electricsheepafrica/africa-summary-findings-from-majidata-project

---
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
- water-sanitation-and-hygiene-wash
- ken
pretty_name: "Summary Findings from Majidata project"
dataset_info:
splits:
- name: train
num_examples: 37
- name: test
num_examples: 9
---

# Summary Findings from Majidata project

**Publisher:** Majidata (inactive) · **Source:** [HDX](https://data.humdata.org/dataset/summary-findings-from-majidata-project) · **License:** `other-pd-nr` · **Updated:** 2023-05-16

---

## Abstract

Summary Findings from Majidata project. MajiData is an initiative of the Kenyan Water Sector. The mandate to prepare MajiData was given to the Water Services Trust Fund (WSTF) by its parent ministry: the Ministry of Water and Irrigation (MWI).

Each row in this dataset represents tabular records. Data was last updated on HDX on 2023-05-16. Geographic scope: **KEN**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Natural hazards and disaster risk |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 47 |
| **Columns** | 20 (16 numeric, 4 categorical, 0 datetime) |
| **Train split** | 37 rows |
| **Test split** | 9 rows |
| **Geographic scope** | KEN |
| **Publisher** | Majidata (inactive) |
| **HDX last updated** | 2023-05-16 |

---

## Variables

**Geographic** — `countyid` (range 1.0–47.0), `countyname` (NAIROBI, BUSIA, NAKURU), `payingforwater` (range 15.16–99.45).

**Demographic** — `pop` (range 7875.0–2925942.0), `avghhsz` (range 2.5–9.0), `popplareas` (range 1641.0–1269017.0), `popunplareas` (range 989.0–1412467.0), `safewaterpop` (range 7.92–84.15) and 2 others.

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-07).

**Other** — `nareas` (range 4.0–386.0), `ntowns` (range 1.0–29.0), `nareasregfloodg` (range 0.0–27.0), `mnsrcpcnt` (Piped water (connection of someone else, outside the plot) 44.1, Yard well(protected) 31.32%, Piped water (own connection, on the plot) 25.12%), `drkwatertreated` (range 15.58–75.87) and 3 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-summary-findings-from-majidata-project")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `countyid` | int64 | 0.0% | 1.0 – 47.0 (mean 24.0) |
| `countyname` | object | 0.0% | NAIROBI, BUSIA, NAKURU |
| `nareas` | int64 | 0.0% | 4.0 – 386.0 (mean 41.7872) |
| `ntowns` | int64 | 0.0% | 1.0 – 29.0 (mean 5.8723) |
| `pop` | int64 | 0.0% | 7875.0 – 2925942.0 (mean 170332.8511) |
| `avghhsz` | float64 | 0.0% | 2.5 – 9.0 (mean 4.5064) |
| `popplareas` | float64 | 12.8% | 1641.0 – 1269017.0 (mean 78883.2683) |
| `popunplareas` | int64 | 0.0% | 989.0 – 1412467.0 (mean 90175.3191) |
| `nareasregfloodg` | int64 | 0.0% | 0.0 – 27.0 (mean 1.7021) |
| `mnsrcpcnt` | object | 0.0% | Piped water (connection of someone else, outside the plot) 44.1, Yard well(protected) 31.32%, Piped water (own connection, on the plot) 25.12% |
| `drkwatertreated` | float64 | 0.0% | 15.58 – 75.87 (mean 47.4138) |
| `payingforwater` | float64 | 0.0% | 15.16 – 99.45 (mean 74.3923) |
| `nareaslinked` | int64 | 0.0% | 1.0 – 357.0 (mean 32.2128) |
| `plotsconnected` | float64 | 0.0% | 3.54 – 83.9 (mean 37.8949) |
| `dusconnected` | float64 | 25.5% | 0.09 – 50.6 (mean 15.1983) |
| `safewaterpop` | float64 | 2.1% | 7.92 – 84.15 (mean 40.0948) |
| `pipedwaterpop` | float64 | 2.1% | 18.15 – 99.34 (mean 60.3857) |
| `impsanpop` | float64 | 0.0% | 4.66 – 67.22 (mean 41.4104) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-07 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `countyid` | 1.0 | 47.0 | 24.0 | 24.0 |
| `nareas` | 4.0 | 386.0 | 41.7872 | 22.0 |
| `ntowns` | 1.0 | 29.0 | 5.8723 | 5.0 |
| `pop` | 7875.0 | 2925942.0 | 170332.8511 | 52395.0 |
| `avghhsz` | 2.5 | 9.0 | 4.5064 | 3.9 |
| `popplareas` | 1641.0 | 1269017.0 | 78883.2683 | 20811.0 |
| `popunplareas` | 989.0 | 1412467.0 | 90175.3191 | 26277.0 |
| `nareasregfloodg` | 0.0 | 27.0 | 1.7021 | 0.0 |
| `drkwatertreated` | 15.58 | 75.87 | 47.4138 | 46.95 |
| `payingforwater` | 15.16 | 99.45 | 74.3923 | 80.68 |
| `nareaslinked` | 1.0 | 357.0 | 32.2128 | 17.0 |
| `plotsconnected` | 3.54 | 83.9 | 37.8949 | 33.17 |
| `dusconnected` | 0.09 | 50.6 | 15.1983 | 11.11 |
| `safewaterpop` | 7.92 | 84.15 | 40.0948 | 34.555 |
| `pipedwaterpop` | 18.15 | 99.34 | 60.3857 | 66.065 |

---

## 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`. 1 column(s) with >80% missing values were removed: `unnamed_18`. 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 Majidata (inactive) 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: `dusconnected`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/summary-findings-from-majidata-project) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_summary_findings_from_majidata_project,
title = {Summary Findings from Majidata project},
author = {Majidata (inactive)},
year = {2023},
url = {https://data.humdata.org/dataset/summary-findings-from-majidata-project},
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.*