electricsheepafrica/africa-ucdp-data-for-angola

---
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
- ago
pretty_name: "Angola - Data on Conflict Events"
dataset_info:
splits:
- name: train
num_examples: 1686
- name: test
num_examples: 421
---

# Angola - Data on Conflict Events

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

*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)** | 2,108 |
| **Columns** | 48 (27 numeric, 18 categorical, 2 datetime) |
| **Train split** | 1,686 rows |
| **Test split** | 421 rows |
| **Geographic scope** | AGO |
| **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 99.0–15993.0), `dyad_new_id` (range 714.0–15993.0) and 9 others.

**Temporal** — `date_prec` (range 1.0–5.0), `date_start`, `date_end`.

**Outcome / Measurement** — `number_of_sources` (range -1.0–7.0), `deaths_a` (range 0.0–225.0), `deaths_b`, `deaths_civilians`, `deaths_unknown`.

**Identifier / Metadata** — `id` (range 20090.0–567485.0), `relid` (ANG-1989-1-7-3, ANG-2001-1-7-54, ANG-2001-1-7-51), `code_status` (Clear), `conflict_dset_id` (range 99.0–567.0), `conflict_new_id` (range 327.0–578.0) and 12 others.

**Other** — `where_prec` (range 1.0–6.0), `where_description` (Kuito town, Angola, Bie province), `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-angola")
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% | 20090.0 – 567485.0 (mean 45119.3686) |
| `relid` | object | 0.0% | ANG-1989-1-7-3, ANG-2001-1-7-54, ANG-2001-1-7-51 |
| `year` | int64 | 0.0% | 1989.0 – 2024.0 (mean 1996.9967) |
| `active_year` | bool | 0.0% | |
| `code_status` | object | 0.0% | Clear |
| `type_of_violence` | int64 | 0.0% | 1.0 – 3.0 (mean 1.3691) |
| `conflict_dset_id` | int64 | 0.0% | 99.0 – 567.0 (mean 352.167) |
| `conflict_new_id` | int64 | 0.0% | 327.0 – 578.0 (mean 375.148) |
| `conflict_name` | object | 0.0% | Angola: Government, Angola: Cabinda, UNITA - Civilians |
| `dyad_dset_id` | int64 | 0.0% | 99.0 – 15993.0 (mean 1329.7078) |
| `dyad_new_id` | int64 | 0.0% | 714.0 – 15993.0 (mean 1438.8667) |
| `dyad_name` | object | 0.0% | Government of Angola - UNITA, UNITA - Civilians, Government of Angola - FLEC-FAC |
| `side_a_dset_id` | int64 | 0.0% | 99.0 – 567.0 (mean 158.4991) |
| `side_a_new_id` | int64 | 0.0% | 99.0 – 567.0 (mean 158.4991) |
| `side_a` | object | 0.0% | Government of Angola, UNITA |
| `side_b_dset_id` | int64 | 0.0% | 540.0 – 9999.0 (mean 2600.7823) |
| `side_b_new_id` | int64 | 0.0% | 1.0 – 7412.0 (mean 755.8003) |
| `side_b` | object | 0.0% | UNITA, Civilians, FLEC-FAC |
| `number_of_sources` | int64 | 0.0% | -1.0 – 7.0 (mean -0.7249) |
| `source_article` | object | 0.0% | "Ad-Hoc Commission for Human Rights in Cabinda,2003-11-27,Angola: Cabinda 2003 - A Year of Pain", KUP news agency [UNITA's news agency] web site 1999-04-12, reported by BBC mon 1999-04-15 "UNITA military communique lists operations from 3rd to 7th April, AGGREGATION |
| `source_original` | object | 7.5% | UNITA, state radio, government |
| `where_prec` | int64 | 0.0% | 1.0 – 6.0 (mean 2.6276) |
| `where_coordinates` | object | 0.0% | Kuito town, Bie province, Angola |
| `where_description` | object | 1.2% | Kuito town, Angola, Bie province |
| `adm_1` | object | 4.9% | |
| `adm_2` | object | 36.7% | |
| `latitude` | float64 | 0.0% | -18.0167 – -4.45 (mean -10.3644) |
| `longitude` | float64 | 0.0% | 12.0833 – 23.4667 (mean 15.8026) |
| `geom_wkt` | object | 0.0% | |
| `priogrid_gid` | int64 | 0.0% | 103363.0 – 123506.0 (mean 114819.9303) |
| `country` | object | 0.0% | |
| `iso3` | object | 0.0% | |
| `country_id` | int64 | 0.0% | 540.0 – 540.0 (mean 540.0) |
| `region` | object | 0.0% | |
| `event_clarity` | int64 | 0.0% | 1.0 – 2.0 (mean 1.2804) |
| `date_prec` | int64 | 0.0% | 1.0 – 5.0 (mean 1.7922) |
| `date_start` | datetime64[ns] | 0.0% | |
| `date_end` | datetime64[ns] | 0.0% | |
| `deaths_a` | int64 | 0.0% | 0.0 – 225.0 (mean 0.6115) |
| `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 | 12.7% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 20090.0 | 567485.0 | 45119.3686 | 21509.5 |
| `year` | 1989.0 | 2024.0 | 1996.9967 | 1995.0 |
| `type_of_violence` | 1.0 | 3.0 | 1.3691 | 1.0 |
| `conflict_dset_id` | 99.0 | 567.0 | 352.167 | 327.0 |
| `conflict_new_id` | 327.0 | 578.0 | 375.148 | 327.0 |
| `dyad_dset_id` | 99.0 | 15993.0 | 1329.7078 | 714.0 |
| `dyad_new_id` | 714.0 | 15993.0 | 1438.8667 | 714.0 |
| `side_a_dset_id` | 99.0 | 567.0 | 158.4991 | 99.0 |
| `side_a_new_id` | 99.0 | 567.0 | 158.4991 | 99.0 |
| `side_b_dset_id` | 540.0 | 9999.0 | 2600.7823 | 567.0 |
| `side_b_new_id` | 1.0 | 7412.0 | 755.8003 | 567.0 |
| `number_of_sources` | -1.0 | 7.0 | -0.7249 | -1.0 |
| `where_prec` | 1.0 | 6.0 | 2.6276 | 2.0 |
| `latitude` | -18.0167 | -4.45 | -10.3644 | -10.85 |
| `longitude` | 12.0833 | 23.4667 | 15.8026 | 15.6667 |

---

## 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: `adm_2`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/ucdp-data-for-angola) for the publisher's own methodology notes and caveats.

---

## Citation

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