electricsheepafrica/africa-tcd-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: - 100K<n<1M source_datasets: - original task_categories: - tabular-regression - other task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - climate-weather - environment - tcd pretty_name: "Chad: Rainfall Indicators at Subnational Level" dataset_info: splits: - name: train num_examples: 121272 - name: test num_examples: 30318 --- # Chad: Rainfall Indicators at Subnational Level **Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/tcd-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: **TCD**. *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)** | 151,590 | | **Columns** | 17 (12 numeric, 4 categorical, 1 datetime) | | **Train split** | 121,272 rows | | **Test split** | 30,318 rows | | **Geographic scope** | TCD | | **Publisher** | WFP - World Food Programme | | **HDX last updated** | 2026-04-03 | --- ## Variables **Geographic** — `n_pixels` (range 13.0–8372.0). **Temporal** — `date`. **Identifier / Metadata** — `adm_id` (range 900172.0–1003195.0), `pcode` (TCD0703, TCD2201, TCD19), `esa_source` (HDX), `esa_processed` (2026-04-06). **Other** — `adm_level` (range 1.0–2.0), `rfh` (range 0.0–249.7955), `rfh_avg` (range 0.0–112.8859), `r1h` (range 0.0–569.2935), `r1h_avg` (range 0.0–322.5119) and 6 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-tcd-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 1.7527) | | `adm_id` | int64 | 0.0% | 900172.0 – 1003195.0 (mean 977692.9462) | | `pcode` | object | 0.0% | TCD0703, TCD2201, TCD19 | | `n_pixels` | float64 | 0.0% | 13.0 – 8372.0 (mean 910.4301) | | `rfh` | float64 | 0.0% | 0.0 – 249.7955 (mean 16.5197) | | `rfh_avg` | float64 | 0.0% | 0.0 – 112.8859 (mean 16.3901) | | `r1h` | float64 | 0.1% | 0.0 – 569.2935 (mean 49.6063) | | `r1h_avg` | float64 | 0.1% | 0.0 – 322.5119 (mean 49.2263) | | `r3h` | float64 | 0.5% | 0.0 – 1150.1631 (mean 149.3431) | | `r3h_avg` | float64 | 0.5% | 0.0 – 811.1459 (mean 148.2129) | | `rfq` | float64 | 0.0% | 13.9173 – 569.6287 (mean 100.3659) | | `r1q` | float64 | 0.1% | 13.8573 – 587.5419 (mean 100.4474) | | `r3q` | float64 | 0.5% | 19.1436 – 564.8682 (mean 100.5778) | | `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 | 1.7527 | 2.0 | | `adm_id` | 900172.0 | 1003195.0 | 977692.9462 | 1003149.0 | | `n_pixels` | 13.0 | 8372.0 | 910.4301 | 370.0 | | `rfh` | 0.0 | 249.7955 | 16.5197 | 1.2695 | | `rfh_avg` | 0.0 | 112.8859 | 16.3901 | 1.6532 | | `r1h` | 0.0 | 569.2935 | 49.6063 | 5.0804 | | `r1h_avg` | 0.0 | 322.5119 | 49.2263 | 5.9782 | | `r3h` | 0.0 | 1150.1631 | 149.3431 | 38.0284 | | `r3h_avg` | 0.0 | 811.1459 | 148.2129 | 40.9487 | | `rfq` | 13.9173 | 569.6287 | 100.3659 | 100.0 | | `r1q` | 13.8573 | 587.5419 | 100.4474 | 100.0 | | `r3q` | 19.1436 | 564.8682 | 100.5778 | 99.9499 | --- ## 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/tcd-rainfall-subnational) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_tcd_rainfall_subnational, title = {Chad: Rainfall Indicators at Subnational Level}, author = {WFP - World Food Programme}, year = {2026}, url = {https://data.humdata.org/dataset/tcd-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.*
annotations_creators: - 无注释 language_creators: - 公开数据源采集 language: - 英语 license: cc-by-4.0 multilinguality: - 单语言 size_categories: - 100K<n<1M source_datasets: - 原创数据集 task_categories: - 表格回归 - 其他 task_ids: [] tags: - 非洲 - 人道主义 - 人道主义数据交换（Humanitarian Data Exchange, HDX） - Electric Sheep Africa - 气候与天气 - 环境 - TCD（乍得） pretty_name: "乍得：次国家级别降雨指标" dataset_info: splits: - name: train num_examples: 121272 - name: test num_examples: 30318 # 乍得：次国家级别降雨指标 **发布方**：世界粮食计划署（World Food Programme, WFP）· **数据源**：[人道主义数据交换（Humanitarian Data Exchange, HDX）](https://data.humdata.org/dataset/tcd-rainfall-subnational) · **许可证**：`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组红外降水卫星影像（Climate Hazards Group InfraRed Precipitation, CHIRPS）版本2及CHIRPS-GEFS短期降雨预报数据，结合原位台站观测数据，按次国家行政单元聚合得到。 包含的指标（每旬对应以下参数）： - 10日降雨量 [毫米] (`rfh`) - 1个月滑动聚合降雨量 [毫米] (`r1h`) - 3个月滑动聚合降雨量 [毫米] (`r3h`) - 降雨量长期平均值 [毫米] (`rfh_avg`) - 1个月滑动聚合降雨量长期平均值 [毫米] (`r1h_avg`) - 3个月滑动聚合降雨量长期平均值 [毫米] (`r3h_avg`) - 降雨量距平百分率 [%] (`rfq`) - 1个月降雨量距平百分率 [%] (`r1q`) - 3个月降雨量距平百分率 [%] (`r3q`) 本次聚合使用的行政单元基于世界粮食计划署数据，每个单元均配有Pcode标识码。用于生成聚合结果的输入像素总数将在`n_pixels`列中提供。此外，`version`列会标注该数值是基于预报、预发布还是最终产品。 预报于每月6日、16日、26日发布，覆盖未来10天时段（旬度），并于每月1日、11日、21日更新为优化版本。 预发布观测数据会在每月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替代——最终数据于月中（13日或23日）发布，覆盖上月全部三个旬度。以下为发布时间表： | 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 | 次月1-10日 | 如需了解更多CHIRPS-GEFS预报信息，请访问：https://www.chc.ucsb.edu/data/chirps-gefs 如需进一步细节，请参阅方法学章节。 本数据集的每一行代表时序观测数据。时间覆盖范围由`date`列标注。地理覆盖范围：**乍得（TCD）**。 *本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适合机器学习的Parquet格式。* --- ## 数据集特征 | | | |---|---| | **领域** | 气候与环境 | | **观测单元** | 时序观测数据 | | **总行数** | 151,590 | | **列数** | 17列（12列数值型、4列分类型、1列日期型） | | **训练集划分** | 121,272行 | | **测试集划分** | 30,318行 | | **地理覆盖范围** | 乍得（TCD） | | **发布方** | 世界粮食计划署（WFP） | | **HDX最后更新时间** | 2026-04-03 | --- ## 变量 **地理相关**：`n_pixels`（取值范围13.0–8372.0）。 **时间相关**：`date`。 **标识符/元数据**：`adm_id`（取值范围900172.0–1003195.0）、`pcode`（示例值：TCD0703、TCD2201、TCD19）、`esa_source`（HDX）、`esa_processed`（2026-04-06）。 **其他**：`adm_level`（取值范围1.0–2.0）、`rfh`（取值范围0.0–249.7955）、`rfh_avg`（取值范围0.0–112.8859）、`r1h`（取值范围0.0–569.2935）、`r1h_avg`（取值范围0.0–322.5119）及另外6列。 --- ## 快速入门 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-tcd-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1.7527） | | `adm_id` | int64 | 0.0% | 900172.0 – 1003195.0（均值977692.9462） | | `pcode` | object | 0.0% | TCD0703、TCD2201、TCD19 | | `n_pixels` | float64 | 0.0% | 13.0 – 8372.0（均值910.4301） | | `rfh` | float64 | 0.0% | 0.0 – 249.7955（均值16.5197） | | `rfh_avg` | float64 | 0.0% | 0.0 – 112.8859（均值16.3901） | | `r1h` | float64 | 0.1% | 0.0 – 569.2935（均值49.6063） | | `r1h_avg` | float64 | 0.1% | 0.0 – 322.5119（均值49.2263） | | `r3h` | float64 | 0.5% | 0.0 – 1150.1631（均值149.3431） | | `r3h_avg` | float64 | 0.5% | 0.0 – 811.1459（均值148.2129） | | `rfq` | float64 | 0.0% | 13.9173 – 569.6287（均值100.3659） | | `r1q` | float64 | 0.1% | 13.8573 – 587.5419（均值100.4474） | | `r3q` | float64 | 0.5% | 19.1436 – 564.8682（均值100.5778） | | `version` | object | 0.0% | final、prelim、forecast | | `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 | 1.7527 | 2.0 | | `adm_id` | 900172.0 | 1003195.0 | 977692.9462 | 1003149.0 | | `n_pixels` | 13.0 | 8372.0 | 910.4301 | 370.0 | | `rfh` | 0.0 | 249.7955 | 16.5197 | 1.2695 | | `rfh_avg` | 0.0 | 112.8859 | 16.3901 | 1.6532 | | `r1h` | 0.0 | 569.2935 | 49.6063 | 5.0804 | | `r1h_avg` | 0.0 | 322.5119 | 49.2263 | 5.9782 | | `r3h` | 0.0 | 1150.1631 | 149.3431 | 38.0284 | | `r3h_avg` | 0.0 | 811.1459 | 148.2129 | 40.9487 | | `rfq` | 13.9173 | 569.6287 | 100.3659 | 100.0 | | `r1q` | 13.8573 | 587.5419 | 100.4474 | 100.0 | | `r3q` | 19.1436 | 564.8682 | 100.5778 | 99.9499 | --- ## 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采用蛇形命名法（snake_case）标准化。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 - 数据源自世界粮食计划署（WFP），未由Electric Sheep Africa独立验证。 - 自动化清洗无法修正原始数据收集中的错报值、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声明，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/tcd-rainfall-subnational)。 --- ## 引用 bibtex @dataset{hdx_africa_tcd_rainfall_subnational, title = {Chad: Rainfall Indicators at Subnational Level}, author = {WFP - World Food Programme}, year = {2026}, url = {https://data.humdata.org/dataset/tcd-rainfall-subnational}, 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。*
