electricsheepafrica/africa-mrt-rainfall-subnational
收藏资源简介：
--- 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-regression - other task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - climate-weather - environment - mrt pretty_name: "Mauritania: Rainfall Indicators at Subnational Level" dataset_info: splits: - name: train num_examples: 75632 - name: test num_examples: 18908 --- # Mauritania: Rainfall Indicators at Subnational Level **Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/mrt-rainfall-subnational) · **License:** `cc-by` · **Updated:** 2026-04-03 --- ## Abstract This dataset contains dekadal rainfall indicators, computed from Climate Hazards Group InfraRed Precipitation satellite imagery with insitu Station data (CHIRPS) version 2 and the CHIRPS-GEFS short term rainfall forecasts, aggregated by subnational administrative units. Included indicators are (for each dekad): - 10 day rainfall [mm] (`rfh`) - rainfall 1-month rolling aggregation [mm] (`r1h`) - rainfall 3-month rolling aggregation [mm] (`r3h`) - rainfall long term average [mm] (`rfh_avg`) - rainfall 1-month rolling aggregation long term average [mm] (`r1h_avg`) - rainfall 3-month rolling aggregation long term average [mm] (`r3h_avg`) - rainfall anomaly [%] (`rfq`) - rainfall 1-month anomaly [%] (`r1q`) - rainfall 3-month anomaly [%] (`r3q`) The administrative units used for aggregation are based on WFP data and contain a Pcode reference attributed to each unit. The number of input pixels used to create the aggregates, is provided in the `n_pixels` column. Finally, the `type` column indicates if the value is based on a forecast, a preliminary or a final product. Forecasts are issued on the 6th, 16th, and 26th of each month for the upcoming 10-day period (dekad), then updated with improved versions on the 1st, 11th, and 21st. Preliminary observations replace the previous dekad’s forecast on the 3rd, 13th, and 23rd, and are later replaced by final observations—published mid-month (13th or 23rd)—covering all three dekads of the prior month. Please find a summary below: Publication Day: Forecast type, Covers (Dekad) - 1st: Updated forecast, 1–10 of the same month - 6th: Initial forecast, 11–20 of the same month - 11th: Updated forecast, 1–10 of the same month - 16th: Initial forecast, 21–end of the same month - 21st: Updated forecast, 11–20 of the same month - 26th: Initial forecast, 1–10 of the following month For more on CHIRPS-GEFS forecasts, see: https://www.chc.ucsb.edu/data/chirps-gefs For further details, please see the methodology section. Each row in this dataset represents time-series observations. Temporal coverage is indicated by the `date` column(s). Geographic scope: **MRT**. *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)** | 94,540 | | **Columns** | 17 (12 numeric, 4 categorical, 1 datetime) | | **Train split** | 75,632 rows | | **Test split** | 18,908 rows | | **Geographic scope** | MRT | | **Publisher** | WFP - World Food Programme | | **HDX last updated** | 2026-04-03 | --- ## Variables **Geographic** — `n_pixels` (range 9.0–9142.0). **Temporal** — `date`. **Identifier / Metadata** — `adm_id` (range 2004.0–1001796.0), `pcode` (MR07, MR055, MR051), `esa_source` (HDX), `esa_processed` (2026-04-06). **Other** — `adm_level` (range 1.0–2.0), `rfh` (range 0.0–155.679), `rfh_avg` (range 0.0–63.7915), `r1h` (range 0.0–306.679), `r1h_avg` (range 0.0–164.9599) and 6 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-mrt-rainfall-subnational") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `date` | datetime64[ns] | 0.0% | | | `adm_level` | int64 | 0.0% | 1.0 – 2.0 (mean 1.7759) | | `adm_id` | int64 | 0.0% | 2004.0 – 1001796.0 (mean 777688.9655) | | `pcode` | object | 0.0% | MR07, MR055, MR051 | | `n_pixels` | float64 | 0.0% | 9.0 – 9142.0 (mean 1239.4828) | | `rfh` | float64 | 0.0% | 0.0 – 155.679 (mean 4.7569) | | `rfh_avg` | float64 | 0.0% | 0.0 – 63.7915 (mean 4.8619) | | `r1h` | float64 | 0.1% | 0.0 – 306.679 (mean 14.2878) | | `r1h_avg` | float64 | 0.1% | 0.0 – 164.9599 (mean 14.6033) | | `r3h` | float64 | 0.5% | 0.0 – 558.2675 (mean 43.016) | | `r3h_avg` | float64 | 0.5% | 0.0 – 366.7362 (mean 43.9642) | | `rfq` | float64 | 0.0% | 15.1638 – 403.1104 (mean 99.6404) | | `r1q` | float64 | 0.1% | 16.2376 – 343.4125 (mean 99.5026) | | `r3q` | float64 | 0.5% | 17.0062 – 310.818 (mean 99.2755) | | `version` | object | 0.0% | final, prelim, forecast | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-06 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `adm_level` | 1.0 | 2.0 | 1.7759 | 2.0 | | `adm_id` | 2004.0 | 1001796.0 | 777688.9655 | 1001767.5 | | `n_pixels` | 9.0 | 9142.0 | 1239.4828 | 432.0 | | `rfh` | 0.0 | 155.679 | 4.7569 | 0.3529 | | `rfh_avg` | 0.0 | 63.7915 | 4.8619 | 0.3407 | | `r1h` | 0.0 | 306.679 | 14.2878 | 1.3216 | | `r1h_avg` | 0.0 | 164.9599 | 14.6033 | 1.3986 | | `r3h` | 0.0 | 558.2675 | 43.016 | 7.2387 | | `r3h_avg` | 0.0 | 366.7362 | 43.9642 | 7.8522 | | `rfq` | 15.1638 | 403.1104 | 99.6404 | 99.9914 | | `r1q` | 16.2376 | 343.4125 | 99.5026 | 99.9325 | | `r3q` | 17.0062 | 310.818 | 99.2755 | 99.095 | --- ## 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) 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 WFP - World Food Programme 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/mrt-rainfall-subnational) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_mrt_rainfall_subnational, title = {Mauritania: Rainfall Indicators at Subnational Level}, author = {WFP - World Food Programme}, year = {2026}, url = {https://data.humdata.org/dataset/mrt-rainfall-subnational}, 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.*
--- 标注创建者： - 无标注 语言创建方式： - 公开采集 语言： - 英语 授权协议： - CC BY 4.0 多语言属性： - 单语言 样本规模区间： - 10000 < 样本量 < 100000 源数据集： - 原创数据集 任务分类： - 表格回归 - 其他 任务子项： - 无 标签： - 非洲 - 人道主义 - HDX（Humanitarian Data Exchange） - Electric Sheep Africa - 气候与天气 - 环境 - MRT（毛里塔尼亚） 友好名称："毛里塔尼亚：次国家级降雨指标数据集" 数据集信息： 划分： - 名称：训练集 样本数：75632 - 名称：测试集 样本数：18908 --- # 毛里塔尼亚：次国家级降雨指标数据集 **发布方**：WFP——世界粮食计划署（World Food Programme） · **数据来源**：[HDX](https://data.humdata.org/dataset/mrt-rainfall-subnational) · **授权协议**：`cc-by` · **更新时间**：2026-04-03 --- ## 摘要 本数据集包含旬度降雨指标，其计算基于气候灾害小组红外降水联合原位站数据（Climate Hazards Group InfraRed Precipitation with Station data，简称CHIRPS）版本2，以及CHIRPS-GEFS短期降雨预报数据，并按次国家级行政单元进行聚合。 包含的旬度指标如下（每旬）： - 10日降雨量（单位：毫米）(`rfh`) - 1个月滑动聚合降雨量（单位：毫米）(`r1h`) - 3个月滑动聚合降雨量（单位：毫米）(`r3h`) - 降雨量长期平均值（单位：毫米）(`rfh_avg`) - 1个月滑动聚合降雨量长期平均值（单位：毫米）(`r1h_avg`) - 3个月滑动聚合降雨量长期平均值（单位：毫米）(`r3h_avg`) - 降雨量距平百分比（单位：%）(`rfq`) - 1个月降雨量距平百分比（单位：%）(`r1q`) - 3个月降雨量距平百分比（单位：%）(`r3q`) 本次聚合使用的行政单元基于WFP数据，每个单元均配有Pcode标识码。用于生成聚合数据的输入像素数量将在`n_pixels`列中给出。此外，`version`列用于标识数据类型：预报数据、初步观测数据或最终观测数据。 预报于每月6日、16日、26日发布，覆盖未来10天（旬度）的降雨数据，并于每月1日、11日、21日更新为优化版本。 初步观测数据会在每月3日、13日、23日替换上一旬的预报数据，后续将由最终观测数据取代——最终观测数据于月中（13日或23日）发布，覆盖上月全部三个旬度。具体发布规则如下： | 发布日期 | 预报类型 | 覆盖旬度 | |---|---|---| | 1日 | 更新预报 | 当月1-10日 | | 6日 | 初始预报 | 当月11-20日 | | 11日 | 更新预报 | 当月1-10日 | | 16日 | 初始预报 | 当月21日至当月月末 | | 21日 | 更新预报 | 当月11-20日 | | 26日 | 初始预报 | 下月1-10日 | 如需了解更多CHIRPS-GEFS预报相关信息，请访问：https://www.chc.ucsb.edu/data/chirps-gefs 如需获取详细方法说明，请参阅对应方法学章节。 本数据集的每一行均代表时序观测数据，时间覆盖范围由`date`列标注。地理覆盖范围：**MRT（毛里塔尼亚）**。 *本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为机器学习可用的Parquet格式。* --- ## 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** | 94,540 | | **列数** | 17列（12列数值型、4列分类型、1列日期型） | | **训练集划分** | 75,632行 | | **测试集划分** | 18,908行 | | **地理覆盖范围** | MRT（毛里塔尼亚） | | **发布方** | WFP——世界粮食计划署 | | **HDX最后更新时间** | 2026-04-03 | --- ## 变量 **地理相关变量**：`n_pixels`（取值范围9.0–9142.0）。 **时序相关变量**：`date`。 **标识符与元数据**：`adm_id`（取值范围2004.0–1001796.0）、`pcode`（示例值：MR07、MR055、MR051）、`esa_source`（HDX）、`esa_processed`（2026-04-06）。 **其他变量**：`adm_level`（取值范围1.0–2.0）、`rfh`（取值范围0.0–155.679）、`rfh_avg`（取值范围0.0–63.7915）、`r1h`（取值范围0.0–306.679）、`r1h_avg`（取值范围0.0–164.9599）及另外6个变量。 --- ## 快速入门 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-mrt-rainfall-subnational") 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 | |---|---|---|---| | `date` | datetime64[ns] | 0.0% | | | `adm_level` | int64 | 0.0% | 1.0 – 2.0（均值1.7759） | | `adm_id` | int64 | 0.0% | 2004.0 – 1001796.0（均值777688.9655） | | `pcode` | object | 0.0% | MR07、MR055、MR051 | | `n_pixels` | float64 | 0.0% | 9.0 – 9142.0（均值1239.4828） | | `rfh` | float64 | 0.0% | 0.0 – 155.679（均值4.7569） | | `rfh_avg` | float64 | 0.0% | 0.0 – 63.7915（均值4.8619） | | `r1h` | float64 | 0.1% | 0.0 – 306.679（均值14.2878） | | `r1h_avg` | float64 | 0.1% | 0.0 – 164.9599（均值14.6033） | | `r3h` | float64 | 0.5% | 0.0 – 558.2675（均值43.016） | | `r3h_avg` | float64 | 0.5% | 0.0 – 366.7362（均值43.9642） | | `rfq` | float64 | 0.0% | 15.1638 – 403.1104（均值99.6404） | | `r1q` | float64 | 0.1% | 16.2376 – 343.4125（均值99.5026） | | `r3q` | float64 | 0.5% | 17.0062 – 310.818（均值99.2755） | | `version` | object | 0.0% | final（最终结果）、prelim（初步结果）、forecast（预报） | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-06 | --- ## 数值统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `adm_level` | 1.0 | 2.0 | 1.7759 | 2.0 | | `adm_id` | 2004.0 | 1001796.0 | 777688.9655 | 1001767.5 | | `n_pixels` | 9.0 | 9142.0 | 1239.4828 | 432.0 | | `rfh` | 0.0 | 155.679 | 4.7569 | 0.3529 | | `rfh_avg` | 0.0 | 63.7915 | 4.8619 | 0.3407 | | `r1h` | 0.0 | 306.679 | 14.2878 | 1.3216 | | `r1h_avg` | 0.0 | 164.9599 | 14.6033 | 1.3986 | | `r3h` | 0.0 | 558.2675 | 43.016 | 7.2387 | | `r3h_avg` | 0.0 | 366.7362 | 43.9642 | 7.8522 | | `rfq` | 15.1638 | 403.1104 | 99.6404 | 99.9914 | | `r1q` | 16.2376 | 343.4125 | 99.5026 | 99.9325 | | `r3q` | 17.0062 | 310.818 | 99.2755 | 99.095 | --- ## 数据整理 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蛇形命名法（snake_case）。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。基于解析成功率（阈值>85%），将1列从字符串类型转换为数值型或日期型。本数据集以固定随机种子（42）按80/20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 - 本数据源自WFP——世界粮食计划署，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、定义不一致或采样偏差问题。 - 如需了解发布方的方法学说明与免责条款，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/mrt-rainfall-subnational)。 --- ## 引用 bibtex @dataset{hdx_africa_mrt_rainfall_subnational, title = {毛里塔尼亚：次国家级降雨指标数据集}, author = {WFP——世界粮食计划署}, year = {2026}, url = {https://data.humdata.org/dataset/mrt-rainfall-subnational}, note = {由Electric Sheep Africa重新打包为机器学习可用格式（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。*
