electricsheepafrica/africa-aid-worker-security-database-som

---
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
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- aid-worker-security
- aid-workers
- conflict-violence
- som
pretty_name: "Somalia - Aid Worker Security Database"
dataset_info:
splits:
- name: train
num_examples: 263
- name: test
num_examples: 65
---

# Somalia - Aid Worker Security Database

**Publisher:** Humanitarian Outcomes · **Source:** [HDX](https://data.humdata.org/dataset/aid-worker-security-database-som) · **License:** `cc-by` · **Updated:** 2026-04-09

---

## Abstract

This dataset shows aid worker security incidents in Somalia. Annually, the data for the previous year undergoes a verification process. Data for the current year is provisional. For incident descriptions, please download data directly from [www.aidworkersecurity.org](www.aidworkersecurity.org)

Each row in this dataset represents discrete events or incidents. Data was last updated on HDX on 2026-04-09. Geographic scope: **SOM**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Conflict and security |
| **Unit of observation** | Discrete events or incidents |
| **Rows (total)** | 329 |
| **Columns** | 46 (30 numeric, 16 categorical, 0 datetime) |
| **Train split** | 263 rows |
| **Test split** | 65 rows |
| **Geographic scope** | SOM |
| **Publisher** | Humanitarian Outcomes |
| **HDX last updated** | 2026-04-09 |

---

## Variables

**Geographic** — `year` (range 1997.0–2025.0), `day` (range 1.0–31.0), `country_code` (SO), `country` (Somalia), `region` (Banadir, Bay, Lower Juba) and 7 others.

**Temporal** — `month` (range 1.0–12.0).

**Demographic** — `gender_male`, `gender_female`, `gender_unknown`.

**Outcome / Measurement** — `total_nationals` (range 0.0–18.0), `total_internationals` (range 0.0–9.0), `total_killed`, `total_wounded`, `total_kidnapped` and 2 others.

**Identifier / Metadata** — `incident_id` (range 4.0–5767.0), `nationals_kidnapped` (range 0.0–7.0), `internationals_kidnapped` (range 0.0–9.0), `actor_name`, `source` and 2 others.

**Other** — `un` (range 0.0–13.0), `ingo` (range 0.0–5.0), `icrc` (range 0.0–7.0), `nrcs_and_ifrc` (range 0.0–18.0), `nngo` (range 0.0–14.0) and 11 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-aid-worker-security-database-som")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `incident_id` | int64 | 0.0% | 4.0 – 5767.0 (mean 1680.1429) |
| `year` | int64 | 0.0% | 1997.0 – 2025.0 (mean 2011.7021) |
| `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.4529) |
| `day` | float64 | 12.8% | 1.0 – 31.0 (mean 15.878) |
| `country_code` | object | 0.0% | SO |
| `country` | object | 0.0% | Somalia |
| `region` | object | 7.3% | Banadir, Bay, Lower Juba |
| `district` | object | 13.4% | Banadir, Baydhaba, Gaalkacyo |
| `city` | object | 19.8% | Mogadishu, Gaalkacyo, Baydhaba |
| `un` | int64 | 0.0% | 0.0 – 13.0 (mean 0.5471) |
| `ingo` | int64 | 0.0% | 0.0 – 5.0 (mean 0.6413) |
| `icrc` | int64 | 0.0% | 0.0 – 7.0 (mean 0.0395) |
| `nrcs_and_ifrc` | int64 | 0.0% | 0.0 – 18.0 (mean 0.1064) |
| `nngo` | int64 | 0.0% | 0.0 – 14.0 (mean 0.4954) |
| `other` | int64 | 0.0% | 0.0 – 1.0 (mean 0.0061) |
| `nationals_killed` | int64 | 0.0% | 0.0 – 14.0 (mean 0.7143) |
| `nationals_wounded` | int64 | 0.0% | 0.0 – 13.0 (mean 0.4924) |
| `nationals_kidnapped` | int64 | 0.0% | 0.0 – 7.0 (mean 0.3283) |
| `nationals_detained` | int64 | 0.0% | 0.0 – 5.0 (mean 0.0182) |
| `total_nationals` | int64 | 0.0% | 0.0 – 18.0 (mean 1.5532) |
| `internationals_killed` | int64 | 0.0% | 0.0 – 4.0 (mean 0.079) |
| `internationals_wounded` | int64 | 0.0% | 0.0 – 3.0 (mean 0.0334) |
| `internationals_kidnapped` | int64 | 0.0% | 0.0 – 9.0 (mean 0.1672) |
| `internationals_detained` | int64 | 0.0% | 0.0 – 1.0 (mean 0.003) |
| `total_internationals` | int64 | 0.0% | 0.0 – 9.0 (mean 0.2827) |
| `total_killed` | int64 | 0.0% | |
| `total_wounded` | int64 | 0.0% | |
| `total_kidnapped` | int64 | 0.0% | |
| `total_detained` | int64 | 0.0% | |
| `total_affected` | int64 | 0.0% | |
| `gender_male` | int64 | 0.0% | |
| `gender_female` | int64 | 0.0% | |
| `gender_unknown` | int64 | 0.0% | |
| `means_of_attack` | object | 0.0% | Shooting, Kidnapping, Unknown |
| `attack_context` | object | 0.0% | Ambush, Individual attack, Unknown |
| `location` | object | 0.0% | Road, Unknown, Public location |
| `latitude` | float64 | 0.0% | |
| `longitude` | float64 | 0.0% | |
| `motive` | object | 0.0% | Unknown, Incidental, Political |
| `actor_type` | object | 0.0% | Unknown, Non-state armed group: National, Non-state armed group: Subnational |
| `actor_name` | object | 0.0% | |
| `details` | object | 0.0% | |
| `verified` | object | 0.0% | |
| `source` | object | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `incident_id` | 4.0 | 5767.0 | 1680.1429 | 1261.0 |
| `year` | 1997.0 | 2025.0 | 2011.7021 | 2011.0 |
| `month` | 1.0 | 12.0 | 6.4529 | 7.0 |
| `day` | 1.0 | 31.0 | 15.878 | 16.0 |
| `un` | 0.0 | 13.0 | 0.5471 | 0.0 |
| `ingo` | 0.0 | 5.0 | 0.6413 | 0.0 |
| `icrc` | 0.0 | 7.0 | 0.0395 | 0.0 |
| `nrcs_and_ifrc` | 0.0 | 18.0 | 0.1064 | 0.0 |
| `nngo` | 0.0 | 14.0 | 0.4954 | 0.0 |
| `other` | 0.0 | 1.0 | 0.0061 | 0.0 |
| `nationals_killed` | 0.0 | 14.0 | 0.7143 | 0.0 |
| `nationals_wounded` | 0.0 | 13.0 | 0.4924 | 0.0 |
| `nationals_kidnapped` | 0.0 | 7.0 | 0.3283 | 0.0 |
| `nationals_detained` | 0.0 | 5.0 | 0.0182 | 0.0 |
| `total_nationals` | 0.0 | 18.0 | 1.5532 | 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`. 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 Humanitarian Outcomes 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/aid-worker-security-database-som) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_aid_worker_security_database_som,
title = {Somalia - Aid Worker Security Database},
author = {Humanitarian Outcomes},
year = {2026},
url = {https://data.humdata.org/dataset/aid-worker-security-database-som},
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.*