electricsheepafrica/africa-ucdp-data-for-burkina-faso

---
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
- bfa
pretty_name: "Burkina Faso - Data on Conflict Events"
dataset_info:
splits:
- name: train
num_examples: 1452
- name: test
num_examples: 363
---

# Burkina Faso - Data on Conflict Events

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

*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)** | 1,816 |
| **Columns** | 51 (27 numeric, 21 categorical, 2 datetime) |
| **Train split** | 1,452 rows |
| **Test split** | 363 rows |
| **Geographic scope** | BFA |
| **Publisher** | HDX |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `year` (range 2016.0–2024.0), `active_year`, `type_of_violence` (range 1.0–3.0), `dyad_dset_id` (range 78.0–16207.0), `dyad_new_id` (range 973.0–16207.0) and 9 others.

**Temporal** — `source_date` (2024-06-03, 2023-06-01, 2019-03-31), `date_prec` (range 1.0–5.0), `date_start`, `date_end`.

**Outcome / Measurement** — `number_of_sources` (range 1.0–25.0), `deaths_a` (range 0.0–150.0), `deaths_b`, `deaths_civilians`, `deaths_unknown`.

**Identifier / Metadata** — `id` (range 219115.0–569102.0), `relid` (AFG-2017-3-973-256, BFO-2023-1-15175-48, BFO-2023-1-15175-95.2), `code_status` (Clear), `conflict_dset_id` (range 78.0–16207.0), `conflict_new_id` (range 360.0–14864.0) and 14 others.

**Other** — `where_prec` (range 1.0–6.0), `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-burkina-faso")
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% | 219115.0 – 569102.0 (mean 431939.1663) |
| `relid` | object | 0.0% | AFG-2017-3-973-256, BFO-2023-1-15175-48, BFO-2023-1-15175-95.2 |
| `year` | int64 | 0.0% | 2016.0 – 2024.0 (mean 2021.7891) |
| `active_year` | bool | 0.0% | |
| `code_status` | object | 0.0% | Clear |
| `type_of_violence` | int64 | 0.0% | 1.0 – 3.0 (mean 1.6916) |
| `conflict_dset_id` | int64 | 0.0% | 78.0 – 16207.0 (mean 3518.0898) |
| `conflict_new_id` | int64 | 0.0% | 360.0 – 14864.0 (mean 4960.4427) |
| `conflict_name` | object | 0.0% | Burkina Faso: Government, JNIM - Civilians, Burkina Faso: Islamic State |
| `dyad_dset_id` | int64 | 0.0% | 78.0 – 16207.0 (mean 11488.0881) |
| `dyad_new_id` | int64 | 0.0% | 973.0 – 16207.0 (mean 13260.8128) |
| `dyad_name` | object | 0.0% | Government of Burkina Faso - JNIM, JNIM - Civilians, Government of Burkina Faso - IS |
| `side_a_dset_id` | int64 | 0.0% | 78.0 – 6857.0 (mean 1450.1074) |
| `side_a_new_id` | int64 | 0.0% | 78.0 – 6857.0 (mean 1450.1074) |
| `side_a` | object | 0.0% | Government of Burkina Faso, JNIM, IS |
| `side_b_dset_id` | int64 | 0.0% | 234.0 – 9999.0 (mean 7093.4345) |
| `side_b_new_id` | int64 | 0.0% | 1.0 – 6857.0 (mean 3784.625) |
| `side_b` | object | 0.0% | JNIM, Civilians, IS |
| `number_of_sources` | int64 | 0.0% | 1.0 – 25.0 (mean 1.929) |
| `source_article` | object | 0.0% | "FAN,2023-06-01,Information bulletin on operations to secure the national territory", "Radio tan Konnon,2019-02-02,Yirgou Massacre: 210 dead to date, according to the Collective Against Impunity";"Le Pays,2019-02-04,DRAMA OF YIRGOU", "“We Found Their Bodies Later That Day” Atrocities by Armed Islamists and Security Forces in Burkina Faso’s Sahel Region,2019-03-31,Burkina Faso Security Force Violations" |
| `source_office` | object | 0.0% | @AlerteTemoin, Crisis Watch, Agence d'Informations du Burkina |
| `source_date` | object | 0.0% | 2024-06-03, 2023-06-01, 2019-03-31 |
| `source_headline` | object | 0.0% | #BurkinaFaso, #Burkina, Tweet |
| `source_original` | object | 43.1% | |
| `where_prec` | int64 | 0.0% | 1.0 – 6.0 (mean 1.9928) |
| `where_coordinates` | object | 0.0% | |
| `where_description` | object | 0.5% | |
| `adm_1` | object | 1.0% | |
| `adm_2` | object | 2.5% | |
| `latitude` | float64 | 0.0% | 9.4295 – 15.0653 (mean 13.1668) |
| `longitude` | float64 | 0.0% | -5.2088 – 3.6588 (mean -1.1567) |
| `geom_wkt` | object | 0.0% | |
| `priogrid_gid` | int64 | 0.0% | 142915.0 – 151560.0 (mean 148553.6988) |
| `country` | object | 0.0% | |
| `iso3` | object | 0.0% | |
| `country_id` | int64 | 0.0% | 439.0 – 439.0 (mean 439.0) |
| `region` | object | 0.0% | |
| `event_clarity` | int64 | 0.0% | 1.0 – 2.0 (mean 1.076) |
| `date_prec` | int64 | 0.0% | 1.0 – 5.0 (mean 1.3194) |
| `date_start` | datetime64[ns] | 0.0% | |
| `date_end` | datetime64[ns] | 0.0% | |
| `deaths_a` | int64 | 0.0% | 0.0 – 150.0 (mean 1.8172) |
| `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 | 29.2% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 219115.0 | 569102.0 | 431939.1663 | 462720.0 |
| `year` | 2016.0 | 2024.0 | 2021.7891 | 2022.0 |
| `type_of_violence` | 1.0 | 3.0 | 1.6916 | 1.0 |
| `conflict_dset_id` | 78.0 | 16207.0 | 3518.0898 | 360.0 |
| `conflict_new_id` | 360.0 | 14864.0 | 4960.4427 | 360.0 |
| `dyad_dset_id` | 78.0 | 16207.0 | 11488.0881 | 15175.0 |
| `dyad_new_id` | 973.0 | 16207.0 | 13260.8128 | 15175.0 |
| `side_a_dset_id` | 78.0 | 6857.0 | 1450.1074 | 78.0 |
| `side_a_new_id` | 78.0 | 6857.0 | 1450.1074 | 78.0 |
| `side_b_dset_id` | 234.0 | 9999.0 | 7093.4345 | 6716.0 |
| `side_b_new_id` | 1.0 | 6857.0 | 3784.625 | 6716.0 |
| `number_of_sources` | 1.0 | 25.0 | 1.929 | 1.0 |
| `where_prec` | 1.0 | 6.0 | 1.9928 | 2.0 |
| `latitude` | 9.4295 | 15.0653 | 13.1668 | 13.4364 |
| `longitude` | -5.2088 | 3.6588 | -1.1567 | -1.0344 |

---

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

---

## Citation

```bibtex
@dataset{hdx_africa_ucdp_data_for_burkina_faso,
title = {Burkina Faso - Data on Conflict Events},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/ucdp-data-for-burkina-faso},
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.*