electricsheepafrica/africa-separation-of-power-2005-2021-for-select-african-countries

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- rule-of-law
- separation-of-powers
- benin
- botswana
- cape-verde
- ethiopia
- kenya
pretty_name: "Separation of Power (2005-2021) for select African countries"
dataset_info:
splits:
- name: train
num_examples: 74
- name: test
num_examples: 18
---

# Separation of Power (2005-2021) for select African countries

**Publisher:** The Charter Project · **Source:** [OpenAfrica](https://open.africa/dataset/separation-of-power-2005-2021-for-select-african-countries) · **License:** `cc-by` · **Updated:** 2023-04-11

---

## Abstract

The variable indicates the extent of mutual checks and balances on political powers. It ranges from 1 to 10 (most separated).

Score
1 No separation of Power 4 The separation of powers is formally established but weak in practice 7 The separation of powers is in place and functioning 10 There is a clear separation of powers with mutual checks and balances. The remaining scores are intermediate categories.

Each row in this dataset represents tabular records. Data was last updated on OpenAfrica on 2023-04-11. Geographic scope: **BENIN, BOTSWANA, CAPE-VERDE, ETHIOPIA, KENYA, NIGERIA, SENEGAL, SOUTH-AFRICA, and 2 others**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 93 |
| **Columns** | 5 (2 numeric, 3 categorical, 0 datetime) |
| **Train split** | 74 rows |
| **Test split** | 18 rows |
| **Geographic scope** | BENIN, BOTSWANA, CAPE-VERDE, ETHIOPIA, KENYA, NIGERIA, SENEGAL, SOUTH-AFRICA, and 2 others |
| **Publisher** | The Charter Project |
| **OpenAfrica last updated** | 2023-04-11 |

---

## Variables

**Identifier / Metadata** — `unnamed_1` (range 2005.0–2021.0), `unnamed_2` (range 1.0–9.0), `esa_source` (HDX), `esa_processed` (2026-04-28).

**Other** — `separation_of_power_2005_2021` (Benin, Botswana, Ethiopia).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-separation-of-power-2005-2021-for-select-african-countries")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `separation_of_power_2005_2021` | object | 1.1% | Benin, Botswana, Ethiopia |
| `unnamed_1` | float64 | 3.2% | 2005.0 – 2021.0 (mean 2013.0) |
| `unnamed_2` | float64 | 3.2% | 1.0 – 9.0 (mean 5.7222) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-28 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `unnamed_1` | 2005.0 | 2021.0 | 2013.0 | 2013.0 |
| `unnamed_2` | 1.0 | 9.0 | 5.7222 | 6.0 |

---

## Curation

Raw data was downloaded from OpenAfrica 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`. 6 column(s) with >80% missing values were removed: `unnamed_3`, `unnamed_4`, `unnamed_5`, `unnamed_6`, `unnamed_7`, `unnamed_8`. 2 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 The Charter 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.
- This dataset spans 10 countries; geographic and methodological inconsistencies across national boundaries may affect cross-country comparability.
- Refer to the [original HDX dataset page](https://open.africa/dataset/separation-of-power-2005-2021-for-select-african-countries) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{openafrica_africa_separation_of_power_2005_2021_for_select_african_countries,
title = {Separation of Power (2005-2021) for select African countries},
author = {The Charter Project},
year = {2023},
url = {https://open.africa/dataset/separation-of-power-2005-2021-for-select-african-countries},
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.*