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

---
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
- ssd
pretty_name: "South Sudan - Aid Worker Security Database"
dataset_info:
splits:
- name: train
num_examples: 572
- name: test
num_examples: 143
---

# South Sudan - Aid Worker Security Database

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

---

## Abstract

This dataset shows aid worker security incidents in South Sudan. 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: **SSD**.

*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)** | 716 |
| **Columns** | 46 (30 numeric, 16 categorical, 0 datetime) |
| **Train split** | 572 rows |
| **Test split** | 143 rows |
| **Geographic scope** | SSD |
| **Publisher** | Humanitarian Outcomes |
| **HDX last updated** | 2026-04-09 |

---

## Variables

**Geographic** — `year` (range 1997.0–2026.0), `day` (range 1.0–31.0), `country_code` (SS), `country` (South Sudan), `region` (Central Equatoria, Jonglei, Unity) and 7 others.

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

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

**Outcome / Measurement** — `total_nationals` (range 0.0–29.0), `total_internationals` (range 0.0–15.0), `total_killed`, `total_wounded`, `total_kidnapped` and 2 others.

**Identifier / Metadata** — `incident_id` (range 24.0–5805.0), `nationals_kidnapped` (range 0.0–29.0), `internationals_kidnapped` (range 0.0–3.0), `actor_name`, `source` and 2 others.

**Other** — `un` (range 0.0–5.0), `ingo` (range 0.0–29.0), `icrc` (range 0.0–1.0), `nrcs_and_ifrc` (range 0.0–4.0), `nngo` (range 0.0–8.0) and 11 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-aid-worker-security-database-ssd")
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% | 24.0 – 5805.0 (mean 3248.9958) |
| `year` | int64 | 0.0% | 1997.0 – 2026.0 (mean 2019.6522) |
| `month` | float64 | 0.1% | 1.0 – 12.0 (mean 6.4112) |
| `day` | float64 | 1.7% | 1.0 – 31.0 (mean 15.3295) |
| `country_code` | object | 0.0% | SS |
| `country` | object | 0.0% | South Sudan |
| `region` | object | 1.4% | Central Equatoria, Jonglei, Unity |
| `district` | object | 3.4% | Juba, Rubkona, Pibor |
| `city` | object | 8.1% | Juba, Bentiu, Malakal |
| `un` | int64 | 0.0% | 0.0 – 5.0 (mean 0.3743) |
| `ingo` | int64 | 0.0% | 0.0 – 29.0 (mean 0.7654) |
| `icrc` | int64 | 0.0% | 0.0 – 1.0 (mean 0.0056) |
| `nrcs_and_ifrc` | int64 | 0.0% | 0.0 – 4.0 (mean 0.007) |
| `nngo` | int64 | 0.0% | 0.0 – 8.0 (mean 0.3939) |
| `other` | int64 | 0.0% | 0.0 – 1.0 (mean 0.0042) |
| `nationals_killed` | int64 | 0.0% | 0.0 – 6.0 (mean 0.3743) |
| `nationals_wounded` | int64 | 0.0% | 0.0 – 8.0 (mean 0.6522) |
| `nationals_kidnapped` | int64 | 0.0% | 0.0 – 29.0 (mean 0.3142) |
| `nationals_detained` | int64 | 0.0% | 0.0 – 4.0 (mean 0.0894) |
| `total_nationals` | int64 | 0.0% | 0.0 – 29.0 (mean 1.4302) |
| `internationals_killed` | int64 | 0.0% | 0.0 – 3.0 (mean 0.0265) |
| `internationals_wounded` | int64 | 0.0% | 0.0 – 15.0 (mean 0.0712) |
| `internationals_kidnapped` | int64 | 0.0% | 0.0 – 3.0 (mean 0.0182) |
| `internationals_detained` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0042) |
| `total_internationals` | int64 | 0.0% | 0.0 – 15.0 (mean 0.1201) |
| `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, Bodily assault, Kidnapping |
| `attack_context` | object | 0.0% | Ambush, Individual attack, Raid |
| `location` | object | 0.0% | Road, Unknown, Public location |
| `latitude` | float64 | 0.0% | |
| `longitude` | float64 | 0.0% | |
| `motive` | object | 0.1% | Unknown, Incidental, Economic |
| `actor_type` | object | 0.0% | Unknown, Unaffiliated, Non-state armed group: Unknown |
| `actor_name` | object | 0.3% | |
| `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` | 24.0 | 5805.0 | 3248.9958 | 3144.5 |
| `year` | 1997.0 | 2026.0 | 2019.6522 | 2020.0 |
| `month` | 1.0 | 12.0 | 6.4112 | 6.0 |
| `day` | 1.0 | 31.0 | 15.3295 | 15.0 |
| `un` | 0.0 | 5.0 | 0.3743 | 0.0 |
| `ingo` | 0.0 | 29.0 | 0.7654 | 0.0 |
| `icrc` | 0.0 | 1.0 | 0.0056 | 0.0 |
| `nrcs_and_ifrc` | 0.0 | 4.0 | 0.007 | 0.0 |
| `nngo` | 0.0 | 8.0 | 0.3939 | 0.0 |
| `other` | 0.0 | 1.0 | 0.0042 | 0.0 |
| `nationals_killed` | 0.0 | 6.0 | 0.3743 | 0.0 |
| `nationals_wounded` | 0.0 | 8.0 | 0.6522 | 1.0 |
| `nationals_kidnapped` | 0.0 | 29.0 | 0.3142 | 0.0 |
| `nationals_detained` | 0.0 | 4.0 | 0.0894 | 0.0 |
| `total_nationals` | 0.0 | 29.0 | 1.4302 | 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-ssd) for the publisher's own methodology notes and caveats.

---

## Citation

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