electricsheepafrica/africa-zambia-current-situation-fewsnet-ipc-classification

--- annotations_creators: - no-annotation language_creators: - found language: - en license: cc-by-4.0 multilinguality: - monolingual size_categories: - 1K<n<10K source_datasets: - original task_categories: - tabular-classification - tabular-regression task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - food-security - zmb pretty_name: "Zambia Current Situation FEWS NET Acute Food Insecurity Classifications Data" dataset_info: splits: - name: train num_examples: 1552 - name: test num_examples: 388 --- # Zambia Current Situation FEWS NET Acute Food Insecurity Classifications Data **Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/zambia_current_situation_fewsnet_ipc_classification) · **License:** `cc-by` · **Updated:** 2026-04-03 --- ## Abstract Zambia Current Situation FEWS NET Acute Food Insecurity Classifications Data from 2011 Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `projection_start`, `projection_end` column(s). Geographic scope: **ZMB**. *Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).* --- ## Dataset Characteristics | | | |---|---| | **Domain** | Food security and nutrition | | **Unit of observation** | First-level administrative unit observations | | **Rows (total)** | 1,940 | | **Columns** | 40 (9 numeric, 23 categorical, 7 datetime) | | **Train split** | 1,552 rows | | **Test split** | 388 rows | | **Geographic scope** | ZMB | | **Publisher** | FEWS NET | | **HDX last updated** | 2026-04-03 | --- ## Variables **Geographic** — `country` (Zambia), `country_code` (ZM), `fewsnet_region` (Southern Africa), `unit_type` (fsc_admin), `specialization_type` and 2 others. **Temporal** — `datacollectionperiod` (range 159430.0–159505.0), `reporting_date`. **Outcome / Measurement** — `value` (range 1.0–2.0). **Identifier / Metadata** — `source_organization` (FEWS NET), `source_document` (Food Security Outlook, Zimbabwe), `geographic_unit_full_name` (Chadiza, Eastern, Zambia, Mbala, Northern, Zambia, Mpulungu, Northern, Zambia), `geographic_unit_name` (Chadiza, Mpika, Mongu), `fnid` (ZM2009C11110, ZM2009C10208, ZM2009C10908) and 8 others. **Other** — `geographic_group` (Eastern Africa), `classification_scale`, `is_allowing_for_assistance`, `projection_start`, `projection_end` and 12 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-zambia-current-situation-fewsnet-ipc-classification") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `source_organization` | object | 0.0% | FEWS NET | | `source_document` | object | 0.0% | Food Security Outlook, Zimbabwe | | `country` | object | 0.0% | Zambia | | `country_code` | object | 0.0% | ZM | | `geographic_group` | object | 0.0% | Eastern Africa | | `fewsnet_region` | object | 0.0% | Southern Africa | | `geographic_unit_full_name` | object | 0.0% | Chadiza, Eastern, Zambia, Mbala, Northern, Zambia, Mpulungu, Northern, Zambia | | `geographic_unit_name` | object | 0.0% | Chadiza, Mpika, Mongu | | `unit_type` | object | 0.0% | fsc_admin | | `fnid` | object | 0.0% | ZM2009C11110, ZM2009C10208, ZM2009C10908 | | `classification_scale` | object | 0.0% | | | `scenario_name` | object | 0.0% | | | `preference_rating` | int64 | 0.0% | 90.0 – 90.0 (mean 90.0) | | `is_allowing_for_assistance` | bool | 0.0% | | | `projection_start` | datetime64[ns] | 0.0% | | | `projection_end` | datetime64[ns] | 0.0% | | | `status` | object | 0.0% | | | `value` | float64 | 0.0% | 1.0 – 2.0 (mean 1.0108) | | `description` | object | 0.0% | | | `id` | int64 | 0.0% | 24539562.0 – 24545379.0 (mean 24542470.5) | | `datacollectionperiod` | int64 | 0.0% | 159430.0 – 159505.0 (mean 159468.6567) | | `datacollection` | int64 | 0.0% | 168671.0 – 168696.0 (mean 168683.8856) | | `scenario` | object | 0.0% | | | `geographic_unit` | int64 | 0.0% | 29334.0 – 29494.0 (mean 29384.2722) | | `datasourceorganization` | int64 | 0.0% | 1.0 – 1.0 (mean 1.0) | | `datasourcedocument` | int64 | 0.0% | 6601.0 – 6601.0 (mean 6601.0) | | `dataseries` | int64 | 0.0% | 6505897.0 – 6506773.0 (mean 6506316.2948) | | `dataseries_name` | object | 0.0% | | | `specialization_type` | object | 0.0% | | | `dataseries_specialization_type` | object | 0.0% | | | `data_usage_policy` | object | 0.0% | | | `created` | datetime64[ns] | 0.0% | | | `modified` | datetime64[ns] | 0.0% | | | `status_changed` | datetime64[ns] | 0.0% | | | `collection_status` | object | 0.0% | | | `collection_status_changed` | datetime64[ns] | 0.0% | | | `collection_schedule` | object | 0.0% | | | `reporting_date` | datetime64[ns] | 0.0% | | | `esa_source` | object | 0.0% | | | `esa_processed` | object | 0.0% | | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `preference_rating` | 90.0 | 90.0 | 90.0 | 90.0 | | `value` | 1.0 | 2.0 | 1.0108 | 1.0 | | `id` | 24539562.0 | 24545379.0 | 24542470.5 | 24542470.5 | | `datacollectionperiod` | 159430.0 | 159505.0 | 159468.6567 | 159469.0 | | `datacollection` | 168671.0 | 168696.0 | 168683.8856 | 168684.0 | | `geographic_unit` | 29334.0 | 29494.0 | 29384.2722 | 29378.0 | | `datasourceorganization` | 1.0 | 1.0 | 1.0 | 1.0 | | `datasourcedocument` | 6601.0 | 6601.0 | 6601.0 | 6601.0 | | `dataseries` | 6505897.0 | 6506773.0 | 6506316.2948 | 6506365.0 | --- ## 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: `pct_phase3`, `pct_phase4`, `pct_phase5`. 7 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 FEWS NET 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/zambia_current_situation_fewsnet_ipc_classification) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_zambia_current_situation_fewsnet_ipc_classification, title = {Zambia Current Situation FEWS NET Acute Food Insecurity Classifications Data}, author = {FEWS NET}, year = {2026}, url = {https://data.humdata.org/dataset/zambia_current_situation_fewsnet_ipc_classification}, 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.*### 数据集元数据 - **注释创建者**：无注释 - **语言创建方式**：现成获取 - **语言**：英语 - **授权协议**：CC-BY-4.0 - **多语言属性**：单语言 - **样本规模**：1000 < n < 10000 - **源数据集类型**：原始数据集 - **任务类别**：表格分类、表格回归 - **任务子项**：无 - **标签**：非洲、人道主义、人道主义数据交换（HDX）、Electric Sheep Africa、粮食安全、赞比亚（ZMB） - **美观名称**："赞比亚当前局势 FEWS NET 急性粮食不安全分类数据集" - **数据集划分**： - 训练集：1552条样本 - 测试集：388条样本 # 赞比亚当前局势 FEWS NET 急性粮食不安全分类数据集 **发布方**：饥荒早期预警系统网络（FEWS NET） · **来源**：[HDX](https://data.humdata.org/dataset/zambia_current_situation_fewsnet_ipc_classification) · **授权协议**：`cc-by` · **更新时间**：2026-04-03 ## 摘要 本数据集为2011年的赞比亚当前局势 FEWS NET 急性粮食不安全分类数据。 数据集中每一行代表一级行政单元的观测记录。时间覆盖范围由`projection_start`、`projection_end`列标注。地理覆盖范围：**ZMB（赞比亚）**。 *本数据集已由[Electric Sheep Africa（电羊非洲）](https://huggingface.co/electricsheepafrica)整理为可供机器学习使用的Parquet格式。* ## 数据集特征 | | | |---|---| | **领域** | 粮食安全与营养 | | **观测单元** | 一级行政单元观测记录 | | **总样本行数** | 1,940 | | **列数** | 40（9个数值型、23个分类型、7个日期时间型） | | **训练集划分** | 1,552行 | | **测试集划分** | 388行 | | **地理覆盖范围** | ZMB（赞比亚） | | **发布方** | FEWS NET | | **HDX最后更新时间** | 2026-04-03 | ## 变量分类 **地理类变量** — `country`（国家：赞比亚）、`country_code`（国家代码：ZM）、`fewsnet_region`（FEWS NET区域：南部非洲）、`unit_type`（单元类型：fsc_admin）、`specialization_type`（专业类型）及其他2个变量。 **时间类变量** — `datacollectionperiod`（数据收集周期，取值范围159430.0–159505.0）、`reporting_date`（报告日期）。 **结果/测量变量** — `value`（目标值，取值范围1.0–2.0）。 **标识符/元数据变量** — `source_organization`（来源机构：FEWS NET）、`source_document`（来源文档：津巴布韦粮食安全展望）、`geographic_unit_full_name`（地理单元完整名称：例如查迪扎、东部省、赞比亚；姆巴拉、北部省、赞比亚；姆普隆古、北部省、赞比亚等）、`geographic_unit_name`（地理单元名称：查迪扎、姆皮卡、蒙古等）、`fnid`（标识符：ZM2009C11110、ZM2009C10208、ZM2009C10908等）及其他8个变量。 **其他变量** — `geographic_group`（地理群组：东非）、`classification_scale`（分类尺度）、`is_allowing_for_assistance`（是否允许援助）、`projection_start`（预测起始时间）、`projection_end`（预测结束时间）及其他12个变量。 ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-zambia-current-situation-fewsnet-ipc-classification") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ## 数据模式 | 列名 | 数据类型 | 缺失率 | 取值范围/示例值 | |---|---|---|---| | `source_organization` | 字符串对象（object） | 0.0% | FEWS NET | | `source_document` | 字符串对象 | 0.0% | 津巴布韦粮食安全展望 | | `country` | 字符串对象 | 0.0% | 赞比亚 | | `country_code` | 字符串对象 | 0.0% | ZM | | `geographic_group` | 字符串对象 | 0.0% | 东非 | | `fewsnet_region` | 字符串对象 | 0.0% | 南部非洲 | | `geographic_unit_full_name` | 字符串对象 | 0.0% | 查迪扎、东部省、赞比亚；姆巴拉、北部省、赞比亚；姆普隆古、北部省、赞比亚等 | | `geographic_unit_name` | 字符串对象 | 0.0% | 查迪扎、姆皮卡、蒙古 | | `unit_type` | 字符串对象 | 0.0% | fsc_admin | | `fnid` | 字符串对象 | 0.0% | ZM2009C11110、ZM2009C10208、ZM2009C10908 | | `classification_scale` | 字符串对象 | 0.0% | 无 | | `scenario_name` | 字符串对象 | 0.0% | 无 | | `preference_rating` | 64位整数（int64） | 0.0% | 90.0 – 90.0（均值为90.0） | | `is_allowing_for_assistance` | 布尔型（bool） | 0.0% | 无 | | `projection_start` | 日期时间类型（datetime64[ns]） | 0.0% | 无 | | `projection_end` | 日期时间类型 | 0.0% | 无 | | `status` | 字符串对象 | 0.0% | 无 | | `value` | 64位浮点数（float64） | 0.0% | 1.0 – 2.0（均值为1.0108） | | `description` | 字符串对象 | 0.0% | 无 | | `id` | 64位整数 | 0.0% | 24539562.0 – 24545379.0（均值为24542470.5） | | `datacollectionperiod` | 64位整数 | 0.0% | 159430.0 – 159505.0（均值为159468.6567） | | `datacollection` | 64位整数 | 0.0% | 168671.0 – 168696.0（均值为168683.8856） | | `scenario` | 字符串对象 | 0.0% | 无 | | `geographic_unit` | 64位整数 | 0.0% | 29334.0 – 29494.0（均值为29384.2722） | | `datasourceorganization` | 64位整数 | 0.0% | 1.0 – 1.0（均值为1.0） | | `datasourcedocument` | 64位整数 | 0.0% | 6601.0 – 6601.0（均值为6601.0） | | `dataseries` | 64位整数 | 0.0% | 6505897.0 – 6506773.0（均值为6506316.2948） | | `dataseries_name` | 字符串对象 | 0.0% | 无 | | `specialization_type` | 字符串对象 | 0.0% | 无 | | `dataseries_specialization_type` | 字符串对象 | 0.0% | 无 | | `data_usage_policy` | 字符串对象 | 0.0% | 无 | | `created` | 日期时间类型 | 0.0% | 无 | | `modified` | 日期时间类型 | 0.0% | 无 | | `status_changed` | 日期时间类型 | 0.0% | 无 | | `collection_status` | 字符串对象 | 0.0% | 无 | | `collection_status_changed` | 日期时间类型 | 0.0% | 无 | | `collection_schedule` | 字符串对象 | 0.0% | 无 | | `reporting_date` | 日期时间类型 | 0.0% | 无 | | `esa_source` | 字符串对象 | 0.0% | 无 | | `esa_processed` | 字符串对象 | 0.0% | 无 | ## 数值型变量统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `preference_rating` | 90.0 | 90.0 | 90.0 | 90.0 | | `value` | 1.0 | 2.0 | 1.0108 | 1.0 | | `id` | 24539562.0 | 24545379.0 | 24542470.5 | 24542470.5 | | `datacollectionperiod` | 159430.0 | 159505.0 | 159468.6567 | 159469.0 | | `datacollection` | 168671.0 | 168696.0 | 168683.8856 | 168684.0 | | `geographic_unit` | 29334.0 | 29494.0 | 29384.2722 | 29378.0 | | `datasourceorganization` | 1.0 | 1.0 | 1.0 | 1.0 | | `datasourcedocument` | 6601.0 | 6601.0 | 6601.0 | 6601.0 | | `dataseries` | 6505897.0 | 6506773.0 | 6506316.2948 | 6506365.0 | ## 数据整理流程 原始数据通过CKAN API从HDX下载，并转换为Parquet格式。列名统一转换为小写并采用蛇形命名法（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`。移除了3个缺失值占比超过80%的列：`pct_phase3`、`pct_phase4`、`pct_phase5`。基于解析成功率（阈值85%），将7个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）将数据集按80/20划分为训练集与测试集，并保存为Snappy压缩的Parquet格式文件。 ## 数据集局限性 - 数据源自饥荒早期预警系统网络（FEWS NET），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、定义不一致或抽样偏差问题。 - 请参阅[HDX数据集原始页面](https://data.humdata.org/dataset/zambia_current_situation_fewsnet_ipc_classification)查看发布方提供的方法说明与注意事项。 ## 引用格式 bibtex @dataset{hdx_africa_zambia_current_situation_fewsnet_ipc_classification, title = {赞比亚当前局势 FEWS NET 急性粮食不安全分类数据集}, author = {FEWS NET}, year = {2026}, url = {https://data.humdata.org/dataset/zambia_current_situation_fewsnet_ipc_classification}, note = {由Electric Sheep Africa（https://huggingface.co/electricsheepafrica）重新打包以适配机器学习场景} } *[Electric Sheep Africa（电羊非洲）](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施提供商。尼日利亚拉各斯。*