electricsheepafrica/africa-wfp-food-security-indicators-for-mozambique

---
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-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- food-security
- hxl
- indicators
- moz
pretty_name: "Mozambique - Food Security Indicators"
dataset_info:
splits:
- name: train
num_examples: 1003
- name: test
num_examples: 250
---

# Mozambique - Food Security Indicators

**Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/wfp-food-security-indicators-for-mozambique) · **License:** `cc-by-igo` · **Updated:** 2024-09-13

---

## Abstract

The World Food Programme (WFP) launched the mobile Vulnerability Analysis and Mapping (mVAM) project in 2013, beginning in DRC and Somalia. mVAM uses mobile technology to track food security trends in real-time, providing high-frequency data that supports humanitarian decision-making. Data collection methods are tailored to the needs of each country that mVAM operates in. This dataset contains data from the [mVAM databank](http://vam.wfp.org/sites/mvam_monitoring/) covering various indicators (one per resource).

Each row in this dataset represents time-series observations. Temporal coverage is indicated by the `svydate` 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** | Time-series observations |
| **Rows (total)** | 1,254 |
| **Columns** | 9 (1 numeric, 7 categorical, 1 datetime) |
| **Train split** | 1,003 rows |
| **Test split** | 250 rows |
| **Geographic scope** | MOZ |
| **Publisher** | WFP - World Food Programme |
| **HDX last updated** | 2024-09-13 |

---

## Variables

**Geographic** — `svydate`, `adminstrata` (Gaza, Inhambane, Mozambique).

**Identifier / Metadata** — `adm0_name` (Mozambique, #country+name), `esa_source` (HDX), `esa_processed` (2026-04-06).

**Other** — `variable` (rCSI, HDDS, LimitPortionSize>=1), `variabledescription` (prevalence-->equals to 1 if household uses this strategy 1 or more times per week, reduced coping strategy, prevalence-->equals to 1 if household using coping strategies), `demographic` (F, M, Assistance), `mean` (range 0.0–21.6182).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-mozambique")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `svydate` | datetime64[ns] | 0.1% | |
| `adm0_name` | object | 0.0% | Mozambique, #country+name |
| `adminstrata` | object | 79.3% | Gaza, Inhambane, Mozambique |
| `variable` | object | 0.0% | rCSI, HDDS, LimitPortionSize>=1 |
| `variabledescription` | object | 68.4% | prevalence-->equals to 1 if household uses this strategy 1 or more times per week, reduced coping strategy, prevalence-->equals to 1 if household using coping strategies |
| `demographic` | object | 22.6% | F, M, Assistance |
| `mean` | float64 | 0.1% | 0.0 – 21.6182 (mean 1.445) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-06 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `mean` | 0.0 | 21.6182 | 1.445 | 0.4859 |

---

## 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`. 2 column(s) with >80% missing values were removed: `adm1_name`, `adm2_name`. 1 exact duplicate rows were removed. 2 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.
- The following columns have >20% missing values and should be treated with caution in modelling: `adminstrata`, `variabledescription`, `demographic`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/wfp-food-security-indicators-for-mozambique) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_mozambique,
title = {Mozambique - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-mozambique},
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:
- 采集自现有公开资源
language:
- 英语
license: CC BY 4.0协议
multilinguality:
- 单语言
size_categories:
- 1000<n<10000条数据
source_datasets:
- 原创数据集
task_categories:
- 表格回归
- 其他
task_ids: []
tags:
- 非洲
- 人道主义
- HDX（Humanitarian Data Exchange，人道主义数据交换）
- 非洲电羊（Electric Sheep Africa）
- 粮食安全
- HXL（Humanitarian Exchange Language，人道主义交换语言）
- 指标
- 莫桑比克（Mozambique）
pretty_name: "莫桑比克——粮食安全指标"
dataset_info:
splits:
- name: 训练集
num_examples: 1003
- name: 测试集
num_examples: 250
---

# 莫桑比克——粮食安全指标

**发布方：** 世界粮食计划署（World Food Programme, WFP） · **来源：** [HDX（Humanitarian Data Exchange，人道主义数据交换）](https://data.humdata.org/dataset/wfp-food-security-indicators-for-mozambique) · **许可证：** `cc-by-igo` · **更新时间：** 2024-09-13

---

## 摘要

世界粮食计划署（World Food Programme, WFP）于2013年启动了移动脆弱性分析与测绘（mobile Vulnerability Analysis and Mapping, mVAM）项目，首批试点覆盖刚果（金）与索马里。mVAM依托移动技术实时追踪粮食安全趋势，提供高频次监测数据以支撑人道主义决策工作。数据收集方法会根据mVAM覆盖国家的实际需求定制适配。本数据集包含来自[mVAM数据库](http://vam.wfp.org/sites/mvam_monitoring/)的各类指标数据（每份资源对应一项指标）。

本数据集的每一行均代表一条时序观测数据，时间覆盖范围由`svydate`（调查日期）列标注。地理覆盖范围：**莫桑比克（Mozambique, MOZ）**。

*本数据集已由[非洲电羊（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** | 时序观测数据 |
| **总数据行数** | 1254条 |
| **列数** | 9列（1个数值型、7个分类型、1个日期时间型） |
| **训练集划分** | 1003条数据 |
| **测试集划分** | 250条数据 |
| **地理覆盖范围** | 莫桑比克（MOZ） |
| **发布方** | 世界粮食计划署（WFP） |
| **HDX平台最后更新时间** | 2024-09-13 |

---

## 变量说明

**地理类变量** — `svydate`（调查日期）、`adminstrata`（行政区域：加扎、伊尼扬巴内、莫桑比克）。

**标识符与元数据类** — `adm0_name`（国家名称：莫桑比克，#country+name）、`esa_source`（数据来源：HDX）、`esa_processed`（数据处理时间：2026-04-06）。

**其他类变量** — `variable`（指标类型：rCSI、HDDS、LimitPortionSize>=1）、`variabledescription`（变量描述：患病率——若家庭每周至少使用1次该应对策略则取值为1；减少应对策略；患病率——若家庭采用应对策略则取值为1）、`demographic`（人口统计维度：F、M、受援助群体）、`mean`（均值范围：0.0–21.6182）。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-mozambique")
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 |
|---|---|---|---|
| `svydate` | datetime64[ns] | 0.1% | 无 |
| `adm0_name` | 字符型 | 0.0% | 莫桑比克，#country+name |
| `adminstrata` | 字符型 | 79.3% | 加扎、伊尼扬巴内、莫桑比克 |
| `variable` | 字符型 | 0.0% | rCSI、HDDS、LimitPortionSize>=1 |
| `variabledescription` | 字符型 | 68.4% | 患病率——若家庭每周至少使用1次该应对策略则取值为1；减少应对策略；患病率——若家庭采用应对策略则取值为1 |
| `demographic` | 字符型 | 22.6% | F、M、受援助群体 |
| `mean` | 浮点型 | 0.1% | 0.0 – 21.6182（均值1.445） |
| `esa_source` | 字符型 | 0.0% | HDX |
| `esa_processed` | 字符型 | 0.0% | 2026-04-06 |

---

## 数值统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `mean` | 0.0 | 21.6182 | 1.445 | 0.4859 |

---

## 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。列名统一转为小写并调整为蛇形命名法（snake_case）。常见的空值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。移除了2个空值占比超过80%的列：`adm1_name`、`adm2_name`。移除了1条完全重复的数据行。根据解析成功率（阈值85%），将2列从字符型转换为数值型或日期时间型。本数据集以固定随机种子（42）按照80/20的比例划分为训练集与测试集，并以Snappy压缩的Parquet格式存储。

---

## 数据集局限性

- 本数据集数据来源于世界粮食计划署（WFP），未经过非洲电羊（Electric Sheep Africa）的独立验证。
- 自动化数据清洗无法修正原始数据收集中的错报、定义不一致或抽样偏差问题。
- 以下列的空值占比超过20%，在建模过程中需谨慎使用：`adminstrata`、`variabledescription`、`demographic`。
- 请参阅[HDX平台原始数据集页面](https://data.humdata.org/dataset/wfp-food-security-indicators-for-mozambique)获取发布方提供的方法说明与注意事项。

---

## 引用格式

bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_mozambique,
title = {Mozambique - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-mozambique},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}

---

*[非洲电羊（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。*