electricsheepafrica/africa-health-facilities-zambia

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- health-facilities
- hxl
- zmb
pretty_name: "Zambia Healthsites"
dataset_info:
splits:
- name: train
num_examples: 1186
- name: test
num_examples: 296
---

# Zambia Healthsites

**Publisher:** Global Healthsites Mapping Project · **Source:** [HDX](https://data.humdata.org/dataset/zambia-healthsites) · **License:** `ODbL` · **Updated:** 2025-04-10

---

## Abstract

This dataset shows the list of operating health facilities. Attributes included: Name,Nature of Facility, Activities, Lat, Long

Each row in this dataset represents tabular records. Data was last updated on HDX on 2025-04-10. Geographic scope: **ZMB**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 1,483 |
| **Columns** | 14 (6 numeric, 7 categorical, 0 datetime) |
| **Train split** | 1,186 rows |
| **Test split** | 296 rows |
| **Geographic scope** | ZMB |
| **Publisher** | Global Healthsites Mapping Project |
| **HDX last updated** | 2025-04-10 |

---

## Variables

**Geographic** — `x` (range 22.0751–33.5544), `y` (range -17.8541–-8.411), `osm_type` (node, way), `amenity` (clinic, hospital, pharmacy).

**Temporal** — `changeset_timestamp`.

**Identifier / Metadata** — `osm_id` (range -18245040.0–12620037249.0), `name` (Clinic, Health Post, Mazabuka Hospital), `changeset_id` (range 8103538.0–164571061.0), `uuid` (ac1e3007ea2649d4874ab2e85fcc8573, 6e62b9c43db64184b6e8717c660be5bb, 1afdc3dc50164053bd0b09777d5f08cb), `esa_source` (HDX) and 1 others.

**Other** — `completeness` (range 3.125–59.375), `operator` (Public, public, Missionary), `changeset_version` (range 1.0–10.0).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-health-facilities-zambia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `x` | float64 | 17.5% | 22.0751 – 33.5544 (mean 29.6654) |
| `y` | float64 | 17.5% | -17.8541 – -8.411 (mean -12.7874) |
| `osm_id` | int64 | 0.0% | -18245040.0 – 12620037249.0 (mean 8865326969.0479) |
| `osm_type` | object | 0.0% | node, way |
| `completeness` | float64 | 0.0% | 3.125 – 59.375 (mean 11.0186) |
| `amenity` | object | 0.4% | clinic, hospital, pharmacy |
| `name` | object | 4.2% | Clinic, Health Post, Mazabuka Hospital |
| `operator` | object | 79.5% | Public, public, Missionary |
| `changeset_id` | float64 | 1.2% | 8103538.0 – 164571061.0 (mean 141604569.3427) |
| `changeset_version` | float64 | 1.2% | 1.0 – 10.0 (mean 1.6949) |
| `changeset_timestamp` | datetime64[ns, UTC] | 1.2% | |
| `uuid` | object | 0.0% | ac1e3007ea2649d4874ab2e85fcc8573, 6e62b9c43db64184b6e8717c660be5bb, 1afdc3dc50164053bd0b09777d5f08cb |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-20 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `x` | 22.0751 | 33.5544 | 29.6654 | 29.637 |
| `y` | -17.8541 | -8.411 | -12.7874 | -12.8303 |
| `osm_id` | -18245040.0 | 12620037249.0 | 8865326969.0479 | 9969420348.0 |
| `completeness` | 3.125 | 59.375 | 11.0186 | 9.375 |
| `changeset_id` | 8103538.0 | 164571061.0 | 141604569.3427 | 155094760.0 |
| `changeset_version` | 1.0 | 10.0 | 1.6949 | 1.0 |

---

## 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`. 24 column(s) with >80% missing values were removed: `healthcare`, `source`, `speciality`, `operator_type`, `operational_status`, `opening_hours`.... 3 exact duplicate rows were removed. 1 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 Global Healthsites Mapping Project 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: `operator`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/zambia-healthsites) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_health_facilities_zambia,
title = {Zambia Healthsites},
author = {Global Healthsites Mapping Project},
year = {2025},
url = {https://data.humdata.org/dataset/zambia-healthsites},
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:
- 无标注
language_creators:
- 公开资源获取
language:
- 英语
license: 其他
multilinguality:
- 单语言
size_categories:
- 1000<n<10000
source_datasets:
- 原创数据集
task_categories:
- 表格分类
task_ids: []
tags:
- 非洲
- 人道主义
- HDX（人道主义数据交换平台，Humanitarian Data Exchange）
- Electric Sheep Africa（非洲电羊团队）
- 医疗设施
- HXL（人道主义交换语言，Humanitarian Exchange Language）
- ZMB（赞比亚ISO国家代码）
pretty_name: "赞比亚医疗设施数据集"
dataset_info:
splits:
- name: train
num_examples: 1186
- name: test
num_examples: 296

---

# 赞比亚医疗设施数据集

**发布方**：全球医疗设施测绘项目（Global Healthsites Mapping Project） · **来源**：[HDX](https://data.humdata.org/dataset/zambia-healthsites) · **许可证**：`ODbL（开放数据库许可证，Open Database License）` · **更新时间**：2025-04-10

---

## 摘要
本数据集收录了赞比亚境内运营中的医疗设施列表，包含的属性包括：设施名称、设施类型、开展业务、纬度、经度。
数据集中每一行均代表一条结构化表格记录。该数据最后一次在HDX平台更新的时间为2025-04-10。地理覆盖范围：**ZMB（赞比亚）**。
*本数据集已由[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

| | |
|---|---|
| **领域** | 公共卫生 |
| **观测单元** | 表格化记录 |
| **总行数** | 1483条 |
| **列数** | 14列（6个数值型、7个分类型、0个日期时间型） |
| **训练集划分** | 1186条 |
| **测试集划分** | 296条 |
| **地理覆盖范围** | ZMB（赞比亚） |
| **发布方** | 全球医疗设施测绘项目 |
| **HDX平台最后更新时间** | 2025-04-10 |

---

## 变量说明

**地理变量**：`x`（经度，取值范围22.0751~33.5544）、`y`（纬度，取值范围-17.8541~-8.411）、`osm_type`（开放街道地图类型，osm_type，可选值：节点、道路）、`amenity`（公共服务设施类型，amenity，可选值：诊所、医院、药房）。
**时间变量**：`changeset_timestamp`（变更集时间戳）。
**标识符/元数据变量**：`osm_id`（开放街道地图标识符，取值范围-18245040.0~12620037249.0）、`name`（设施名称，示例值：Clinic、Health Post、Mazabuka Hospital）、`changeset_id`（变更集标识符，取值范围8103538.0~164571061.0）、`uuid`（通用唯一识别码，示例值：ac1e3007ea2649d4874ab2e85fcc8573、6e62b9c43db64184b6e8717c660be5bb、1afdc3dc50164053bd0b09777d5f08cb）、`esa_source`（数据来源，值为HDX）及其他1个字段。
**其他变量**：`completeness`（数据完整度，取值范围3.125~59.375）、`operator`（运营方，可选值：公立、传教士运营）、`changeset_version`（变更集版本号，取值范围1.0~10.0）。

---

## 快速使用指南

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-health-facilities-zambia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据结构（Schema）

| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `x` | float64 | 17.5% | 22.0751 – 33.5544（均值29.6654） |
| `y` | float64 | 17.5% | -17.8541 – -8.411（均值-12.7874） |
| `osm_id` | int64 | 0.0% | -18245040.0 – 12620037249.0（均值8865326969.0479） |
| `osm_type` | 字符串型 | 0.0% | 节点、道路 |
| `completeness` | float64 | 0.0% | 3.125 – 59.375（均值11.0186） |
| `amenity` | 字符串型 | 0.4% | 诊所、医院、药房 |
| `name` | 字符串型 | 4.2% | 诊所、健康站、马扎布卡医院 |
| `operator` | 字符串型 | 79.5% | 公立、公立、传教士运营 |
| `changeset_id` | float64 | 1.2% | 8103538.0 – 164571061.0（均值141604569.3427） |
| `changeset_version` | float64 | 1.2% | 1.0 – 10.0（均值1.6949） |
| `changeset_timestamp` | datetime64[ns, UTC] | 1.2% | |
| `uuid` | 字符串型 | 0.0% | ac1e3007ea2649d4874ab2e85fcc8573、6e62b9c43db64184b6e8717c660be5bb、1afdc3dc50164053bd0b09777d5f08cb |
| `esa_source` | 字符串型 | 0.0% | HDX |
| `esa_processed` | 字符串型 | 0.0% | 2026-04-20 |

---

## 数值型变量统计汇总

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `x` | 22.0751 | 33.5544 | 29.6654 | 29.637 |
| `y` | -17.8541 | -8.411 | -12.7874 | -12.8303 |
| `osm_id` | -18245040.0 | 12620037249.0 | 8865326969.0479 | 9969420348.0 |
| `completeness` | 3.125 | 59.375 | 11.0186 | 9.375 |
| `changeset_id` | 8103538.0 | 164571061.0 | 141604569.3427 | 155094760.0 |
| `changeset_version` | 1.0 | 10.0 | 1.6949 | 1.0 |

---

## 数据整理流程

原始数据通过CKAN（综合知识存档网络，Comprehensive Knowledge Archive Network）API从HDX平台下载，并转换为Parquet格式。对列名进行了小写转换与蛇形命名法标准化。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。移除了24个缺失值占比超过80%的列，包括`healthcare`、`source`、`speciality`、`operator_type`、`operational_status`、`opening_hours`等。删除了3条完全重复的记录。基于解析成功率阈值（>85%），将1列从字符串类型转换为数值型或日期时间型。本数据集以固定随机种子（42）按照80/20的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

- 本数据源自全球医疗设施测绘项目，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阶段的错报值、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：`operator`。
- 请查阅[原始HDX数据集页面](https://data.humdata.org/dataset/zambia-healthsites)以获取发布方提供的方法说明与相关注意事项。

---

## 引用格式

bibtex
@dataset{hdx_africa_health_facilities_zambia,
title = {Zambia Healthsites},
author = {Global Healthsites Mapping Project},
year = {2025},
url = {https://data.humdata.org/dataset/zambia-healthsites},
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。*