electricsheepafrica/africa-demographics-tunisia

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- demographics
- health
- tun
pretty_name: "Tunisia - Subnational Demographic and Health Data"
dataset_info:
splits:
- name: train
num_examples: 33
- name: test
num_examples: 8
---

# Tunisia - Subnational Demographic and Health Data

**Publisher:** The DHS Program · **Source:** [HDX](https://data.humdata.org/dataset/dhs-subnational-data-for-tunisia) · **License:** `hdx-other` · **Updated:** 2026-04-20

---

## Abstract

Contains data from the [DHS data portal](https://api.dhsprogram.com/). There is also a dataset containing [Tunisia - National Demographic and Health Data](https://data.humdata.org/dataset/dhs-data-for-tunisia) on HDX.

The DHS Program Application Programming Interface (API) provides software developers access to aggregated indicator data from The Demographic and Health Surveys (DHS) Program. The API can be used to create various applications to help analyze, visualize, explore and disseminate data on population, health, HIV, and nutrition from more than 90 countries.

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2026-04-20. Geographic scope: **TUN**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 42 |
| **Columns** | 32 (16 numeric, 16 categorical, 0 datetime) |
| **Train split** | 33 rows |
| **Test split** | 8 rows |
| **Geographic scope** | TUN |
| **Publisher** | The DHS Program |
| **HDX last updated** | 2026-04-20 |

---

## Variables

**Geographic** — `iso3` (TUN), `location` (Tunis, Nord Est, Nord Ouest), `dhs_countrycode` (TN), `countryname` (Tunisia), `surveyyear` (range 1988.0–1988.0) and 8 others.

**Outcome / Measurement** — `value` (range 0.5–107.0), `istotal` (range 0.0–0.0).

**Identifier / Metadata** — `dataid` (range 999142.0–7970284.0), `indicatorid` (FE_FRTR_W_TFR, FP_CUSM_W_ANY, FP_CUSM_W_MOD), `characteristicid` (range 449001.0–449006.0), `characteristiclabel` (Tunis, Nord Est, Nord Ouest), `ispreferred` (range 1.0–1.0) and 3 others.

**Other** — `indicator` (Total fertility rate 15-49, Married women currently using any method of contraception, Married women currently using any modern method of contraception), `precision` (range 0.0–1.0), `indicatororder` (range 11763080.0–104336020.0), `characteristicorder` (range 1449001.0–1449006.0), `denominatorweighted` (range 587.0–748.0) and 4 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-demographics-tunisia")
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% | TUN |
| `location` | object | 0.0% | Tunis, Nord Est, Nord Ouest |
| `dataid` | int64 | 0.0% | 999142.0 – 7970284.0 (mean 3462838.0) |
| `indicator` | object | 0.0% | Total fertility rate 15-49, Married women currently using any method of contraception, Married women currently using any modern method of contraception |
| `value` | float64 | 0.0% | 0.5 – 107.0 (mean 34.7571) |
| `precision` | int64 | 0.0% | 0.0 – 1.0 (mean 0.7143) |
| `dhs_countrycode` | object | 0.0% | TN |
| `countryname` | object | 0.0% | Tunisia |
| `surveyyear` | int64 | 0.0% | 1988.0 – 1988.0 (mean 1988.0) |
| `surveyid` | object | 0.0% | TN1988DHS |
| `indicatorid` | object | 0.0% | FE_FRTR_W_TFR, FP_CUSM_W_ANY, FP_CUSM_W_MOD |
| `indicatororder` | int64 | 0.0% | 11763080.0 – 104336020.0 (mean 49915757.1429) |
| `indicatortype` | object | 0.0% | I |
| `characteristicid` | int64 | 0.0% | 449001.0 – 449006.0 (mean 449003.5) |
| `characteristicorder` | int64 | 0.0% | 1449001.0 – 1449006.0 (mean 1449003.5) |
| `characteristiccategory` | object | 0.0% | Region |
| `characteristiclabel` | object | 0.0% | Tunis, Nord Est, Nord Ouest |
| `byvariableid` | int64 | 0.0% | 0.0 – 14003.0 (mean 4000.8571) |
| `byvariablelabel` | object | 71.4% | |
| `istotal` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `ispreferred` | int64 | 0.0% | 1.0 – 1.0 (mean 1.0) |
| `sdrid` | object | 0.0% | |
| `regionid` | object | 0.0% | |
| `surveyyearlabel` | int64 | 0.0% | 1988.0 – 1988.0 (mean 1988.0) |
| `surveytype` | object | 0.0% | |
| `denominatorweighted` | float64 | 71.4% | 587.0 – 748.0 (mean 668.6667) |
| `denominatorunweighted` | float64 | 71.4% | 587.0 – 748.0 (mean 668.6667) |
| `cilow` | float64 | 71.4% | 23.0 – 89.0 (mean 47.6667) |
| `cihigh` | float64 | 71.4% | 52.0 – 124.0 (mean 80.5833) |
| `levelrank` | int64 | 0.0% | 1.0 – 1.0 (mean 1.0) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `dataid` | 999142.0 | 7970284.0 | 3462838.0 | 1776224.0 |
| `value` | 0.5 | 107.0 | 34.7571 | 35.3 |
| `precision` | 0.0 | 1.0 | 0.7143 | 1.0 |
| `surveyyear` | 1988.0 | 1988.0 | 1988.0 | 1988.0 |
| `indicatororder` | 11763080.0 | 104336020.0 | 49915757.1429 | 41633090.0 |
| `characteristicid` | 449001.0 | 449006.0 | 449003.5 | 449003.5 |
| `characteristicorder` | 1449001.0 | 1449006.0 | 1449003.5 | 1449003.5 |
| `byvariableid` | 0.0 | 14003.0 | 4000.8571 | 0.0 |
| `istotal` | 0.0 | 0.0 | 0.0 | 0.0 |
| `ispreferred` | 1.0 | 1.0 | 1.0 | 1.0 |
| `surveyyearlabel` | 1988.0 | 1988.0 | 1988.0 | 1988.0 |
| `denominatorweighted` | 587.0 | 748.0 | 668.6667 | 661.5 |
| `denominatorunweighted` | 587.0 | 748.0 | 668.6667 | 661.5 |
| `cilow` | 23.0 | 89.0 | 47.6667 | 46.5 |
| `cihigh` | 52.0 | 124.0 | 80.5833 | 77.5 |

---

## 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`. 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 The DHS Program 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: `byvariablelabel`, `denominatorweighted`, `denominatorunweighted`, `cilow`, `cihigh`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/dhs-subnational-data-for-tunisia) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_demographics_tunisia,
title = {Tunisia - Subnational Demographic and Health Data},
author = {The DHS Program},
year = {2026},
url = {https://data.humdata.org/dataset/dhs-subnational-data-for-tunisia},
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:
- 现有公开资源抓取（found）
language:
- 英语（en）
license: 其他
multilinguality:
- 单语言
size_categories:
- 样本量小于1000
source_datasets:
- 原生数据集
task_categories:
- 表格分类
- 其他
task_ids: []
tags:
- 非洲
- 人道主义
- HDX（Humanitarian Data Exchange）
- Electric Sheep Africa
- 人口统计
- 健康
- 突尼斯（TUN）
pretty_name: "突尼斯——次国家级人口与健康数据"
dataset_info:
splits:
- name: 训练集
num_examples: 33
- name: 测试集
num_examples: 8
---

# 突尼斯——次国家级人口与健康数据

**发布方**：人口与健康调查项目（DHS Program） · **来源**：[HDX（Humanitarian Data Exchange）](https://data.humdata.org/dataset/dhs-subnational-data-for-tunisia) · **许可证**：`hdx-other` · **最后更新**：2026-04-20

---

## 摘要

本数据集数据源自[DHS数据门户（DHS Data Portal）](https://api.dhsprogram.com/)。HDX平台上另有一份包含[突尼斯——国家级人口与健康数据](https://data.humdata.org/dataset/dhs-data-for-tunisia)的数据集。

人口与健康调查项目（DHS Program）应用程序编程接口（API）可为软件开发人员提供来自该项目的聚合指标数据访问权限。该API可用于构建各类应用程序，以辅助分析、可视化、探索并传播全球90余个国家的人口、健康、艾滋病病毒（HIV）及营养相关数据。

本数据集的每一行均代表一级行政单元的观测数据。数据集最后更新于HDX平台的时间为2026-04-20，地理覆盖范围：**突尼斯（TUN）**。

*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

| | |
|---|---|
| **领域** | 公共卫生 |
| **观测单元** | 一级行政单元 |
| **总行数** | 42 |
| **列数** | 32列（16个数值型、16个分类型、0个日期时间型） |
| **训练集样本量** | 33条 |
| **测试集样本量** | 8条 |
| **地理覆盖范围** | 突尼斯（TUN） |
| **发布方** | 人口与健康调查项目（DHS Program） |
| **HDX平台最后更新时间** | 2026-04-20 |

---

## 变量分类

### 地理类变量
`iso3`（突尼斯，TUN）、`location`（突尼斯市、东北部、西北部）、`dhs_countrycode`（TN）、`countryname`（突尼斯）、`surveyyear`（取值范围1988.0–1988.0）及另外8个变量。

### 结果/测量类变量
`value`（取值范围0.5–107.0）、`istotal`（取值范围0.0–0.0）。

### 标识符/元数据类变量
`dataid`（取值范围999142.0–7970284.0）、`indicatorid`（FE_FRTR_W_TFR、FP_CUSM_W_ANY、FP_CUSM_W_MOD）、`characteristicid`（取值范围449001.0–449006.0）、`characteristiclabel`（突尼斯市、东北部、西北部）、`ispreferred`（取值范围1.0–1.0）及另外3个变量。

### 其他类变量
`indicator`（15-49岁总生育率、当前使用任何避孕方法的已婚女性占比、当前使用任何现代避孕方法的已婚女性占比）、`precision`（取值范围0.0–1.0）、`indicatororder`（取值范围11763080.0–104336020.0）、`characteristicorder`（取值范围1449001.0–1449006.0）、`denominatorweighted`（取值范围587.0–748.0）及另外4个变量。

---

## 快速上手示例

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-demographics-tunisia")
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 |
|---|---|---|---|
| `iso3` | 字符串型（object） | 0.0% | TUN |
| `location` | 字符串型（object） | 0.0% | 突尼斯市、东北部、西北部 |
| `dataid` | 64位整数型（int64） | 0.0% | 999142.0 – 7970284.0（均值3462838.0） |
| `indicator` | 字符串型（object） | 0.0% | 15-49岁总生育率、当前使用任何避孕方法的已婚女性占比、当前使用任何现代避孕方法的已婚女性占比 |
| `value` | 64位浮点型（float64） | 0.0% | 0.5 – 107.0（均值34.7571） |
| `precision` | 64位整数型（int64） | 0.0% | 0.0 – 1.0（均值0.7143） |
| `dhs_countrycode` | 字符串型（object） | 0.0% | TN |
| `countryname` | 字符串型（object） | 0.0% | 突尼斯 |
| `surveyyear` | 64位整数型（int64） | 0.0% | 1988.0 – 1988.0（均值1988.0） |
| `surveyid` | 字符串型（object） | 0.0% | TN1988DHS |
| `indicatorid` | 字符串型（object） | 0.0% | FE_FRTR_W_TFR、FP_CUSM_W_ANY、FP_CUSM_W_MOD |
| `indicatororder` | 64位整数型（int64） | 0.0% | 11763080.0 – 104336020.0（均值49915757.1429） |
| `indicatortype` | 字符串型（object） | 0.0% | I |
| `characteristicid` | 64位整数型（int64） | 0.0% | 449001.0 – 449006.0（均值449003.5） |
| `characteristicorder` | 64位整数型（int64） | 0.0% | 1449001.0 – 1449006.0（均值1449003.5） |
| `characteristiccategory` | 字符串型（object） | 0.0% | 区域 |
| `characteristiclabel` | 字符串型（object） | 0.0% | 突尼斯市、东北部、西北部 |
| `byvariableid` | 64位整数型（int64） | 0.0% | 0.0 – 14003.0（均值4000.8571） |
| `byvariablelabel` | 字符串型（object） | 71.4% | 无 |
| `istotal` | 64位整数型（int64） | 0.0% | 0.0 – 0.0（均值0.0） |
| `ispreferred` | 64位整数型（int64） | 0.0% | 1.0 – 1.0（均值1.0） |
| `sdrid` | 字符串型（object） | 0.0% | 无 |
| `regionid` | 字符串型（object） | 0.0% | 无 |
| `surveyyearlabel` | 64位整数型（int64） | 0.0% | 1988.0 – 1988.0（均值1988.0） |
| `surveytype` | 字符串型（object） | 0.0% | 无 |
| `denominatorweighted` | 64位浮点型（float64） | 71.4% | 587.0 – 748.0（均值668.6667） |
| `denominatorunweighted` | 64位浮点型（float64） | 71.4% | 587.0 – 748.0（均值668.6667） |
| `cilow` | 64位浮点型（float64） | 71.4% | 23.0 – 89.0（均值47.6667） |
| `cihigh` | 64位浮点型（float64） | 71.4% | 52.0 – 124.0（均值80.5833） |
| `levelrank` | 64位整数型（int64） | 0.0% | 1.0 – 1.0（均值1.0） |
| `esa_source` | 字符串型（object） | 0.0% | 无 |
| `esa_processed` | 字符串型（object） | 0.0% | 无 |

---

## 数值统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `dataid` | 999142.0 | 7970284.0 | 3462838.0 | 1776224.0 |
| `value` | 0.5 | 107.0 | 34.7571 | 35.3 |
| `precision` | 0.0 | 1.0 | 0.7143 | 1.0 |
| `surveyyear` | 1988.0 | 1988.0 | 1988.0 | 1988.0 |
| `indicatororder` | 11763080.0 | 104336020.0 | 49915757.1429 | 41633090.0 |
| `characteristicid` | 449001.0 | 449006.0 | 449003.5 | 449003.5 |
| `characteristicorder` | 1449001.0 | 1449006.0 | 1449003.5 | 1449003.5 |
| `byvariableid` | 0.0 | 14003.0 | 4000.8571 | 0.0 |
| `istotal` | 0.0 | 0.0 | 0.0 | 0.0 |
| `ispreferred` | 1.0 | 1.0 | 1.0 | 1.0 |
| `surveyyearlabel` | 1988.0 | 1988.0 | 1988.0 | 1988.0 |
| `denominatorweighted` | 587.0 | 748.0 | 668.6667 | 661.5 |
| `denominatorunweighted` | 587.0 | 748.0 | 668.6667 | 661.5 |
| `cilow` | 23.0 | 89.0 | 47.6667 | 46.5 |
| `cihigh` | 52.0 | 124.0 | 80.5833 | 77.5 |

---

## 数据整理流程

原始数据通过CKAN应用程序编程接口（API）从HDX平台下载并转换为Parquet格式。列名被统一转换为小写并标准化为蛇形命名法（snake_case）。常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。本数据集以80/20的比例划分为训练集与测试集，使用固定随机种子（42）进行划分，并以Snappy压缩的Parquet格式存储。

---

## 数据集局限性

1. 本数据集源自人口与健康调查项目（DHS Program），Electric Sheep Africa（ESA）未对其进行独立验证。
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. 以下列的缺失值占比超过20%，在建模时需谨慎使用：`byvariablelabel`、`denominatorweighted`、`denominatorunweighted`、`cilow`、`cihigh`。
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/dhs-subnational-data-for-tunisia)。

---

## 引用格式

bibtex
@dataset{hdx_africa_demographics_tunisia,
title = {Tunisia - Subnational Demographic and Health Data},
author = {The DHS Program},
year = {2026},
url = {https://data.humdata.org/dataset/dhs-subnational-data-for-tunisia},
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提供商，尼日利亚拉各斯。*