electricsheepafrica/africa-ken-climate-trace

--- 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: - tabular-classification - tabular-regression task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - climate-weather - environment - points-of-interest-poi - ken pretty_name: "Kenya: Greenhouse Gas and Air Pollutant Emissions" dataset_info: splits: - name: train num_examples: 32560 - name: test num_examples: 8140 --- # Kenya: Greenhouse Gas and Air Pollutant Emissions **Publisher:** Climate TRACE · **Source:** [HDX](https://data.humdata.org/dataset/ken-climate-trace) · **License:** `cc-by` · **Updated:** 2026-03-30 --- ## Abstract Climate TRACE is a non-profit coalition of organizations building a timely, open, and accessible inventory of exactly where greenhouse gas emissions are coming from. Climate TRACE estimates greenhouse gas (GHG) and air pollutant emissions for over 2.7 million sources (from over 744 million assets), and every single country globally. The Climate TRACE emissions inventory includes: - Annual country-level emissions by sub-sector and by gas beginning in 2015 - Monthly source-level emissions by sub-sector and gas beginning in 2021 and confidence - Emissions source ownership where and when available. Each row in this dataset represents time-series observations. Data was last updated on HDX on 2026-03-30. Geographic scope: **KEN**. *Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).* --- ## Dataset Characteristics | | | |---|---| | **Domain** | Climate and environment | | **Unit of observation** | Time-series observations | | **Rows (total)** | 40,700 | | **Columns** | 13 (4 numeric, 9 categorical, 0 datetime) | | **Train split** | 32,560 rows | | **Test split** | 8,140 rows | | **Geographic scope** | KEN | | **Publisher** | Climate TRACE | | **HDX last updated** | 2026-03-30 | --- ## Variables **Geographic** — `year` (range 2024.0–2026.0), `emissionsquantity` (range 0.0–172382.649). **Temporal** — `month` (range 1.0–12.0). **Identifier / Metadata** — `full_name` (Kenya, Mombasa County, KEN, Kwale County, KEN), `id` (KEN, KEN.28_1, KEN.19_1), `level_0_id` (KEN), `level_1_id` (KEN.28_1, KEN.19_1, KEN.17_1), `name` (Kenya, Mombasa County, Kwale County) and 2 others. **Other** — `level` (range 0.0–1.0), `sector` (agriculture, waste, transportation), `gas` (ch4). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-ken-climate-trace") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `full_name` | object | 0.0% | Kenya, Mombasa County, KEN, Kwale County, KEN | | `id` | object | 0.0% | KEN, KEN.28_1, KEN.19_1 | | `level` | int64 | 0.0% | 0.0 – 1.0 (mean 0.9768) | | `level_0_id` | object | 0.0% | KEN | | `level_1_id` | object | 2.3% | KEN.28_1, KEN.19_1, KEN.17_1 | | `name` | object | 0.0% | Kenya, Mombasa County, Kwale County | | `year` | int64 | 0.0% | 2024.0 – 2026.0 (mean 2024.6156) | | `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.6754) | | `sector` | object | 0.0% | agriculture, waste, transportation | | `gas` | object | 0.0% | ch4 | | `emissionsquantity` | float64 | 0.0% | 0.0 – 172382.649 (mean 459.0062) | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-04 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `level` | 0.0 | 1.0 | 0.9768 | 1.0 | | `year` | 2024.0 | 2026.0 | 2024.6156 | 2025.0 | | `month` | 1.0 | 12.0 | 6.6754 | 7.0 | | `emissionsquantity` | 0.0 | 172382.649 | 459.0062 | 0.176 | --- ## 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) with >80% missing values were removed: `level_2_id`. 40,996 exact duplicate rows were removed. 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 Climate TRACE 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/ken-climate-trace) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_ken_climate_trace, title = {Kenya: Greenhouse Gas and Air Pollutant Emissions}, author = {Climate TRACE}, year = {2026}, url = {https://data.humdata.org/dataset/ken-climate-trace}, 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: - 无注释 language_creators: - 采集所得 language: - 英语 license: CC BY 4.0 multilinguality: - 单语言 size_categories: - 10000 < 样本数 < 100000 source_datasets: - 原始数据集 task_categories: - 表格分类 - 表格回归 task_ids: [] tags: - 非洲 - 人道主义 - HDX - Electric Sheep Africa - 气候与天气 - 环境 - 兴趣点（POI） - 肯尼亚 pretty_name: "肯尼亚：温室气体与空气污染物排放" dataset_info: splits: - name: train num_examples: 32560 - name: test num_examples: 8140 --- # 肯尼亚：温室气体与空气污染物排放数据集 **发布方**：气候追踪（Climate TRACE） · **来源**：[HDX](https://data.humdata.org/dataset/ken-climate-trace) · **许可协议**：`CC BY 4.0` · **更新时间**：2026-03-30 --- ## 摘要 气候追踪（Climate TRACE）是一个由多家机构组成的非营利联盟，旨在构建及时、开放且可获取的温室气体排放源精准清单。该联盟基于全球超过7.44亿个资产点，估算了全球所有国家超过270万个排放源的温室气体（GHG）与空气污染物排放量。 气候追踪的排放清单包含以下内容： - 2015年起按子行业与气体类型划分的国家级年度排放量数据 - 2021年起按子行业、气体类型划分的排放源级月度排放量数据及置信度信息 - 可获取的排放源权属信息 本数据集的每一行均代表时序观测数据。该数据集最后一次在HDX平台更新的时间为2026-03-30，地理覆盖范围为**肯尼亚（KEN）**。 *由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式（Parquet）。* --- ## 数据集特征 | | | |---|---| | **领域** | 气候与环境 | | **观测单元** | 时序观测数据 | | **总行数** | 40700 | | **列数** | 13列（4个数值列、9个分类列、0个日期时间列） | | **训练集划分** | 32560行 | | **测试集划分** | 8140行 | | **地理覆盖范围** | 肯尼亚（KEN） | | **发布方** | 气候追踪（Climate TRACE） | | **HDX平台最后更新时间** | 2026-03-30 | --- ## 变量说明 **地理相关变量**：`year`（取值范围2024.0–2026.0）、`emissionsquantity`（取值范围0.0–172382.649）。 **时间相关变量**：`month`（取值范围1.0–12.0）。 **标识符/元数据变量**：`full_name`（取值如肯尼亚、蒙巴萨郡、肯尼亚（KEN）、夸莱郡、肯尼亚（KEN））、`id`（取值如KEN、KEN.28_1、KEN.19_1）、`level_0_id`（取值为KEN）、`level_1_id`（取值如KEN.28_1、KEN.19_1、KEN.17_1）、`name`（取值如肯尼亚、蒙巴萨郡、夸莱郡）及另外2个变量。 **其他变量**：`level`（取值范围0.0–1.0）、`sector`（取值为农业、废弃物处理、交通运输）、`gas`（取值为ch4）。 --- ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-ken-climate-trace") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据结构 | 列名 | 数据类型 | 空值占比 | 取值范围/示例值 | |---|---|---|---| | `full_name` | 对象类型（object） | 0.0% | 取值如肯尼亚、蒙巴萨郡、肯尼亚（KEN）、夸莱郡、肯尼亚（KEN） | | `id` | 对象类型（object） | 0.0% | 取值如KEN、KEN.28_1、KEN.19_1 | | `level` | 64位整数类型（int64） | 0.0% | 取值范围0.0–1.0（均值0.9768） | | `level_0_id` | 对象类型（object） | 0.0% | 取值为KEN | | `level_1_id` | 对象类型（object） | 2.3% | 取值如KEN.28_1、KEN.19_1、KEN.17_1 | | `name` | 对象类型（object） | 0.0% | 取值如肯尼亚、蒙巴萨郡、夸莱郡 | | `year` | 64位整数类型（int64） | 0.0% | 取值范围2024.0–2026.0（均值2024.6156） | | `month` | 64位整数类型（int64） | 0.0% | 取值范围1.0–12.0（均值6.6754） | | `sector` | 对象类型（object） | 0.0% | 取值为农业、废弃物处理、交通运输 | | `gas` | 对象类型（object） | 0.0% | 取值为ch4 | | `emissionsquantity` | 64位浮点数类型（float64） | 0.0% | 取值范围0.0–172382.649（均值459.0062） | | `esa_source` | 对象类型（object） | 0.0% | 取值为HDX | | `esa_processed` | 对象类型（object） | 0.0% | 取值为2026-04-04 | --- ## 数值统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `level` | 0.0 | 1.0 | 0.9768 | 1.0 | | `year` | 2024.0 | 2026.0 | 2024.6156 | 2025.0 | | `month` | 1.0 | 12.0 | 6.6754 | 7.0 | | `emissionsquantity` | 0.0 | 172382.649 | 459.0062 | 0.176 | --- ## 数据整理流程 原始数据通过CKAN应用程序编程接口（CKAN API）从HDX平台下载，并转换为Parquet格式（Parquet）。列名统一转为小写并标准化为蛇形命名法（snake_case）。常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。删除了1个缺失值占比超过80%的列：`level_2_id`。移除了40996条完全重复的行。使用固定随机种子（42）将数据集按80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式（Parquet）。 --- ## 局限性说明 - 数据源自气候追踪（Climate TRACE），尚未由Electric Sheep Africa（ESA）进行独立验证。 - 自动化清洗流程无法修正原始数据收集中的错误报告值、定义不一致或采样偏差问题。 - 请查阅[HDX原始数据集页面](https://data.humdata.org/dataset/ken-climate-trace)获取发布方提供的方法说明与免责声明。 --- ## 引用格式 bibtex @dataset{hdx_africa_ken_climate_trace, title = {Kenya: Greenhouse Gas and Air Pollutant Emissions}, author = {Climate TRACE}, year = {2026}, url = {https://data.humdata.org/dataset/ken-climate-trace}, 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。*