electricsheepafrica/africa-disability-djibouti

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-classification
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- disability
- disease
- environment
- health
- hxl
- indicators
- malaria
- maternity
- dji
pretty_name: "Djibouti - Health Indicators"
dataset_info:
splits:
- name: train
num_examples: 14008
- name: test
num_examples: 3502
---

# Djibouti - Health Indicators

**Publisher:** World Health Organization · **Source:** [HDX](https://data.humdata.org/dataset/who-data-for-djibouti) · **License:** `hdx-other` · **Updated:** 2025-02-07

---

## Abstract

This dataset contains data from WHO's [data portal](https://www.who.int/gho/en/) covering the following categories:

Air pollution, Antimicrobial resistance (AMR), Assistive technology, Child mortality, Dementia diagnosis, treatment and care, Dementia policy and legislation, Environment and health, Foodborne Diseases Estimates, Global Dementia Observatory (GDO), Global Health Estimates: Life expectancy and leading causes of death and disability, Global Information System on Alcohol and Health, HIV, Health Inequality Monitor, Health financing, Health systems, Health taxes, Health workforce, Hepatitis, Immunization coverage and vaccine-preventable diseases, International Health Regulations (2005) monitoring framework, Malaria, Maternal and reproductive health, Mental health, Neglected tropical diseases, Noncommunicable diseases, Nutrition, Oral Health, Priority health technologies, Resources for Substance Use Disorders, Road Safety, SDG Target 3.8 | Achieve universal health coverage (UHC), Sexually Transmitted Infections, Tobacco control, Tuberculosis, Vaccine-preventable communicable diseases, Violence against women, Violence prevention, Water, sanitation and hygiene (WASH), Women and health, World Health Statistics.

For links to individual indicator metadata, see resource descriptions.

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2025-02-07. Geographic scope: **DJI**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 17,511 |
| **Columns** | 19 (6 numeric, 13 categorical, 0 datetime) |
| **Train split** | 14,008 rows |
| **Test split** | 3,502 rows |
| **Geographic scope** | DJI |
| **Publisher** | World Health Organization |
| **HDX last updated** | 2025-02-07 |

---

## Variables

**Geographic** — `gho_display` (Number of deaths, Deaths per 1 000 live births, Distribution of causes of death among children aged < 5 years (%)), `year_display` (range 1961.0–2030.0), `startyear` (range 1961.0–2030.0), `endyear` (range 1961.0–2030.0), `region_code` (EMR, #region+code) and 4 others.

**Outcome / Measurement** — `value`.

**Identifier / Metadata** — `gho_code` (MORT_100, MORT_200, MORT_300), `dimension_code` (SEX_BTSX, SEX_FMLE, SEX_MLE), `dimension_name` (Both sexes, Female, Male), `esa_source`, `esa_processed`.

**Other** — `gho_url` (https://www.who.int/data/gho/data/indicators/indicator-details/GHO/number-of-deaths, https://www.who.int/data/gho/data/indicators/indicator-details/GHO/gho-ghe-life-tables-by-who-region-global-health-estimates, https://www.who.int/data/gho/data/indicators/indicator-details/GHO/distribution-of-causes-of-death-among-children-aged-5-years-%28-%29), `numeric` (range 0.0–6777696.094), `low` (range 0.0–22696.2754), `high` (range 0.0–34113.4102).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-disability-djibouti")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `gho_code` | object | 0.0% | MORT_100, MORT_200, MORT_300 |
| `gho_display` | object | 0.0% | Number of deaths, Deaths per 1 000 live births, Distribution of causes of death among children aged < 5 years (%) |
| `gho_url` | object | 0.0% | https://www.who.int/data/gho/data/indicators/indicator-details/GHO/number-of-deaths, https://www.who.int/data/gho/data/indicators/indicator-details/GHO/gho-ghe-life-tables-by-who-region-global-health-estimates, https://www.who.int/data/gho/data/indicators/indicator-details/GHO/distribution-of-causes-of-death-among-children-aged-5-years-%28-%29 |
| `year_display` | float64 | 0.0% | 1961.0 – 2030.0 (mean 2008.1354) |
| `startyear` | float64 | 0.0% | 1961.0 – 2030.0 (mean 2008.1335) |
| `endyear` | float64 | 0.0% | 1961.0 – 2030.0 (mean 2008.1354) |
| `region_code` | object | 0.0% | EMR, #region+code |
| `region_display` | object | 0.0% | Eastern Mediterranean, #region+name |
| `country_code` | object | 0.0% | DJI, #country+code |
| `country_display` | object | 0.0% | Djibouti, #country+name |
| `dimension_type` | object | 18.4% | SEX, RESIDENCEAREATYPE, AGEGROUP |
| `dimension_code` | object | 18.4% | SEX_BTSX, SEX_FMLE, SEX_MLE |
| `dimension_name` | object | 18.4% | Both sexes, Female, Male |
| `numeric` | float64 | 11.8% | 0.0 – 6777696.094 (mean 61462.2593) |
| `value` | object | 0.2% | |
| `low` | float64 | 49.4% | 0.0 – 22696.2754 (mean 90.8079) |
| `high` | float64 | 49.4% | 0.0 – 34113.4102 (mean 190.3969) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `year_display` | 1961.0 | 2030.0 | 2008.1354 | 2010.0 |
| `startyear` | 1961.0 | 2030.0 | 2008.1335 | 2010.0 |
| `endyear` | 1961.0 | 2030.0 | 2008.1354 | 2010.0 |
| `numeric` | 0.0 | 6777696.094 | 61462.2593 | 11.6049 |
| `low` | 0.0 | 22696.2754 | 90.8079 | 4.5678 |
| `high` | 0.0 | 34113.4102 | 190.3969 | 18.4 |

---

## 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`. 253 exact duplicate rows were removed. 6 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 World Health Organization 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: `low`, `high`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/who-data-for-djibouti) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_disability_djibouti,
title = {Djibouti - Health Indicators},
author = {World Health Organization},
year = {2025},
url = {https://data.humdata.org/dataset/who-data-for-djibouti},
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.*

注释创建者：
- 无注释
语言创建方式：
- 爬取获取
语言：
- 英语
许可证：
- 其他
多语言属性：
- 单语言
样本规模：
- 10000 < 样本数 < 100000
源数据集：
- 原始数据集
任务类别：
- 表格分类
任务子类别：
- 无
标签：
- 非洲
- 人道主义
- 人道主义数据交换（HDX）
- Electric Sheep Africa
- 残疾
- 疾病
- 环境
- 健康
- 人道主义交换语言（HXL）
- 指标
- 疟疾
- 孕产妇
- DJI
美观名称："吉布提——健康指标"
数据集信息：
划分集：
- 名称：训练集，样本数：14008
- 名称：测试集，样本数：3502

# 吉布提——健康指标

**发布方：世界卫生组织 · **来源：[人道主义数据交换平台（HDX）](https://data.humdata.org/dataset/who-data-for-djibouti) · **许可证：`hdx-other` · **更新时间：2025-02-07**

---

## 摘要

本数据集收录了来自世界卫生组织（World Health Organization，WHO）[数据门户](https://www.who.int/gho/en/)的相关数据，涵盖以下类别：
空气污染、抗菌素耐药性（Antimicrobial Resistance，AMR）、辅助技术、儿童死亡率、痴呆症诊断治疗与照护、痴呆症政策与法规、环境与健康、食源性疾病估算、全球痴呆症观测站（Global Dementia Observatory，GDO）、全球健康估算：预期寿命及主要死亡与致残原因、全球酒精与健康信息系统、艾滋病、健康不平等监测、卫生筹资、卫生系统、健康税、卫生人力、肝炎、免疫接种覆盖率与疫苗可预防疾病、《国际卫生条例（2005）》监测框架、疟疾、孕产妇与生殖健康、精神卫生、被忽视的热带病、非传染性疾病、营养学、口腔健康、优先卫生技术、物质使用障碍相关资源、道路安全、可持续发展目标3.8指标 | 实现全民健康覆盖（Universal Health Coverage，UHC）、性传播感染、烟草控制、结核病、疫苗可预防传染病、针对妇女的暴力行为、暴力预防、水、环境卫生与个人卫生（Water, Sanitation and Hygiene，WASH）、妇女与健康、世界卫生统计。

如需获取各指标元数据的链接，请参阅资源描述部分。

本数据集的每一行均代表一级行政单元的观测数据。本数据集最近一次在HDX平台更新的时间为2025年2月7日，地理覆盖范围：**DJI（吉布提）**。

*本数据集由[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 |
|---|---|
| **研究领域** | 粮食安全与营养 |
| **观测单元** | 一级行政单元观测数据 |
| **总样本行数** | 17511 |
| **列数** | 19列（6个数值型、13个分类型、0个日期时间型） |
| **训练集样本数** | 14008行 |
| **测试集样本数** | 3502行 |
| **地理覆盖范围** | DJI（吉布提） |
| **发布方** | 世界卫生组织 |
| **HDX平台最后更新时间** | 2025-02-07 |

---

## 变量说明

**地理类变量** — `gho_display`（死亡数、每1000活产儿死亡数、5岁以下儿童死亡原因分布占比）、`year_display`（取值范围1961.0~2030.0）、`startyear`（取值范围1961.0~2030.0）、`endyear`（取值范围1961.0~2030.0）、`region_code`（EMR、#region+code）等共9个变量（含上述5个及另外4个）。

**结果/测量类变量** — `value`。

**标识符/元数据类变量** — `gho_code`（MORT_100、MORT_200、MORT_300）、`dimension_code`（SEX_BTSX、SEX_FMLE、SEX_MLE）、`dimension_name`（男女合计、女性、男性）、`esa_source`、`esa_processed`。

**其他变量** — `gho_url`（各指标详情链接，示例：https://www.who.int/data/gho/data/indicators/indicator-details/GHO/number-of-deaths）、`numeric`（取值范围0.0~6777696.094）、`low`（取值范围0.0~22696.2754）、`high`（取值范围0.0~34113.4102）。

---

## 快速上手示例

python
from datasets import load_dataset

# 加载吉布提健康指标数据集
ds = load_dataset("electricsheepafrica/africa-disability-djibouti")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

# 输出训练集维度
print(train.shape)
# 查看训练集前5行数据
train.head()

---

## 数据结构

| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `gho_code` | 字符型 | 0.0% | MORT_100、MORT_200、MORT_300 |
| `gho_display` | 字符型 | 0.0% | 死亡数、每1000活产儿死亡数、5岁以下儿童死亡原因分布占比 |
| `gho_url` | 字符型 | 0.0% | 各指标详情链接，示例：https://www.who.int/data/gho/data/indicators/indicator-details/GHO/number-of-deaths |
| `year_display` | 双精度浮点型 | 0.0% | 1961.0 ~ 2030.0（均值2008.1354） |
| `startyear` | 双精度浮点型 | 0.0% | 1961.0 ~ 2030.0（均值2008.1335） |
| `endyear` | 双精度浮点型 | 0.0% | 1961.0 ~ 2030.0（均值2008.1354） |
| `region_code` | 字符型 | 0.0% | EMR、#region+code |
| `region_display` | 字符型 | 0.0% | 东地中海区域、#region+name |
| `country_code` | 字符型 | 0.0% | DJI、#country+code |
| `country_display` | 字符型 | 0.0% | 吉布提、#country+name |
| `dimension_type` | 字符型 | 18.4% | 性别、居住区域类型、年龄组 |
| `dimension_code` | 字符型 | 18.4% | SEX_BTSX、SEX_FMLE、SEX_MLE |
| `dimension_name` | 字符型 | 18.4% | 男女合计、女性、男性 |
| `numeric` | 双精度浮点型 | 11.8% | 0.0 ~ 6777696.094（均值61462.2593） |
| `value` | 字符型 | 0.2% | 无 |
| `low` | 双精度浮点型 | 49.4% | 0.0 ~ 22696.2754（均值90.8079） |
| `high` | 双精度浮点型 | 49.4% | 0.0 ~ 34113.4102（均值190.3969） |
| `esa_source` | 字符型 | 0.0% | 无 |
| `esa_processed` | 字符型 | 0.0% | 无 |

---

## 数值型变量统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `year_display` | 1961.0 | 2030.0 | 2008.1354 | 2010.0 |
| `startyear` | 1961.0 | 2030.0 | 2008.1335 | 2010.0 |
| `endyear` | 1961.0 | 2030.0 | 2008.1354 | 2010.0 |
| `numeric` | 0.0 | 6777696.094 | 61462.2593 | 11.6049 |
| `low` | 0.0 | 22696.2754 | 90.8079 | 4.5678 |
| `high` | 0.0 | 34113.4102 | 190.3969 | 18.4 |

---

## 数据整理流程

原始数据通过综合知识存档网络应用程序编程接口（CKAN API）从HDX平台下载，并转换为Parquet格式。对列名进行了小写转换并统一为蛇形命名规范。将常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。移除了253条完全重复的样本行。基于解析成功率（阈值>85%），将6列从字符型转换为数值型或日期时间型。本数据集以80:20的比例划分为训练集与测试集，采用固定随机种子（42）进行划分，并以Snappy压缩的Parquet格式存储。

---

## 数据集局限性

- 本数据集的数据源自世界卫生组织，并未由Electric Sheep Africa进行独立验证。
- 自动化清洗流程无法修正原始数据集中的错报值、定义不一致问题或抽样偏差。
- 以下列的缺失率超过20%，在建模过程中需谨慎使用：`low`、`high`。
- 如需查看发布方的方法说明与免责声明，请参阅[HDX平台原始数据集页面](https://data.humdata.org/dataset/who-data-for-djibouti)。

---

## 引用格式

bibtex
@dataset{hdx_africa_disability_djibouti,
title = {吉布提——健康指标},
author = {世界卫生组织},
year = {2025},
url = {https://data.humdata.org/dataset/who-data-for-djibouti},
note = {由Electric Sheep Africa（https://huggingface.co/electricsheepafrica）重新打包为机器学习适配格式}
}

---

*[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。*