electricsheepafrica/africa-sira-disability-and-older-age-dataset-metuge-and-pemba-cabo-delgado-mozambique-may-2024

---
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
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- affected-population
- conflict-violence
- disability
- displacement
- elderly
- gender-and-age-disaggregated-data-gadd
- gender-based-violence-gbv
- internally-displaced-persons-idp
- moz
pretty_name: "Mozambique: Survey for Inclusive Rapid Assessment (SIRA)"
dataset_info:
splits:
- name: train
num_examples: 18408
- name: test
num_examples: 4602
---

# Mozambique: Survey for Inclusive Rapid Assessment (SIRA)

**Publisher:** Light for the World · **Source:** [HDX](https://data.humdata.org/dataset/sira-disability-and-older-age-dataset-metuge-and-pemba-cabo-delgado-mozambique-may-2024) · **License:** `cc-by` · **Updated:** 2025-07-22

---

## Abstract

# SIRA Dataset for disability and older age - Cabo Delgado, Mozambique

## Background

The Survey for Inclusive Rapid Assessment (SIRA) Dataset for disability and older age was collected in May 2024 in Pemba (urban) and Metuge (rural) localities of Cabo Delgado, Mozambique, as part of the Data that Matters project funded by Elrha. Stratified clustered random sampling was used in this survey, the aim of which is to assess the barriers and enablers people face in accessing humanitarian assistance, in particular persons with disabilities and older persons.

## The Data

The dataset consists of:
* SIRA Dataset #1. Household-level data: locality, household size, displacement status, registration
* SIRA Dataset #2. Individual-level data: sex, age, education, health, employment
* SIRA Dataset #3. Individual-level data: Washington Group (WG) questions taken from short (WG_SS), extended (WG-ES) of questions and child functioning modules (0-4 and 5-17 years). Questions include functioning domains associated with mental health.
* SIRA Dataset #4. Individual-level data: barriers in accessing humanitarian assistance for i) distributions, ii) services, iii) livelihood opportunities, iv) sexual, maternal and reproductive health, v) safety and security.

The datasets can be merged via the respondent identifier "indID", with "hhID" allowing to group individuals linked to a common household.

Each row in this dataset represents household-level survey responses. Data was last updated on HDX on 2025-07-22. Geographic scope: **MOZ**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Household-level survey responses |
| **Rows (total)** | 23,011 |
| **Columns** | 9 (0 numeric, 9 categorical, 0 datetime) |
| **Train split** | 18,408 rows |
| **Test split** | 4,602 rows |
| **Geographic scope** | MOZ |
| **Publisher** | Light for the World |
| **HDX last updated** | 2025-07-22 |

---

## Variables

**Geographic** — `respsex` (2. Female, 1. Male), `barrierwhy` (2. Fear of attack, harrassement, aggression, 16. I don't face any of these barriers, 1. I do not know where the service or support is available or who can help).

**Demographic** — `hhid` (cyojyxolvhxlq6hb, c83s42tlvumb61w3, chi8xz2lvm8328ea), `respage` (16 to 50, 51 and above, 0 to 15).

**Identifier / Metadata** — `indid` (cjfmoimlvz25w5u9, cpjg383lvw0sz7ka, cr2t7iylvxkz4t24), `esa_source` (HDX), `esa_processed` (2026-04-18).

**Other** — `barrierwhich` (SRH, Services, Fear), `barrierwhere` (1. Food, 2. Family planning, 1. Water).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sira-disability-and-older-age-dataset-metuge-and-pemba-cabo-delgado-mozambique-may-2024")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `hhid` | object | 0.0% | cyojyxolvhxlq6hb, c83s42tlvumb61w3, chi8xz2lvm8328ea |
| `indid` | object | 0.0% | cjfmoimlvz25w5u9, cpjg383lvw0sz7ka, cr2t7iylvxkz4t24 |
| `respsex` | object | 0.0% | 2. Female, 1. Male |
| `respage` | object | 0.0% | 16 to 50, 51 and above, 0 to 15 |
| `barrierwhich` | object | 0.0% | SRH, Services, Fear |
| `barrierwhere` | object | 0.0% | 1. Food, 2. Family planning, 1. Water |
| `barrierwhy` | object | 0.0% | 2. Fear of attack, harrassement, aggression, 16. I don't face any of these barriers, 1. I do not know where the service or support is available or who can help |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-18 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
_No numeric columns._

---

## 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`. 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 Light for the World 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://data.humdata.org/dataset/sira-disability-and-older-age-dataset-metuge-and-pemba-cabo-delgado-mozambique-may-2024) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_sira_disability_and_older_age_dataset_metuge_and_pemba_cabo_delgado_mozambique_may_2024,
title = {Mozambique: Survey for Inclusive Rapid Assessment (SIRA)},
author = {Light for the World},
year = {2025},
url = {https://data.humdata.org/dataset/sira-disability-and-older-age-dataset-metuge-and-pemba-cabo-delgado-mozambique-may-2024},
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.*