electricsheepafrica/africa-wfp-hungermap-data-for-civ

--- 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 - food-security - indicators - civ pretty_name: "Côte d'Ivoire - HungerMap data" dataset_info: splits: - name: train num_examples: 0 - name: test num_examples: 0 --- # Côte d'Ivoire - HungerMap data **Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/wfp-hungermap-data-for-civ) · **License:** `cc-by-sa` · **Updated:** 2026-03-04 --- ## Abstract HungerMapLIVE is the World Food Programme (WFP)’s global hunger monitoring system. It combines key metrics from various data sources – such as food security information, weather, population size, conflict, hazards, nutrition information and macro-economic data – to help assess, monitor and predict the magnitude and severity of hunger in near real-time. The resulting analysis is displayed on an interactive map that helps WFP staff, key decision makers and the broader humanitarian community to make more informed and timely decisions relating to food security. The platform covers 94 countries, including countries where WFP has operations as well as most lower and lower-middle income countries (as classified by the World Bank). Each row in this dataset represents country-level aggregates. Temporal coverage is indicated by the `date` column(s). Geographic scope: **CIV**. *Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).* --- ## Dataset Characteristics | | | |---|---| | **Domain** | Food security and nutrition | | **Unit of observation** | Country-level aggregates | | **Rows (total)** | 1 | | **Columns** | 13 (6 numeric, 6 categorical, 1 datetime) | | **Train split** | 0 rows | | **Test split** | 0 rows | | **Geographic scope** | CIV | | **Publisher** | WFP - World Food Programme | | **HDX last updated** | 2026-03-04 | --- ## Variables **Geographic** — `countrycode` (CIV), `countryname` (Côte d'Ivoire), `adminlevel` (national), `datatype` (SURVEY). **Temporal** — `date`. **Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-07). **Other** — `fcs_people` (range 5136499.0–5136499.0), `fcs_prevalence` (range 0.1748–0.1748), `rcsi_people` (range 7146630.0–7146630.0), `rcsi_prevalence` (range 0.2432–0.2432), `market_access_people` (range 8577335.0–8577335.0) and 1 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-wfp-hungermap-data-for-civ") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `countrycode` | object | 0.0% | CIV | | `countryname` | object | 0.0% | Côte d'Ivoire | | `adminlevel` | object | 0.0% | national | | `date` | datetime64[ns] | 0.0% | | | `datatype` | object | 0.0% | SURVEY | | `fcs_people` | int64 | 0.0% | 5136499.0 – 5136499.0 (mean 5136499.0) | | `fcs_prevalence` | float64 | 0.0% | 0.1748 – 0.1748 (mean 0.1748) | | `rcsi_people` | int64 | 0.0% | 7146630.0 – 7146630.0 (mean 7146630.0) | | `rcsi_prevalence` | float64 | 0.0% | 0.2432 – 0.2432 (mean 0.2432) | | `market_access_people` | int64 | 0.0% | 8577335.0 – 8577335.0 (mean 8577335.0) | | `market_access_prevalence` | float64 | 0.0% | 0.2919 – 0.2919 (mean 0.2919) | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-07 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `fcs_people` | 5136499.0 | 5136499.0 | 5136499.0 | 5136499.0 | | `fcs_prevalence` | 0.1748 | 0.1748 | 0.1748 | 0.1748 | | `rcsi_people` | 7146630.0 | 7146630.0 | 7146630.0 | 7146630.0 | | `rcsi_prevalence` | 0.2432 | 0.2432 | 0.2432 | 0.2432 | | `market_access_people` | 8577335.0 | 8577335.0 | 8577335.0 | 8577335.0 | | `market_access_prevalence` | 0.2919 | 0.2919 | 0.2919 | 0.2919 | --- ## 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: `adminone`, `population`, `health_access_people`, `health_access_prevalence`. 1 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 WFP - World Food Programme and has not been independently validated by ESA. - Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/wfp-hungermap-data-for-civ) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_wfp_hungermap_data_for_civ, title = {Côte d'Ivoire - HungerMap data}, author = {WFP - World Food Programme}, year = {2026}, url = {https://data.humdata.org/dataset/wfp-hungermap-data-for-civ}, 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: 注释创建者：无注释 language_creators: 语言来源：公开数据源采集 language: 语言：英语 license: 许可协议：CC BY-SA 4.0 multilinguality: 多语言属性：单语言 size_categories: 数据规模：不足1000条 source_datasets: 源数据集：原创数据集 task_categories: 任务类别：表格分类、表格回归、其他 task_ids: 任务子类别：无 tags: 标签：非洲、人道主义、HDX（Humanitarian Data Exchange，人类数据交换平台）、Electric Sheep Africa、粮食安全、指标、CIV（科特迪瓦国家代码） pretty_name: "科特迪瓦——HungerMap数据集" dataset_info: splits: - name: train num_examples: 0 - name: test num_examples: 0 # 科特迪瓦——HungerMap数据集 **发布方：** 世界粮食计划署（World Food Programme，WFP） · **来源：** [HDX（Humanitarian Data Exchange，人类数据交换平台）](https://data.humdata.org/dataset/wfp-hungermap-data-for-civ) · **许可协议：** `cc-by-sa` · **更新时间：** 2026-03-04 --- ## 摘要 HungerMapLIVE是世界粮食计划署（WFP）打造的全球饥饿监测系统。该系统整合了来自各类数据源的核心指标，涵盖粮食安全信息、气象数据、人口规模、冲突情况、灾害事件、营养信息以及宏观经济数据等，可助力近实时地评估、监测并预测饥饿问题的波及范围与严重程度。生成的分析结果将通过交互式地图进行展示，协助WFP工作人员、核心决策者以及更广泛的人道主义社群，针对粮食安全问题制定更具前瞻性与时效性的决策。 该平台覆盖94个国家，既包含WFP开展业务的国家，也涵盖世界银行分类下的绝大多数低收入及中低收入国家。 本数据集的每一行均代表国家级别的汇总数据，时间覆盖范围由`date`（日期）列标注。地理覆盖范围：**CIV（科特迪瓦）**。 *本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式。* --- ## 数据集特征 | | | |---|---| | **领域** | 粮食安全与营养 | | **观测单元** | 国家级汇总数据 | | **总数据行数** | 1 | | **列数** | 13（6个数值型、6个分类型、1个日期时间型） | | **训练集划分** | 0行 | | **测试集划分** | 0行 | | **地理覆盖范围** | CIV（科特迪瓦） | | **发布方** | 世界粮食计划署（WFP） | | **HDX平台最后更新时间** | 2026-03-04 | --- ## 变量 **地理类变量** — `countrycode`（CIV，科特迪瓦国家代码）、`countryname`（科特迪瓦）、`adminlevel`（国家级）、`datatype`（SURVEY，调查类数据）。 **时间类变量** — `date`（日期）。 **标识符/元数据类变量** — `esa_source`（HDX）、`esa_processed`（2026-04-07）。 **其他类变量** — `fcs_people`（取值范围5136499.0–5136499.0）、`fcs_prevalence`（取值范围0.1748–0.1748）、`rcsi_people`（取值范围7146630.0–7146630.0）、`rcsi_prevalence`（取值范围0.2432–0.2432）、`market_access_people`（取值范围8577335.0–8577335.0）及另外1个变量。 --- ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-wfp-hungermap-data-for-civ") 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 | 空值占比 | 取值范围/示例值 | |---|---|---|---| | `countrycode` | 字符型 | 0.0% | CIV | | `countryname` | 字符型 | 0.0% | 科特迪瓦 | | `adminlevel` | 字符型 | 0.0% | 国家级 | | `date` | 日期时间型 | 0.0% | 无 | | `datatype` | 字符型 | 0.0% | SURVEY | | `fcs_people` | 整型 | 0.0% | 5136499.0 – 5136499.0（均值5136499.0） | | `fcs_prevalence` | 浮点型 | 0.0% | 0.1748 – 0.1748（均值0.1748） | | `rcsi_people` | 整型 | 0.0% | 7146630.0 – 7146630.0（均值7146630.0） | | `rcsi_prevalence` | 浮点型 | 0.0% | 0.2432 – 0.2432（均值0.2432） | | `market_access_people` | 整型 | 0.0% | 8577335.0 – 8577335.0（均值8577335.0） | | `market_access_prevalence` | 浮点型 | 0.0% | 0.2919 – 0.2919（均值0.2919） | | `esa_source` | 字符型 | 0.0% | HDX | | `esa_processed` | 字符型 | 0.0% | 2026-04-07 | --- ## 数值型变量统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `fcs_people` | 5136499.0 | 5136499.0 | 5136499.0 | 5136499.0 | | `fcs_prevalence` | 0.1748 | 0.1748 | 0.1748 | 0.1748 | | `rcsi_people` | 7146630.0 | 7146630.0 | 7146630.0 | 7146630.0 | | `rcsi_prevalence` | 0.2432 | 0.2432 | 0.2432 | 0.2432 | | `market_access_people` | 8577335.0 | 8577335.0 | 8577335.0 | 8577335.0 | | `market_access_prevalence` | 0.2919 | 0.2919 | 0.2919 | 0.2919 | --- ## 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。对列名进行了小写转换，并统一采用蛇形命名法（snake_case）进行标准化。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4个缺失值占比超过80%的列：`adminone`、`population`、`health_access_people`、`health_access_prevalence`。根据解析成功率（阈值>85%），将1列从字符串类型转换为数值型或日期时间型。采用固定随机种子（42）将数据集以80/20的比例划分为训练集与测试集，并保存为Snappy压缩格式的Parquet文件。 --- ## 数据集局限性 - 数据源自世界粮食计划署（WFP），并未经Electric Sheep Africa独立验证。 - 自动化清洗流程无法修正原始数据收集中的错报值、定义不一致或抽样偏差问题。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/wfp-hungermap-data-for-civ)以获取发布方提供的方法论说明与相关注意事项。 --- ## 引用格式 bibtex @dataset{hdx_africa_wfp_hungermap_data_for_civ, title = {Côte d'Ivoire - HungerMap data}, author = {WFP - World Food Programme}, year = {2026}, url = {https://data.humdata.org/dataset/wfp-hungermap-data-for-civ}, 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服务商，总部位于尼日利亚拉各斯。*