electricsheepafrica/africa-conflict-libya

---
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
- lby
pretty_name: "Libya - Data on Conflict Events"
dataset_info:
splits:
- name: train
num_examples: 1010
- name: test
num_examples: 252
---

# Libya - Data on Conflict Events

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

*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)** | 1,263 |
| **Columns** | 50 (27 numeric, 20 categorical, 2 datetime) |
| **Train split** | 1,010 rows |
| **Test split** | 252 rows |
| **Geographic scope** | LBY |
| **Publisher** | HDX |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `year` (range 2008.0–2024.0), `active_year`, `type_of_violence` (range 1.0–3.0), `dyad_dset_id` (range 111.0–17497.0), `dyad_new_id` (range 524.0–17497.0) and 9 others.

**Temporal** — `source_date` (2016-06-16, 2015-11-16, 2018-04-01), `date_prec` (range 1.0–5.0), `date_start`, `date_end`.

**Outcome / Measurement** — `number_of_sources` (range -1.0–14.0), `deaths_a` (range 0.0–214.0), `deaths_b`, `deaths_civilians`, `deaths_unknown`.

**Identifier / Metadata** — `id` (range 32485.0–529672.0), `relid` (IRQ-2015-1-448-732, LIB-2016-1-14745-101, LIB-2016-1-14745-133), `code_status` (Clear), `conflict_dset_id` (range 111.0–16051.0), `conflict_new_id` (range 259.0–14733.0) and 14 others.

**Other** — `where_prec` (range 1.0–6.0), `where_description`, `adm_1`, `geom_wkt`, `best` and 3 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-conflict-libya")
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% | 32485.0 – 529672.0 (mean 212833.0673) |
| `relid` | object | 0.0% | IRQ-2015-1-448-732, LIB-2016-1-14745-101, LIB-2016-1-14745-133 |
| `year` | int64 | 0.0% | 2008.0 – 2024.0 (mean 2015.848) |
| `active_year` | bool | 0.0% | |
| `code_status` | object | 0.0% | Clear |
| `type_of_violence` | int64 | 0.0% | 1.0 – 3.0 (mean 1.4521) |
| `conflict_dset_id` | int64 | 0.0% | 111.0 – 16051.0 (mean 12412.4814) |
| `conflict_new_id` | int64 | 0.0% | 259.0 – 14733.0 (mean 12038.0602) |
| `conflict_name` | object | 0.0% | Libya: Government, Benghazi Revolutionaries Shura Council - Forces of the House of Representatives, Libya: Islamic State |
| `dyad_dset_id` | int64 | 0.0% | 111.0 – 17497.0 (mean 13434.5004) |
| `dyad_new_id` | int64 | 0.0% | 524.0 – 17497.0 (mean 13460.8535) |
| `dyad_name` | object | 0.0% | Government of Libya - Forces of the House of Representatives, Government of Libya - NTC, Benghazi Revolutionaries Shura Council - Forces of the House of Representatives |
| `side_a_dset_id` | int64 | 0.0% | 111.0 – 7456.0 (mean 2105.3373) |
| `side_a_new_id` | int64 | 0.0% | 111.0 – 7456.0 (mean 2105.3373) |
| `side_a` | object | 0.0% | Government of Libya, Benghazi Revolutionaries Shura Council, DPF |
| `side_b_dset_id` | int64 | 0.0% | 234.0 – 9999.0 (mean 3962.726) |
| `side_b_new_id` | int64 | 0.0% | 1.0 – 8635.0 (mean 3614.4188) |
| `side_b` | object | 0.0% | Forces of the House of Representatives, IS, NTC |
| `number_of_sources` | int64 | 0.0% | -1.0 – 14.0 (mean 1.1995) |
| `source_article` | object | 0.0% | "Libya Security Monitor,2016-06-16,April 2016 SigActs:", "UNSMIL & OHCHR,2015-11-16,REPORT ON THE HUMAN RIGHTS SITUATION IN LIBYA 16 November 2015 ", "Garda World,2019-05-17,Weekly Libya .Xplored preview" |
| `source_office` | object | 18.5% | BBC Monitoring Middle East, Reuters News, Agence France Presse |
| `source_date` | object | 18.5% | 2016-06-16, 2015-11-16, 2018-04-01 |
| `source_headline` | object | 19.8% | REPORT ON THE HUMAN RIGHTS SITUATION IN LIBYA 16 November 2015, April 2016 SigActs:, Weekly Libya .Xplored preview |
| `source_original` | object | 2.0% | |
| `where_prec` | int64 | 0.0% | 1.0 – 6.0 (mean 1.4838) |
| `where_coordinates` | object | 0.0% | |
| `where_description` | object | 4.1% | |
| `adm_1` | object | 1.7% | |
| `latitude` | float64 | 0.0% | 20.8505 – 33.1667 (mean 31.5149) |
| `longitude` | float64 | 0.0% | 10.8106 – 24.8165 (mean 16.6709) |
| `geom_wkt` | object | 0.0% | |
| `priogrid_gid` | int64 | 0.0% | 159530.0 – 177504.0 (mean 175007.3777) |
| `country` | object | 0.0% | |
| `iso3` | object | 0.0% | |
| `country_id` | int64 | 0.0% | 620.0 – 620.0 (mean 620.0) |
| `region` | object | 0.0% | |
| `event_clarity` | int64 | 0.0% | 1.0 – 2.0 (mean 1.118) |
| `date_prec` | int64 | 0.0% | 1.0 – 5.0 (mean 1.4466) |
| `date_start` | datetime64[ns] | 0.0% | |
| `date_end` | datetime64[ns] | 0.0% | |
| `deaths_a` | int64 | 0.0% | 0.0 – 214.0 (mean 2.7728) |
| `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 | 41.1% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 32485.0 | 529672.0 | 212833.0673 | 236171.0 |
| `year` | 2008.0 | 2024.0 | 2015.848 | 2016.0 |
| `type_of_violence` | 1.0 | 3.0 | 1.4521 | 1.0 |
| `conflict_dset_id` | 111.0 | 16051.0 | 12412.4814 | 11346.0 |
| `conflict_new_id` | 259.0 | 14733.0 | 12038.0602 | 11346.0 |
| `dyad_dset_id` | 111.0 | 17497.0 | 13434.5004 | 14061.0 |
| `dyad_new_id` | 524.0 | 17497.0 | 13460.8535 | 14061.0 |
| `side_a_dset_id` | 111.0 | 7456.0 | 2105.3373 | 111.0 |
| `side_a_new_id` | 111.0 | 7456.0 | 2105.3373 | 111.0 |
| `side_b_dset_id` | 234.0 | 9999.0 | 3962.726 | 5802.0 |
| `side_b_new_id` | 1.0 | 8635.0 | 3614.4188 | 5802.0 |
| `number_of_sources` | -1.0 | 14.0 | 1.1995 | 1.0 |
| `where_prec` | 1.0 | 6.0 | 1.4838 | 1.0 |
| `latitude` | 20.8505 | 33.1667 | 31.5149 | 32.1177 |
| `longitude` | 10.8106 | 24.8165 | 16.6709 | 16.3895 |

---

## 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`. 2 column(s) with >80% missing values were removed: `adm_2`, `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-libya) for the publisher's own methodology notes and caveats.

---

## Citation

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