electricsheepafrica/africa-ucdp-data-for-somalia

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- conflict-violence
- hxl
- som
pretty_name: "Somalia - Data on Conflict Events"
dataset_info:
splits:
- name: train
num_examples: 5494
- name: test
num_examples: 1373
---

# Somalia - Data on Conflict Events

**Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/ucdp-data-for-somalia) · **License:** `cc-by-igo` · **Updated:** 2026-04-03

---

## Abstract

This dataset is UCDP's most disaggregated dataset, covering individual events of organized violence (phenomena of lethal violence occurring at a given time and place). These events are sufficiently fine-grained to be geo-coded down to the level of individual villages, with temporal durations disaggregated to single, individual days.
Sundberg, Ralph, and Erik Melander, 2013, “Introducing the UCDP Georeferenced Event Dataset”, Journal of Peace Research, vol.50, no.4, 523-532
Högbladh Stina, 2019, “UCDP GED Codebook version 19.1”, Department of Peace and Conflict Research, Uppsala University

Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `date_start`, `date_end` column(s). 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** | First-level administrative unit observations |
| **Rows (total)** | 6,868 |
| **Columns** | 51 (27 numeric, 21 categorical, 2 datetime) |
| **Train split** | 5,494 rows |
| **Test split** | 1,373 rows |
| **Geographic scope** | SOM |
| **Publisher** | HDX |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `year` (range 1989.0–2024.0), `active_year`, `type_of_violence` (range 1.0–3.0), `dyad_dset_id` (range 90.0–18169.0), `dyad_new_id` (range 718.0–18169.0) and 9 others.

**Temporal** — `source_date` (2021-09-02, 2022-02-03, 2021-09-13), `date_prec` (range 1.0–5.0), `date_start`, `date_end`.

**Outcome / Measurement** — `number_of_sources` (range -1.0–32.0), `deaths_a` (range 0.0–400.0), `deaths_b`, `deaths_civilians`, `deaths_unknown`.

**Identifier / Metadata** — `id` (range 11921.0–563077.0), `relid` (ETH-1996-1-283-2.2, SOM-2021-1-750-323, SOM-2021-1-750-321), `code_status` (Clear), `conflict_dset_id` (range 90.0–17635.0), `conflict_new_id` (range 329.0–16379.0) and 14 others.

**Other** — `where_prec` (range 1.0–7.0), `where_description`, `adm_1`, `adm_2`, `geom_wkt` and 4 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-ucdp-data-for-somalia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `id` | int64 | 0.0% | 11921.0 – 563077.0 (mean 188360.9275) |
| `relid` | object | 0.0% | ETH-1996-1-283-2.2, SOM-2021-1-750-323, SOM-2021-1-750-321 |
| `year` | int64 | 0.0% | 1989.0 – 2024.0 (mean 2013.6481) |
| `active_year` | bool | 0.0% | |
| `code_status` | object | 0.0% | Clear |
| `type_of_violence` | int64 | 0.0% | 1.0 – 3.0 (mean 1.3151) |
| `conflict_dset_id` | int64 | 0.0% | 90.0 – 17635.0 (mean 1185.9578) |
| `conflict_new_id` | int64 | 0.0% | 329.0 – 16379.0 (mean 1113.7199) |
| `conflict_name` | object | 0.0% | Somalia: Government, Al-Shabaab - Civilians, Government of Somalia - Civilians |
| `dyad_dset_id` | int64 | 0.0% | 90.0 – 18169.0 (mean 1508.6013) |
| `dyad_new_id` | int64 | 0.0% | 718.0 – 18169.0 (mean 1557.4713) |
| `dyad_name` | object | 0.0% | Government of Somalia - Al-Shabaab, Al-Shabaab - Civilians, Government of Somalia - ARS/UIC |
| `side_a_dset_id` | int64 | 0.0% | 3.0 – 7229.0 (mean 234.4646) |
| `side_a_new_id` | int64 | 0.0% | 3.0 – 7229.0 (mean 234.4646) |
| `side_a` | object | 0.0% | Government of Somalia, Al-Shabaab, RRA |
| `side_b_dset_id` | int64 | 0.0% | 234.0 – 9999.0 (mean 1699.3818) |
| `side_b_new_id` | int64 | 0.0% | 1.0 – 9260.0 (mean 674.5431) |
| `side_b` | object | 0.0% | Al-Shabaab, Civilians, ARS/UIC |
| `number_of_sources` | int64 | 0.0% | -1.0 – 32.0 (mean 0.93) |
| `source_article` | object | 0.0% | "Strategic Intelligence,2021-09-02,Monthly Counter-Terrorism Intelligence Brief for East Africa (Kenya & Somalia) Shabaab Al-Mujahideen in Period of August 1st – August 31st, 2021: Tracking and Monitoring Al-Shabaab’s Activity in East Africa Region", "Strategic Intelligence,2022-02-03,Monthly Counter-Terrorism Intelligence Brief for East Africa (Kenya & Somalia) Shabaab Al-Mujahideen in Period of January 1st – January 31st, 2022: Tracking and Monitoring Al-Shabaab’s Activity in East Africa", "Strategic Intelligence,2021-09-13,Weekly Counter Terrorism Intelligence Brief for East Africa (Kenya & Somalia) Shabaab Al-Mujahideen in Period of September 1st – September 10th, 2021: Tracking and Monitoring Al-Shabaab’s Activity in East Africa (Kenya and Somalia)" |
| `source_office` | object | 36.1% | BBC Monitoring Africa, All Africa, Xinhua News Agency |
| `source_date` | object | 36.1% | 2021-09-02, 2022-02-03, 2021-09-13 |
| `source_headline` | object | 36.1% | Monthly Counter-Terrorism Intelligence Brief for East Africa (Kenya & Somalia) Shabaab Al-Mujahideen in Period of August 1st – August 31st, 2021: Tracking and Monitoring Al-Shabaab’s Activity in East Africa Region, Al-Shabaab Degraded by U.S., Federal Government of Somalia, Monthly Counter-Terrorism Intelligence Brief for East Africa (Kenya & Somalia) Shabaab Al-Mujahideen in Period of January 1st – January 31st, 2022: Tracking and Monitoring Al-Shabaab’s Activity in East Africa |
| `source_original` | object | 14.3% | |
| `where_prec` | int64 | 0.0% | 1.0 – 7.0 (mean 1.6386) |
| `where_coordinates` | object | 0.0% | |
| `where_description` | object | 4.1% | |
| `adm_1` | object | 0.8% | |
| `adm_2` | object | 8.5% | |
| `latitude` | float64 | 0.0% | -1.6367 – 12.4738 (mean 2.7965) |
| `longitude` | float64 | 0.0% | 40.9931 – 51.2667 (mean 44.7725) |
| `geom_wkt` | object | 0.0% | |
| `priogrid_gid` | int64 | 0.0% | 127164.0 – 147341.0 (mean 133838.4198) |
| `country` | object | 0.0% | |
| `iso3` | object | 0.0% | |
| `country_id` | int64 | 0.0% | 520.0 – 520.0 (mean 520.0) |
| `region` | object | 0.0% | |
| `event_clarity` | int64 | 0.0% | 1.0 – 2.0 (mean 1.0467) |
| `date_prec` | int64 | 0.0% | 1.0 – 5.0 (mean 1.2199) |
| `date_start` | datetime64[ns] | 0.0% | |
| `date_end` | datetime64[ns] | 0.0% | |
| `deaths_a` | int64 | 0.0% | 0.0 – 400.0 (mean 1.0734) |
| `deaths_b` | int64 | 0.0% | |
| `deaths_civilians` | int64 | 0.0% | |
| `deaths_unknown` | int64 | 0.0% | |
| `best` | int64 | 0.0% | |
| `high` | int64 | 0.0% | |
| `low` | int64 | 0.0% | |
| `gwnoa` | float64 | 18.8% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 11921.0 | 563077.0 | 188360.9275 | 176313.5 |
| `year` | 1989.0 | 2024.0 | 2013.6481 | 2015.0 |
| `type_of_violence` | 1.0 | 3.0 | 1.3151 | 1.0 |
| `conflict_dset_id` | 90.0 | 17635.0 | 1185.9578 | 337.0 |
| `conflict_new_id` | 329.0 | 16379.0 | 1113.7199 | 337.0 |
| `dyad_dset_id` | 90.0 | 18169.0 | 1508.6013 | 750.0 |
| `dyad_new_id` | 718.0 | 18169.0 | 1557.4713 | 750.0 |
| `side_a_dset_id` | 3.0 | 7229.0 | 234.4646 | 95.0 |
| `side_a_new_id` | 3.0 | 7229.0 | 234.4646 | 95.0 |
| `side_b_dset_id` | 234.0 | 9999.0 | 1699.3818 | 717.0 |
| `side_b_new_id` | 1.0 | 9260.0 | 674.5431 | 717.0 |
| `number_of_sources` | -1.0 | 32.0 | 0.93 | 1.0 |
| `where_prec` | 1.0 | 7.0 | 1.6386 | 1.0 |
| `latitude` | -1.6367 | 12.4738 | 2.7965 | 2.0667 |
| `longitude` | 40.9931 | 51.2667 | 44.7725 | 45.3667 |

---

## 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`. 1 column(s) with >80% missing values were removed: `gwnob`. 2 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 HDX 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: `source_office`, `source_date`, `source_headline`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/ucdp-data-for-somalia) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_ucdp_data_for_somalia,
title = {Somalia - Data on Conflict Events},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/ucdp-data-for-somalia},
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.*