electricsheepafrica/africa-demographics-ghana
收藏资源简介：
--- 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 - other task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - demographics - health - gha pretty_name: "Ghana - Subnational Demographic and Health Data" dataset_info: splits: - name: train num_examples: 1623 - name: test num_examples: 405 --- # Ghana - Subnational Demographic and Health Data **Publisher:** The DHS Program · **Source:** [HDX](https://data.humdata.org/dataset/dhs-subnational-data-for-ghana) · **License:** `hdx-other` · **Updated:** 2026-02-24 --- ## Abstract Contains data from the [DHS data portal](https://api.dhsprogram.com/). There is also a dataset containing [Ghana - National Demographic and Health Data](https://data.humdata.org/dataset/dhs-data-for-ghana) 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 2026-02-24. Geographic scope: **GHA**. *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)** | 2,029 | | **Columns** | 30 (14 numeric, 16 categorical, 0 datetime) | | **Train split** | 1,623 rows | | **Test split** | 405 rows | | **Geographic scope** | GHA | | **Publisher** | The DHS Program | | **HDX last updated** | 2026-02-24 | --- ## Variables **Geographic** — `iso3` (GHA), `location` (Western (pre 2022), Ashanti, Brong-Ahafo), `dhs_countrycode` (GH), `countryname` (Ghana), `surveyyear` (range 1988.0–2022.0) and 8 others. **Outcome / Measurement** — `value` (range 0.2–237.0), `istotal` (range 0.0–0.0). **Identifier / Metadata** — `dataid` (range 102859.0–7980959.0), `indicatorid` (RH_DELP_C_DHF, CH_DIAT_C_ORT, FE_FRTR_W_TFR), `characteristicid` (range 408001.0–408021.0), `characteristiclabel` (Western (pre 2022), Ashanti, Brong-Ahafo), `ispreferred` (range 0.0–1.0) and 3 others. **Other** — `indicator` (Place of delivery: Health facility, Treatment of diarrhea: Either ORS or RHF, Total fertility rate 15-49), `precision` (range 0.0–1.0), `indicatororder` (range 11763080.0–260321010.0), `characteristicorder` (range 1408010.0–1408110.0), `denominatorweighted` (range 12.0–3469.0) and 2 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-demographics-ghana") 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% | GHA | | `location` | object | 0.0% | Western (pre 2022), Ashanti, Brong-Ahafo | | `dataid` | int64 | 0.0% | 102859.0 – 7980959.0 (mean 4062075.5702) | | `indicator` | object | 0.0% | Place of delivery: Health facility, Treatment of diarrhea: Either ORS or RHF, Total fertility rate 15-49 | | `value` | float64 | 0.0% | 0.2 – 237.0 (mean 34.7802) | | `precision` | int64 | 0.0% | 0.0 – 1.0 (mean 0.9177) | | `dhs_countrycode` | object | 0.0% | GH | | `countryname` | object | 0.0% | Ghana | | `surveyyear` | int64 | 0.0% | 1988.0 – 2022.0 (mean 2009.1646) | | `surveyid` | object | 0.0% | GH2022DHS, GH2014DHS, GH2003DHS | | `indicatorid` | object | 0.0% | RH_DELP_C_DHF, CH_DIAT_C_ORT, FE_FRTR_W_TFR | | `indicatororder` | int64 | 0.0% | 11763080.0 – 260321010.0 (mean 101996419.5909) | | `indicatortype` | object | 0.0% | I | | `characteristicid` | int64 | 0.0% | 408001.0 – 408021.0 (mean 408007.2942) | | `characteristicorder` | int64 | 0.0% | 1408010.0 – 1408110.0 (mean 1408059.7733) | | `characteristiccategory` | object | 0.0% | Region | | `characteristiclabel` | object | 0.0% | Western (pre 2022), Ashanti, Brong-Ahafo | | `byvariableid` | int64 | 0.0% | 0.0 – 631002.0 (mean 19898.3903) | | `byvariablelabel` | object | 73.0% | | | `istotal` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) | | `ispreferred` | int64 | 0.0% | 0.0 – 1.0 (mean 0.8911) | | `sdrid` | object | 0.0% | | | `regionid` | object | 0.0% | | | `surveyyearlabel` | int64 | 0.0% | 1988.0 – 2022.0 (mean 2009.1646) | | `surveytype` | object | 0.0% | | | `denominatorweighted` | float64 | 25.5% | 12.0 – 3469.0 (mean 432.4405) | | `denominatorunweighted` | float64 | 25.5% | 25.0 – 5349.0 (mean 507.6548) | | `levelrank` | float64 | 12.8% | 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` | 102859.0 | 7980959.0 | 4062075.5702 | 4157785.0 | | `value` | 0.2 | 237.0 | 34.7802 | 26.6 | | `precision` | 0.0 | 1.0 | 0.9177 | 1.0 | | `surveyyear` | 1988.0 | 2022.0 | 2009.1646 | 2008.0 | | `indicatororder` | 11763080.0 | 260321010.0 | 101996419.5909 | 93906230.0 | | `characteristicid` | 408001.0 | 408021.0 | 408007.2942 | 408007.0 | | `characteristicorder` | 1408010.0 | 1408110.0 | 1408059.7733 | 1408060.0 | | `byvariableid` | 0.0 | 631002.0 | 19898.3903 | 0.0 | | `istotal` | 0.0 | 0.0 | 0.0 | 0.0 | | `ispreferred` | 0.0 | 1.0 | 0.8911 | 1.0 | | `surveyyearlabel` | 1988.0 | 2022.0 | 2009.1646 | 2008.0 | | `denominatorweighted` | 12.0 | 3469.0 | 432.4405 | 317.0 | | `denominatorunweighted` | 25.0 | 5349.0 | 507.6548 | 361.5 | | `levelrank` | 1.0 | 1.0 | 1.0 | 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`. 2 column(s) with >80% missing values were removed: `cilow`, `cihigh`. 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`. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/dhs-subnational-data-for-ghana) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_demographics_ghana, title = {Ghana - Subnational Demographic and Health Data}, author = {The DHS Program}, year = {2026}, url = {https://data.humdata.org/dataset/dhs-subnational-data-for-ghana}, 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: - 采集获取 language: - 英语 license: - 其他 multilinguality: - 单语言 size_categories: - 1000 < 样本数 < 10000 source_datasets: - 原创数据集 task_categories: - 表格分类 - 其他 task_ids: [] tags: - 非洲 - 人道主义 - HDX - Electric Sheep Africa - 人口统计 - 健康 - GHA pretty_name: "加纳 - 次国家人口与健康数据" dataset_info: splits: - name: train num_examples: 1623 - name: test num_examples: 405 # 加纳 - 次国家人口与健康数据 **发布方**：人口与健康调查项目（Demographic and Health Surveys，简称DHS） · **来源**：[人道主义数据交换平台（Humanitarian Data Exchange，简称HDX）](https://data.humdata.org/dataset/dhs-subnational-data-for-ghana) · **许可协议**：`hdx-other` · **最后更新时间**：2026-02-24 --- ## 摘要 本数据集的数据源自[DHS数据门户（DHS Data Portal）](https://api.dhsprogram.com/)。人道主义数据交换平台（HDX）上还发布有另一项名为[加纳 - 国家人口与健康数据](https://data.humdata.org/dataset/dhs-data-for-ghana)的数据集。 人口与健康调查项目（DHS）的应用程序编程接口（API）可为软件开发人员提供来自DHS项目的聚合指标数据。借助该API，开发者可构建各类应用，用于分析、可视化、探索并传播全球90余个国家的人口、健康、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。本数据集最后于2026-02-24在HDX平台完成更新。地理覆盖范围：**GHA（加纳）**。 *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 | 特征项 | 详情 | |---|---| | **领域** | 公共卫生 | | **观测单元** | 一级行政单元观测数据 | | **总样本行数** | 2029 | | **列数** | 30列（14个数值型、16个分类型、0个日期时间型） | | **训练集样本数** | 1623行 | | **测试集样本数** | 405行 | | **地理覆盖范围** | GHA（加纳） | | **发布方** | 人口与健康调查项目（DHS） | | **HDX平台最后更新时间** | 2026-02-24 | --- ## 变量说明 ### 地理类变量 `iso3`（国家代码，值为GHA）、`location`（地区，例如2022年前的西部区、阿散蒂区、布朗阿哈福区）、`dhs_countrycode`（DHS国家代码，值为GH）、`countryname`（国家名称，值为加纳）、`surveyyear`（调查年份，范围1988.0–2022.0）及另外8个变量。 ### 结果/测量类变量 `value`（指标数值，范围0.2–237.0）、`istotal`（是否总计标识，范围0.0–0.0）。 ### 标识符/元数据类变量 `dataid`（数据ID，范围102859.0–7980959.0）、`indicatorid`（指标ID，例如RH_DELP_C_DHF、CH_DIAT_C_ORT、FE_FRTR_W_TFR）、`characteristicid`（特征ID，范围408001.0–408021.0）、`characteristiclabel`（特征标签，例如2022年前的西部区、阿散蒂区、布朗阿哈福区）、`ispreferred`（是否首选标识，范围0.0–1.0）及另外3个变量。 ### 其他变量 `indicator`（指标名称，例如“分娩地点：卫生机构”、“腹泻治疗：口服补液盐（ORS）或重组人乳铁蛋白（RHF）”、“15-49岁女性总生育率”）、`precision`（精度值，范围0.0–1.0）、`indicatororder`（指标排序号，范围11763080.0–260321010.0）、`characteristicorder`（特征排序号，范围1408010.0–1408110.0）、`denominatorweighted`（加权分母，范围12.0–3469.0）及另外2个变量。 --- ## 快速入门 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-demographics-ghana") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据Schema | 列名 | 数据类型 | 空值占比 | 取值范围/示例值 | |---|---|---|---| | `iso3` | 对象型 | 0.0% | GHA | | `location` | 对象型 | 0.0% | 2022年前的西部区、阿散蒂区、布朗阿哈福区 | | `dataid` | 64位整数型 | 0.0% | 102859.0 – 7980959.0（均值 4062075.5702） | | `indicator` | 对象型 | 0.0% | 分娩地点：卫生机构、腹泻治疗：口服补液盐（ORS）或重组人乳铁蛋白（RHF）、15-49岁女性总生育率 | | `value` | 64位浮点型 | 0.0% | 0.2 – 237.0（均值 34.7802） | | `precision` | 64位整数型 | 0.0% | 0.0 – 1.0（均值 0.9177） | | `dhs_countrycode` | 对象型 | 0.0% | GH | | `countryname` | 对象型 | 0.0% | 加纳 | | `surveyyear` | 64位整数型 | 0.0% | 1988.0 – 2022.0（均值 2009.1646） | | `surveyid` | 对象型 | 0.0% | GH2022DHS、GH2014DHS、GH2003DHS | | `indicatorid` | 对象型 | 0.0% | RH_DELP_C_DHF、CH_DIAT_C_ORT、FE_FRTR_W_TFR | | `indicatororder` | 64位整数型 | 0.0% | 11763080.0 – 260321010.0（均值 101996419.5909） | | `indicatortype` | 对象型 | 0.0% | I | | `characteristicid` | 64位整数型 | 0.0% | 408001.0 – 408021.0（均值 408007.2942） | | `characteristicorder` | 64位整数型 | 0.0% | 1408010.0 – 1408110.0（均值 1408059.7733） | | `characteristiccategory` | 对象型 | 0.0% | 地区 | | `characteristiclabel` | 对象型 | 0.0% | 2022年前的西部区、阿散蒂区、布朗阿哈福区 | | `byvariableid` | 64位整数型 | 0.0% | 0.0 – 631002.0（均值 19898.3903） | | `byvariablelabel` | 对象型 | 73.0% | 无有效内容 | | `istotal` | 64位整数型 | 0.0% | 0.0 – 0.0（均值 0.0） | | `ispreferred` | 64位整数型 | 0.0% | 0.0 – 1.0（均值 0.8911） | | `sdrid` | 对象型 | 0.0% | 无有效内容 | | `regionid` | 对象型 | 0.0% | 无有效内容 | | `surveyyearlabel` | 64位整数型 | 0.0% | 1988.0 – 2022.0（均值 2009.1646） | | `surveytype` | 对象型 | 0.0% | 无有效内容 | | `denominatorweighted` | 64位浮点型 | 25.5% | 12.0 – 3469.0（均值 432.4405） | | `denominatorunweighted` | 64位浮点型 | 25.5% | 25.0 – 5349.0（均值 507.6548） | | `levelrank` | 64位浮点型 | 12.8% | 1.0 – 1.0（均值 1.0） | | `esa_source` | 对象型 | 0.0% | 无有效内容 | | `esa_processed` | 对象型 | 0.0% | 无有效内容 | --- ## 数值型变量统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `dataid` | 102859.0 | 7980959.0 | 4062075.5702 | 4157785.0 | | `value` | 0.2 | 237.0 | 34.7802 | 26.6 | | `precision` | 0.0 | 1.0 | 0.9177 | 1.0 | | `surveyyear` | 1988.0 | 2022.0 | 2009.1646 | 2008.0 | | `indicatororder` | 11763080.0 – 260321010.0 | 101996419.5909 | 93906230.0 | | `characteristicid` | 408001.0 | 408021.0 | 408007.2942 | 408007.0 | | `characteristicorder` | 1408010.0 | 1408110.0 | 1408059.7733 | 1408060.0 | | `byvariableid` | 0.0 | 631002.0 | 19898.3903 | 0.0 | | `istotal` | 0.0 | 0.0 | 0.0 | 0.0 | | `ispreferred` | 0.0 | 1.0 | 0.8911 | 1.0 | | `surveyyearlabel` | 1988.0 | 2022.0 | 2009.1646 | 2008.0 | | `denominatorweighted` | 12.0 | 3469.0 | 432.4405 | 317.0 | | `denominatorunweighted` | 25.0 | 5349.0 | 507.6548 | 361.5 | | `levelrank` | 1.0 | 1.0 | 1.0 | 1.0 | --- ## 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。所有列名均转为小写并标准化为蛇形命名法（snake_case）。常见的缺失值标记（如`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。移除了2个缺失值占比超过80%的列：`cilow`和`cihigh`。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格式文件。 --- ## 数据集局限性 - 本数据集的数据源自DHS项目，未由Electric Sheep Africa（ESA）进行独立验证。 - 自动化数据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。 - 以下列的缺失值占比超过20%，在建模过程中需谨慎使用：`byvariablelabel`、`denominatorweighted`、`denominatorunweighted`。 - 如需了解发布方的方法说明与免责声明，请参考[HDX平台上的原始数据集页面](https://data.humdata.org/dataset/dhs-subnational-data-for-ghana)。 --- ## 引用格式 bibtex @dataset{hdx_africa_demographics_ghana, title = {Ghana - Subnational Demographic and Health Data}, author = {The DHS Program}, year = {2026}, url = {https://data.humdata.org/dataset/dhs-subnational-data-for-ghana}, 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。*
