sudan - Health Facilities"
dataset_info:
splits:
- name: train
num_examples: 1590
- name: test
num_examples: 397
---

# South Sudan - Health Facilities

**Publisher:** OCHA South Sudan · **Source:** [HDX](https://data.humdata.org/dataset/south-sudan-health-facilities) · **License:** `cc-by` · **Updated:** 2025-07-18

---

## Abstract

The health facilities dataset outlines the types of health facilities present at the Payam level.

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2025-07-18. Geographic scope: **SSD**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 1,988 |
| **Columns** | 12 (2 numeric, 10 categorical, 0 datetime) |
| **Train split** | 1,590 rows |
| **Test split** | 397 rows |
| **Geographic scope** | SSD |
| **Publisher** | OCHA South Sudan |
| **HDX last updated** | 2025-07-18 |

---

## Variables

**Geographic** — `old_state` (cent eq, west eq, east eq), `state_code` (SS01, SS10, SS02), `county` (juba, yambio, aweil east), `county_code` (SS0101, SS1010, SS0502), `payam` (abyei region, yambio town, tambura) and 3 others.

**Identifier / Metadata** — `site_dhis2_name` (Malek PHCU, Mandeng PHCU, Mayen PHCU), `esa_source` (HDX), `esa_processed` (2026-04-17).

**Other** — `site` (malek phcu, mandeng phcu, pandit phcu).

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `old_state` | object | 0.0% | cent eq, west eq, east eq |
| `state_code` | object | 0.0% | SS01, SS10, SS02 |
| `county` | object | 0.0% | juba, yambio, aweil east |
| `county_code` | object | 0.0% | SS0101, SS1010, SS0502 |
| `payam` | object | 1.2% | abyei region, yambio town, tambura |
| `payam_code` | object | 1.5% | SS000101, SS101005, SS100904 |
| `site` | object | 0.0% | malek phcu, mandeng phcu, pandit phcu |
| `site_dhis2_name` | object | 32.1% | Malek PHCU, Mandeng PHCU, Mayen PHCU |
| `latitude` | float64 | 5.7% | 3.5416 – 12.1695 (mean 6.9643) |
| `longitude` | float64 | 5.7% | 24.8158 – 35.0749 (mean 30.269) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-17 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `latitude` | 3.5416 | 12.1695 | 6.9643 | 7.224 |
| `longitude` | 24.8158 | 35.0749 | 30.269 | 30.3827 |

---

## 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 South Sudan 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: `site_dhis2_name`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/south-sudan-health-facilities) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_south_sudan_health_facilities,
title = {South Sudan - Health Facilities},
author = {OCHA South Sudan},
year = {2025},
url = {https://data.humdata.org/dataset/south-sudan-health-facilities},
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.*