electricsheepafrica/africa-malaria-all

---
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
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- malaria
- prevalence
pretty_name: "Global Malaria National Unit Statistics"
dataset_info:
splits:
- name: train
num_examples: 2798
- name: test
num_examples: 699
---

# Global Malaria National Unit Statistics

**Publisher:** Code for Africa · **Source:** [OpenAfrica](https://open.africa/dataset/global-malaria-national-unit-statistics) · **License:** `cc-by` · **Updated:** 2024-02-20

---

## Abstract

Data showing Malaria Mortality Rate, Incidence Rate, and Infection Prevalence.

Each row in this dataset represents country-level aggregates. Data was last updated on OpenAfrica on 2024-02-20. Geographic scope: **Africa (multiple countries)**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 3,498 |
| **Columns** | 9 (2 numeric, 7 categorical, 0 datetime) |
| **Train split** | 2,798 rows |
| **Test split** | 699 rows |
| **Geographic scope** | Africa (multiple countries) |
| **Publisher** | Code for Africa |
| **OpenAfrica last updated** | 2024-02-20 |

---

## Variables

**Geographic** — `iso3` (AFG, SEN, STP), `admin_level` (admin0), `year` (range 2010.0–2020.0).

**Outcome / Measurement** — `value` (range 0.0–571.2892).

**Identifier / Metadata** — `name` (Afghanistan, Senegal, Sao Tome And Principe), `esa_source` (HDX), `esa_processed` (2026-04-27).

**Other** — `metric` (Incidence Rate, Infection Prevalence, Mortality Rate), `units` (Cases per Thousand, per 100 Children, Deaths per 100 Thousand).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-malaria-all")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `iso3` | object | 0.0% | AFG, SEN, STP |
| `name` | object | 0.0% | Afghanistan, Senegal, Sao Tome And Principe |
| `admin_level` | object | 0.0% | admin0 |
| `metric` | object | 0.0% | Incidence Rate, Infection Prevalence, Mortality Rate |
| `units` | object | 0.0% | Cases per Thousand, per 100 Children, Deaths per 100 Thousand |
| `year` | int64 | 0.0% | 2010.0 – 2020.0 (mean 2015.0) |
| `value` | float64 | 0.0% | 0.0 – 571.2892 (mean 39.754) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-27 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `year` | 2010.0 | 2020.0 | 2015.0 | 2015.0 |
| `value` | 0.0 | 571.2892 | 39.754 | 0.649 |

---

## Curation

Raw data was downloaded from OpenAfrica 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 Code for Africa and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- Refer to the [original HDX dataset page](https://open.africa/dataset/global-malaria-national-unit-statistics) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{openafrica_africa_malaria_all,
title = {Global Malaria National Unit Statistics},
author = {Code for Africa},
year = {2024},
url = {https://open.africa/dataset/global-malaria-national-unit-statistics},
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.*