electricsheepafrica/africa-mozambique-cyclone-1001053

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-sa-4.0
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
- geodata
- moz
pretty_name: "Mozambique: Cyclone - Tropical storm - Mar 2024"
dataset_info:
splits:
- name: train
num_examples: 134
- name: test
num_examples: 33
---

# Mozambique: Cyclone - Tropical storm - Mar 2024

**Publisher:** WFP Advanced Disaster Analysis & Mapping · **Source:** [HDX](https://data.humdata.org/dataset/mozambique-cyclone-1001053) · **License:** `cc-by-sa` · **Updated:** 2025-11-24

---

## Abstract

**ADAM ID: 1001053\_10** Cyclone (tropical storm) during the period Mar 03 2024-Mar 13 2024 in Mozambique, South Africa, Eswatini, Zimbabwe, Malawi. It impacted 0 people.

Each row in this dataset represents tabular records. Data was last updated on HDX on 2025-11-24. 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)** | 168 |
| **Columns** | 8 (3 numeric, 5 categorical, 0 datetime) |
| **Train split** | 134 rows |
| **Test split** | 33 rows |
| **Geographic scope** | MOZ |
| **Publisher** | WFP Advanced Disaster Analysis & Mapping |
| **HDX last updated** | 2025-11-24 |

---

## Variables

**Demographic** — `pop_60_kmh` (range 0.0–1923985.0), `pop_90_kmh` (range 0.0–472057.0).

**Identifier / Metadata** — `unnamed_0` (range 0.0–187.0), `adm0_name` (Mozambique, Eswatini, South Africa), `adm1_name` (Manzini, Shiselweni, Hhohho), `adm2_name` (---, Dondo, Namaacha), `esa_source` (HDX) and 1 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-mozambique-cyclone-1001053")
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 – 187.0 (mean 91.8274) |
| `adm0_name` | object | 0.0% | Mozambique, Eswatini, South Africa |
| `adm1_name` | object | 0.0% | Manzini, Shiselweni, Hhohho |
| `adm2_name` | object | 0.0% | ---, Dondo, Namaacha |
| `pop_60_kmh` | int64 | 0.0% | 0.0 – 1923985.0 (mean 160311.0536) |
| `pop_90_kmh` | int64 | 0.0% | 0.0 – 472057.0 (mean 8122.5179) |
| `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 | 187.0 | 91.8274 | 91.5 |
| `pop_60_kmh` | 0.0 | 1923985.0 | 160311.0536 | 40792.0 |
| `pop_90_kmh` | 0.0 | 472057.0 | 8122.5179 | 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`. 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 WFP Advanced Disaster Analysis & Mapping 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/mozambique-cyclone-1001053) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_mozambique_cyclone_1001053,
title = {Mozambique: Cyclone - Tropical storm - Mar 2024},
author = {WFP Advanced Disaster Analysis & Mapping},
year = {2025},
url = {https://data.humdata.org/dataset/mozambique-cyclone-1001053},
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.*

### 数据集元数据
- 标注创建者：无标注（no-annotation）
- 语言创建方式：公开获取（found）
- 语言：英语（en）
- 许可协议：CC BY-SA 4.0
- 多语言属性：单语言（monolingual）
- 样本规模：少于1000条（n<1K）
- 源数据集类型：原生数据集（original）
- 任务类别：表格分类（tabular-classification）、表格回归（tabular-regression）
- 任务子类别：无
- 标签：非洲（africa）、人道主义（humanitarian）、HDX（人道主义数据交换，Humanitarian Data Exchange）、Electric Sheep Africa、受影响人口（affected-population）、气旋-飓风-台风（cyclones-hurricanes-typhoons）、地理数据（geodata）、莫桑比克（moz）
- 友好名称：莫桑比克：2024年3月气旋与热带风暴

# 莫桑比克：2024年3月气旋与热带风暴

**发布方：** 世界粮食计划署（World Food Programme, WFP）高级灾害分析与制图部门 · **来源：** [HDX（人道主义数据交换，Humanitarian Data Exchange）](https://data.humdata.org/dataset/mozambique-cyclone-1001053) · **许可协议：** `cc-by-sa` · **最后更新：** 2025-11-24

---

## 摘要

**ADAM编号：1001053_10** 2024年3月3日至3月13日期间，莫桑比克、南非、斯威士兰、津巴布韦、马拉维遭遇气旋（热带风暴）袭击，此次灾害未造成受影响人口。
本数据集每条记录均为表格型数据，数据最后于2025年11月24日在HDX平台更新。地理覆盖范围：**莫桑比克（MOZ）**。
*本数据集由Electric Sheep Africa整理为适配机器学习的Parquet格式（Parquet）。*

---

## 数据集特征

| 指标 | 详情 |
|---|---|
| **领域** | 人口与人口统计 |
| **观测单元** | 表格记录 |
| **总记录数** | 168条 |
| **字段数** | 8个（3个数值型、5个分类型、0个日期时间型） |
| **训练集划分** | 134条 |
| **测试集划分** | 33条 |
| **地理覆盖范围** | 莫桑比克（MOZ） |
| **发布方** | 世界粮食计划署（WFP）高级灾害分析与制图部门 |
| **HDX平台最后更新时间** | 2025年11月24日 |

---

## 字段说明

### 人口统计类字段
- `pop_60_kmh`：取值范围0.0–1923985.0
- `pop_90_kmh`：取值范围0.0–472057.0

### 标识符/元数据类字段
- `unnamed_0`：取值范围0.0–187.0
- `adm0_name`：取值包括莫桑比克、斯威士兰、南非
- `adm1_name`：取值包括曼齐尼、希塞卢韦尼、霍霍
- `adm2_name`：取值包括---、栋多、马马查
- `esa_source`：取值为HDX，另有1个其他字段

---

## 快速上手示例
python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-mozambique-cyclone-1001053")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据结构
| 字段名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `unnamed_0` | int64 | 0.0% | 0.0 – 187.0（均值91.8274） |
| `adm0_name` | 字符串（object） | 0.0% | 莫桑比克、斯威士兰、南非 |
| `adm1_name` | 字符串（object） | 0.0% | 曼齐尼、希塞卢韦尼、霍霍 |
| `adm2_name` | 字符串（object） | 0.0% | ---、栋多、马马查 |
| `pop_60_kmh` | int64 | 0.0% | 0.0 – 1923985.0（均值160311.0536） |
| `pop_90_kmh` | int64 | 0.0% | 0.0 – 472057.0（均值8122.5179） |
| `esa_source` | 字符串（object） | 0.0% | HDX |
| `esa_processed` | 字符串（object） | 0.0% | 2026-04-06 |

---

## 数值型字段统计摘要
| 字段名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `unnamed_0` | 0.0 | 187.0 | 91.8274 | 91.5 |
| `pop_60_kmh` | 0.0 | 1923985.0 | 160311.0536 | 40792.0 |
| `pop_90_kmh` | 0.0 | 472057.0 | 8122.5179 | 0.0 |

---

## 数据整理流程
原始数据通过CKAN API（CKAN API）从HDX平台下载，并转换为Parquet格式（Parquet）。所有字段名均转为小写并标准化为蛇形命名法（snake_case）。将常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。采用固定随机种子（42）将数据集按80/20的比例划分为训练集与测试集，并以Snappy压缩（Snappy）的Parquet格式存储。

---

## 数据集局限性
- 本数据源自世界粮食计划署（WFP）高级灾害分析与制图部门，未经过欧洲空间局（European Space Agency, ESA）的独立验证。
- 自动化清洗流程无法修正原始数据集中的错报值、定义不一致或采样偏差问题。
- 如需了解发布方的方法论说明与注意事项，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/mozambique-cyclone-1001053)。

---

## 引用格式
bibtex
@dataset{hdx_africa_mozambique_cyclone_1001053,
title = {莫桑比克：2024年3月气旋与热带风暴},
author = {世界粮食计划署（WFP）高级灾害分析与制图部门},
year = {2025},
url = {https://data.humdata.org/dataset/mozambique-cyclone-1001053},
note = {由Electric Sheep Africa重新打包以适配机器学习应用 (https://huggingface.co/electricsheepafrica)}
}

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施平台，尼日利亚拉各斯。*