electricsheepafrica/africa-cyclone-enawo-madagascar-windspeed-track-and-rainfall

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- cyclones-hurricanes-typhoons
- geodata
- mdg
pretty_name: "Cyclone Enawo - Madagascar - windspeed, track and rainfall"
dataset_info:
splits:
- name: train
num_examples: 1262
- name: test
num_examples: 315
---

# Cyclone Enawo - Madagascar - windspeed, track and rainfall

**Publisher:** Netherlands Red Cross - 510 · **Source:** [HDX](https://data.humdata.org/dataset/cyclone-enawo-madagascar-windspeed-track-and-rainfall) · **License:** `cc-by` · **Updated:** 2023-10-18

---

## Abstract

Please note that the windspeed and track dataset only covers the part where the this was still a tropical cyclone. For explanation see below caveats. Due to this we will not release a priority index, since windspeed data is missing for most of the country.

Dataset of windspeed and track was kindly provided by University College London.

The rainfall data is calculated based on GPM. It is the accumulated rainfall from March 6th midnight to March 10th 10:00am Madagascar time.

Each row in this dataset represents tabular records. Data was last updated on HDX on 2023-10-18. Geographic scope: **MDG**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Climate and environment |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 1,578 |
| **Columns** | 5 (2 numeric, 3 categorical, 0 datetime) |
| **Train split** | 1,262 rows |
| **Test split** | 315 rows |
| **Geographic scope** | MDG |
| **Publisher** | Netherlands Red Cross - 510 |
| **HDX last updated** | 2023-10-18 |

---

## Variables

**Outcome / Measurement** — `rainfallme` (range 4.9455–522.65).

**Identifier / Metadata** — `unnamed_0` (range 0.0–1577.0), `p_code` (MDG11101001, MDG42411190, MDG42411150), `esa_source` (HDX), `esa_processed` (2026-04-06).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-cyclone-enawo-madagascar-windspeed-track-and-rainfall")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `unnamed_0` | int64 | 0.0% | 0.0 – 1577.0 (mean 788.5) |
| `p_code` | object | 0.0% | MDG11101001, MDG42411190, MDG42411150 |
| `rainfallme` | float64 | 0.0% | 4.9455 – 522.65 (mean 191.0401) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-06 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `unnamed_0` | 0.0 | 1577.0 | 788.5 | 788.5 |
| `rainfallme` | 4.9455 | 522.65 | 191.0401 | 180.6107 |

---

## 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 Netherlands Red Cross - 510 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/cyclone-enawo-madagascar-windspeed-track-and-rainfall) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_cyclone_enawo_madagascar_windspeed_track_and_rainfall,
title = {Cyclone Enawo - Madagascar - windspeed, track and rainfall},
author = {Netherlands Red Cross - 510},
year = {2023},
url = {https://data.humdata.org/dataset/cyclone-enawo-madagascar-windspeed-track-and-rainfall},
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.*