electricsheepafrica/africa-zwe-ibtracs-tropical-storm-tracks

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- cyclones-hurricanes-typhoons
- hxl
- zwe
pretty_name: "Zimbabwe: IBTrACS Storm Tracks"
dataset_info:
splits:
- name: train
num_examples: 44840
- name: test
num_examples: 11210
---

# Zimbabwe: IBTrACS Storm Tracks

**Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/zwe-ibtracs-tropical-storm-tracks) · **License:** `cc-by-igo` · **Updated:** 2026-02-24

---

## Abstract

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons.

Fields available:
SID: A unique storm identifier (SID) assigned by IBTrACS algorithm.
ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss)
BASIN: Basin of the current storm position
SUBBASIN: Sub-basin of the current storm position
NATURE: Type of storm (a combination of the various types from the available sources)
NUMBER: Number of the storm for the year (restarts at 1 for each year
LAT: Mean position - latitude (a combination of the available positions)
LON: Mean position - longitude (a combination of the available positions)
WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency
WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

Each row in this dataset represents geolocated point observations. Temporal coverage is indicated by the `iso_time` column(s). Geographic scope: **ZWE**.

*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)** | 56,050 |
| **Columns** | 12 (3 numeric, 8 categorical, 1 datetime) |
| **Train split** | 44,840 rows |
| **Test split** | 11,210 rows |
| **Geographic scope** | ZWE |
| **Publisher** | HDX |
| **HDX last updated** | 2026-02-24 |

---

## Variables

**Geographic** — `iso_time`, `lat` (range -47.4–-3.0), `lon` (range 11.3–119.1).

**Outcome / Measurement** — `number` (range 1.0–145.0).

**Identifier / Metadata** — `sid` (2023036S12117, 2000032S11116, 2008033S11083), `esa_source` (HDX), `esa_processed` (2026-04-07).

**Other** — `basin` (South Indian, ), `subbasin` (Missing, Western Australia, ), `nature` (Tropical, Not reported, Mixture(contradicting report from different agencies)), `wmo_wind` ( , 20, 25), `wmo_pres` ( , 1000, 997).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-zwe-ibtracs-tropical-storm-tracks")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `sid` | object | 0.0% | 2023036S12117, 2000032S11116, 2008033S11083 |
| `number` | float64 | 0.0% | 1.0 – 145.0 (mean 26.5951) |
| `basin` | object | 0.0% | South Indian, |
| `subbasin` | object | 0.0% | Missing, Western Australia, |
| `iso_time` | datetime64[ns] | 0.0% | |
| `nature` | object | 0.0% | Tropical, Not reported, Mixture(contradicting report from different agencies) |
| `lat` | float64 | 0.0% | -47.4 – -3.0 (mean -18.821) |
| `lon` | float64 | 0.0% | 11.3 – 119.1 (mean 53.2592) |
| `wmo_wind` | object | 0.0% | , 20, 25 |
| `wmo_pres` | object | 0.0% | , 1000, 997 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-07 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `number` | 1.0 | 145.0 | 26.5951 | 12.0 |
| `lat` | -47.4 | -3.0 | -18.821 | -18.3 |
| `lon` | 11.3 | 119.1 | 53.2592 | 52.4 |

---

## 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`. 4 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 HDX 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/zwe-ibtracs-tropical-storm-tracks) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_zwe_ibtracs_tropical_storm_tracks,
title = {Zimbabwe: IBTrACS Storm Tracks},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/zwe-ibtracs-tropical-storm-tracks},
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.*

---
annotations_creators:
- 无标注
language_creators:
- 采集自现有数据
language:
- 英语
license: cc-by-4.0
multilinguality:
- 单语言
size_categories:
- 10000 < n < 100000
source_datasets:
- 原创数据集
task_categories:
- 其他任务类别
task_ids: []
tags:
- 非洲
- 人道主义
- HDX
- electric-sheep-africa
- 气旋、飓风、台风
- HXL
- ZWE
pretty_name: "津巴布韦：IBTrACS风暴路径"
---

# 津巴布韦：IBTrACS风暴路径

**发布方：** HDX · **来源：** [HDX](https://data.humdata.org/dataset/zwe-ibtracs-tropical-storm-tracks) · **许可协议：** `cc-by-igo` · **更新时间：** 2026-02-24

---

## 摘要

国际最佳路径档案气候管理项目（International Best Track Archive for Climate Stewardship, IBTrACS）是当前可获取的最完整的全球热带气旋数据集。该项目整合多机构的最新及历史热带气旋数据，构建了统一的公开最佳路径数据集，可有效提升不同机构间的比对效率。

可用字段如下：
SID：IBTrACS算法分配的唯一风暴标识符（SID）
ISO_TIME：采用ISO 8601格式的观测时间（YYYY-MM-DD hh:mm:ss）
BASIN：当前风暴所处的洋盆
SUBBASIN：当前风暴所处的子洋盆
NATURE：风暴类型（整合各来源的不同类型信息）
NUMBER：当年风暴编号（每年从1重新开始计数）
LAT：平均位置纬度（整合所有可用位置信息）
LON：平均位置经度（整合所有可用位置信息）
WMO_WIND：由负责世界气象组织（World Meteorological Organization, WMO）的机构指定的最大持续风速
WMO_PRES：由负责WMO的机构指定的最低中心气压

本数据集每一行代表一条地理定位的点观测数据。时间覆盖范围由`iso_time`列标注。地理覆盖范围：**ZWE（津巴布韦）**。

*本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式。*

---

## 数据集特征

| | |
|---|---|
| **领域** | 气候与环境 |
| **观测单元** | 地理定位点观测数据 |
| **总行数** | 56,050 |
| **列数** | 12（3个数值型、8个分类型、1个日期时间型） |
| **训练集划分** | 44,840 条数据 |
| **测试集划分** | 11,210 条数据 |
| **地理覆盖范围** | ZWE（津巴布韦） |
| **发布方** | HDX |
| **HDX最后更新时间** | 2026-02-24 |

---

## 变量说明

**地理类变量** — `iso_time`、`lat`（取值范围：-47.4~-3.0）、`lon`（取值范围：11.3~119.1）。
**结果/测量类变量** — `number`（取值范围：1.0~145.0）。
**标识符/元数据类变量** — `sid`（示例值：2023036S12117、2000032S11116、2008033S11083）、`esa_source`（HDX）、`esa_processed`（2026-04-07）。
**其他类变量** — `basin`（南印度洋）、`subbasin`（缺失、西澳大利亚海域）、`nature`（热带气旋、未报告、混合（不同机构报告存在矛盾））、`wmo_wind`（示例值：20、25）、`wmo_pres`（示例值：1000、997）。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-zwe-ibtracs-tropical-storm-tracks")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据模式

| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `sid` | 对象类型 | 0.0% | 2023036S12117、2000032S11116、2008033S11083 |
| `number` | float64 | 0.0% | 1.0~145.0（平均值：26.5951） |
| `basin` | 对象类型 | 0.0% | 南印度洋 |
| `subbasin` | 对象类型 | 0.0% | 缺失、西澳大利亚海域 |
| `iso_time` | datetime64[ns] | 0.0% | 无 |
| `nature` | 对象类型 | 0.0% | 热带气旋、未报告、混合（不同机构报告存在矛盾） |
| `lat` | float64 | 0.0% | -47.4~-3.0（平均值：-18.821） |
| `lon` | float64 | 0.0% | 11.3~119.1（平均值：53.2592） |
| `wmo_wind` | 对象类型 | 0.0% | 20、25 |
| `wmo_pres` | 对象类型 | 0.0% | 1000、997 |
| `esa_source` | 对象类型 | 0.0% | HDX |
| `esa_processed` | 对象类型 | 0.0% | 2026-04-07 |

---

## 数值型变量统计摘要

| 列名 | 最小值 | 最大值 | 平均值 | 中位数 |
|---|---|---|---|---|
| `number` | 1.0 | 145.0 | 26.5951 | 12.0 |
| `lat` | -47.4 | -3.0 | -18.821 | -18.3 |
| `lon` | 11.3 | 119.1 | 53.2592 | 52.4 |

---

## 数据整理流程

原始数据通过CKAN API从HDX下载，并转换为Parquet格式。列名全部转为小写，并统一采用蛇形命名法（snake_case）。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。根据解析成功率（阈值>85%），将4列从字符串类型转换为数值型或日期时间型。本数据集采用固定随机种子（42）以80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式。

---

## 局限性

- 数据来源于HDX，未经过Electric Sheep Africa的独立验证。
- 自动化清洗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。
- 如需查看发布方的方法说明与注意事项，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/zwe-ibtracs-tropical-storm-tracks)。

---

## 引用格式

bibtex
@dataset{hdx_africa_zwe_ibtracs_tropical_storm_tracks,
title = {津巴布韦：IBTrACS风暴路径},
author = {HDX},
year = {2026},
url = {https://data.humdata.org/dataset/zwe-ibtracs-tropical-storm-tracks},
note = {由Electric Sheep Africa（https://huggingface.co/electricsheepafrica）重新打包以适配机器学习场景}
}

---

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