electricsheepafrica/africa-somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-sa-4.0
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- aid-worker-security
- aid-workers
- complex-emergency-conflict-security
- conflict-violence
- damage-assessment
- disease
- education
- education-facilities-schools
- som
pretty_name: "Somalia (SOM): Attacks on Aid Operations, Education, Food and Water Systems and Health Care"
dataset_info:
splits:
- name: train
num_examples: 267
- name: test
num_examples: 66
---

# Somalia (SOM): Attacks on Aid Operations, Education, Food and Water Systems and Health Care

**Publisher:** Insecurity Insight · **Source:** [HDX](https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites) · **License:** `cc-by-sa` · **Updated:** 2026-04-06

---

## Abstract

This page contains information on reported incidents of violence and threats affecting aid operations and workers, education, food systems and health care services in [Somalia](https://insecurityinsight.org/country-pages/somalia). Also included are datasets cited in the [Safeguarding Health in Conflict Coalition (SHCC)'s](https://www.safeguardinghealth.org/) annual reports. Please get in touch if you are interested in curated datasets: [e-mail]

Each row in this dataset represents discrete events or incidents. Temporal coverage is indicated by the `date`, `date_event_entered` column(s). Geographic scope: **SOM**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Discrete events or incidents |
| **Rows (total)** | 334 |
| **Columns** | 42 (26 numeric, 13 categorical, 3 datetime) |
| **Train split** | 267 rows |
| **Test split** | 66 rows |
| **Geographic scope** | SOM |
| **Publisher** | Insecurity Insight |
| **HDX last updated** | 2026-04-06 |

---

## Variables

**Geographic** — `country` (Somalia), `country_iso` (SOM), `admin_1` (Banaadir, No Information, Bay), `location_of_incident` (Road, No information, Compound or Office Building), `aid_workers_killed_in_captivity` (range 0.0–7.0) and 4 others.

**Temporal** — `date`, `date_event_entered`, `date_event_modified`.

**Demographic** — `female_aid_workers_killed` (range 0.0–2.0), `male_aid_workers_killed` (range 0.0–3.0), `female_aid_workers_injured` (range 0.0–2.0), `male_aid_workers_injured` (range 0.0–5.0), `female_aid_workers_kidnapped` (range 0.0–3.0) and 3 others.

**Outcome / Measurement** — `organisation_affected` (INGO, UN Agency, LNGO).

**Identifier / Metadata** — `reported_perpetrator_name` (Unidentified armed actor, Al-Shabaab, Militia), `aid_workers_killed` (range 0.0–14.0), `aid_workers_injured` (range 0.0–7.0), `aid_workers_kidnapped` (range 0.0–12.0), `aid_workers_arrested` (range 0.0–6.0) and 12 others.

**Other** — `geo_precision` (censored), `reported_perpetrator` (NSA, No Information, Police), `weapon_carried_used` (Firearms, No Information on the Weapon Used, Hand Grenade), `programme_focus` (No information, Health, Hunger).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `date` | datetime64[ns] | 0.0% | |
| `country` | object | 0.0% | Somalia |
| `country_iso` | object | 0.0% | SOM |
| `admin_1` | object | 0.0% | Banaadir, No Information, Bay |
| `geo_precision` | object | 0.0% | censored |
| `location_of_incident` | object | 0.0% | Road, No information, Compound or Office Building |
| `reported_perpetrator` | object | 0.0% | NSA, No Information, Police |
| `reported_perpetrator_name` | object | 0.0% | Unidentified armed actor, Al-Shabaab, Militia |
| `weapon_carried_used` | object | 0.0% | Firearms, No Information on the Weapon Used, Hand Grenade |
| `organisation_affected` | object | 0.0% | INGO, UN Agency, LNGO |
| `programme_focus` | object | 0.0% | No information, Health, Hunger |
| `aid_workers_killed` | int64 | 0.0% | 0.0 – 14.0 (mean 0.6198) |
| `aid_workers_injured` | int64 | 0.0% | 0.0 – 7.0 (mean 0.5329) |
| `aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 12.0 (mean 0.8174) |
| `aid_workers_arrested` | int64 | 0.0% | 0.0 – 6.0 (mean 0.1347) |
| `known_kidnapping_or_arrest_outcome` | object | 62.9% | |
| `aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 7.0 (mean 0.0329) |
| `international_aid_workers_killed` | int64 | 0.0% | 0.0 – 4.0 (mean 0.0749) |
| `international_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `national_aid_workers_killed` | int64 | 0.0% | 0.0 – 14.0 (mean 0.485) |
| `national_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 7.0 (mean 0.0329) |
| `female_aid_workers_killed` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0479) |
| `female_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `male_aid_workers_killed` | int64 | 0.0% | 0.0 – 3.0 (mean 0.3772) |
| `male_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 1.0 (mean 0.012) |
| `international_aid_workers_injured` | int64 | 0.0% | 0.0 – 5.0 (mean 0.0569) |
| `national_aid_workers_injured` | int64 | 0.0% | 0.0 – 7.0 (mean 0.3503) |
| `female_aid_workers_injured` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0269) |
| `male_aid_workers_injured` | int64 | 0.0% | 0.0 – 5.0 (mean 0.2216) |
| `international_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 12.0 (mean 0.2545) |
| `national_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 10.0 (mean 0.4641) |
| `female_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 3.0 (mean 0.0629) |
| `male_aid_workers_kidnapped` | int64 | 0.0% | |
| `international_aid_workers_arrested` | int64 | 0.0% | |
| `national_aid_workers_arrested` | int64 | 0.0% | |
| `female_aid_workers_arrested` | int64 | 0.0% | |
| `male_aid_workers_arrested` | int64 | 0.0% | |
| `sind_event_id` | int64 | 0.0% | |
| `date_event_entered` | datetime64[ns] | 0.0% | |
| `date_event_modified` | datetime64[ns] | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `aid_workers_killed` | 0.0 | 14.0 | 0.6198 | 0.0 |
| `aid_workers_injured` | 0.0 | 7.0 | 0.5329 | 0.0 |
| `aid_workers_kidnapped` | 0.0 | 12.0 | 0.8174 | 0.0 |
| `aid_workers_arrested` | 0.0 | 6.0 | 0.1347 | 0.0 |
| `aid_workers_killed_in_captivity` | 0.0 | 7.0 | 0.0329 | 0.0 |
| `international_aid_workers_killed` | 0.0 | 4.0 | 0.0749 | 0.0 |
| `international_aid_workers_killed_in_captivity` | 0.0 | 0.0 | 0.0 | 0.0 |
| `national_aid_workers_killed` | 0.0 | 14.0 | 0.485 | 0.0 |
| `national_aid_workers_killed_in_captivity` | 0.0 | 7.0 | 0.0329 | 0.0 |
| `female_aid_workers_killed` | 0.0 | 2.0 | 0.0479 | 0.0 |
| `female_aid_workers_killed_in_captivity` | 0.0 | 0.0 | 0.0 | 0.0 |
| `male_aid_workers_killed` | 0.0 | 3.0 | 0.3772 | 0.0 |
| `male_aid_workers_killed_in_captivity` | 0.0 | 1.0 | 0.012 | 0.0 |
| `international_aid_workers_injured` | 0.0 | 5.0 | 0.0569 | 0.0 |
| `national_aid_workers_injured` | 0.0 | 7.0 | 0.3503 | 0.0 |

---

## 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`. 3 column(s) with >80% missing values were removed: `event_description`, `latitude`, `longitude`. 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 Insecurity Insight 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: `known_kidnapping_or_arrest_outcome`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_somalia_violence_agaiinst_civilian_and_vital_civilian_facilitites,
title = {Somalia (SOM): Attacks on Aid Operations, Education, Food and Water Systems and Health Care},
author = {Insecurity Insight},
year = {2026},
url = {https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites},
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.*