electricsheepafrica/africa-malnutrition-somalia

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- global-acute-malnutrition-gam
- hxl
- malnutrition
- nutrition
- severe-acute-malnutrition-sam
- som
pretty_name: "Somalia : Acute Malnutrition"
dataset_info:
splits:
- name: train
num_examples: 62
- name: test
num_examples: 15
---

# Somalia : Acute Malnutrition

**Publisher:** OCHA Somalia · **Source:** [HDX](https://data.humdata.org/dataset/somalia-acute-malnutrition-burden-and-prevalence) · **License:** `cc-by` · **Updated:** 2025-04-10

---

## Abstract

Global Acute Malnutrition (GAM) is the presence of both moderate acute malnutrition (MAM) and severe acute malnutrition (SAM) in a population. Height and body weight ratios are measured for children between 6 months and 5 years old to determine the prevalence of malnutrition. Rates above 15 per cent are ordinarily considered an emergency but rates above 30 per cent contribute to the case for famine in a given area.

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2025-04-10. Geographic scope: **SOM**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Demographics and population |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 78 |
| **Columns** | 8 (4 numeric, 4 categorical, 0 datetime) |
| **Train split** | 62 rows |
| **Test split** | 15 rows |
| **Geographic scope** | SOM |
| **Publisher** | OCHA Somalia |
| **HDX last updated** | 2025-04-10 |

---

## Variables

**Geographic** — `somalia_2023_post_gu_total_acute_malnutrition_burden_by_district_estimated` (range 9091.8–574886.2).

**Identifier / Metadata** — `unnamed_0` (Lower Shabelle, Bari, Gedo), `unnamed_1` (District, Baraawe, Diinsoor), `unnamed_3` (range 390.0–87790.0), `unnamed_4` (range 1900.0–229730.0), `unnamed_5` (range 2290.0–317520.0) and 2 others.

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `unnamed_0` | object | 1.3% | Lower Shabelle, Bari, Gedo |
| `unnamed_1` | object | 2.6% | District, Baraawe, Diinsoor |
| `somalia_2023_post_gu_total_acute_malnutrition_burden_by_district_estimated` | float64 | 5.1% | 9091.8 – 574886.2 (mean 45825.0432) |
| `unnamed_3` | float64 | 5.1% | 390.0 – 87790.0 (mean 4467.973) |
| `unnamed_4` | float64 | 5.1% | 1900.0 – 229730.0 (mean 15143.7838) |
| `unnamed_5` | float64 | 5.1% | 2290.0 – 317520.0 (mean 19611.7568) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-27 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `somalia_2023_post_gu_total_acute_malnutrition_burden_by_district_estimated` | 9091.8 | 574886.2 | 45825.0432 | 27091.3 |
| `unnamed_3` | 390.0 | 87790.0 | 4467.973 | 1885.0 |
| `unnamed_4` | 1900.0 | 229730.0 | 15143.7838 | 8490.0 |
| `unnamed_5` | 2290.0 | 317520.0 | 19611.7568 | 10525.0 |

---

## 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`. 4 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 OCHA Somalia 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://data.humdata.org/dataset/somalia-acute-malnutrition-burden-and-prevalence) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_malnutrition_somalia,
title = {Somalia : Acute Malnutrition},
author = {OCHA Somalia},
year = {2025},
url = {https://data.humdata.org/dataset/somalia-acute-malnutrition-burden-and-prevalence},
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.*