electricsheepafrica/africa-south-sudan-2015-5w-response-data-by-cluster-and-indicator

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- humanitarian-needs-overview-hno
- who-is-doing-what-and-where-3w-4w-5w
- ssd
pretty_name: "South Sudan 2015 5W response data by cluster and indicator"
dataset_info:
splits:
- name: train
num_examples: 10449
- name: test
num_examples: 2612
---

# South Sudan 2015 5W response data by cluster and indicator

**Publisher:** OCHA South Sudan · **Source:** [HDX](https://data.humdata.org/dataset/south-sudan-2015-5w-response-data-by-cluster-and-indicator) · **License:** `cc-by` · **Updated:** 2023-09-20

---

## Abstract

This is humanitarian response data compiled in 2015 for South Sudan. It represents cluster information which was compiled on monthly basis from the 5W submissions shared with OCHA by the clusters.

Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `month` column(s). Geographic scope: **SSD**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 13,062 |
| **Columns** | 10 (3 numeric, 6 categorical, 1 datetime) |
| **Train split** | 10,449 rows |
| **Test split** | 2,612 rows |
| **Geographic scope** | SSD |
| **Publisher** | OCHA South Sudan |
| **HDX last updated** | 2023-09-20 |

---

## Variables

**Geographic** — `state` (Jonglei, Upper Nile, Unity), `county` (Juba, Bor South, Malakal).

**Temporal** — `month`.

**Demographic** — `total_female` (range -11.0–361085.32), `total_male` (range 0.0–447293.0).

**Outcome / Measurement** — `total_beneficiaries` (range 0.0–3461154.2).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-19).

**Other** — `cluster` (Nutrition, CCCM, WASH), `indicators` (Number of children, adolescents who have received critical child protection services, Number of boys and girls aged 0-59 months with SAM admitted for treatment, Number of pregnant and lactating women and caretakers of children 0-23 months reached with IYCF counselling).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-south-sudan-2015-5w-response-data-by-cluster-and-indicator")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `state` | object | 0.0% | Jonglei, Upper Nile, Unity |
| `county` | object | 0.1% | Juba, Bor South, Malakal |
| `cluster` | object | 0.0% | Nutrition, CCCM, WASH |
| `indicators` | object | 0.0% | Number of children, adolescents who have received critical child protection services, Number of boys and girls aged 0-59 months with SAM admitted for treatment, Number of pregnant and lactating women and caretakers of children 0-23 months reached with IYCF counselling |
| `month` | datetime64[ns] | 0.0% | |
| `total_beneficiaries` | float64 | 13.3% | 0.0 – 3461154.2 (mean 14686.8997) |
| `total_female` | float64 | 60.5% | -11.0 – 361085.32 (mean 5063.6677) |
| `total_male` | float64 | 65.8% | 0.0 – 447293.0 (mean 4957.5488) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-19 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `total_beneficiaries` | 0.0 | 3461154.2 | 14686.8997 | 1492.0 |
| `total_female` | -11.0 | 361085.32 | 5063.6677 | 443.0 |
| `total_male` | 0.0 | 447293.0 | 4957.5488 | 515.0 |

---

## 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`. 16 column(s) with >80% missing values were removed: `total_households`, `0_5_yrs`, `6_12_yrs`, `13_18yrs`, `19_30_yrs`, `31_59_yrs`.... 359 exact duplicate rows were removed. 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 OCHA South Sudan 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: `total_female`, `total_male`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/south-sudan-2015-5w-response-data-by-cluster-and-indicator) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_south_sudan_2015_5w_response_data_by_cluster_and_indicator,
title = {South Sudan 2015 5W response data by cluster and indicator},
author = {OCHA South Sudan},
year = {2023},
url = {https://data.humdata.org/dataset/south-sudan-2015-5w-response-data-by-cluster-and-indicator},
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.*