electricsheepafrica/africa-ports-mauritius

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- ports
- trade
- mus
pretty_name: "Mauritius: Daily Port Activity Data and Shipment Estimates"
dataset_info:
splits:
- name: train
num_examples: 2131
- name: test
num_examples: 532
---

# Mauritius: Daily Port Activity Data and Shipment Estimates

**Publisher:** PortWatch · **Source:** [HDX](https://data.humdata.org/dataset/mauritius-daily-port-activity-data-and-shipment-estimates) · **License:** `hdx-other` · **Updated:** 2026-04-21

---

## Abstract

Daily count of port calls, estimates of incoming shipment volumes and outgoing shipment volumes (in metric tons) for ports in Mauritius.

Each row in this dataset represents country-level aggregates. Data was last updated on HDX on 2026-04-21. Geographic scope: **MUS**.

*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)** | 2,664 |
| **Columns** | 31 (24 numeric, 6 categorical, 0 datetime) |
| **Train split** | 2,131 rows |
| **Test split** | 532 rows |
| **Geographic scope** | MUS |
| **Publisher** | PortWatch |
| **HDX last updated** | 2026-04-21 |

---

## Variables

**Geographic** — `year` (range 2019.0–2026.0), `day` (range 1.0–31.0), `country` (Mauritius), `iso3` (MUS), `portcalls_dry_bulk` (range 0.0–3.0) and 8 others.

**Temporal** — `date`, `month` (range 1.0–12.0).

**Identifier / Metadata** — `portid` (port965), `portname` (Port Louis), `esa_source` (HDX), `esa_processed` (2026-04-26).

**Other** — `portcalls_container` (range 0.0–4.0), `portcalls_general_cargo` (range 0.0–3.0), `portcalls_roro` (range 0.0–2.0), `portcalls_tanker` (range 0.0–6.0), `portcalls_cargo` (range 0.0–6.0) and 7 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-ports-mauritius")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `date` | datetime64[ns, UTC] | 0.0% | |
| `year` | int64 | 0.0% | 2019.0 – 2026.0 (mean 2022.1607) |
| `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.3536) |
| `day` | int64 | 0.0% | 1.0 – 31.0 (mean 15.6813) |
| `portid` | object | 0.0% | port965 |
| `portname` | object | 0.0% | Port Louis |
| `country` | object | 0.0% | Mauritius |
| `iso3` | object | 0.0% | MUS |
| `portcalls_container` | int64 | 0.0% | 0.0 – 4.0 (mean 1.1772) |
| `portcalls_dry_bulk` | int64 | 0.0% | 0.0 – 3.0 (mean 0.1607) |
| `portcalls_general_cargo` | int64 | 0.0% | 0.0 – 3.0 (mean 0.2909) |
| `portcalls_roro` | int64 | 0.0% | 0.0 – 2.0 (mean 0.1029) |
| `portcalls_tanker` | int64 | 0.0% | 0.0 – 6.0 (mean 0.8082) |
| `portcalls_cargo` | int64 | 0.0% | 0.0 – 6.0 (mean 1.7316) |
| `portcalls` | int64 | 0.0% | 0.0 – 8.0 (mean 2.5398) |
| `import_container` | int64 | 0.0% | 0.0 – 53386.0 (mean 4688.8896) |
| `import_dry_bulk` | int64 | 0.0% | 0.0 – 102781.0 (mean 4328.589) |
| `import_general_cargo` | int64 | 0.0% | 0.0 – 19574.0 (mean 251.7545) |
| `import_roro` | int64 | 0.0% | 0.0 – 4258.0 (mean 81.5518) |
| `import_tanker` | int64 | 0.0% | 0.0 – 97919.0 (mean 8265.6982) |
| `import_cargo` | int64 | 0.0% | 0.0 – 106137.0 (mean 9350.9073) |
| `import` | int64 | 0.0% | 0.0 – 147416.0 (mean 17616.8232) |
| `export_container` | int64 | 0.0% | 0.0 – 58160.0 (mean 3000.8986) |
| `export_dry_bulk` | int64 | 0.0% | 0.0 – 29831.0 (mean 33.982) |
| `export_general_cargo` | int64 | 0.0% | 0.0 – 7763.0 (mean 193.3889) |
| `export_roro` | int64 | 0.0% | |
| `export_tanker` | int64 | 0.0% | |
| `export_cargo` | int64 | 0.0% | |
| `export` | int64 | 0.0% | |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-26 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `year` | 2019.0 | 2026.0 | 2022.1607 | 2022.0 |
| `month` | 1.0 | 12.0 | 6.3536 | 6.0 |
| `day` | 1.0 | 31.0 | 15.6813 | 16.0 |
| `portcalls_container` | 0.0 | 4.0 | 1.1772 | 1.0 |
| `portcalls_dry_bulk` | 0.0 | 3.0 | 0.1607 | 0.0 |
| `portcalls_general_cargo` | 0.0 | 3.0 | 0.2909 | 0.0 |
| `portcalls_roro` | 0.0 | 2.0 | 0.1029 | 0.0 |
| `portcalls_tanker` | 0.0 | 6.0 | 0.8082 | 1.0 |
| `portcalls_cargo` | 0.0 | 6.0 | 1.7316 | 2.0 |
| `portcalls` | 0.0 | 8.0 | 2.5398 | 2.0 |
| `import_container` | 0.0 | 53386.0 | 4688.8896 | 1943.0 |
| `import_dry_bulk` | 0.0 | 102781.0 | 4328.589 | 0.0 |
| `import_general_cargo` | 0.0 | 19574.0 | 251.7545 | 0.0 |
| `import_roro` | 0.0 | 4258.0 | 81.5518 | 0.0 |
| `import_tanker` | 0.0 | 97919.0 | 8265.6982 | 0.0 |

---

## 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`. 1 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 PortWatch 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/mauritius-daily-port-activity-data-and-shipment-estimates) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_ports_mauritius,
title = {Mauritius: Daily Port Activity Data and Shipment Estimates},
author = {PortWatch},
year = {2026},
url = {https://data.humdata.org/dataset/mauritius-daily-port-activity-data-and-shipment-estimates},
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.*