electricsheepafrica/africa-health-centers-data-base

---
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
- water-sanitation-and-hygiene-wash
- gin
pretty_name: "Guinea: Health Centers Data Base"
dataset_info:
splits:
- name: train
num_examples: 1397
- name: test
num_examples: 349
---

# Guinea: Health Centers Data Base

**Publisher:** WASH Cluster Guinea (inactive) · **Source:** [HDX](https://data.humdata.org/dataset/health-centers-data-base) · **License:** `other-pd-nr` · **Updated:** 2023-03-03

---

## Abstract

This "Health Center Database" is a compilation about a work of the WASH cluster Guinea in collaboration with all his partners.
This data base has been built from the initial data base from the Health Ministry of Guinea.
If you get any suggestions or updates to this "Health center database", please send an email to: [e-mail]
The compilation of the update will be send to this HDX regularly.

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2023-03-03. Geographic scope: **GIN**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 1,747 |
| **Columns** | 22 (2 numeric, 20 categorical, 0 datetime) |
| **Train split** | 1,397 rows |
| **Test split** | 349 rows |
| **Geographic scope** | GIN |
| **Publisher** | WASH Cluster Guinea (inactive) |
| **HDX last updated** | 2023-03-03 |

---

## Variables

**Geographic** — `code_provisoire` (1, GIN00700109 CSMitt, GIN00700110PSKene), `x` (range -15.0219–12.5832), `y` (range 7.2563–14.4817), `sourcecoord` (geonode, Ministere Plan, CRS), `type_cxxxgroupes` (PS, CS, HP) and 3 others.

**Identifier / Metadata** — `name_structure_sanitaire` (Balandougou, Hamdallaye, Hafia), `georef` (OK, Coord absent), `pref`, `spref`, `prefecture_prioritaire` and 2 others.

**Other** — `nom_localite` (Labé, Hafia, Kankan), `nom_hop` (Sanoyah, Hérico, Balandougou), `liste_officielle` (ok, Non), `reg` (Nzerekore, Kankan, Kindia), `acteur` and 2 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-health-centers-data-base")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `code_provisoire` | object | 0.0% | 1, GIN00700109 CSMitt, GIN00700110PSKene |
| `x` | float64 | 33.0% | -15.0219 – 12.5832 (mean -10.7227) |
| `y` | float64 | 33.0% | 7.2563 – 14.4817 (mean 10.0786) |
| `sourcecoord` | object | 29.4% | geonode, Ministere Plan, CRS |
| `nom_localite` | object | 38.6% | Labé, Hafia, Kankan |
| `name_structure_sanitaire` | object | 0.0% | Balandougou, Hamdallaye, Hafia |
| `nom_hop` | object | 33.7% | Sanoyah, Hérico, Balandougou |
| `georef` | object | 0.1% | OK, Coord absent |
| `type_cxxxgroupes` | object | 0.0% | PS, CS, HP |
| `typo_ministere` | object | 1.4% | PS, CS, CS |
| `liste_officielle` | object | 0.1% | ok, Non |
| `reg` | object | 0.0% | Nzerekore, Kankan, Kindia |
| `pref` | object | 0.0% | |
| `admin2_code` | object | 1.7% | |
| `spref` | object | 0.0% | |
| `admin3_code` | object | 0.0% | |
| `prefecture_prioritaire` | object | 45.6% | |
| `acteur` | object | 71.7% | |
| `kit` | object | 76.8% | |
| `remarque` | object | 80.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `x` | -15.0219 | 12.5832 | -10.7227 | -10.7212 |
| `y` | 7.2563 | 14.4817 | 10.0786 | 10.2138 |

---

## 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`. 7 column(s) with >80% missing values were removed: `activite`, `tri_isolement`, `infra`, `nan`, `unnamed_24`, `unnamed_25`.... 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 WASH Cluster Guinea (inactive) 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`, `sourcecoord`, `nom_localite`, `nom_hop`, `prefecture_prioritaire`, `acteur`, `kit`....
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/health-centers-data-base) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_health_centers_data_base,
title = {Guinea: Health Centers Data Base},
author = {WASH Cluster Guinea (inactive)},
year = {2023},
url = {https://data.humdata.org/dataset/health-centers-data-base},
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.*