electricsheepafrica/africa-icpac-geonode-2015-tropical-cyclone-chapala-path

---
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:
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- geodata
- hazards-and-risk
- som
pretty_name: "2015 Tropical Cyclone Chapala Path"
dataset_info:
splits:
- name: train
num_examples: 49
- name: test
num_examples: 12
---

# 2015 Tropical Cyclone Chapala Path

**Publisher:** IGAD Climate Prediction and Applications Center (ICPAC) · **Source:** [HDX](https://data.humdata.org/dataset/icpac-geonode-2015-tropical-cyclone-chapala-path) · **License:** `cc-by` · **Updated:** 2026-04-05

---

## Abstract

<p>This layer shows the movement path of 2015 Tropical Cyclone Chapala. On Monday 2 November 2015, Tropical Cyclone Chapala made a landfall in Yemen; however, its effects were also felt across the Gulf of Aden in Somalia where extensive rainfall was experienced in the Northern Bari region in Bosaso district, Puntland. The storm reached maximum wind speed of 130knots.&nbsp;</p>

<p>According to a joint inter-agency rapid assessment more than 500 families (4,000 people) were affected by Tropical Cyclones Chapala and Megh, most affected lived in Gardaful Region, Puntland. No human loss of life was reported, but the rainfall and waves destroyed people&rsquo;s homes, washed fishing boats and nets, killed livestock (an estimated 3,000 sheep and goats, as well as 200 camels) and caused damage/destruction to public infrastructure including hospitals, roads and schools.</p>
<p>It was also estimated that 4,000 people were displaced, with 1,129 people being worst affected, having lost their homes and livelihoods (business, fishing boats, engines and nets), which were swept away by waves. It was reported that there had been extensive damage/destruction to people&rsquo;s livelihoods, with 80 per cent of villages in Alula and 60 per cent of villages in Af Kalahay Bareda, BiyoCade, Boolimoog, Dhurbo, Fagoora, Geesalay, Murcanyo, Murcanyo, Sayn Weyn, Sayn Yar, Toxiin and Xaabo experiencing loss of livestock and damage to crops and fisheries.</p>
<p>&nbsp;</p>

Each row in this dataset represents geolocated point observations. Data was last updated on HDX on 2026-04-05. Geographic scope: **SOM**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Climate and environment |
| **Unit of observation** | Geolocated point observations |
| **Rows (total)** | 62 |
| **Columns** | 32 (21 numeric, 11 categorical, 0 datetime) |
| **Train split** | 49 rows |
| **Test split** | 12 rows |
| **Geographic scope** | SOM |
| **Publisher** | IGAD Climate Prediction and Applications Center (ICPAC) |
| **HDX last updated** | 2026-04-05 |

---

## Variables

**Geographic** — `cy` (range 4.0–4.0), `yyyymmddhh` (range 2015102912.0–2015110318.0), `lat` (range 13.2–14.3), `long` (range 47.4–63.1), `vmax` (range 30.0–130.0) and 3 others.

**Identifier / Metadata** — `fid` (a__2015_TC_Chapala0.1, a__2015_TC_Chapala0.47, a__2015_TC_Chapala0.34), `fid_1` (range 1.0–62.0), `windcode` (NEQ), `stormname` (CHAPALA), `esa_source` (HDX) and 1 others.

**Other** — `the_geom` (POINT (55.7 13.5), POINT (56.4 13.6), POINT (49.6 13.7)), `basin` (IO), `tech` (BEST), `tau` (range 0.0–0.0), `mslp` (range 926.0–1000.0) and 13 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-icpac-geonode-2015-tropical-cyclone-chapala-path")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `fid` | object | 0.0% | a__2015_TC_Chapala0.1, a__2015_TC_Chapala0.47, a__2015_TC_Chapala0.34 |
| `fid_1` | int64 | 0.0% | 1.0 – 62.0 (mean 31.5) |
| `the_geom` | object | 0.0% | POINT (55.7 13.5), POINT (56.4 13.6), POINT (49.6 13.7) |
| `basin` | object | 0.0% | IO |
| `cy` | int64 | 0.0% | 4.0 – 4.0 (mean 4.0) |
| `yyyymmddhh` | int64 | 0.0% | 2015102912.0 – 2015110318.0 (mean 2015106847.7097) |
| `tech` | object | 0.0% | BEST |
| `tau` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `lat` | float64 | 0.0% | 13.2 – 14.3 (mean 13.771) |
| `long` | float64 | 0.0% | 47.4 – 63.1 (mean 55.6903) |
| `vmax` | int64 | 0.0% | 30.0 – 130.0 (mean 101.129) |
| `mslp` | int64 | 0.0% | 926.0 – 1000.0 (mean 947.2903) |
| `ty` | object | 0.0% | TY, TS, ST |
| `rad` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `windcode` | object | 1.6% | NEQ |
| `rad1` | int64 | 0.0% | 0.0 – 115.0 (mean 58.2258) |
| `rad2` | int64 | 0.0% | 0.0 – 115.0 (mean 56.6129) |
| `rad3` | int64 | 0.0% | 0.0 – 110.0 (mean 52.9032) |
| `rad4` | int64 | 0.0% | 0.0 – 120.0 (mean 61.5323) |
| `radp` | int64 | 0.0% | 1006.0 – 1008.0 (mean 1007.7097) |
| `rrp` | int64 | 0.0% | 155.0 – 205.0 (mean 189.5968) |
| `mrd` | int64 | 0.0% | 5.0 – 25.0 (mean 12.0645) |
| `gusts` | int64 | 0.0% | 0.0 – 160.0 (mean 7.7419) |
| `eye` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `subregn` | object | 4.8% | A |
| `maxseas` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `dir` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `speed` | int64 | 0.0% | |
| `stormname` | object | 0.0% | CHAPALA |
| `depth` | object | 4.8% | D |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `fid_1` | 1.0 | 62.0 | 31.5 | 31.5 |
| `cy` | 4.0 | 4.0 | 4.0 | 4.0 |
| `yyyymmddhh` | 2015102912.0 | 2015110318.0 | 2015106847.7097 | 2015110100.0 |
| `tau` | 0.0 | 0.0 | 0.0 | 0.0 |
| `lat` | 13.2 | 14.3 | 13.771 | 13.8 |
| `long` | 47.4 | 63.1 | 55.6903 | 56.4 |
| `vmax` | 30.0 | 130.0 | 101.129 | 110.0 |
| `mslp` | 926.0 | 1000.0 | 947.2903 | 941.0 |
| `rad` | 0.0 | 0.0 | 0.0 | 0.0 |
| `rad1` | 0.0 | 115.0 | 58.2258 | 55.0 |
| `rad2` | 0.0 | 115.0 | 56.6129 | 50.0 |
| `rad3` | 0.0 | 110.0 | 52.9032 | 45.0 |
| `rad4` | 0.0 | 120.0 | 61.5323 | 55.0 |
| `radp` | 1006.0 | 1008.0 | 1007.7097 | 1008.0 |
| `rrp` | 155.0 | 205.0 | 189.5968 | 195.0 |

---

## 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`. 8 column(s) with >80% missing values were removed: `technum`, `initials`, `seas`, `seascode`, `seas1`, `seas2`.... 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 IGAD Climate Prediction and Applications Center (ICPAC) 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/icpac-geonode-2015-tropical-cyclone-chapala-path) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_icpac_geonode_2015_tropical_cyclone_chapala_path,
title = {2015 Tropical Cyclone Chapala Path},
author = {IGAD Climate Prediction and Applications Center (ICPAC)},
year = {2026},
url = {https://data.humdata.org/dataset/icpac-geonode-2015-tropical-cyclone-chapala-path},
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.*