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

--- 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: - other task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - cyclones-hurricanes-typhoons - hxl - cog pretty_name: "Congo: IBTrACS Storm Tracks" dataset_info: splits: - name: train num_examples: 412 - name: test num_examples: 103 --- # Congo: IBTrACS Storm Tracks **Publisher:** HDX · **Source:** [HDX](https://data.humdata.org/dataset/cog-ibtracs-tropical-storm-tracks) · **License:** `cc-by-igo` · **Updated:** 2025-05-23 --- ## 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: **COG**. *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)** | 516 | | **Columns** | 12 (3 numeric, 8 categorical, 1 datetime) | | **Train split** | 412 rows | | **Test split** | 103 rows | | **Geographic scope** | COG | | **Publisher** | HDX | | **HDX last updated** | 2025-05-23 | --- ## Variables **Geographic** — `iso_time`, `lat` (range -23.8–-10.5), `lon` (range 11.3–115.5). **Outcome / Measurement** — `number` (range 7.0–120.0). **Identifier / Metadata** — `sid` (2000032S11116, 1977025S11064, 2020355S11065), `esa_source` (HDX), `esa_processed` (2026-04-07). **Other** — `basin` (South Indian, ), `subbasin` (Missing, Western Australia, ), `nature` (Tropical, Not reported, Disturbance), `wmo_wind` ( , 40, 25), `wmo_pres` ( , 1000, 990). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-cog-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% | 2000032S11116, 1977025S11064, 2020355S11065 | | `number` | float64 | 0.2% | 7.0 – 120.0 (mean 34.5553) | | `basin` | object | 0.0% | South Indian, | | `subbasin` | object | 0.0% | Missing, Western Australia, | | `iso_time` | datetime64[ns] | 0.2% | | | `nature` | object | 0.0% | Tropical, Not reported, Disturbance | | `lat` | float64 | 0.2% | -23.8 – -10.5 (mean -17.6245) | | `lon` | float64 | 0.2% | 11.3 – 115.5 (mean 54.9819) | | `wmo_wind` | object | 0.0% | , 40, 25 | | `wmo_pres` | object | 0.0% | , 1000, 990 | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-07 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `number` | 7.0 | 120.0 | 34.5553 | 9.0 | | `lat` | -23.8 | -10.5 | -17.6245 | -18.8 | | `lon` | 11.3 | 115.5 | 54.9819 | 52.6 | --- ## 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/cog-ibtracs-tropical-storm-tracks) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_cog_ibtracs_tropical_storm_tracks, title = {Congo: IBTrACS Storm Tracks}, author = {HDX}, year = {2025}, url = {https://data.humdata.org/dataset/cog-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: - 获取型 language: - 英语 license: CC-BY-4.0 multilinguality: - 单语言 size_categories: - n<1K source_datasets: - 原创数据集 task_categories: - 其他 task_ids: [] tags: - 非洲 - 人道主义 - HDX - electric-sheep-africa - 气旋、飓风、台风 - HXL - COG pretty_name: "刚果：IBTrACS风暴路径数据集" dataset_info: splits: - name: train num_examples: 412 - name: test num_examples: 103 --- # 刚果：IBTrACS风暴路径数据集 **发布方**：HDX · **来源**：[HDX](https://data.humdata.org/dataset/cog-ibtracs-tropical-storm-tracks) · **许可证**：`cc-by-4.0` · **更新时间**：2025-05-23 --- ## 摘要 国际最佳路径气候管理项目（International Best Track Archive for Climate Stewardship, IBTrACS）是目前公开的最完整的全球热带气旋数据集。该项目整合了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，以提升跨机构间的比对效率。 可用字段： - SID：IBTrACS算法分配的唯一风暴标识符（SID） - ISO_TIME：采用ISO格式的观测时间（YYYY-MM-DD hh:mm:ss） - BASIN：当前风暴位置所属的大洋区域 - SUBBASIN：当前风暴位置所属的次级大洋区域 - NATURE：风暴类型（整合各来源提供的多种类型） - NUMBER：当年风暴编号（每年从1重新计数） - LAT：平均位置纬度（整合各来源的观测位置） - LON：平均位置经度（整合各来源的观测位置） - WMO_WIND：世界气象组织（World Meteorological Organization, WMO）指定的最大持续风速 - WMO_PRES：世界气象组织指定的最低中心气压 本数据集的每一行均代表一条地理定位点观测数据。时间覆盖范围由`iso_time`列标注。地理覆盖范围：**COG**。 *本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的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** | 516 | | **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** | 412条数据 | | **测试集划分** | 103条数据 | | **地理覆盖范围** | COG | | **发布方** | HDX | | **HDX最后更新时间** | 2025-05-23 | --- ## 变量 **地理相关字段**：`iso_time`、`lat`（取值范围 -23.8–-10.5）、`lon`（取值范围 11.3–115.5）。 **结果/测量字段**：`number`（取值范围 7.0–120.0）。 **标识符/元数据字段**：`sid`（示例值：2000032S11116、1977025S11064、2020355S11065）、`esa_source`（HDX）、`esa_processed`（2026-04-07）。 **其他字段**：`basin`（南印度洋等）、`subbasin`（缺失、西澳大利亚海域等）、`nature`（热带气旋、未报告、扰动）、`wmo_wind`（示例值：空、40、25）、`wmo_pres`（示例值：空、1000、990）。 --- ## 快速开始 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-cog-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 | 空值占比 | 取值范围/示例值 | |---|---|---|---| | `sid` | object | 0.0% | 2000032S11116、1977025S11064、2020355S11065 | | `number` | float64 | 0.2% | 7.0 – 120.0（平均值 34.5553） | | `basin` | object | 0.0% | 南印度洋等 | | `subbasin` | object | 0.0% | 缺失、西澳大利亚海域等 | | `iso_time` | datetime64[ns] | 0.2% | - | | `nature` | object | 0.0% | 热带气旋、未报告、扰动 | | `lat` | float64 | 0.2% | -23.8 – -10.5（平均值 -17.6245） | | `lon` | float64 | 0.2% | 11.3 – 115.5（平均值 54.9819） | | `wmo_wind` | object | 0.0% | 空、40、25 | | `wmo_pres` | object | 0.0% | 空、1000、990 | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-07 | --- ## 数值型字段统计摘要 | 列名 | 最小值 | 最大值 | 平均值 | 中位数 | |---|---|---|---|---| | `number` | 7.0 | 120.0 | 34.5553 | 9.0 | | `lat` | -23.8 | -10.5 | -17.6245 | -18.8 | | `lon` | 11.3 | 115.5 | 54.9819 | 52.6 | --- ## 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。列名统一转换为小写并标准化为蛇形命名法。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`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。数据集采用固定随机种子（42）按80/20比例划分为训练集与测试集，并以Snappy压缩格式保存为Parquet文件。 --- ## 局限性 - 数据源自HDX，未由Electric Sheep Africa进行独立验证。 - 自动化清洗流程无法修正原始数据集中的错误报告值、定义不一致或采样偏差问题。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/cog-ibtracs-tropical-storm-tracks)查看发布方提供的方法说明与注意事项。 --- ## 引用 bibtex @dataset{hdx_africa_cog_ibtracs_tropical_storm_tracks, title = {Congo: IBTrACS Storm Tracks}, author = {HDX}, year = {2025}, url = {https://data.humdata.org/dataset/cog-ibtracs-tropical-storm-tracks}, note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)} } --- *[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。*