electricsheepafrica/africa-demographics-kenya

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-classification
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- demographics
- health
- ken
pretty_name: "Kenya - National Demographic and Health Data"
dataset_info:
splits:
- name: train
num_examples: 152
- name: test
num_examples: 38
---

# Kenya - National Demographic and Health Data

**Publisher:** The DHS Program · **Source:** [HDX](https://data.humdata.org/dataset/dhs-data-for-kenya) · **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 [Kenya - Subnational Demographic and Health Data](https://data.humdata.org/dataset/dhs-subnational-data-for-kenya) 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 country-level aggregates. Data was last updated on HDX on 2026-04-20. Geographic scope: **KEN**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 191 |
| **Columns** | 27 (12 numeric, 15 categorical, 0 datetime) |
| **Train split** | 152 rows |
| **Test split** | 38 rows |
| **Geographic scope** | KEN |
| **Publisher** | The DHS Program |
| **HDX last updated** | 2026-04-20 |

---

## Variables

**Geographic** — `iso3` (KEN), `dhs_countrycode` (KE), `countryname` (Kenya), `surveyyear` (range 1989.0–2022.0), `surveyid` (KE2003DHS, KE2008DHS, KE2014DHS) and 6 others.

**Outcome / Measurement** — `value` (range 0.5–743.0), `istotal` (range 1.0–1.0).

**Identifier / Metadata** — `dataid` (range 1361.0–824316.0), `indicatorid` (RH_DELP_C_DHF, CM_ECMR_C_IMR, CM_ECMR_C_U5M), `characteristicid` (range 1000.0–10000.0), `characteristiclabel` (Total, Total 15-49), `ispreferred` (range 0.0–1.0) and 3 others.

**Other** — `indicator` (Place of delivery: Health facility, Infant mortality rate, Under-five mortality rate), `precision` (range 0.0–1.0), `indicatororder` (range 11763080.0–260321010.0), `characteristicorder` (range 0.0–10000.0), `denominatorweighted` (range 549.0–37911.0) and 1 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-demographics-kenya")
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% | KEN |
| `dataid` | int64 | 0.0% | 1361.0 – 824316.0 (mean 439095.9476) |
| `indicator` | object | 0.0% | Place of delivery: Health facility, Infant mortality rate, Under-five mortality rate |
| `value` | float64 | 0.0% | 0.5 – 743.0 (mean 50.256) |
| `precision` | int64 | 0.0% | 0.0 – 1.0 (mean 0.8325) |
| `dhs_countrycode` | object | 0.0% | KE |
| `countryname` | object | 0.0% | Kenya |
| `surveyyear` | int64 | 0.0% | 1989.0 – 2022.0 (mean 2006.6963) |
| `surveyid` | object | 0.0% | KE2003DHS, KE2008DHS, KE2014DHS |
| `indicatorid` | object | 0.0% | RH_DELP_C_DHF, CM_ECMR_C_IMR, CM_ECMR_C_U5M |
| `indicatororder` | int64 | 0.0% | 11763080.0 – 260321010.0 (mean 100874966.4921) |
| `indicatortype` | object | 0.0% | I |
| `characteristicid` | int64 | 0.0% | 1000.0 – 10000.0 (mean 2554.9738) |
| `characteristicorder` | int64 | 0.0% | 0.0 – 10000.0 (mean 1727.7487) |
| `characteristiccategory` | object | 0.0% | Total, Total 15-49 |
| `characteristiclabel` | object | 0.0% | Total, Total 15-49 |
| `byvariableid` | int64 | 0.0% | 0.0 – 631002.0 (mean 20550.1728) |
| `byvariablelabel` | object | 68.6% | Five years preceding the survey, Ten years preceding the survey, Three years preceding the survey |
| `istotal` | int64 | 0.0% | 1.0 – 1.0 (mean 1.0) |
| `ispreferred` | int64 | 0.0% | 0.0 – 1.0 (mean 0.822) |
| `sdrid` | object | 0.0% | |
| `surveyyearlabel` | object | 0.0% | |
| `surveytype` | object | 0.0% | |
| `denominatorweighted` | float64 | 31.9% | 549.0 – 37911.0 (mean 8269.8692) |
| `denominatorunweighted` | float64 | 31.9% | 538.0 – 37911.0 (mean 8494.9077) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `dataid` | 1361.0 | 824316.0 | 439095.9476 | 462342.0 |
| `value` | 0.5 | 743.0 | 50.256 | 39.2 |
| `precision` | 0.0 | 1.0 | 0.8325 | 1.0 |
| `surveyyear` | 1989.0 | 2022.0 | 2006.6963 | 2008.0 |
| `indicatororder` | 11763080.0 | 260321010.0 | 100874966.4921 | 83566070.0 |
| `characteristicid` | 1000.0 | 10000.0 | 2554.9738 | 1000.0 |
| `characteristicorder` | 0.0 | 10000.0 | 1727.7487 | 0.0 |
| `byvariableid` | 0.0 | 631002.0 | 20550.1728 | 0.0 |
| `istotal` | 1.0 | 1.0 | 1.0 | 1.0 |
| `ispreferred` | 0.0 | 1.0 | 0.822 | 1.0 |
| `denominatorweighted` | 549.0 | 37911.0 | 8269.8692 | 5394.0 |
| `denominatorunweighted` | 538.0 | 37911.0 | 8494.9077 | 5394.0 |

---

## 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`. 4 column(s) with >80% missing values were removed: `regionid`, `cilow`, `cihigh`, `levelrank`. 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-data-for-kenya) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_demographics_kenya,
title = {Kenya - National Demographic and Health Data},
author = {The DHS Program},
year = {2026},
url = {https://data.humdata.org/dataset/dhs-data-for-kenya},
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.*