electricsheepafrica/africa-hotspot-priority-woredas

---
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-classification
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- education
- logistics
- eth
pretty_name: "Ethiopia - Hotspot Priority Woredas"
dataset_info:
splits:
- name: train
num_examples: 379
- name: test
num_examples: 94
---

# Ethiopia - Hotspot Priority Woredas

**Publisher:** OCHA Ethiopia · **Source:** [HDX](https://data.humdata.org/dataset/hotspot-priority-woredas) · **License:** `cc-by` · **Updated:** 2025-04-28

---

## Abstract

This table has priority woredas in three categories (priority 1, 2 and 3) by different sectors (Health, Nutrition, WASH, Agriculture, Market, Education, Child Protection & GBV and others).

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2025-04-28. Geographic scope: **ETH**.

*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)** | 474 |
| **Columns** | 16 (10 numeric, 6 categorical, 0 datetime) |
| **Train split** | 379 rows |
| **Test split** | 94 rows |
| **Geographic scope** | ETH |
| **Publisher** | OCHA Ethiopia |
| **HDX last updated** | 2025-04-28 |

---

## Variables

**Geographic** — `region` (Oromia, Somali, Amhara), `zone` (South Wello, East Hararge, Bale), `woreda` (Babile, Kersa, Erer), `hs_july_2018` (range 1.0–3.0).

**Identifier / Metadata** — `wid` (ET040810, ET020504, ET020502), `esa_source` (HDX), `esa_processed` (2026-04-10).

**Other** — `s_n` (range 1.0–474.0), `health_nutrition` (range 1.0–3.0), `agriculture` (range 1.0–3.0), `market` (range 1.0–3.0), `water_cluster` (range 1.0–3.0) and 4 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-hotspot-priority-woredas")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `s_n` | int64 | 0.0% | 1.0 – 474.0 (mean 237.5) |
| `region` | object | 0.0% | Oromia, Somali, Amhara |
| `zone` | object | 0.0% | South Wello, East Hararge, Bale |
| `wid` | object | 1.7% | ET040810, ET020504, ET020502 |
| `woreda` | object | 0.0% | Babile, Kersa, Erer |
| `hs_july_2018` | float64 | 10.5% | 1.0 – 3.0 (mean 1.6769) |
| `health_nutrition` | float64 | 5.1% | 1.0 – 3.0 (mean 1.5133) |
| `agriculture` | float64 | 9.1% | 1.0 – 3.0 (mean 1.4432) |
| `market` | float64 | 22.4% | 1.0 – 3.0 (mean 1.4484) |
| `water_cluster` | float64 | 10.8% | 1.0 – 3.0 (mean 1.5248) |
| `education` | float64 | 10.5% | 1.0 – 3.0 (mean 1.8302) |
| `child_protection_gbv` | float64 | 45.4% | 1.0 – 3.0 (mean 1.9923) |
| `others` | float64 | 50.8% | 1.0 – 3.0 (mean 2.03) |
| `hs_dcember_2018` | float64 | 1.5% | 1.0 – 3.0 (mean 1.5931) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-10 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `s_n` | 1.0 | 474.0 | 237.5 | 237.5 |
| `hs_july_2018` | 1.0 | 3.0 | 1.6769 | 1.0 |
| `health_nutrition` | 1.0 | 3.0 | 1.5133 | 1.0 |
| `agriculture` | 1.0 | 3.0 | 1.4432 | 1.0 |
| `market` | 1.0 | 3.0 | 1.4484 | 1.0 |
| `water_cluster` | 1.0 | 3.0 | 1.5248 | 1.0 |
| `education` | 1.0 | 3.0 | 1.8302 | 2.0 |
| `child_protection_gbv` | 1.0 | 3.0 | 1.9923 | 2.0 |
| `others` | 1.0 | 3.0 | 2.03 | 2.0 |
| `hs_dcember_2018` | 1.0 | 3.0 | 1.5931 | 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`. 2 column(s) with >80% missing values were removed: `unnamed_14`, `unnamed_15`. 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 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.
- The following columns have >20% missing values and should be treated with caution in modelling: `market`, `child_protection_gbv`, `others`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/hotspot-priority-woredas) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_hotspot_priority_woredas,
title = {Ethiopia - Hotspot Priority Woredas},
author = {OCHA Ethiopia},
year = {2025},
url = {https://data.humdata.org/dataset/hotspot-priority-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.*