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.*annotations_creators: - 无注释 language_creators: - 现有资源获取 language: - 英语 license: CC BY-SA 4.0 multilinguality: - 单语言 size_categories: - 10000 < 样本量 < 100000 source_datasets: - 原创数据集 task_categories: - 表格分类 - 表格回归 - 其他 task_ids: [] tags: - 非洲 - 人道主义 - HDX（Humanitarian Data Exchange） - Electric Sheep Africa - 复杂紧急冲突与安全 - 冲突暴力 - 大中东危机 - AFG - AGO - ARM - AZE - BGD pretty_name: "Insecurity Insight 爆炸武器监测数据集" dataset_info: splits: - name: 训练集 num_examples: 12569 - name: 测试集 num_examples: 3142 --- # Insecurity Insight 爆炸武器监测数据集 **发布方：Insecurity Insight · 来源：[HDX（Humanitarian Data Exchange）](https://data.humdata.org/dataset/explosive-weapons-use-affecting-aid-access-education-and-healthcare-services) · 许可证：`CC BY-SA` · 最后更新：2026-04-13** --- ## 摘要 本页面收录了来自机构及开源渠道的事件记录，这些事件中，援助通道、教育系统、粮食体系与医疗服务均受到[爆炸武器（explosive weapons）](https://insecurityinsight.org/projects/explosive-weapons)的影响，数据按国家分类整理。Insecurity Insight 与[国际爆炸武器网络（International Network on Explosive Weapons, INEW）](https://www.inew.org/)合作，通过记录爆炸武器对医疗、教育、粮食体系及援助通道的影响，为[爆炸武器监测平台（Explosive Weapons Monitor）](https://www.explosiveweaponsmonitor.org/)提供相关研究与分析。若您希望获取精选资源，请联系：[e-mail]。 本数据集的每一行代表一起独立事件或事故。时间覆盖范围由`date`、`date_event_entered`两个字段标注。地理覆盖范围：**阿富汗（AFG）、安哥拉（AGO）、亚美尼亚（ARM）、阿塞拜疆（AZE）、孟加拉国（BGD）、比利时（BEL）、玻利维亚（BOL）、巴西（BRA）以及另外46个国家**。 *本数据集已由[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** | 15712 | | **字段数** | 21（5个数值型字段、13个分类型字段、3个日期时间型字段） | | **训练集样本量** | 12569 | | **测试集样本量** | 3142 | | **地理覆盖范围** | AFG、AGO、ARM、AZE、BGD、BEL、BOL、BRA 及另外46个国家 | | **发布方** | Insecurity Insight | | **HDX最后更新时间** | 2026-04-13 | --- ## 变量 ### 地理类字段 `country`（可选值：OPT、乌克兰、缅甸）、`country_iso`（可选值：PSE、UKR、MMR）、`admin_1`（可选值：加沙地带、顿涅茨克州、哈尔科夫州）、`launch_type`（可选值：空射：战机、陆基发射、空射：无人机）、`explosive_weapon_type`（可选值：航空炸弹、未指定爆炸物、炮击）及另外3个字段。 ### 时间类字段 `date`、`date_event_entered`、`date_event_modified`。 ### 结果/测量类字段 `sector_affected`（可选值：医疗、保护、教育）、`affected`。 ### 标识符/元数据类字段 `provider`（可选值：境内流离失所者/难民服务机构、地方医疗服务提供者、地方教育服务提供者）、`reported_perpetrator_name`（可选值：以色列国防军、俄罗斯联邦武装力量、未识别武装人员）、`idp_refugee_camp_building`（取值范围：0.0–2.0）、`sind_event_id`（取值范围：19018.0–128406.0）、`esa_source`及另外1个字段。 ### 其他类字段 `geo_precision`（经脱敏处理）、`reported_perpetrator`（可选值：政府：军方、外国军队：军方、国安部门）。 --- ## 快速上手 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() --- ## 字段结构 | 字段名 | 数据类型 | 缺失率 | 取值范围/示例值 | |---|---|---|---| | `date` | datetime64[ns] | 0.0% | | | `country` | object | 0.0% | OPT、乌克兰、缅甸 | | `country_iso` | object | 0.0% | PSE、UKR、MMR | | `admin_1` | object | 0.1% | 加沙地带、顿涅茨克州、哈尔科夫州 | | `geo_precision` | object | 0.0% | 经脱敏处理 | | `sector_affected` | object | 0.0% | 医疗、保护、教育 | | `provider` | object | 0.0% | 境内流离失所者/难民服务机构、地方医疗服务提供者、地方教育服务提供者 | | `launch_type` | object | 0.0% | 空射：战机、陆基发射、空射：无人机 | | `explosive_weapon_type` | object | 0.0% | 航空炸弹、未指定爆炸物、炮击 | | `reported_perpetrator` | object | 0.0% | 政府：军方、外国军队：军方、国安部门 | | `reported_perpetrator_name` | object | 0.0% | 以色列国防军、俄罗斯联邦武装力量、未识别武装人员 | | `affected` | object | 0.0% | | | `aid_infrastructure_damaged_destroyed` | int64 | 0.0% | 0.0 – 2.0（均值 0.0399） | | `health_infrastructure_damaged_destroyed` | int64 | 0.0% | 0.0 – 3.0（均值 0.2618） | | `education_infrastructure_damaged_destroyed` | int64 | 0.0% | 0.0 – 3.0（均值 0.2035） | | `idp_refugee_camp_building` | int64 | 0.0% | 0.0 – 2.0（均值 0.2888） | | `sind_event_id` | int64 | 0.0% | 19018.0 – 128406.0（均值 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% | | --- ## 数值型字段统计 | 字段名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `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 | --- ## 数据整理流程 原始数据通过CKAN API从HDX平台下载，并转换为Parquet格式。字段名称统一转为小写蛇形命名法。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。删除了10个缺失值占比超过80%的字段：`event_description`、`latitude`、`longitude`、`food_systems_damaged_destroyed`、`water_systems_damaged_destroyed`、`aid_workers_killed`等。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，并以Snappy压缩格式保存为Parquet文件。 --- ## 数据集局限性 - 数据来源于Insecurity Insight，未由Electric Sheep Africa进行独立验证。 - 自动化清洗无法修正原始数据收集阶段的错报、定义不一致或采样偏差问题。 - 本数据集覆盖54个国家，不同国家间的地理与方法学差异可能影响跨国家可比性。 - 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/explosive-weapons-use-affecting-aid-access-education-and-healthcare-services)。 --- ## 引用格式 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) — 非洲机器学习数据集基础设施，尼日利亚拉各斯。*