electricsheepafrica/africa-explosive-weapons-use-affecting-aid-access-education-and-healthcare-services

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-sa-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- complex-emergency-conflict-security
- conflict-violence
- crisis-greater-middle-east
- afg
- ago
- arm
- aze
- bgd
pretty_name: "Explosive Weapons Monitor Data by Insecurity Insight"
dataset_info:
splits:
- name: train
num_examples: 12569
- name: test
num_examples: 3142
---

# Explosive Weapons Monitor Data by Insecurity Insight

**Publisher:** Insecurity Insight · **Source:** [HDX](https://data.humdata.org/dataset/explosive-weapons-use-affecting-aid-access-education-and-healthcare-services) · **License:** `cc-by-sa` · **Updated:** 2026-04-13

---

## Abstract

This page contains agency- and open source events in which aid access, education, food systems and health care services were impacted by [explosive weapons](https://insecurityinsight.org/projects/explosive-weapons). Categorized by country. Insecurity Insight collaborates with the [International Network on Explosive Weapons (INEW)](https://www.inew.org/) in producing research and analysis on the harm and use of explosive weapons for the [Explosive Weapons Monitor](https://www.explosiveweaponsmonitor.org/) by documenting their effects on health care, education, food systems and aid access. Please get in touch if you are interested in curated Resources: [e-mail]

Each row in this dataset represents discrete events or incidents. Temporal coverage is indicated by the `date`, `date_event_entered` column(s). Geographic scope: **AFG, AGO, ARM, AZE, BGD, BEL, BOL, BRA, and 46 others**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Discrete events or incidents |
| **Rows (total)** | 15,712 |
| **Columns** | 21 (5 numeric, 13 categorical, 3 datetime) |
| **Train split** | 12,569 rows |
| **Test split** | 3,142 rows |
| **Geographic scope** | AFG, AGO, ARM, AZE, BGD, BEL, BOL, BRA, and 46 others |
| **Publisher** | Insecurity Insight |
| **HDX last updated** | 2026-04-13 |

---

## Variables

**Geographic** — `country` (OPT, Ukraine, Myanmar), `country_iso` (PSE, UKR, MMR), `admin_1` (Gaza Strip, Donetsk Oblast, Kharkiv Oblast), `launch_type` (Air-Launched: Plane, Ground-Launched, Air-Launched: Drone), `explosive_weapon_type` (Aerial Bomb, Unspecified Explosive, Shelling) and 3 others.

**Temporal** — `date`, `date_event_entered`, `date_event_modified`.

**Outcome / Measurement** — `sector_affected` (Health Care, Protection, Education), `affected`.

**Identifier / Metadata** — `provider` (IDP/Refugee Service, Local Health Care Provider, Local Education Provider), `reported_perpetrator_name` (Israeli Defence Forces, Armed Forces of the Russian Federation, Unidentified Armed Actor), `idp_refugee_camp_building` (range 0.0–2.0), `sind_event_id` (range 19018.0–128406.0), `esa_source` and 1 others.

**Other** — `geo_precision` (censored), `reported_perpetrator` (Government: Military, Foreign Forces: Military, NSA).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-explosive-weapons-use-affecting-aid-access-education-and-healthcare-services")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `date` | datetime64[ns] | 0.0% | |
| `country` | object | 0.0% | OPT, Ukraine, Myanmar |
| `country_iso` | object | 0.0% | PSE, UKR, MMR |
| `admin_1` | object | 0.1% | Gaza Strip, Donetsk Oblast, Kharkiv Oblast |
| `geo_precision` | object | 0.0% | censored |
| `sector_affected` | object | 0.0% | Health Care, Protection, Education |
| `provider` | object | 0.0% | IDP/Refugee Service, Local Health Care Provider, Local Education Provider |
| `launch_type` | object | 0.0% | Air-Launched: Plane, Ground-Launched, Air-Launched: Drone |
| `explosive_weapon_type` | object | 0.0% | Aerial Bomb, Unspecified Explosive, Shelling |
| `reported_perpetrator` | object | 0.0% | Government: Military, Foreign Forces: Military, NSA |
| `reported_perpetrator_name` | object | 0.0% | Israeli Defence Forces, Armed Forces of the Russian Federation, Unidentified Armed Actor |
| `affected` | object | 0.0% | |
| `aid_infrastructure_damaged_destroyed` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0399) |
| `health_infrastructure_damaged_destroyed` | int64 | 0.0% | 0.0 – 3.0 (mean 0.2618) |
| `education_infrastructure_damaged_destroyed` | int64 | 0.0% | 0.0 – 3.0 (mean 0.2035) |
| `idp_refugee_camp_building` | int64 | 0.0% | 0.0 – 2.0 (mean 0.2888) |
| `sind_event_id` | int64 | 0.0% | 19018.0 – 128406.0 (mean 84977.1484) |
| `date_event_entered` | datetime64[ns] | 0.0% | |
| `date_event_modified` | datetime64[ns] | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `aid_infrastructure_damaged_destroyed` | 0.0 | 2.0 | 0.0399 | 0.0 |
| `health_infrastructure_damaged_destroyed` | 0.0 | 3.0 | 0.2618 | 0.0 |
| `education_infrastructure_damaged_destroyed` | 0.0 | 3.0 | 0.2035 | 0.0 |
| `idp_refugee_camp_building` | 0.0 | 2.0 | 0.2888 | 0.0 |
| `sind_event_id` | 19018.0 | 128406.0 | 84977.1484 | 89676.5 |

---

## 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`. 10 column(s) with >80% missing values were removed: `event_description`, `latitude`, `longitude`, `food_systems_damaged_destroyed`, `water_systems_damaged_destroyed`, `aid_workers_killed`.... 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 Insecurity Insight and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- This dataset spans 54 countries; geographic and methodological inconsistencies across national boundaries may affect cross-country comparability.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/explosive-weapons-use-affecting-aid-access-education-and-healthcare-services) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_explosive_weapons_use_affecting_aid_access_education_and_healthcare_services,
title = {Explosive Weapons Monitor Data by Insecurity Insight},
author = {Insecurity Insight},
year = {2026},
url = {https://data.humdata.org/dataset/explosive-weapons-use-affecting-aid-access-education-and-healthcare-services},
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.*