electricsheepafrica/africa-mozambique-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 - moz pretty_name: "Mozambique Current Situation FEWS NET Acute Food Insecurity Classifications Data" dataset_info: splits: - name: train num_examples: 7269 - name: test num_examples: 1817 --- # Mozambique Current Situation FEWS NET Acute Food Insecurity Classifications Data **Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/mozambique_current_situation_fewsnet_ipc_classification) · **License:** `cc-by` · **Updated:** 2026-04-01 --- ## Abstract Mozambique 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: **MOZ**. *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)** | 9,087 | | **Columns** | 40 (9 numeric, 23 categorical, 7 datetime) | | **Train split** | 7,269 rows | | **Test split** | 1,817 rows | | **Geographic scope** | MOZ | | **Publisher** | FEWS NET | | **HDX last updated** | 2026-04-01 | --- ## Variables **Geographic** — `country` (Mozambique), `country_code` (MZ), `fewsnet_region` (Southern Africa), `unit_type` (fsc_admin_lhz, fsc_admin), `specialization_type` and 2 others. **Temporal** — `datacollectionperiod` (range 158531.0–377925.0), `reporting_date`. **Outcome / Measurement** — `value` (range 1.0–3.0). **Identifier / Metadata** — `source_organization` (FEWS NET, Mozambique), `source_document` (Food Security Outlook, Mozambique), `geographic_unit_full_name` (Alto Molocue, Zambezia, Mozambique, Mecufi, Cabo Delgado, Mozambique, Massingir, Gaza, Mozambique), `geographic_unit_name` (North-Central Coastal Fishing, Northern Highland with Mixed Cropping, Northeastern Cassava, Cashew, and Coconut), `fnid` (MZ2009C11101, MZ2009C10210, MZ2009C10208) 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-mozambique-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, Mozambique | | `source_document` | object | 0.0% | Food Security Outlook, Mozambique | | `country` | object | 0.0% | Mozambique | | `country_code` | object | 0.0% | MZ | | `geographic_group` | object | 0.0% | Eastern Africa | | `fewsnet_region` | object | 0.0% | Southern Africa | | `geographic_unit_full_name` | object | 0.0% | Alto Molocue, Zambezia, Mozambique, Mecufi, Cabo Delgado, Mozambique, Massingir, Gaza, Mozambique | | `geographic_unit_name` | object | 0.0% | North-Central Coastal Fishing, Northern Highland with Mixed Cropping, Northeastern Cassava, Cashew, and Coconut | | `unit_type` | object | 0.0% | fsc_admin_lhz, fsc_admin | | `fnid` | object | 0.0% | MZ2009C11101, MZ2009C10210, MZ2009C10208 | | `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 – 3.0 (mean 1.4425) | | `description` | object | 0.0% | | | `id` | int64 | 0.0% | 24359209.0 – 41422894.0 (mean 27458095.2796) | | `datacollectionperiod` | int64 | 0.0% | 158531.0 – 377925.0 (mean 210719.0898) | | `datacollection` | int64 | 0.0% | 168258.0 – 388759.0 (mean 221782.5272) | | `scenario` | object | 0.0% | | | `geographic_unit` | int64 | 0.0% | 24965.0 – 203435.0 (mean 101794.9464) | | `datasourceorganization` | int64 | 0.0% | 2031.0 – 2031.0 (mean 2031.0) | | `datasourcedocument` | int64 | 0.0% | 6565.0 – 6565.0 (mean 6565.0) | | `dataseries` | int64 | 0.0% | 6472963.0 – 7847754.0 (mean 6585353.9275) | | `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 | 3.0 | 1.4425 | 1.0 | | `id` | 24359209.0 | 41422894.0 | 27458095.2796 | 24520509.0 | | `datacollectionperiod` | 158531.0 | 377925.0 | 210719.0898 | 159580.0 | | `datacollection` | 168258.0 | 388759.0 | 221782.5272 | 168722.0 | | `geographic_unit` | 24965.0 | 203435.0 | 101794.9464 | 87808.0 | | `datasourceorganization` | 2031.0 | 2031.0 | 2031.0 | 2031.0 | | `datasourcedocument` | 6565.0 | 6565.0 | 6565.0 | 6565.0 | | `dataseries` | 6472963.0 | 7847754.0 | 6585353.9275 | 6507257.0 | --- ## 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/mozambique_current_situation_fewsnet_ipc_classification) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_mozambique_current_situation_fewsnet_ipc_classification, title = {Mozambique Current Situation FEWS NET Acute Food Insecurity Classifications Data}, author = {FEWS NET}, year = {2026}, url = {https://data.humdata.org/dataset/mozambique_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.*annotations_creators: - 无注释 language_creators: - 采集所得 language: - 英语 license: 知识共享署名4.0（CC BY 4.0） multilinguality: - 单语言 size_categories: - 1000<样本数<10000 source_datasets: - 原始数据集 task_categories: - 表格分类 - 表格回归 task_ids: - 无任务子类别 tags: - 非洲 - 人道主义 - HDX（人类数据交换平台） - Electric Sheep Africa - 粮食安全 - 莫桑比克 pretty_name: "莫桑比克当前局势FEWS NET急性粮食不安全等级数据（Mozambique Current Situation FEWS NET Acute Food Insecurity Classifications Data）" dataset_info: splits: - name: train num_examples: 7269 - name: test num_examples: 1817 # 莫桑比克当前局势FEWS NET急性粮食不安全等级数据 **发布方：** FEWS NET · **来源：** [HDX（人类数据交换平台）](https://data.humdata.org/dataset/mozambique_current_situation_fewsnet_ipc_classification) · **许可协议：** `CC BY` · **最后更新：** 2026-04-01 --- ## 摘要 本数据集为2011年发布的莫桑比克当前局势FEWS NET急性粮食不安全等级数据。 数据集内每一行对应一级行政单元的观测结果。时间覆盖范围由`projection_start`（预测开始时间）、`projection_end`（预测结束时间）列标注。地理覆盖范围：**莫桑比克（MOZ）**。 *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** | 一级行政单元 | | **总样本行数** | 9087 | | **列数** | 40列（数值型9列、分类型23列、日期时间型7列） | | **训练集样本数** | 7269条 | | **测试集样本数** | 1817条 | | **地理覆盖范围** | 莫桑比克（MOZ） | | **发布方** | FEWS NET | | **HDX平台最后更新时间** | 2026年4月1日 | --- ## 变量分类 ### 地理类变量 包含`country`（国家：莫桑比克）、`country_code`（国家代码：MZ）、`fewsnet_region`（FEWS NET区域：南部非洲）、`unit_type`（单元类型：fsc_admin_lhz、fsc_admin）、`specialization_type`（专业类型）及另外2个变量。 ### 时间类变量 包含`datacollectionperiod`（数据收集周期，取值范围158531.0~377925.0）、`reporting_date`（报告日期）。 ### 结果/测量类变量 包含`value`（测量值，取值范围1.0~3.0）。 ### 标识/元数据类变量 包含`source_organization`（来源机构：莫桑比克FEWS NET）、`source_document`（来源文件：莫桑比克粮食安全展望）、`geographic_unit_full_name`（地理单元全称：例如莫桑比克赞比西亚省阿尔托莫洛库埃、莫桑比克德尔加杜角省梅库菲、莫桑比克加扎省马辛吉尔等）、`geographic_unit_name`（地理单元名称：北中沿海渔业区、北部混合种植高地区、东北部木薯腰果椰子种植区等）、`fnid`（地理标识：例如MZ2009C11101、MZ2009C10210、MZ2009C10208等）及另外8个变量。 ### 其他类变量 包含`geographic_group`（地理群组：东非）、`classification_scale`（分类等级）、`is_allowing_for_assistance`（是否允许援助）、`projection_start`（预测开始时间）、`projection_end`（预测结束时间）及另外12个变量。 --- ## 快速入门 可通过以下代码快速加载并处理本数据集： python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-mozambique-current-situation-fewsnet-ipc-classification") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据schema | 列名 | 数据类型 | 缺失率 | 取值范围/示例值 | |---|---|---|---| | `source_organization` | 对象型（object） | 0.0% | 莫桑比克FEWS NET | | `source_document` | 对象型（object） | 0.0% | 莫桑比克粮食安全展望 | | `country` | 对象型（object） | 0.0% | 莫桑比克 | | `country_code` | 对象型（object） | 0.0% | MZ | | `geographic_group` | 对象型（object） | 0.0% | 东非 | | `fewsnet_region` | 对象型（object） | 0.0% | 南部非洲 | | `geographic_unit_full_name` | 对象型（object） | 0.0% | 莫桑比克赞比西亚省阿尔托莫洛库埃、莫桑比克德尔加杜角省梅库菲、莫桑比克加扎省马辛吉尔等 | | `geographic_unit_name` | 对象型（object） | 0.0% | 北中沿海渔业区、北部混合种植高地区、东北部木薯腰果椰子种植区等 | | `unit_type` | 对象型（object） | 0.0% | fsc_admin_lhz、fsc_admin | | `fnid` | 对象型（object） | 0.0% | MZ2009C11101、MZ2009C10210、MZ2009C10208等 | | `classification_scale` | 对象型（object） | 0.0% | 无 | | `scenario_name` | 对象型（object） | 0.0% | 无 | | `preference_rating` | 64位整型（int64） | 0.0% | 90.0~90.0（均值90.0） | | `is_allowing_for_assistance` | 布尔型（bool） | 0.0% | 无 | | `projection_start` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `projection_end` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `status` | 对象型（object） | 0.0% | 无 | | `value` | 64位浮点型（float64） | 0.0% | 1.0~3.0（均值1.4425） | | `description` | 对象型（object） | 0.0% | 无 | | `id` | 64位整型（int64） | 0.0% | 24359209.0~41422894.0（均值27458095.2796） | | `datacollectionperiod` | 64位整型（int64） | 0.0% | 158531.0~377925.0（均值210719.0898） | | `datacollection` | 64位整型（int64） | 0.0% | 168258.0~388759.0（均值221782.5272） | | `scenario` | 对象型（object） | 0.0% | 无 | | `geographic_unit` | 64位整型（int64） | 0.0% | 24965.0~203435.0（均值101794.9464） | | `datasourceorganization` | 64位整型（int64） | 0.0% | 2031.0~2031.0（均值2031.0） | | `datasourcedocument` | 64位整型（int64） | 0.0% | 6565.0~6565.0（均值6565.0） | | `dataseries` | 64位整型（int64） | 0.0% | 6472963.0~7847754.0（均值6585353.9275） | | `dataseries_name` | 对象型（object） | 0.0% | 无 | | `specialization_type` | 对象型（object） | 0.0% | 无 | | `dataseries_specialization_type` | 对象型（object） | 0.0% | 无 | | `data_usage_policy` | 对象型（object） | 0.0% | 无 | | `created` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `modified` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `status_changed` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `collection_status` | 对象型（object） | 0.0% | 无 | | `collection_status_changed` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `collection_schedule` | 对象型（object） | 0.0% | 无 | | `reporting_date` | 纳秒级日期时间型（datetime64[ns]） | 0.0% | 无 | | `esa_source` | 对象型（object） | 0.0% | 无 | | `esa_processed` | 对象型（object） | 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 | 3.0 | 1.4425 | 1.0 | | `id` | 24359209.0 | 41422894.0 | 27458095.2796 | 24520509.0 | | `datacollectionperiod` | 158531.0 | 377925.0 | 210719.0898 | 159580.0 | | `datacollection` | 168258.0 | 388759.0 | 221782.5272 | 168722.0 | | `geographic_unit` | 24965.0 | 203435.0 | 101794.9464 | 87808.0 | | `datasourceorganization` | 2031.0 | 2031.0 | 2031.0 | 2031.0 | | `datasourcedocument` | 6565.0 | 6565.0 | 6565.0 | 6565.0 | | `dataseries` | 6472963.0 | 7847754.0 | 6585353.9275 | 6507257.0 | --- ## 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。对列名进行小写化处理，并统一为蛇形命名法（snake_case）。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的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式。 --- ## 局限性说明 1. 本数据集源自FEWS NET，尚未经ESA独立验证。 2. 自动化数据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。 3. 如需了解发布方的方法说明与注意事项，请参阅[HDX平台原始数据集页面](https://data.humdata.org/dataset/mozambique_current_situation_fewsnet_ipc_classification)。 --- ## 引用格式 bibtex @dataset{hdx_africa_mozambique_current_situation_fewsnet_ipc_classification, title = {莫桑比克当前局势FEWS NET急性粮食不安全等级数据}, author = {FEWS NET}, year = {2026}, url = {https://data.humdata.org/dataset/mozambique_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](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施。尼日利亚拉各斯。*