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

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- food-security
- hxl
- indicators
- nga
pretty_name: "Nigeria - Food Security Indicators"
dataset_info:
splits:
- name: train
num_examples: 11873
- name: test
num_examples: 2968
---

# Nigeria - Food Security Indicators

**Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/wfp-food-security-indicators-for-nigeria) · **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: **NGA**.

*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)** | 14,842 |
| **Columns** | 9 (1 numeric, 7 categorical, 1 datetime) |
| **Train split** | 11,873 rows |
| **Test split** | 2,968 rows |
| **Geographic scope** | NGA |
| **Publisher** | WFP - World Food Programme |
| **HDX last updated** | 2024-09-13 |

---

## Variables

**Geographic** — `svydate`, `adminstrata` (BORNO CENTRAL, BORNO SOUTH, ADAMAWA CENTRAL).

**Identifier / Metadata** — `adm0_name` (Nigeria, #country+name), `esa_source` (HDX), `esa_processed` (2026-04-08).

**Other** — `variable` (RestrictConsumption>=1, Veg, Pulses), `variabledescription` (# of days household using this coping strategy per week, prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household eating this food item per week), `demographic` (M, N, Y), `mean` (range 0.0–2001.2658).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-nigeria")
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] | 0.0% | |
| `adm0_name` | object | 0.0% | Nigeria, #country+name |
| `adminstrata` | object | 17.1% | BORNO CENTRAL, BORNO SOUTH, ADAMAWA CENTRAL |
| `variable` | object | 0.0% | RestrictConsumption>=1, Veg, Pulses |
| `variabledescription` | object | 26.0% | # of days household using this coping strategy per week, prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household eating this food item per week |
| `demographic` | object | 47.8% | M, N, Y |
| `mean` | float64 | 0.0% | 0.0 – 2001.2658 (mean 78.1224) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `mean` | 0.0 | 2001.2658 | 78.1224 | 1.64 |

---

## 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`. 83 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: `variabledescription`, `demographic`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/wfp-food-security-indicators-for-nigeria) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_nigeria,
title = {Nigeria - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-nigeria},
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:
- 爬取获取
language:
- 英语
license: CC-BY-4.0
multilinguality:
- 单语言
size_categories:
- 10K<n<100K
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
- electric-sheep-africa
- 粮食安全
- HXL
- 指标
- NGA
pretty_name: "尼日利亚——粮食安全指标"

# 尼日利亚——粮食安全指标

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

---

## 摘要

世界粮食计划署（WFP）于2013年启动了移动脆弱性分析与绘图（mobile Vulnerability Analysis and Mapping，简称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，提供高频数据以支撑人道主义决策。数据收集方法针对mVAM运营所在的每个国家的需求定制。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时序观测数据，时间覆盖范围由`svydate`列标注。地理覆盖范围：**NGA（尼日利亚）**。

*由[电动绵羊非洲（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

| 指标 | 详情 |
|---|---|
| **领域** | 粮食安全与营养 |
| **观测单元** | 时序观测数据 |
| **总数据行数** | 14842条 |
| **列数** | 9列（1个数值型列、7个分类型列、1个日期时间型列） |
| **训练集划分** | 11873行 |
| **测试集划分** | 2968行 |
| **地理覆盖范围** | NGA（尼日利亚） |
| **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`、`adminstrata`（取值包括BORNO CENTRAL、BORNO SOUTH、ADAMAWA CENTRAL）。

**标识/元数据类变量**：`adm0_name`（尼日利亚，#country+name）、`esa_source`（HDX）、`esa_processed`（2026-04-08）。

**其他变量**：`variable`（取值包括RestrictConsumption>=1、Veg、Pulses）、`variabledescription`（家庭每周使用该应对策略的天数；流行度指标——若家庭每周至少使用该策略1次则取值为1；家庭每周食用该食品的天数）、`demographic`（取值包括M、N、Y）、`mean`（取值范围0.0–2001.2658）。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-nigeria")
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 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `svydate` | datetime64[ns] | 0.0% | 无 |
| `adm0_name` | object | 0.0% | Nigeria, #country+name |
| `adminstrata` | object | 17.1% | BORNO CENTRAL, BORNO SOUTH, ADAMAWA CENTRAL |
| `variable` | object | 0.0% | RestrictConsumption>=1, Veg, Pulses |
| `variabledescription` | object | 26.0% | # of days household using this coping strategy per week, prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household eating this food item per week |
| `demographic` | object | 47.8% | M, N, Y |
| `mean` | float64 | 0.0% | 0.0 – 2001.2658（均值78.1224） |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## 数值型变量统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `mean` | 0.0 | 2001.2658 | 78.1224 | 1.64 |

---

## 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标准化为蛇形命名法。常见空值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。移除了2个空值占比超过80%的列：`adm1_name`与`adm2_name`。删除了83条完全重复的行。基于解析成功率（阈值>85%），将2列从字符串类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80/20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. 本数据集源自世界粮食计划署（WFP），尚未由电动绵羊非洲（ESA）进行独立验证。
2. 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。
3. 以下列的空值占比超过20%，在建模时需谨慎使用：`variabledescription`、`demographic`。
4. 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/wfp-food-security-indicators-for-nigeria)。

---

## 引用格式

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

---

*[电动绵羊非洲（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。*