electricsheepafrica/africa-faostat-food-security-indicators-for-south-africa

---
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
- indicators
- nutrition
- zaf
pretty_name: "South Africa - Food Security and Nutrition Indicators"
dataset_info:
splits:
- name: train
num_examples: 863
- name: test
num_examples: 215
---

# South Africa - Food Security and Nutrition Indicators

**Publisher:** Food and Agriculture Organization (FAO) of the United Nations · **Source:** [HDX](https://data.humdata.org/dataset/faostat-food-security-indicators-for-south-africa) · **License:** `cc-by-igo` · **Updated:** 2026-04-06

---

## Abstract

Food Security and Nutrition Indicators for South Africa.

Contains data from the FAOSTAT [bulk data service](https://fenixservices.fao.org/faostat/static/bulkdownloads/datasets_E.json).

Each row in this dataset represents country-level aggregates. Temporal coverage is indicated by the `startdate`, `enddate` column(s). Geographic scope: **ZAF**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 1,079 |
| **Columns** | 18 (5 numeric, 11 categorical, 2 datetime) |
| **Train split** | 863 rows |
| **Test split** | 215 rows |
| **Geographic scope** | ZAF |
| **Publisher** | Food and Agriculture Organization (FAO) of the United Nations |
| **HDX last updated** | 2026-04-06 |

---

## Variables

**Geographic** — `iso3` (ZAF), `year_code` (range 2000.0–20222024.0), `year` (range 2000.0–2024.0).

**Temporal** — `startdate`, `enddate`.

**Outcome / Measurement** — `value` (range -0.75–14699.0).

**Identifier / Metadata** — `area_code` (range 202.0–202.0), `area_code_m49` ('710), `item_code` (210071M, 210091F, 210081F), `element_code` (range 6121.0–61322.0), `esa_source` (HDX) and 1 others.

**Other** — `area` (South Africa), `item` (Number of severely food insecure male adults (million) (3-year average), Prevalence of moderate or severe food insecurity in the female adult population (percent) (3-year average), Number of moderately or severely food insecure female adults (million) (3-year average)), `element` (Value, Confidence interval: Lower bound, Confidence interval: Upper bound), `unit` (%, million No, kcal/cap/d), `flag` (E, X, O) and 1 others.

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `iso3` | object | 0.0% | ZAF |
| `startdate` | datetime64[ns] | 0.0% | |
| `enddate` | datetime64[ns] | 0.0% | |
| `area_code` | int64 | 0.0% | 202.0 – 202.0 (mean 202.0) |
| `area_code_m49` | object | 0.0% | '710 |
| `area` | object | 0.0% | South Africa |
| `item_code` | object | 0.0% | 210071M, 210091F, 210081F |
| `item` | object | 0.0% | Number of severely food insecure male adults (million) (3-year average), Prevalence of moderate or severe food insecurity in the female adult population (percent) (3-year average), Number of moderately or severely food insecure female adults (million) (3-year average) |
| `element_code` | int64 | 0.0% | 6121.0 – 61322.0 (mean 17164.5644) |
| `element` | object | 0.0% | Value, Confidence interval: Lower bound, Confidence interval: Upper bound |
| `year_code` | int64 | 0.0% | 2000.0 – 20222024.0 (mean 10570846.6024) |
| `year` | int64 | 0.0% | 2000.0 – 2024.0 (mean 2014.3503) |
| `unit` | object | 2.0% | %, million No, kcal/cap/d |
| `value` | float64 | 10.0% | -0.75 – 14699.0 (mean 615.0662) |
| `flag` | object | 0.0% | E, X, O |
| `note` | object | 79.4% | Official estimate integrated with FAO data, Official estimate, Age-Adjusted |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `area_code` | 202.0 | 202.0 | 202.0 | 202.0 |
| `element_code` | 6121.0 | 61322.0 | 17164.5644 | 6128.0 |
| `year_code` | 2000.0 | 20222024.0 | 10570846.6024 | 20022004.0 |
| `year` | 2000.0 | 2024.0 | 2014.3503 | 2016.0 |
| `value` | -0.75 | 14699.0 | 615.0662 | 13.1 |

---

## 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) 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 Food and Agriculture Organization (FAO) of the United Nations 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: `note`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/faostat-food-security-indicators-for-south-africa) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_faostat_food_security_indicators_for_south_africa,
title = {South Africa - Food Security and Nutrition Indicators},
author = {Food and Agriculture Organization (FAO) of the United Nations},
year = {2026},
url = {https://data.humdata.org/dataset/faostat-food-security-indicators-for-south-africa},
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:
- 公开获取
language:
- 英语
license: cc-by-4.0
multilinguality:
- 单语言
size_categories:
- 1000 < 数据量 < 10000
source_datasets:
- 原创
task_categories:
- 表格分类
- 表格回归
task_ids: []
tags:
- 非洲
- 人道主义
- HDX
- Electric Sheep Africa
- 粮食安全
- 指标
- 营养
- ZAF
pretty_name: "南非——粮食安全与营养指标"
dataset_info:
splits:
- name: train
num_examples: 863
- name: test
num_examples: 215

# 南非——粮食安全与营养指标

**发布方**: 联合国粮食及农业组织（Food and Agriculture Organization, FAO） · **来源**: [HDX](https://data.humdata.org/dataset/faostat-food-security-indicators-for-south-africa) · **许可证**: `cc-by-igo` · **更新时间**: 2026-04-06

---

## 摘要
南非粮食安全与营养指标数据集。
数据源自FAOSTAT [批量数据服务](https://fenixservices.fao.org/faostat/static/bulkdownloads/datasets_E.json)。
本数据集每一行代表国家级汇总数据。时间覆盖范围由`startdate`、`enddate`列标注。地理范围：**ZAF**。
*由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适合机器学习的Parquet格式。*

---

## 数据集特征
| | |
|---|---|
| **领域** | 粮食安全与营养 |
| **观测单元** | 国家级汇总数据 |
| **总数据行数** | 1079条 |
| **列数** | 18列（5列数值型、11列分类型、2列日期时间型） |
| **训练集拆分** | 863行 |
| **测试集拆分** | 215行 |
| **地理范围** | ZAF |
| **发布方** | 联合国粮食及农业组织（Food and Agriculture Organization, FAO） |
| **HDX最后更新时间** | 2026-04-06 |

---

## 变量
**地理类变量** — `iso3`（ZAF）、`year_code`（取值范围2000.0–20222024.0）、`year`（取值范围2000.0–2024.0）。
**时间类变量** — `startdate`、`enddate`。
**结果/测量变量** — `value`（取值范围-0.75–14699.0）。
**标识符/元数据变量** — `area_code`（取值范围202.0–202.0）、`area_code_m49`（'710）、`item_code`（210071M、210091F、210081F）、`element_code`（取值范围6121.0–61322.0）、`esa_source`（HDX）及其他1项。
**其他变量** — `area`（南非）、`item`（严重粮食不安全成年男性人口数量（百万）（3年平均值）、成年女性人口中度或重度粮食不安全患病率（百分比）（3年平均值）、中度或重度粮食不安全成年女性人口数量（百万）（3年平均值））、`element`（数值、置信区间下限、置信区间上限）、`unit`（%、百万、千卡/人/天）、`flag`（E、X、O）及其他1项。

---

## 快速上手
python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-faostat-food-security-indicators-for-south-africa")
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 |
|---|---|---|---|
| `iso3` | object | 0.0% | ZAF |
| `startdate` | datetime64[ns] | 0.0% | |
| `enddate` | datetime64[ns] | 0.0% | |
| `area_code` | int64 | 0.0% | 202.0 – 202.0（均值202.0） |
| `area_code_m49` | object | 0.0% | '710 |
| `area` | object | 0.0% | 南非 |
| `item_code` | object | 0.0% | 210071M、210091F、210081F |
| `item` | object | 0.0% | 严重粮食不安全成年男性人口数量（百万）（3年平均值）、成年女性人口中度或重度粮食不安全患病率（百分比）（3年平均值）、中度或重度粮食不安全成年女性人口数量（百万）（3年平均值） |
| `element_code` | int64 | 0.0% | 6121.0 – 61322.0（均值17164.5644） |
| `element` | object | 0.0% | 数值、置信区间下限、置信区间上限 |
| `year_code` | int64 | 0.0% | 2000.0 – 20222024.0（均值10570846.6024） |
| `year` | int64 | 0.0% | 2000.0 – 2024.0（均值2014.3503） |
| `unit` | object | 2.0% | %、百万、千卡/人/天 |
| `value` | float64 | 10.0% | -0.75 – 14699.0（均值615.0662） |
| `flag` | object | 0.0% | E、X、O |
| `note` | object | 79.4% | 与FAO数据整合的官方估算值、官方估算值、年龄标准化 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | |

---

## 数值型变量统计摘要
| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `area_code` | 202.0 | 202.0 | 202.0 | 202.0 |
| `element_code` | 6121.0 | 61322.0 | 17164.5644 | 6128.0 |
| `year_code` | 2000.0 | 20222024.0 | 10570846.6024 | 20022004.0 |
| `year` | 2000.0 | 2024.0 | 2014.3503 | 2016.0 |
| `value` | -0.75 | 14699.0 | 615.0662 | 13.1 |

---

## 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。列名统一转为小写并标准化为蛇形命名法（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`。根据解析成功率（阈值>85%）将2列从字符串类型转换为数值型或日期时间型。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。

---

## 数据集局限性
- 数据源自联合国粮食及农业组织（Food and Agriculture Organization, FAO），未经Electric Sheep Africa独立验证。
- 自动化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。
- 以下列缺失率超过20%，在建模时需谨慎使用：`note`。
- 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/faostat-food-security-indicators-for-south-africa)获取发布方提供的方法说明与注意事项。

---

## 引用
bibtex
@dataset{hdx_africa_faostat_food_security_indicators_for_south_africa,
title = {South Africa - Food Security and Nutrition Indicators},
author = {Food and Agriculture Organization (FAO) of the United Nations},
year = {2026},
url = {https://data.humdata.org/dataset/faostat-food-security-indicators-for-south-africa},
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。*