electricsheepafrica/africa-south-sudan-shapefiles-2023

---
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:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- gis
- map
- shapefiles
pretty_name: "South Sudan Shapefiles"
dataset_info:
splits:
- name: train
num_examples: 409
- name: test
num_examples: 102
---

# South Sudan Shapefiles

**Publisher:** UNOCHA · **Source:** [OpenAfrica](https://open.africa/dataset/south-sudan-shapefiles-2023) · **License:** `cc-by` · **Updated:** 2024-10-22

---

## Abstract

2023 South Sudan administrative level 0-3 boundaries (with Abyei region included in administrative level 2 and 3 layers)

Each row in this dataset represents time-series observations. Temporal coverage is indicated by the `date`, `validon` column(s). Geographic scope: **Africa (multiple countries)**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Time-series observations |
| **Rows (total)** | 512 |
| **Columns** | 13 (1 numeric, 10 categorical, 2 datetime) |
| **Train split** | 409 rows |
| **Test split** | 102 rows |
| **Geographic scope** | Africa (multiple countries) |
| **Publisher** | UNOCHA |
| **OpenAfrica last updated** | 2024-10-22 |

---

## Variables

**Temporal** — `date`.

**Identifier / Metadata** — `adm3_pcode` (SS000101, SS010101, SS070304), `adm2_pcode` (SS0101, SS0606, SS0803), `adm1_pcode` (SS06, SS03, SS07), `adm0_pcode` (SS), `validon` and 2 others.

**Other** — `adm3_en` (Abyei Region, Bungu, Malual), `adm2_en` (Juba, Mayom, Tonj East), `adm1_en` (Unity, Jonglei, Upper Nile), `adm0_en` (South Sudan), `area_sqkm` (range 2.2672–23780.1013).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-south-sudan-shapefiles-2023")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `adm3_en` | object | 0.0% | Abyei Region, Bungu, Malual |
| `adm3_pcode` | object | 0.0% | SS000101, SS010101, SS070304 |
| `adm2_en` | object | 0.0% | Juba, Mayom, Tonj East |
| `adm2_pcode` | object | 0.0% | SS0101, SS0606, SS0803 |
| `adm1_en` | object | 0.0% | Unity, Jonglei, Upper Nile |
| `adm1_pcode` | object | 0.0% | SS06, SS03, SS07 |
| `adm0_en` | object | 0.0% | South Sudan |
| `adm0_pcode` | object | 0.0% | SS |
| `date` | datetime64[ns] | 0.0% | |
| `validon` | datetime64[ns] | 0.0% | |
| `area_sqkm` | float64 | 0.0% | 2.2672 – 23780.1013 (mean 1255.6463) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-27 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `area_sqkm` | 2.2672 | 23780.1013 | 1255.6463 | 673.3193 |

---

## 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`. 1 column(s) with >80% missing values were removed: `validto`. 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 UNOCHA and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- Refer to the [original HDX dataset page](https://open.africa/dataset/south-sudan-shapefiles-2023) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{openafrica_africa_south_sudan_shapefiles_2023,
title = {South Sudan Shapefiles},
author = {UNOCHA},
year = {2024},
url = {https://open.africa/dataset/south-sudan-shapefiles-2023},
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.*