electricsheepafrica/africa-sea-carrier-portal-events

---
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
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- carrier
- sea
pretty_name: "Global Sea Carrier Portal Events"
dataset_info:
splits:
- name: train
num_examples: 35
- name: test
num_examples: 8
---

# Global Sea Carrier Portal Events

**Publisher:** Global Fishing Watch · **Source:** [OpenAfrica](https://open.africa/dataset/sea-carrier-portal-events) · **License:** `cc-by` · **Updated:** 2023-03-09

---

## Abstract

Data from the Carrier Vessel Portal public portal to help policymakers and fishery managers better understand the activity of carriers, refrigerated cargo vessels that can support the transfer of fish from commercial fishing vessels out at sea and delivery of fish to ports for processing worldwide.

Each row in this dataset represents country-level aggregates. Data was last updated on OpenAfrica on 2023-03-09. Geographic scope: **Africa (multiple countries)**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 44 |
| **Columns** | 5 (1 numeric, 4 categorical, 0 datetime) |
| **Train split** | 35 rows |
| **Test split** | 8 rows |
| **Geographic scope** | Africa (multiple countries) |
| **Publisher** | Global Fishing Watch |
| **OpenAfrica last updated** | 2023-03-09 |

---

## Variables

**Geographic** — `vessel_origin_port_country` (Senegal, Spain, Cote d'Ivoire), `vessel_destination_port_country` (Senegal, Sierra Leone, Guinea).

**Outcome / Measurement** — `number_of_events` (range 1.0–15.0).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-28).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sea-carrier-portal-events")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `vessel_origin_port_country` | object | 0.0% | Senegal, Spain, Cote d'Ivoire |
| `vessel_destination_port_country` | object | 0.0% | Senegal, Sierra Leone, Guinea |
| `number_of_events` | int64 | 0.0% | 1.0 – 15.0 (mean 2.8864) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-28 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `number_of_events` | 1.0 | 15.0 | 2.8864 | 2.0 |

---

## Curation

Raw data was downloaded from OpenAfrica 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 Global Fishing Watch 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://open.africa/dataset/sea-carrier-portal-events) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{openafrica_africa_sea_carrier_portal_events,
title = {Global Sea Carrier Portal Events},
author = {Global Fishing Watch},
year = {2023},
url = {https://open.africa/dataset/sea-carrier-portal-events},
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.*