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

---
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
- tcd
pretty_name: "Chad - Food Security Indicators"
dataset_info:
splits:
- name: train
num_examples: 1341
- name: test
num_examples: 335
---

# Chad - Food Security Indicators

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

*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)** | 1,677 |
| **Columns** | 9 (1 numeric, 7 categorical, 1 datetime) |
| **Train split** | 1,341 rows |
| **Test split** | 335 rows |
| **Geographic scope** | TCD |
| **Publisher** | WFP - World Food Programme |
| **HDX last updated** | 2024-09-13 |

---

## Variables

**Geographic** — `svydate`, `adminstrata` (Goz Amir, Belom, #loc+name).

**Identifier / Metadata** — `adm0_name` (Chad, #country+name), `esa_source` (HDX), `esa_processed` (2026-04-05).

**Other** — `variable` (Proteins, LimitPortionSize>=1, Sugars), `variabledescription` (prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household eating this food item per week, prevalence-->food consumption group = poor+borderline), `demographic` (M, F, High_income), `mean` (range 0.0–57.7273).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-chad")
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% | Chad, #country+name |
| `adminstrata` | object | 0.0% | Goz Amir, Belom, #loc+name |
| `variable` | object | 0.0% | Proteins, LimitPortionSize>=1, Sugars |
| `variabledescription` | object | 26.5% | prevalence-->equals to 1 if household uses this strategy 1 or more times per week, # of days household eating this food item per week, prevalence-->food consumption group = poor+borderline |
| `demographic` | object | 17.2% | M, F, High_income |
| `mean` | float64 | 0.1% | 0.0 – 57.7273 (mean 4.2308) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-05 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `mean` | 0.0 | 57.7273 | 4.2308 | 0.8476 |

---

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

---

## Citation

```bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_chad,
title = {Chad - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-chad},
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:
- 现有资源采集
language:
- en
license: CC BY 4.0
multilinguality:
- 单语种
size_categories:
- 1000 < 样本数 < 10000
source_datasets:
- 原生数据集
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
- TCD
pretty_name: "乍得——粮食安全指标"
dataset_info:
splits:
- name: train
num_examples: 1341
- name: test
num_examples: 335

# 乍得——粮食安全指标

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

---

## 摘要
世界粮食计划署（WFP）于2013年启动移动脆弱性分析与制图（mobile Vulnerability Analysis and Mapping, mVAM）项目，最初在刚果民主共和国与索马里开展试点。mVAM依托移动技术实时追踪粮食安全趋势，可提供高频观测数据以支撑人道主义决策制定。数据收集方法将根据mVAM运营所在国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）。

数据集中的每一行均代表一组时序观测值。时间覆盖范围由`svydate`（调查日期）列标注。地理覆盖范围：**乍得（TCD）**。

*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
| | |
|---|---|
| **研究领域** | 粮食安全与营养 |
| **观测单元** | 时序观测值 |
| **总行数** | 1677 |
| **列数** | 9（1个数值列、7个分类列、1个日期时间列） |
| **训练集拆分** | 1341行 |
| **测试集拆分** | 335行 |
| **地理覆盖范围** | TCD（乍得） |
| **发布方** | WFP - 世界粮食计划署 |
| **HDX最后更新时间** | 2024-09-13 |

---

## 变量说明
**地理相关字段** — `svydate`、`adminstrata`（戈兹阿米尔、贝洛姆，#loc+name，即地点名称）。
**标识符与元数据字段** — `adm0_name`（乍得，#country+name，即国家名称）、`esa_source`（HDX）、`esa_processed`（2026-04-05，即数据处理日期）。
**其他字段** — `variable`（蛋白质、LimitPortionSize>=1、糖类）、`variabledescription`（患病率——若家庭每周至少1次采用该策略则取值为1；家庭每周食用该食品的天数；患病率——食物消费组为贫困+临界贫困）、`demographic`（男性、女性、高收入群体）、`mean`（取值范围0.0–57.7273）。

---

## 快速上手
python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-security-indicators-for-chad")
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 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `svydate` | datetime64[ns] | 0.1% | 无 |
| `adm0_name` | object | 0.0% | 乍得，#country+name |
| `adminstrata` | object | 0.0% | 戈兹阿米尔、贝洛姆，#loc+name |
| `variable` | object | 0.0% | 蛋白质、LimitPortionSize>=1、糖类 |
| `variabledescription` | object | 26.5% | 患病率——若家庭每周至少1次采用该策略则取值为1；家庭每周食用该食品的天数；患病率——食物消费组为贫困+临界贫困 |
| `demographic` | object | 17.2% | 男性、女性、高收入群体 |
| `mean` | float64 | 0.1% | 0.0 – 57.7273（均值为4.2308） |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-05 |

---

## 数值统计摘要
| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `mean` | 0.0 | 57.7273 | 4.2308 | 0.8476 |

---

## 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。列名已统一转换为小写蛇形命名法。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）已统一替换为`NaN`。移除了2个缺失值占比超过80%的列：`adm1_name`、`adm2_name`。基于解析成功率（阈值85%），将2个列从字符串类型转换为数值或日期时间类型。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
- 数据源自世界粮食计划署（WFP），尚未由Electric Sheep Africa进行独立验证。
- 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。
- 以下列的缺失值占比超过20%，在建模时需谨慎使用：`variabledescription`（变量描述）。
- 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/wfp-food-security-indicators-for-chad)获取发布方提供的方法论说明与相关注意事项。

---

## 引用格式
bibtex
@dataset{hdx_africa_wfp_food_security_indicators_for_chad,
title = {Chad - Food Security Indicators},
author = {WFP - World Food Programme},
year = {2024},
url = {https://data.humdata.org/dataset/wfp-food-security-indicators-for-chad},
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。*