electricsheepafrica/africa-lso-climate-trace

--- annotations_creators: - no-annotation language_creators: - found language: - en license: cc-by-4.0 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 - climate-weather - environment - points-of-interest-poi - lso pretty_name: "Lesotho: Greenhouse Gas and Air Pollutant Emissions" dataset_info: splits: - name: train num_examples: 7080 - name: test num_examples: 1770 --- # Lesotho: Greenhouse Gas and Air Pollutant Emissions **Publisher:** Climate TRACE · **Source:** [HDX](https://data.humdata.org/dataset/lso-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: **LSO**. *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)** | 8,851 | | **Columns** | 13 (4 numeric, 9 categorical, 0 datetime) | | **Train split** | 7,080 rows | | **Test split** | 1,770 rows | | **Geographic scope** | LSO | | **Publisher** | Climate TRACE | | **HDX last updated** | 2026-03-30 | --- ## Variables **Geographic** — `year` (range 2024.0–2026.0), `emissionsquantity` (range 0.0–3286.2615). **Temporal** — `month` (range 1.0–12.0). **Identifier / Metadata** — `full_name` (Lesotho, Maseru District, LSO, Leribe District, LSO), `id` (LSO, LSO.5_1, LSO.3_1), `level_0_id` (LSO), `level_1_id` (LSO.5_1, LSO.3_1, LSO.2_1), `name` (Lesotho, Maseru District, Leribe District) and 2 others. **Other** — `level` (range 0.0–1.0), `sector` (agriculture, transportation, manufacturing), `gas` (ch4). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-lso-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% | Lesotho, Maseru District, LSO, Leribe District, LSO | | `id` | object | 0.0% | LSO, LSO.5_1, LSO.3_1 | | `level` | int64 | 0.0% | 0.0 – 1.0 (mean 0.905) | | `level_0_id` | object | 0.0% | LSO | | `level_1_id` | object | 9.5% | LSO.5_1, LSO.3_1, LSO.2_1 | | `name` | object | 0.0% | Lesotho, Maseru District, Leribe District | | `year` | int64 | 0.0% | 2024.0 – 2026.0 (mean 2024.6085) | | `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.7131) | | `sector` | object | 0.0% | agriculture, transportation, manufacturing | | `gas` | object | 0.0% | ch4 | | `emissionsquantity` | float64 | 0.0% | 0.0 – 3286.2615 (mean 52.2056) | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-05 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `level` | 0.0 | 1.0 | 0.905 | 1.0 | | `year` | 2024.0 | 2026.0 | 2024.6085 | 2025.0 | | `month` | 1.0 | 12.0 | 6.7131 | 7.0 | | `emissionsquantity` | 0.0 | 3286.2615 | 52.2056 | 0.0577 | --- ## 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`. 9,871 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/lso-climate-trace) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_lso_climate_trace, title = {Lesotho: Greenhouse Gas and Air Pollutant Emissions}, author = {Climate TRACE}, year = {2026}, url = {https://data.humdata.org/dataset/lso-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: - 现有公开资源采集 language: - 英语 license: CC BY 4.0 multilinguality: - 单语言 size_categories: - 1000 < 样本量 < 10000 source_datasets: - 原创数据集 task_categories: - 表格分类 - 表格回归 task_ids: - 无 tags: - 非洲 - 人道主义 - HDX - Electric Sheep Africa - 气候与气象 - 环境 - 兴趣点（POI，Points of Interest） - LSO pretty_name: "莱索托：温室气体与空气污染物排放" dataset_info: splits: - name: 训练集 num_examples: 7080 - name: 测试集 num_examples: 1770 # 莱索托：温室气体与空气污染物排放 **发布方：Climate TRACE · **来源：[HDX（Humanitarian Data Exchange）](https://data.humdata.org/dataset/lso-climate-trace) · **许可协议：`cc-by` · **更新时间：2026-03-30 --- ## 摘要 Climate TRACE是由多家机构组成的非营利性联盟，致力于构建及时、开放且易于访问的温室气体排放源精准清单。该联盟对全球所有国家的超270万个排放源（源自7.44亿余个资产）的温室气体（GHG，Greenhouse Gas）与空气污染物排放量进行估算。 Climate TRACE排放清单涵盖： - 2015年起按子行业与气体类型划分的年度国家级排放量数据 - 2021年起按子行业与气体类型划分的月度排放源级排放量数据及置信度信息 - 可用情况下的排放源所有权信息。 本数据集的每一行均代表一条时间序列观测数据。该数据集最后一次在HDX平台更新的时间为2026年3月30日，地理覆盖范围：**莱索托（LSO）**。 *本数据集已由[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** | 时间序列观测数据 | | **总样本行数** | 8,851 | | **列数** | 13（4个数值型、9个分类型、0个日期时间型） | | **训练集划分** | 7,080条数据 | | **测试集划分** | 1,770条数据 | | **地理覆盖范围** | 莱索托（LSO） | | **发布方** | Climate TRACE | | **HDX平台最后更新时间** | 2026-03-30 | --- ## 变量说明 **地理类变量**：`year`（取值范围2024.0–2026.0）、`emissionsquantity`（取值范围0.0–3286.2615）。 **时间类变量**：`month`（取值范围1.0–12.0）。 **标识符与元数据变量**：`full_name`（莱索托、马塞卢区、莱索托、莱里贝区、莱索托）、`id`（LSO、LSO.5_1、LSO.3_1）、`level_0_id`（LSO）、`level_1_id`（LSO.5_1、LSO.3_1、LSO.2_1）、`name`（莱索托、马塞卢区、莱里贝区）及另外2个变量。 **其他变量**：`level`（取值范围0.0–1.0）、`sector`（农业、交通运输、制造业）、`gas`（ch4）。 --- ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-lso-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` | 字符型（object） | 0.0% | 莱索托、马塞卢区、莱索托、莱里贝区、莱索托 | | `id` | 字符型（object） | 0.0% | LSO、LSO.5_1、LSO.3_1 | | `level` | 64位整型（int64） | 0.0% | 0.0 – 1.0（均值 0.905） | | `level_0_id` | 字符型（object） | 0.0% | LSO | | `level_1_id` | 字符型（object） | 9.5% | LSO.5_1、LSO.3_1、LSO.2_1 | | `name` | 字符型（object） | 0.0% | 莱索托、马塞卢区、莱里贝区 | | `year` | 64位整型（int64） | 0.0% | 2024.0 – 2026.0（均值 2024.6085） | | `month` | 64位整型（int64） | 0.0% | 1.0 – 12.0（均值 6.7131） | | `sector` | 字符型（object） | 0.0% | 农业、交通运输、制造业 | | `gas` | 字符型（object） | 0.0% | ch4 | | `emissionsquantity` | 64位浮点型（float64） | 0.0% | 0.0 – 3286.2615（均值 52.2056） | | `esa_source` | 字符型（object） | 0.0% | HDX | | `esa_processed` | 字符型（object） | 0.0% | 2026-04-05 | --- ## 数值型变量统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `level` | 0.0 | 1.0 | 0.905 | 1.0 | | `year` | 2024.0 | 2026.0 | 2024.6085 | 2025.0 | | `month` | 1.0 | 12.0 | 6.7131 | 7.0 | | `emissionsquantity` | 0.0 | 3286.2615 | 52.2056 | 0.0577 | --- ## 数据整理流程 原始数据通过CKAN API从HDX平台下载，并转换为Parquet格式。对列名进行了小写转换与蛇形命名法标准化处理。将常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。删除了1列缺失值占比超过80%的字段：`level_2_id`。移除了9,871条完全重复的数据。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，并保存为Snappy压缩格式的Parquet文件。 --- ## 数据集局限性 - 数据源自Climate TRACE，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收集中的错报值、定义不一致或抽样偏差问题。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/lso-climate-trace)以获取发布方提供的方法说明与注意事项。 --- ## 引用格式 bibtex @dataset{hdx_africa_lso_climate_trace, title = {Lesotho: Greenhouse Gas and Air Pollutant Emissions}, author = {Climate TRACE}, year = {2026}, url = {https://data.humdata.org/dataset/lso-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。*