electricsheepafrica/africa-ucdp-data-for-kenya

---
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
- ken
pretty_name: "Kenya - Data on Conflict Events"
dataset_info:
splits:
- name: train
num_examples: 972
- name: test
num_examples: 243
---

# Kenya - Data on Conflict Events

**Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/ucdp-data-for-kenya) · **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: **KEN**.

*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)** | 1,215 |
| **Columns** | 51 (27 numeric, 21 categorical, 2 datetime) |
| **Train split** | 972 rows |
| **Test split** | 243 rows |
| **Geographic scope** | KEN |
| **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 90.0–16240.0), `dyad_new_id` (range 719.0–16240.0) and 9 others.

**Temporal** — `source_date` (2017-10-15, 2017-12-20, 2017-08-27), `date_prec` (range 1.0–5.0), `date_start`, `date_end`.

**Outcome / Measurement** — `number_of_sources` (range -1.0–26.0), `deaths_a` (range 0.0–121.0), `deaths_b`, `deaths_civilians`, `deaths_unknown`.

**Identifier / Metadata** — `id` (range 8933.0–559347.0), `relid` (ETH-2011-1-54-6, KEN-2009-2-405-2, KEN-2009-2-405-1), `code_status` (Clear), `conflict_dset_id` (range 90.0–15879.0), `conflict_new_id` (range 329.0–14592.0) 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-kenya")
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% | 8933.0 – 559347.0 (mean 181595.5449) |
| `relid` | object | 0.0% | ETH-2011-1-54-6, KEN-2009-2-405-2, KEN-2009-2-405-1 |
| `year` | int64 | 0.0% | 1989.0 – 2024.0 (mean 2012.4049) |
| `active_year` | bool | 0.0% | |
| `code_status` | object | 0.0% | Clear |
| `type_of_violence` | int64 | 0.0% | 1.0 – 3.0 (mean 2.0025) |
| `conflict_dset_id` | int64 | 0.0% | 90.0 – 15879.0 (mean 5816.3539) |
| `conflict_new_id` | int64 | 0.0% | 329.0 – 14592.0 (mean 5571.8156) |
| `conflict_name` | object | 0.0% | Kenya: Northeastern Province and Coast, Government of Kenya - Civilians, Pokot - Turkana |
| `dyad_dset_id` | int64 | 0.0% | 90.0 – 16240.0 (mean 5153.2247) |
| `dyad_new_id` | int64 | 0.0% | 719.0 – 16240.0 (mean 5321.1819) |
| `dyad_name` | object | 0.0% | Government of Kenya - Al-Shabaab, Government of Kenya - Civilians, Pokot - Turkana |
| `side_a_dset_id` | int64 | 0.0% | 90.0 – 7112.0 (mean 526.6798) |
| `side_a_new_id` | int64 | 0.0% | 90.0 – 7112.0 (mean 526.6798) |
| `side_a` | object | 0.0% | Government of Kenya, Pokot, Al-Shabaab |
| `side_b_dset_id` | int64 | 0.0% | 497.0 – 9999.0 (mean 3302.8535) |
| `side_b_new_id` | int64 | 0.0% | 1.0 – 7595.0 (mean 628.4914) |
| `side_b` | object | 0.0% | Civilians, Al-Shabaab, Turkana |
| `number_of_sources` | int64 | 0.0% | -1.0 – 26.0 (mean 0.9276) |
| `source_article` | object | 0.0% | Kenya National Commission on Human Rights, Report on Extra-Judicial Killings and Disappearances, September 2008, KENYA Tracking of killings and displacement in Pastoral areas, OCHA Annual Review", at http://reliefweb.int/sites/reliefweb.int/files/resources/9C18D2E8FB4F442CC1257808003B2038-Full_Report.pdf, Report of the UN Special Rapporteur on extrajudicial, summary or arbitrary executions Mr. Philip Alston, 26 may 2009 |
| `source_office` | object | 41.8% | The Star (Kenya), BBC Monitoring Africa, Xinhua News Agency |
| `source_date` | object | 41.8% | 2017-10-15, 2017-12-20, 2017-08-27 |
| `source_headline` | object | 41.8% | Still a Mirage - 4.2.1 Log of Deaths, RAIDING DEMOCRACY: The Slaughter of the Marakwet in Kerio Valley, Killings by Police in Kisumu and Siaya Counties |
| `source_original` | object | 30.6% | |
| `where_prec` | int64 | 0.0% | 1.0 – 7.0 (mean 2.1399) |
| `where_coordinates` | object | 0.0% | |
| `where_description` | object | 1.2% | |
| `adm_1` | object | 3.0% | |
| `adm_2` | object | 17.5% | |
| `latitude` | float64 | 0.0% | -4.5528 – 5.2562 (mean 0.8011) |
| `longitude` | float64 | 0.0% | 34.1532 – 41.867 (mean 38.049) |
| `geom_wkt` | object | 0.0% | |
| `priogrid_gid` | int64 | 0.0% | 122839.0 – 137232.0 (mean 130849.6716) |
| `country` | object | 0.0% | |
| `iso3` | object | 0.0% | |
| `country_id` | int64 | 0.0% | 501.0 – 501.0 (mean 501.0) |
| `region` | object | 0.0% | |
| `event_clarity` | int64 | 0.0% | 1.0 – 2.0 (mean 1.1037) |
| `date_prec` | int64 | 0.0% | 1.0 – 5.0 (mean 1.5317) |
| `date_start` | datetime64[ns] | 0.0% | |
| `date_end` | datetime64[ns] | 0.0% | |
| `deaths_a` | int64 | 0.0% | 0.0 – 121.0 (mean 1.2255) |
| `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 | 58.7% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 8933.0 | 559347.0 | 181595.5449 | 152642.0 |
| `year` | 1989.0 | 2024.0 | 2012.4049 | 2014.0 |
| `type_of_violence` | 1.0 | 3.0 | 2.0025 | 2.0 |
| `conflict_dset_id` | 90.0 | 15879.0 | 5816.3539 | 5314.0 |
| `conflict_new_id` | 329.0 | 14592.0 | 5571.8156 | 4704.0 |
| `dyad_dset_id` | 90.0 | 16240.0 | 5153.2247 | 5314.0 |
| `dyad_new_id` | 719.0 | 16240.0 | 5321.1819 | 5314.0 |
| `side_a_dset_id` | 90.0 | 7112.0 | 526.6798 | 670.0 |
| `side_a_new_id` | 90.0 | 7112.0 | 526.6798 | 670.0 |
| `side_b_dset_id` | 497.0 | 9999.0 | 3302.8535 | 717.0 |
| `side_b_new_id` | 1.0 | 7595.0 | 628.4914 | 693.0 |
| `number_of_sources` | -1.0 | 26.0 | 0.9276 | 1.0 |
| `where_prec` | 1.0 | 7.0 | 2.1399 | 2.0 |
| `latitude` | -4.5528 | 5.2562 | 0.8011 | 0.8167 |
| `longitude` | 34.1532 | 41.867 | 38.049 | 37.5833 |

---

## 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`, `source_original`, `gwnoa`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/ucdp-data-for-kenya) for the publisher's own methodology notes and caveats.

---

## Citation

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