electricsheepafrica/africa-impact-of-cyclones

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- affected-population
- cyclones-hurricanes-typhoons
- natural-disasters
- moz
pretty_name: "Mozambique: Impact of Cyclones"
dataset_info:
splits:
- name: train
num_examples: 88
- name: test
num_examples: 22
---

# Mozambique: Impact of Cyclones

**Publisher:** OCHA Mozambique · **Source:** [HDX](https://data.humdata.org/dataset/impact-of-cyclones) · **License:** `other-pd-nr` · **Updated:** 2025-11-25

---

## Abstract

Impact of cyclones (people affected and injured by cyclones) in Mozambique from 2017 to 2025.

Each row in this dataset represents tabular records. Data was last updated on HDX on 2025-11-25. Geographic scope: **MOZ**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Demographics and population |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 111 |
| **Columns** | 15 (11 numeric, 4 categorical, 0 datetime) |
| **Train split** | 88 rows |
| **Test split** | 22 rows |
| **Geographic scope** | MOZ |
| **Publisher** | OCHA Mozambique |
| **HDX last updated** | 2025-11-25 |

---

## Variables

**Identifier / Metadata** — `unnamed_0` (Nampula, Zambezia, Cabo Delgado), `unnamed_1` (ADM2 PT, Chibabava, Cidade De Tete), `unnamed_2` (range 0.0–1067630.0), `unnamed_3` (range 0.0–512462.4), `unnamed_4` (range 0.0–555167.6) and 6 others.

**Other** — `451910` (range 0.0–90749.0), `283493` (range 0.0–62003.0), `778036_3999999999` (range 0.0–76021.4), `1302815_4999999998` (range 0.0–90749.0).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-impact-of-cyclones")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `unnamed_0` | object | 0.0% | Nampula, Zambezia, Cabo Delgado |
| `unnamed_1` | object | 0.0% | ADM2 PT, Chibabava, Cidade De Tete |
| `unnamed_2` | float64 | 0.9% | 0.0 – 1067630.0 (mean 214115.9909) |
| `unnamed_3` | float64 | 0.9% | 0.0 – 512462.4 (mean 102995.332) |
| `unnamed_4` | float64 | 0.9% | 0.0 – 555167.6 (mean 111120.6589) |
| `unnamed_5` | float64 | 0.9% | 0.0 – 608549.1 (mean 122046.1148) |
| `unnamed_6` | float64 | 0.9% | 0.0 – 405699.4 (mean 81364.0765) |
| `unnamed_7` | float64 | 0.9% | 0.0 – 53381.5 (mean 10705.7995) |
| `unnamed_8` | float64 | 0.9% | 0.0 – 160144.5 (mean 32117.3986) |
| `451910` | float64 | 71.2% | 0.0 – 90749.0 (mean 14122.1875) |
| `283493` | float64 | 79.3% | 0.0 – 62003.0 (mean 12325.7826) |
| `778036_3999999999` | float64 | 60.4% | 0.0 – 76021.4 (mean 17682.6455) |
| `1302815_4999999998` | float64 | 0.9% | 0.0 – 90749.0 (mean 11843.7773) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-06 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `unnamed_2` | 0.0 | 1067630.0 | 214115.9909 | 174587.5 |
| `unnamed_3` | 0.0 | 512462.4 | 102995.332 | 83220.96 |
| `unnamed_4` | 0.0 | 555167.6 | 111120.6589 | 94778.06 |
| `unnamed_5` | 0.0 | 608549.1 | 122046.1148 | 99514.875 |
| `unnamed_6` | 0.0 | 405699.4 | 81364.0765 | 66343.25 |
| `unnamed_7` | 0.0 | 53381.5 | 10705.7995 | 8729.375 |
| `unnamed_8` | 0.0 | 160144.5 | 32117.3986 | 26188.125 |
| `451910` | 0.0 | 90749.0 | 14122.1875 | 665.0 |
| `283493` | 0.0 | 62003.0 | 12325.7826 | 2320.0 |
| `778036_3999999999` | 0.0 | 76021.4 | 17682.6455 | 15565.05 |
| `1302815_4999999998` | 0.0 | 90749.0 | 11843.7773 | 57.0 |

---

## 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`. 11 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 Mozambique 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: `451910`, `283493`, `778036_3999999999`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/impact-of-cyclones) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_impact_of_cyclones,
title = {Mozambique: Impact of Cyclones},
author = {OCHA Mozambique},
year = {2025},
url = {https://data.humdata.org/dataset/impact-of-cyclones},
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.*