electricsheepafrica/africa-chad-list-of-health-facilities-and-health-districts

---
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
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- facilities-infrastructure
- geodata
- health
- health-facilities
- tcd
pretty_name: "Chad - List of health facilities and health districts"
dataset_info:
splits:
- name: train
num_examples: 1588
- name: test
num_examples: 397
---

# Chad - List of health facilities and health districts

**Publisher:** OCHA Chad · **Source:** [HDX](https://data.humdata.org/dataset/chad-list-of-health-facilities-and-health-districts) · **License:** `cc-by` · **Updated:** 2025-05-05

---

## Abstract

Liste of health facilities (Hospitals, health center...) from the ministry of health

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2025-05-05. Geographic scope: **TCD**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 1,985 |
| **Columns** | 13 (3 numeric, 10 categorical, 0 datetime) |
| **Train split** | 1,588 rows |
| **Test split** | 397 rows |
| **Geographic scope** | TCD |
| **Publisher** | OCHA Chad |
| **HDX last updated** | 2025-05-05 |

---

## Variables

**Geographic** — `types` (Centre de santé, Hôpital de district, Hôpital Provincial), `longitude` (range 13.612–23.3455), `latitude` (range 7.527–21.8119), `nomdistrict` (Mao, Mondo, Moussoro), `pcodedistrict` (TDDS20190601, TDDS20190602, TDDS20191903) and 2 others.

**Identifier / Metadata** — `code_cs_msp` (range 0.0–80007.0), `esa_source` (HDX), `esa_processed` (2026-04-16).

**Other** — `nom` (Bedogo, Koutou, Tagal), `affiliation` (Publique, Confessionnelle EEMET, Confessionnelle CATH), `fonctionnalite` (Fonctionnelle, Non Fonctionnelle, Planifiée).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-chad-list-of-health-facilities-and-health-districts")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `code_cs_msp` | int64 | 0.0% | 0.0 – 80007.0 (mean 47371.2302) |
| `nom` | object | 0.0% | Bedogo, Koutou, Tagal |
| `types` | object | 0.0% | Centre de santé, Hôpital de district, Hôpital Provincial |
| `affiliation` | object | 0.0% | Publique, Confessionnelle EEMET, Confessionnelle CATH |
| `fonctionnalite` | object | 0.0% | Fonctionnelle, Non Fonctionnelle, Planifiée |
| `longitude` | float64 | 0.0% | 13.612 – 23.3455 (mean 17.2005) |
| `latitude` | float64 | 0.0% | 7.527 – 21.8119 (mean 11.6909) |
| `nomdistrict` | object | 0.0% | Mao, Mondo, Moussoro |
| `pcodedistrict` | object | 0.0% | TDDS20190601, TDDS20190602, TDDS20191903 |
| `nomprovince` | object | 0.0% | Kanem, Logone Oriental, Mayo Kebbi Est |
| `pcodeprovincesanitaire` | object | 0.0% | TDDSR201906, TDDSR201909, TDDSR201911 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-16 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `code_cs_msp` | 0.0 | 80007.0 | 47371.2302 | 50845.0 |
| `longitude` | 13.612 | 23.3455 | 17.2005 | 16.4236 |
| `latitude` | 7.527 | 21.8119 | 11.6909 | 12.0488 |

---

## 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 OCHA Chad and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/chad-list-of-health-facilities-and-health-districts) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_chad_list_of_health_facilities_and_health_districts,
title = {Chad - List of health facilities and health districts},
author = {OCHA Chad},
year = {2025},
url = {https://data.humdata.org/dataset/chad-list-of-health-facilities-and-health-districts},
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:
- 现有公开数据源
language:
- en
license: cc-by-4.0
multilinguality:
- 单语言
size_categories:
- 1K<n<10K
source_datasets:
- 原创数据集
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- facilities-infrastructure
- geodata
- health
- health-facilities
- tcd
pretty_name: "乍得——医疗设施与医疗行政区列表"
dataset_info:
splits:
- name: train
num_examples: 1588
- name: test
num_examples: 397

# 乍得——医疗设施与医疗行政区列表

**发布方：乍得联合国人道主义事务协调办公室（OCHA Chad） · 来源：[HDX（人道主义数据交换）](https://data.humdata.org/dataset/chad-list-of-health-facilities-and-health-districts) · 许可协议：`cc-by` · 更新时间：2025-05-05**

---

## 摘要
本数据集收录乍得卫生部下属的医疗设施（医院、医疗中心等）列表。数据集的每一行代表一个次国家级行政单元的观测记录。本数据集最后于HDX平台更新于2025年5月5日，地理覆盖范围为**TCD（乍得）**。
*本数据集经[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
| | |
|---|---|
| **领域** | 公共卫生 |
| **观测单元** | 次国家级行政单元观测记录 |
| **总样本行数** | 1,985 |
| **列数** | 13（3个数值型列，10个分类型列，0个日期时间型列） |
| **训练集划分** | 1,588行 |
| **测试集划分** | 397行 |
| **地理覆盖范围** | TCD（乍得） |
| **发布方** | 乍得联合国人道主义事务协调办公室（OCHA Chad） |
| **HDX平台最后更新时间** | 2025-05-05 |

---

## 变量说明
### 地理相关变量
`types`（医疗中心、地区医院、省级医院）、`longitude`（取值范围13.612–23.3455）、`latitude`（取值范围7.527–21.8119）、`nomdistrict`（马奥、蒙多、穆索罗）、`pcodedistrict`（TDDS20190601、TDDS20190602、TDDS20191903）及另外2个变量。
### 标识符与元数据变量
`code_cs_msp`（取值范围0.0–80007.0）、`esa_source`（HDX）、`esa_processed`（2026-04-16）。
### 其他变量
`nom`（贝多戈、库图、塔加尔）、`affiliation`（公立、EEMET教派、天主教教派）、`fonctionnalite`（可用、不可用、规划中）。

---

## 快速入门
python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-chad-list-of-health-facilities-and-health-districts")
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 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `code_cs_msp` | int64 | 0.0% | 0.0 – 80007.0（均值47371.2302） |
| `nom` | object | 0.0% | Bedogo, Koutou, Tagal |
| `types` | object | 0.0% | 医疗中心、地区医院、省级医院 |
| `affiliation` | object | 0.0% | 公立、EEMET教派、天主教教派 |
| `fonctionnalite` | object | 0.0% | 可用、不可用、规划中 |
| `longitude` | float64 | 0.0% | 13.612 – 23.3455（均值17.2005） |
| `latitude` | float64 | 0.0% | 7.527 – 21.8119（均值11.6909） |
| `nomdistrict` | object | 0.0% | 马奥、蒙多、穆索罗 |
| `pcodedistrict` | object | 0.0% | TDDS20190601、TDDS20190602、TDDS20191903 |
| `nomprovince` | object | 0.0% | 卡涅姆、洛贡东方、马约凯比东部 |
| `pcodeprovincesanitaire` | object | 0.0% | TDDSR201906、TDDSR201909、TDDSR201911 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-16 |

---

## 数值型变量统计
| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `code_cs_msp` | 0.0 | 80007.0 | 47371.2302 | 50845.0 |
| `longitude` | 13.612 | 23.3455 | 17.2005 | 16.4236 |
| `latitude` | 7.527 | 21.8119 | 11.6909 | 12.0488 |

---

## 数据整理流程
原始数据通过CKAN API从HDX平台下载，并转换为Parquet格式。列名统一转换为小写并标准化为蛇形命名法。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。本数据集使用固定随机种子（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。

---

## 使用限制
- 本数据集数据源自乍得联合国人道主义事务协调办公室，未经Electric Sheep Africa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。
- 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/chad-list-of-health-facilities-and-health-districts)查看发布方提供的方法说明与免责条款。

---

## 引用格式
bibtex
@dataset{hdx_africa_chad_list_of_health_facilities_and_health_districts,
title = {Chad - List of health facilities and health districts},
author = {OCHA Chad},
year = {2025},
url = {https://data.humdata.org/dataset/chad-list-of-health-facilities-and-health-districts},
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服务商，总部位于尼日利亚拉各斯。*