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

---
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
- lbr
pretty_name: "Liberia - Food Security Indicators"
dataset_info:
splits:
- name: train
num_examples: 3384
- name: test
num_examples: 846
---

# Liberia - Food Security Indicators

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

*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)** | 4,231 |
| **Columns** | 9 (1 numeric, 7 categorical, 1 datetime) |
| **Train split** | 3,384 rows |
| **Test split** | 846 rows |
| **Geographic scope** | LBR |
| **Publisher** | WFP - World Food Programme |
| **HDX last updated** | 2024-09-13 |

---

## Variables

**Geographic** — `svydate`, `adminstrata` (Montserrado, Bong, Grand Bassa).

**Identifier / Metadata** — `adm0_name` (Liberia, #country+name), `esa_source` (HDX), `esa_processed` (2026-04-07).

**Other** — `variable` (RestrictConsumption>=1, BorrowOrHelp>=1, LessExpensiveFood>=1), `variabledescription` (prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household using this coping strategy per week, Daily wages for manual labor), `demographic` (Cement pit latrine, Own flush toilet, Shared flush toilet), `mean` (range -0.1166–263.6143).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-liberia")
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% | Liberia, #country+name |
| `adminstrata` | object | 43.8% | Montserrado, Bong, Grand Bassa |
| `variable` | object | 0.0% | RestrictConsumption>=1, BorrowOrHelp>=1, LessExpensiveFood>=1 |
| `variabledescription` | object | 5.7% | prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household using this coping strategy per week, Daily wages for manual labor |
| `demographic` | object | 56.2% | Cement pit latrine, Own flush toilet, Shared flush toilet |
| `mean` | float64 | 0.0% | -0.1166 – 263.6143 (mean 20.3504) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-07 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `mean` | -0.1166 | 263.6143 | 20.3504 | 1.5267 |

---

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

---

## Citation

```bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_liberia,
title = {Liberia - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-liberia},
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
- 语言来源：公开采集
- 语言：英语（en）
- 许可协议：CC BY 4.0
- 多语言属性：单语言
- 数据规模：1000 < 样本数 < 10000
- 源数据集：原生数据集
- 任务类别：表格回归、其他
- 任务子项：无
- 标签：非洲、人道主义、HDX、Electric Sheep Africa、粮食安全、HXL、指标、LBR
- 友好名称："利比里亚——粮食安全指标"
- 数据集信息：
- 拆分集：
- 训练集：3384条样本
- 测试集：846条样本

# 利比里亚——粮食安全指标数据集

**发布方**：世界粮食计划署（WFP） · **来源**：[HDX](https://data.humdata.org/dataset/wfp-food-security-indicators-for-liberia) · **许可协议**：`cc-by-igo` · **更新时间**：2024年9月13日

---

## 摘要
世界粮食计划署（WFP）于2013年启动了移动脆弱性分析与制图（mVAM）项目，首批覆盖刚果民主共和国（DRC）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制定。数据采集方法会根据mVAM运营所在国家的实际需求进行定制。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`（调查日期）列标注。地理覆盖范围：**利比里亚（LBR）**。
*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
| 特征项 | 详情 |
|---|---|
| **领域** | 粮食安全与营养 |
| **观测单元** | 时序观测数据 |
| **总样本行数** | 4231条 |
| **列数** | 9列（1列数值型、7列分类型、1列日期时间型） |
| **训练集样本数** | 3384条 |
| **测试集样本数** | 846条 |
| **地理覆盖范围** | 利比里亚（LBR） |
| **发布方** | 世界粮食计划署（WFP） |
| **HDX最后更新时间** | 2024年9月13日 |

---

## 变量说明
1. **地理类变量**：`svydate`（调查日期）、`adminstrata`（行政区域：蒙特塞拉多、邦、大巴萨）。
2. **标识/元数据类变量**：`adm0_name`（国家名称：利比里亚，#country+name）、`esa_source`（数据来源：HDX）、`esa_processed`（数据处理日期：2026-04-07）。
3. **其他变量**：
- `variable`（指标类型：RestrictConsumption>=1、BorrowOrHelp>=1、LessExpensiveFood>=1）
- `variabledescription`（指标描述：患病率——若家庭每周使用该策略1次及以上则取值为1；家庭每周使用该应对策略的天数；体力劳动者日工资）
- `demographic`（人口统计特征：水泥坑式厕所、独立冲水马桶、共用冲水马桶）
- `mean`（均值指标：取值范围-0.1166至263.6143）

---

## 快速上手
python
from datasets import load_dataset

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

print(train.shape)
train.head()

---

## 数据Schema
| 列名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `svydate` | datetime64[ns] | 0.0% | - |
| `adm0_name` | 字符串类型 | 0.0% | 利比里亚, #country+name |
| `adminstrata` | 字符串类型 | 43.8% | 蒙特塞拉多、邦、大巴萨 |
| `variable` | 字符串类型 | 0.0% | RestrictConsumption>=1、BorrowOrHelp>=1、LessExpensiveFood>=1 |
| `variabledescription` | 字符串类型 | 5.7% | 患病率——若家庭每周使用该策略1次及以上则取值为1；家庭每周使用该应对策略的天数；体力劳动者日工资 |
| `demographic` | 字符串类型 | 56.2% | 水泥坑式厕所、独立冲水马桶、共用冲水马桶 |
| `mean` | 浮点型 | 0.0% | -0.1166 至 263.6143（均值为20.3504） |
| `esa_source` | 字符串类型 | 0.0% | HDX |
| `esa_processed` | 字符串类型 | 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 |
|---|---|---|---|---|
| `mean` | -0.1166 | 263.6143 | 20.3504 | 1.5267 |

---

## 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。对列名进行小写转换并统一为蛇形命名法。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2列缺失值占比超过80%的字段：`adm1_name`、`adm2_name`。根据解析成功率（阈值为85%），将2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。

---

## 数据集局限性
1. 本数据集源自世界粮食计划署（WFP），未由Electric Sheep Africa（ESA）进行独立验证。
2. 自动化清洗流程无法修正原始数据采集阶段的错报值、定义不一致问题或抽样偏差。
3. 以下列的缺失值占比超过20%，在建模过程中需谨慎使用：`adminstrata`、`demographic`。
4. 如需了解发布方提供的方法说明与注意事项，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/wfp-food-security-indicators-for-liberia)。

---

## 引用格式
bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_liberia,
title = {Liberia - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-liberia},
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。尼日利亚拉各斯。*