electricsheepafrica/africa-somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites

--- annotations_creators: - no-annotation language_creators: - found language: - en license: cc-by-sa-4.0 multilinguality: - monolingual size_categories: - n<1K source_datasets: - original task_categories: - tabular-classification - tabular-regression - other task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - aid-worker-security - aid-workers - complex-emergency-conflict-security - conflict-violence - damage-assessment - disease - education - education-facilities-schools - som pretty_name: "Somalia (SOM): Attacks on Aid Operations, Education, Food and Water Systems and Health Care" dataset_info: splits: - name: train num_examples: 267 - name: test num_examples: 66 --- # Somalia (SOM): Attacks on Aid Operations, Education, Food and Water Systems and Health Care **Publisher:** Insecurity Insight · **Source:** [HDX](https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites) · **License:** `cc-by-sa` · **Updated:** 2026-04-06 --- ## Abstract This page contains information on reported incidents of violence and threats affecting aid operations and workers, education, food systems and health care services in [Somalia](https://insecurityinsight.org/country-pages/somalia). Also included are datasets cited in the [Safeguarding Health in Conflict Coalition (SHCC)'s](https://www.safeguardinghealth.org/) annual reports. Please get in touch if you are interested in curated datasets: [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: **SOM**. *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)** | 334 | | **Columns** | 42 (26 numeric, 13 categorical, 3 datetime) | | **Train split** | 267 rows | | **Test split** | 66 rows | | **Geographic scope** | SOM | | **Publisher** | Insecurity Insight | | **HDX last updated** | 2026-04-06 | --- ## Variables **Geographic** — `country` (Somalia), `country_iso` (SOM), `admin_1` (Banaadir, No Information, Bay), `location_of_incident` (Road, No information, Compound or Office Building), `aid_workers_killed_in_captivity` (range 0.0–7.0) and 4 others. **Temporal** — `date`, `date_event_entered`, `date_event_modified`. **Demographic** — `female_aid_workers_killed` (range 0.0–2.0), `male_aid_workers_killed` (range 0.0–3.0), `female_aid_workers_injured` (range 0.0–2.0), `male_aid_workers_injured` (range 0.0–5.0), `female_aid_workers_kidnapped` (range 0.0–3.0) and 3 others. **Outcome / Measurement** — `organisation_affected` (INGO, UN Agency, LNGO). **Identifier / Metadata** — `reported_perpetrator_name` (Unidentified armed actor, Al-Shabaab, Militia), `aid_workers_killed` (range 0.0–14.0), `aid_workers_injured` (range 0.0–7.0), `aid_workers_kidnapped` (range 0.0–12.0), `aid_workers_arrested` (range 0.0–6.0) and 12 others. **Other** — `geo_precision` (censored), `reported_perpetrator` (NSA, No Information, Police), `weapon_carried_used` (Firearms, No Information on the Weapon Used, Hand Grenade), `programme_focus` (No information, Health, Hunger). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites") 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% | Somalia | | `country_iso` | object | 0.0% | SOM | | `admin_1` | object | 0.0% | Banaadir, No Information, Bay | | `geo_precision` | object | 0.0% | censored | | `location_of_incident` | object | 0.0% | Road, No information, Compound or Office Building | | `reported_perpetrator` | object | 0.0% | NSA, No Information, Police | | `reported_perpetrator_name` | object | 0.0% | Unidentified armed actor, Al-Shabaab, Militia | | `weapon_carried_used` | object | 0.0% | Firearms, No Information on the Weapon Used, Hand Grenade | | `organisation_affected` | object | 0.0% | INGO, UN Agency, LNGO | | `programme_focus` | object | 0.0% | No information, Health, Hunger | | `aid_workers_killed` | int64 | 0.0% | 0.0 – 14.0 (mean 0.6198) | | `aid_workers_injured` | int64 | 0.0% | 0.0 – 7.0 (mean 0.5329) | | `aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 12.0 (mean 0.8174) | | `aid_workers_arrested` | int64 | 0.0% | 0.0 – 6.0 (mean 0.1347) | | `known_kidnapping_or_arrest_outcome` | object | 62.9% | | | `aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 7.0 (mean 0.0329) | | `international_aid_workers_killed` | int64 | 0.0% | 0.0 – 4.0 (mean 0.0749) | | `international_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) | | `national_aid_workers_killed` | int64 | 0.0% | 0.0 – 14.0 (mean 0.485) | | `national_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 7.0 (mean 0.0329) | | `female_aid_workers_killed` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0479) | | `female_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) | | `male_aid_workers_killed` | int64 | 0.0% | 0.0 – 3.0 (mean 0.3772) | | `male_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 1.0 (mean 0.012) | | `international_aid_workers_injured` | int64 | 0.0% | 0.0 – 5.0 (mean 0.0569) | | `national_aid_workers_injured` | int64 | 0.0% | 0.0 – 7.0 (mean 0.3503) | | `female_aid_workers_injured` | int64 | 0.0% | 0.0 – 2.0 (mean 0.0269) | | `male_aid_workers_injured` | int64 | 0.0% | 0.0 – 5.0 (mean 0.2216) | | `international_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 12.0 (mean 0.2545) | | `national_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 10.0 (mean 0.4641) | | `female_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 3.0 (mean 0.0629) | | `male_aid_workers_kidnapped` | int64 | 0.0% | | | `international_aid_workers_arrested` | int64 | 0.0% | | | `national_aid_workers_arrested` | int64 | 0.0% | | | `female_aid_workers_arrested` | int64 | 0.0% | | | `male_aid_workers_arrested` | int64 | 0.0% | | | `sind_event_id` | int64 | 0.0% | | | `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_workers_killed` | 0.0 | 14.0 | 0.6198 | 0.0 | | `aid_workers_injured` | 0.0 | 7.0 | 0.5329 | 0.0 | | `aid_workers_kidnapped` | 0.0 | 12.0 | 0.8174 | 0.0 | | `aid_workers_arrested` | 0.0 | 6.0 | 0.1347 | 0.0 | | `aid_workers_killed_in_captivity` | 0.0 | 7.0 | 0.0329 | 0.0 | | `international_aid_workers_killed` | 0.0 | 4.0 | 0.0749 | 0.0 | | `international_aid_workers_killed_in_captivity` | 0.0 | 0.0 | 0.0 | 0.0 | | `national_aid_workers_killed` | 0.0 | 14.0 | 0.485 | 0.0 | | `national_aid_workers_killed_in_captivity` | 0.0 | 7.0 | 0.0329 | 0.0 | | `female_aid_workers_killed` | 0.0 | 2.0 | 0.0479 | 0.0 | | `female_aid_workers_killed_in_captivity` | 0.0 | 0.0 | 0.0 | 0.0 | | `male_aid_workers_killed` | 0.0 | 3.0 | 0.3772 | 0.0 | | `male_aid_workers_killed_in_captivity` | 0.0 | 1.0 | 0.012 | 0.0 | | `international_aid_workers_injured` | 0.0 | 5.0 | 0.0569 | 0.0 | | `national_aid_workers_injured` | 0.0 | 7.0 | 0.3503 | 0.0 | --- ## 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. - The following columns have >20% missing values and should be treated with caution in modelling: `known_kidnapping_or_arrest_outcome`. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_somalia_violence_agaiinst_civilian_and_vital_civilian_facilitites, title = {Somalia (SOM): Attacks on Aid Operations, Education, Food and Water Systems and Health Care}, author = {Insecurity Insight}, year = {2026}, url = {https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites}, 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.*--- 注释创建者： - 无注释 语言创建者： - 采集所得 语言： - 英语 许可证：CC BY-SA 4.0 多语言属性： - 单语言 规模类别： - 样本数少于1000 源数据集： - 原创数据集 任务类别： - 表格分类 - 表格回归 - 其他 任务子类别： - 无 标签： - 非洲 - 人道主义 - 人道主义数据交换（HDX） - Electric Sheep Africa - 援助人员安全 - 援助人员 - 复杂紧急冲突安全 - 冲突暴力 - 损害评估 - 疾病 - 教育 - 教育设施-学校 - 索马里（SOM） 数据集名称："索马里（SOM）：针对援助行动、教育、粮食与水系统及医疗保健的袭击事件" 数据集信息： 拆分情况： - 名称：训练集，样本数：267 - 名称：测试集，样本数：66 --- # 索马里（SOM）：针对援助行动、教育、粮食与水系统及医疗保健的袭击事件 **发布方：Insecurity Insight · **来源：[HDX](https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites) · **许可证：**`cc-by-sa` · **更新时间：**2026-04-06 --- ## 摘要 本页面收录了索马里（https://insecurityinsight.org/country-pages/somalia）境内已上报的、影响援助行动与人员、教育、粮食系统及医疗服务的暴力与威胁事件信息。同时收录了冲突中卫生保障联盟（Safeguarding Health in Conflict Coalition, SHCC）年度报告中引用的数据集。若您希望获取经过整理的数据集，请联系：[e-mail]。 本数据集的每一行代表一个独立的事件或事故。时间覆盖范围由`date`、`date_event_entered`列标注。地理覆盖范围：**SOM（索马里）**。 *本数据集经[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的Parquet格式。* --- ## 数据集特征 | | | |---|---| | **领域** | 粮食安全与营养 | | **观测单元** | 独立事件或事故 | | **总行数** | 334 | | **列数** | 42（26个数值型、13个分类型、3个日期时间型） | | **训练集拆分** | 267行 | | **测试集拆分** | 66行 | | **地理覆盖范围** | SOM（索马里） | | **发布方** | Insecurity Insight | | **HDX最后更新时间** | 2026-04-06 | --- ## 变量分类 ### 地理变量 `country`（国家：索马里）、`country_iso`（国家ISO代码：SOM）、`admin_1`（一级行政区域：巴纳迪尔、无信息、贝）、`location_of_incident`（事件发生地点：道路、无信息、建筑群或办公楼）、`aid_workers_killed_in_captivity`（被囚禁期间遇难的援助人员，取值范围0.0–7.0）等共4项。 ### 时间变量 `date`（事件日期）、`date_event_entered`（事件录入日期）、`date_event_modified`（事件修改日期）。 ### 人口统计变量 `female_aid_workers_killed`（遇难女性援助人员，取值范围0.0–2.0）、`male_aid_workers_killed`（遇难男性援助人员，取值范围0.0–3.0）、`female_aid_workers_injured`（受伤女性援助人员，取值范围0.0–2.0）、`male_aid_workers_injured`（受伤男性援助人员，取值范围0.0–5.0）、`female_aid_workers_kidnapped`（被绑架女性援助人员，取值范围0.0–3.0）等共3项。 ### 结果/测量变量 `organisation_affected`（受影响机构：国际非政府组织、联合国机构、本地非政府组织）。 ### 标识符/元数据变量 `reported_perpetrator_name`（上报的作案者姓名：不明武装人员、青年党、民兵）、`aid_workers_killed`（遇难援助人员，取值范围0.0–14.0）、`aid_workers_injured`（受伤援助人员，取值范围0.0–7.0）、`aid_workers_kidnapped`（被绑架援助人员，取值范围0.0–12.0）、`aid_workers_arrested`（被逮捕援助人员，取值范围0.0–6.0）等共12项。 ### 其他变量 `geo_precision`（地理精度：已脱敏）、`reported_perpetrator`（上报的作案者：国家安全局、无信息、警方）、`weapon_carried_used`（携带/使用的武器：枪械、无武器使用信息、手榴弹）、`programme_focus`（项目聚焦方向：无信息、医疗、饥荒救助）。 --- ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据结构 | 列名 | 数据类型 | 缺失率 | 取值范围/示例值 | |---|---|---|---| | `date` | datetime64[ns] | 0.0% | | | `country` | object | 0.0% | 索马里 | | `country_iso` | object | 0.0% | SOM | | `admin_1` | object | 0.0% | 巴纳迪尔、无信息、贝 | | `geo_precision` | object | 0.0% | 已脱敏 | | `location_of_incident` | object | 0.0% | 道路、无信息、建筑群或办公楼 | | `reported_perpetrator` | object | 0.0% | 国家安全局、无信息、警方 | | `reported_perpetrator_name` | object | 0.0% | 不明武装人员、青年党、民兵 | | `weapon_carried_used` | object | 0.0% | 枪械、无武器使用信息、手榴弹 | | `organisation_affected` | object | 0.0% | 国际非政府组织、联合国机构、本地非政府组织 | | `programme_focus` | object | 0.0% | 无信息、医疗、饥荒救助 | | `aid_workers_killed` | int64 | 0.0% | 0.0 – 14.0（均值0.6198） | | `aid_workers_injured` | int64 | 0.0% | 0.0 – 7.0（均值0.5329） | | `aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 12.0（均值0.8174） | | `aid_workers_arrested` | int64 | 0.0% | 0.0 – 6.0（均值0.1347） | | `known_kidnapping_or_arrest_outcome` | object | 62.9% | | | `aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 7.0（均值0.0329） | | `international_aid_workers_killed` | int64 | 0.0% | 0.0 – 4.0（均值0.0749） | | `international_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 0.0（均值0.0） | | `national_aid_workers_killed` | int64 | 0.0% | 0.0 – 14.0（均值0.485） | | `national_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 7.0（均值0.0329） | | `female_aid_workers_killed` | int64 | 0.0% | 0.0 – 2.0（均值0.0479） | | `female_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 0.0（均值0.0） | | `male_aid_workers_killed` | int64 | 0.0% | 0.0 – 3.0（均值0.3772） | | `male_aid_workers_killed_in_captivity` | int64 | 0.0% | 0.0 – 1.0（均值0.012） | | `international_aid_workers_injured` | int64 | 0.0% | 0.0 – 5.0（均值0.0569） | | `national_aid_workers_injured` | int64 | 0.0% | 0.0 – 7.0（均值0.3503） | | `female_aid_workers_injured` | int64 | 0.0% | 0.0 – 2.0（均值0.0269） | | `male_aid_workers_injured` | int64 | 0.0% | 0.0 – 5.0（均值0.2216） | | `international_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 12.0（均值0.2545） | | `national_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 10.0（均值0.4641） | | `female_aid_workers_kidnapped` | int64 | 0.0% | 0.0 – 3.0（均值0.0629） | | `male_aid_workers_kidnapped` | int64 | 0.0% | | | `international_aid_workers_arrested` | int64 | 0.0% | | | `national_aid_workers_arrested` | int64 | 0.0% | | | `female_aid_workers_arrested` | int64 | 0.0% | | | `male_aid_workers_arrested` | int64 | 0.0% | | | `sind_event_id` | int64 | 0.0% | | | `date_event_entered` | datetime64[ns] | 0.0% | | | `date_event_modified` | datetime64[ns] | 0.0% | | | `esa_source` | object | 0.0% | | | `esa_processed` | object | 0.0% | | --- ## 数值型变量统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `aid_workers_killed` | 0.0 | 14.0 | 0.6198 | 0.0 | | `aid_workers_injured` | 0.0 | 7.0 | 0.5329 | 0.0 | | `aid_workers_kidnapped` | 0.0 | 12.0 | 0.8174 | 0.0 | | `aid_workers_arrested` | 0.0 | 6.0 | 0.1347 | 0.0 | | `aid_workers_killed_in_captivity` | 0.0 | 7.0 | 0.0329 | 0.0 | | `international_aid_workers_killed` | 0.0 | 4.0 | 0.0749 | 0.0 | | `international_aid_workers_killed_in_captivity` | 0.0 | 0.0 | 0.0 | 0.0 | | `national_aid_workers_killed` | 0.0 | 14.0 | 0.485 | 0.0 | | `national_aid_workers_killed_in_captivity` | 0.0 | 7.0 | 0.0329 | 0.0 | | `female_aid_workers_killed` | 0.0 | 2.0 | 0.0479 | 0.0 | | `female_aid_workers_killed_in_captivity` | 0.0 | 0.0 | 0.0 | 0.0 | | `male_aid_workers_killed` | 0.0 | 3.0 | 0.3772 | 0.0 | | `male_aid_workers_killed_in_captivity` | 0.0 | 1.0 | 0.012 | 0.0 | | `international_aid_workers_injured` | 0.0 | 5.0 | 0.0569 | 0.0 | | `national_aid_workers_injured` | 0.0 | 7.0 | 0.3503 | 0.0 | --- ## 数据整理流程 原始数据通过CKAN应用程序编程接口（API）从HDX下载，并转换为Parquet格式。将列名转换为小写并统一为蛇形命名法。将常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。删除了3个缺失值占比超过80%的列：`event_description`、`latitude`、`longitude`。使用固定随机种子（42）将数据集按80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式。 --- ## 数据集局限性 - 数据源自Insecurity Insight，未经过Electric Sheep Africa的独立验证。 - 自动化清洗无法修正原始数据收集中的错报值、定义不一致或采样偏差问题。 - 以下列的缺失值占比超过20%，在建模过程中需谨慎使用：`known_kidnapping_or_arrest_outcome`。 - 如需了解发布方的方法论说明与免责声明，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites)。 --- ## 引用格式 bibtex @dataset{hdx_africa_somalia_violence_agaiinst_civilian_and_vital_civilian_facilitites, title = {索马里（SOM）：针对援助行动、教育、粮食与水系统及医疗保健的袭击事件}, author = {Insecurity Insight}, year = {2026}, url = {https://data.humdata.org/dataset/somalia-violence-agaiinst-civilian-and-vital-civilian-facilitites}, note = {经Electric Sheep Africa（https://huggingface.co/electricsheepafrica）重新打包以适配机器学习场景} } --- *[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — 非洲的机器学习数据集基础设施。尼日利亚拉各斯。*