electricsheepafrica/africa-sind-protection-in-danger-monthly-news-briefs-dataset

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-sa-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- aid-worker-security
- crisis-opt-israel-hostilities
- internally-displaced-persons-idp
- populated-places-settlements
- refugee-crisis
- refugees
- afg
- bgd
- blr
- bih
- bfa
pretty_name: "Protection in Danger Data"
dataset_info:
splits:
- name: train
num_examples: 6718
- name: test
num_examples: 1679
---

# Protection in Danger Data

**Publisher:** Insecurity Insight · **Source:** [HDX](https://data.humdata.org/dataset/sind-protection-in-danger-monthly-news-briefs-dataset) · **License:** `cc-by-sa` · **Updated:** 2026-04-13

---

## Abstract

This page contains violent agency- and open source events affecting refugee and IDP camps published in the [Protection in Danger Monthly News Brief](https://insecurityinsight.org/projects/ensuring-protection/protection-in-danger-monthly-news-brief-2). Categorized by country. Please get in touch if you are interested in curated datasets: [e-mail]

Each row in this dataset represents country-level aggregates. Temporal coverage is indicated by the `date`, `date_event_entered` column(s). Geographic scope: **AFG, BGD, BLR, BIH, BFA, CMR, CAF, TCD, and 42 others**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 8,398 |
| **Columns** | 29 (12 numeric, 14 categorical, 3 datetime) |
| **Train split** | 6,718 rows |
| **Test split** | 1,679 rows |
| **Geographic scope** | AFG, BGD, BLR, BIH, BFA, CMR, CAF, TCD, and 42 others |
| **Publisher** | Insecurity Insight |
| **HDX last updated** | 2026-04-13 |

---

## Variables

**Geographic** — `country` (OPT, Sudan, Syria), `country_iso` (PSE, SDN, SYR), `admin_1` (Gaza Strip, West Bank, North Darfur), `protection_event_context` (Airstrike/Shelling, Security Operation, Targetted Attack on Camp), `survivor_or_victim_sex`.

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

**Demographic** — `number_of_attacks_on_camps_reporting_damaged` (range 0.0–110.0).

**Outcome / Measurement** — `number_of_attacks_on_camps_reporting_destruction` (range 0.0–24.0).

**Identifier / Metadata** — `camp_name` (Temporary/Makeshift Site, Nuseirat Camp, Jabalia Camp), `reported_perpetrator_name` (Israeli Defence Forces, Rapid Support Forces, Armed men), `camp_resident_killed` (range 0.0–274.0), `camp_resident_injured` (range 0.0–647.0), `camp_residents_kidnapped` (range 0.0–137.0) and 9 others.

**Other** — `geo_precision` (censored), `reported_perpetrator` (Host Government: Military, NSA, Multiple), `weapon_carried_used` (Firearms, Aerial Bomb: Plane, Aerial Bomb: Drone), `victim_of_violence` (Camp Resident, No Direct Victim Reported, Health Worker ), `survivor_or_victim_minor`.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sind-protection-in-danger-monthly-news-briefs-dataset")
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, Sudan, Syria |
| `country_iso` | object | 0.0% | PSE, SDN, SYR |
| `admin_1` | object | 0.0% | Gaza Strip, West Bank, North Darfur |
| `geo_precision` | object | 0.0% | censored |
| `camp_name` | object | 4.5% | Temporary/Makeshift Site, Nuseirat Camp, Jabalia Camp |
| `reported_perpetrator` | object | 0.0% | Host Government: Military, NSA, Multiple |
| `reported_perpetrator_name` | object | 0.0% | Israeli Defence Forces, Rapid Support Forces, Armed men |
| `weapon_carried_used` | object | 0.0% | Firearms, Aerial Bomb: Plane, Aerial Bomb: Drone |
| `protection_event_context` | object | 0.7% | Airstrike/Shelling, Security Operation, Targetted Attack on Camp |
| `victim_of_violence` | object | 0.1% | Camp Resident, No Direct Victim Reported, Health Worker |
| `survivor_or_victim_sex` | object | 0.2% | |
| `survivor_or_victim_minor` | object | 0.4% | |
| `number_of_attacks_on_camps_reporting_destruction` | int64 | 0.0% | 0.0 – 24.0 (mean 0.01) |
| `number_of_attacks_on_camps_reporting_damaged` | int64 | 0.0% | 0.0 – 110.0 (mean 0.5925) |
| `camp_resident_killed` | int64 | 0.0% | 0.0 – 274.0 (mean 1.9402) |
| `camp_resident_injured` | int64 | 0.0% | 0.0 – 647.0 (mean 1.5569) |
| `camp_residents_kidnapped` | int64 | 0.0% | 0.0 – 137.0 (mean 0.0562) |
| `camp_residents_arrested` | int64 | 0.0% | 0.0 – 538.0 (mean 0.6081) |
| `camp_residents_targeted_with_crsv` | int64 | 0.0% | 0.0 – 32.0 (mean 0.021) |
| `service_provider_killed` | int64 | 0.0% | 0.0 – 11.0 (mean 0.0246) |
| `service_provider_kidnapped` | int64 | 0.0% | 0.0 – 5.0 (mean 0.0024) |
| `service_provider_arrested` | int64 | 0.0% | 0.0 – 70.0 (mean 0.0196) |
| `service_provider_targeted_with_crsv` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0005) |
| `sind_id` | int64 | 0.0% | 19018.0 – 126955.0 (mean 87731.1185) |
| `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 |
|---|---|---|---|---|
| `number_of_attacks_on_camps_reporting_destruction` | 0.0 | 24.0 | 0.01 | 0.0 |
| `number_of_attacks_on_camps_reporting_damaged` | 0.0 | 110.0 | 0.5925 | 1.0 |
| `camp_resident_killed` | 0.0 | 274.0 | 1.9402 | 0.0 |
| `camp_resident_injured` | 0.0 | 647.0 | 1.5569 | 0.0 |
| `camp_residents_kidnapped` | 0.0 | 137.0 | 0.0562 | 0.0 |
| `camp_residents_arrested` | 0.0 | 538.0 | 0.6081 | 0.0 |
| `camp_residents_targeted_with_crsv` | 0.0 | 32.0 | 0.021 | 0.0 |
| `service_provider_killed` | 0.0 | 11.0 | 0.0246 | 0.0 |
| `service_provider_kidnapped` | 0.0 | 5.0 | 0.0024 | 0.0 |
| `service_provider_arrested` | 0.0 | 70.0 | 0.0196 | 0.0 |
| `service_provider_targeted_with_crsv` | 0.0 | 2.0 | 0.0005 | 0.0 |
| `sind_id` | 19018.0 | 126955.0 | 87731.1185 | 92661.5 |

---

## 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`. 3 column(s) with >80% missing values were removed: `event_description`, `latitude`, `longitude`. 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 50 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/sind-protection-in-danger-monthly-news-briefs-dataset) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_sind_protection_in_danger_monthly_news_briefs_dataset,
title = {Protection in Danger Data},
author = {Insecurity Insight},
year = {2026},
url = {https://data.humdata.org/dataset/sind-protection-in-danger-monthly-news-briefs-dataset},
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.*