electricsheepafrica/africa-food-security-ethiopia

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- food-security
- health
- nutrition
- eth
pretty_name: "Ethiopia - Hotspot Woredas"
dataset_info:
splits:
- name: train
num_examples: 347
- name: test
num_examples: 86
---

# Ethiopia - Hotspot Woredas

**Publisher:** OCHA Ethiopia · **Source:** [HDX](https://data.humdata.org/dataset/hotspot-woredas) · **License:** `other-pd-nr` · **Updated:** 2022-09-14

---

## Abstract

Hotspot woreda classification is derived using six multisector indicators, including agriculture and nutrition, agreed at regional and federal levels. A hotspot matrix is often used as a proxy for the acute Integrated Phase Food Security Classification (IPC) and is indicative of food security and nutrition status. Hotspot woredas require urgent humanitarian response.

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2022-09-14. Geographic scope: **ETH**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 434 |
| **Columns** | 16 (10 numeric, 6 categorical, 0 datetime) |
| **Train split** | 347 rows |
| **Test split** | 86 rows |
| **Geographic scope** | ETH |
| **Publisher** | OCHA Ethiopia |
| **HDX last updated** | 2022-09-14 |

---

## Variables

**Geographic** — `woreda_code` (range 10101.0–508061.0), `region` (Oromia, Amhara, SNNP), `zone` (North Shewa, Arsi, South Wello), `woreda` (Moyale, Babile, Gursum), `regional_hs` (range 0.0–3.0).

**Identifier / Metadata** — `pcode_et` (ET130105, ET020203, ET030403), `esa_source` (HDX), `esa_processed` (2026-04-21).

**Other** — `as_of_march_2016` (range 0.0–3.0), `health_nutrition` (range 0.0–3.0), `agriculture` (range 0.0–3.0), `water` (range 0.0–3.0), `education` (range 1.0–3.0) and 3 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-food-security-ethiopia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `woreda_code` | int64 | 0.0% | 10101.0 – 508061.0 (mean 48116.2696) |
| `pcode_et` | object | 0.0% | ET130105, ET020203, ET030403 |
| `region` | object | 0.0% | Oromia, Amhara, SNNP |
| `zone` | object | 0.0% | North Shewa, Arsi, South Wello |
| `woreda` | object | 0.0% | Moyale, Babile, Gursum |
| `as_of_march_2016` | float64 | 2.1% | 0.0 – 3.0 (mean 1.5953) |
| `health_nutrition` | int64 | 0.0% | 0.0 – 3.0 (mean 1.6935) |
| `agriculture` | int64 | 0.0% | 0.0 – 3.0 (mean 1.4539) |
| `water` | int64 | 0.0% | 0.0 – 3.0 (mean 1.5576) |
| `education` | float64 | 15.7% | 1.0 – 3.0 (mean 1.6585) |
| `cpgbv` | int64 | 0.0% | 0.0 – 3.0 (mean 1.6935) |
| `food` | int64 | 0.0% | 0.0 – 3.0 (mean 1.4954) |
| `regional_hs` | int64 | 0.0% | 0.0 – 3.0 (mean 1.5899) |
| `federal_hs` | int64 | 0.0% | 0.0 – 3.0 (mean 1.6037) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-21 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `woreda_code` | 10101.0 | 508061.0 | 48116.2696 | 41012.5 |
| `as_of_march_2016` | 0.0 | 3.0 | 1.5953 | 1.0 |
| `health_nutrition` | 0.0 | 3.0 | 1.6935 | 2.0 |
| `agriculture` | 0.0 | 3.0 | 1.4539 | 1.0 |
| `water` | 0.0 | 3.0 | 1.5576 | 2.0 |
| `education` | 1.0 | 3.0 | 1.6585 | 1.0 |
| `cpgbv` | 0.0 | 3.0 | 1.6935 | 2.0 |
| `food` | 0.0 | 3.0 | 1.4954 | 1.0 |
| `regional_hs` | 0.0 | 3.0 | 1.5899 | 1.0 |
| `federal_hs` | 0.0 | 3.0 | 1.6037 | 1.0 |

---

## 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) with >80% missing values were removed: `unnamed_14`, `unnamed_15`, `unnamed_16`, `unnamed_17`. 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 Ethiopia 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/hotspot-woredas) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_food_security_ethiopia,
title = {Ethiopia - Hotspot Woredas},
author = {OCHA Ethiopia},
year = {2022},
url = {https://data.humdata.org/dataset/hotspot-woredas},
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.*