electricsheepafrica/africa-ucdp-data-for-guinea

---
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
- conflict-violence
- hxl
- gin
pretty_name: "Guinea - Data on Conflict Events"
dataset_info:
splits:
- name: train
num_examples: 66
- name: test
num_examples: 16
---

# Guinea - Data on Conflict Events

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

*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)** | 83 |
| **Columns** | 48 (27 numeric, 18 categorical, 2 datetime) |
| **Train split** | 66 rows |
| **Test split** | 16 rows |
| **Geographic scope** | GIN |
| **Publisher** | HDX |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `year` (range 1994.0–2021.0), `active_year`, `type_of_violence` (range 1.0–3.0), `dyad_dset_id` (range 77.0–16493.0), `dyad_new_id` (range 654.0–16493.0) and 9 others.

**Temporal** — `date_prec` (range 1.0–4.0), `date_start`, `date_end`.

**Outcome / Measurement** — `number_of_sources` (range -1.0–3.0), `deaths_a` (range 0.0–5.0), `deaths_b`, `deaths_civilians`, `deaths_unknown`.

**Identifier / Metadata** — `id` (range 11856.0–393367.0), `relid` (GUI-2000-1-57-2, SIE-1998-3-1384-41, GUI-2015-3-438-0), `code_status` (Clear), `conflict_dset_id` (range 77.0–16493.0), `conflict_new_id` (range 307.0–15103.0) and 12 others.

**Other** — `where_prec` (range 1.0–6.0), `where_description` (Conakry city, Conakry prefecture, Conakry region, Gueckedou town, Gueckedou prefecture, Nzrkor region, Macenta prefecture ((Macarbou vilalge in), Nzrkor region)), `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-guinea")
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% | 11856.0 – 393367.0 (mean 42753.0241) |
| `relid` | object | 0.0% | GUI-2000-1-57-2, SIE-1998-3-1384-41, GUI-2015-3-438-0 |
| `year` | int64 | 0.0% | 1994.0 – 2021.0 (mean 2005.1084) |
| `active_year` | bool | 0.0% | |
| `code_status` | object | 0.0% | Clear |
| `type_of_violence` | int64 | 0.0% | 1.0 – 3.0 (mean 2.3133) |
| `conflict_dset_id` | int64 | 0.0% | 77.0 – 16493.0 (mean 1107.1807) |
| `conflict_new_id` | int64 | 0.0% | 307.0 – 15103.0 (mean 1224.6627) |
| `conflict_name` | object | 0.0% | Government of Guinea - Civilians, Guinea: Government, RUF - Civilians |
| `dyad_dset_id` | int64 | 0.0% | 77.0 – 16493.0 (mean 1207.5181) |
| `dyad_new_id` | int64 | 0.0% | 654.0 – 16493.0 (mean 1682.1205) |
| `dyad_name` | object | 0.0% | Government of Guinea - Civilians, Government of Guinea - RFDG, RUF - Civilians |
| `side_a_dset_id` | int64 | 0.0% | 77.0 – 1713.0 (mean 285.3253) |
| `side_a_new_id` | int64 | 0.0% | 77.0 – 1713.0 (mean 285.3253) |
| `side_a` | object | 0.0% | Government of Guinea, RUF, Torma |
| `side_b_dset_id` | int64 | 0.0% | 463.0 – 9999.0 (mean 6358.9398) |
| `side_b_new_id` | int64 | 0.0% | 1.0 – 7813.0 (mean 336.0482) |
| `side_b` | object | 0.0% | Civilians, RFDG, Torma Manian |
| `number_of_sources` | int64 | 0.0% | -1.0 – 3.0 (mean -0.5904) |
| `source_article` | object | 0.0% | Amnesty InternationalOctober 2001, "Guinea and Sierra Leone: No place of refuge", 18, HRW Report, "Dying for Change", April 2007, Vol.18, No.5(A), Amnesty Report, AFR 29/003/2007 |
| `source_original` | object | 13.3% | witnesses, military sources, government |
| `where_prec` | int64 | 0.0% | 1.0 – 6.0 (mean 1.6988) |
| `where_coordinates` | object | 0.0% | Conakry city, Macenta town, Macenta prefecture |
| `where_description` | object | 0.0% | Conakry city, Conakry prefecture, Conakry region, Gueckedou town, Gueckedou prefecture, Nzrkor region, Macenta prefecture ((Macarbou vilalge in), Nzrkor region) |
| `adm_1` | object | 3.6% | |
| `adm_2` | object | 12.0% | |
| `latitude` | float64 | 0.0% | 7.3499 – 11.4167 (mean 9.1949) |
| `longitude` | float64 | 0.0% | -14.6167 – -8.5333 (mean -11.3618) |
| `geom_wkt` | object | 0.0% | |
| `priogrid_gid` | int64 | 0.0% | 140022.0 – 145782.0 (mean 142967.1446) |
| `country` | object | 0.0% | |
| `iso3` | object | 0.0% | |
| `country_id` | int64 | 0.0% | 438.0 – 438.0 (mean 438.0) |
| `region` | object | 0.0% | |
| `event_clarity` | int64 | 0.0% | 1.0 – 2.0 (mean 1.0361) |
| `date_prec` | int64 | 0.0% | 1.0 – 4.0 (mean 1.3494) |
| `date_start` | datetime64[ns] | 0.0% | |
| `date_end` | datetime64[ns] | 0.0% | |
| `deaths_a` | int64 | 0.0% | 0.0 – 5.0 (mean 0.1687) |
| `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 | 25.3% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 11856.0 | 393367.0 | 42753.0241 | 12770.0 |
| `year` | 1994.0 | 2021.0 | 2005.1084 | 2006.0 |
| `type_of_violence` | 1.0 | 3.0 | 2.3133 | 3.0 |
| `conflict_dset_id` | 77.0 | 16493.0 | 1107.1807 | 307.0 |
| `conflict_new_id` | 307.0 | 15103.0 | 1224.6627 | 458.0 |
| `dyad_dset_id` | 77.0 | 16493.0 | 1207.5181 | 532.0 |
| `dyad_new_id` | 654.0 | 16493.0 | 1682.1205 | 925.0 |
| `side_a_dset_id` | 77.0 | 1713.0 | 285.3253 | 77.0 |
| `side_a_new_id` | 77.0 | 1713.0 | 285.3253 | 77.0 |
| `side_b_dset_id` | 463.0 | 9999.0 | 6358.9398 | 9999.0 |
| `side_b_new_id` | 1.0 | 7813.0 | 336.0482 | 1.0 |
| `number_of_sources` | -1.0 | 3.0 | -0.5904 | -1.0 |
| `where_prec` | 1.0 | 6.0 | 1.6988 | 1.0 |
| `latitude` | 7.3499 | 11.4167 | 9.1949 | 9.3667 |
| `longitude` | -14.6167 | -8.5333 | -11.3618 | -10.7333 |

---

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

---

## Citation

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