electricsheepafrica/africa-health-facilities-senegal

---
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
- sen
pretty_name: "Senegal Healthsites"
dataset_info:
splits:
- name: train
num_examples: 1504
- name: test
num_examples: 376
---

# Senegal Healthsites

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

*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)** | 1,881 |
| **Columns** | 25 (7 numeric, 17 categorical, 0 datetime) |
| **Train split** | 1,504 rows |
| **Test split** | 376 rows |
| **Geographic scope** | SEN |
| **Publisher** | Global Healthsites Mapping Project |
| **HDX last updated** | 2025-10-15 |

---

## Variables

**Geographic** — `x` (range -17.515–-11.4513), `y` (range 12.3861–16.6686), `osm_type` (node, way), `loc_amenity` (pharmacy, doctors, clinic), `meta_operator_type` (public, private, Public) and 3 others.

**Temporal** — `changeset_timestamp`.

**Identifier / Metadata** — `osm_id` (range 100202397.0–13136847901.0), `loc_name` (Pharmacie, Poste de santé, Centre de Santé), `meta_water_source`, `changeset_id` (range 3030977.0–172511655.0), `meta_id` and 2 others.

**Other** — `completeness` (range 6.25–65.625), `meta_healthcare` (pharmacy, doctor, clinic), `meta_operator` (Ministère de la santé et de l'action sociale, Ministère de la Santé et de l'Action Sociale, MINISTERE DE LA SANTE ET DE L'ACTION SOCIALE), `geo_bounds_url` (#senegal #covid-19 #emergency-health-data-validation #healthsites, #senegal #Public Health #Sunu Wer Gye Yaram #WNAH #Healthsites, #senegal #covid-19 #emergency-health-data #healthsites), `status_operational_status` (operational, non_operational, needs_maintenance) and 4 others.

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `x` | float64 | 19.1% | -17.515 – -11.4513 (mean -16.0635) |
| `y` | float64 | 19.1% | 12.3861 – 16.6686 (mean 15.1962) |
| `osm_id` | int64 | 0.0% | 100202397.0 – 13136847901.0 (mean 5879564115.8538) |
| `osm_type` | object | 0.0% | node, way |
| `completeness` | float64 | 0.0% | 6.25 – 65.625 (mean 25.5748) |
| `loc_amenity` | object | 0.5% | pharmacy, doctors, clinic |
| `meta_healthcare` | object | 29.8% | pharmacy, doctor, clinic |
| `loc_name` | object | 8.0% | Pharmacie, Poste de santé, Centre de Santé |
| `meta_operator` | object | 71.8% | Ministère de la santé et de l'action sociale, Ministère de la Santé et de l'Action Sociale, MINISTERE DE LA SANTE ET DE L'ACTION SOCIALE |
| `geo_bounds_url` | object | 57.9% | #senegal #covid-19 #emergency-health-data-validation #healthsites, #senegal #Public Health #Sunu Wer Gye Yaram #WNAH #Healthsites, #senegal #covid-19 #emergency-health-data #healthsites |
| `meta_operator_type` | object | 62.0% | public, private, Public |
| `status_operational_status` | object | 62.6% | operational, non_operational, needs_maintenance |
| `access_hours` | object | 65.4% | 24/7, Mo-Fr 8:00 18:00; PH off, Mo-Fr 09:00-18:00; PH off |
| `capacity_beds` | float64 | 69.8% | 0.0 – 420.0 (mean 7.7236) |
| `meta_wheelchair` | object | 64.5% | yes, no, limited |
| `meta_emergency` | object | 75.0% | |
| `meta_insurance` | object | 71.6% | |
| `meta_water_source` | object | 65.3% | |
| `meta_electricity` | object | 65.9% | |
| `changeset_id` | int64 | 0.0% | 3030977.0 – 172511655.0 (mean 109990138.0234) |
| `changeset_version` | int64 | 0.0% | 1.0 – 14.0 (mean 2.5332) |
| `changeset_timestamp` | datetime64[ns, UTC] | 0.0% | |
| `meta_id` | object | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `x` | -17.515 | -11.4513 | -16.0635 | -16.491 |
| `y` | 12.3861 | 16.6686 | 15.1962 | 14.7906 |
| `osm_id` | 100202397.0 | 13136847901.0 | 5879564115.8538 | 5179083125.0 |
| `completeness` | 6.25 | 65.625 | 25.5748 | 15.625 |
| `capacity_beds` | 0.0 | 420.0 | 7.7236 | 3.0 |
| `changeset_id` | 3030977.0 | 172511655.0 | 109990138.0234 | 125591076.0 |
| `changeset_version` | 1.0 | 14.0 | 2.5332 | 2.0 |

---

## 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`. 12 column(s) with >80% missing values were removed: `meta_speciality`, `contact_phone`, `capacity_staff`, `meta_health_amenity_type`, `meta_dispensing`, `meta_is_in_health_area`.... 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: `meta_healthcare`, `meta_operator`, `geo_bounds_url`, `meta_operator_type`, `status_operational_status`, `access_hours`, `capacity_beds`, `meta_wheelchair`....
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/senegal-healthsites) for the publisher's own methodology notes and caveats.

---

## Citation

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