electricsheepafrica/africa-sle-rainfall-subnational

---
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
- sle
pretty_name: "Sierra Leone: Rainfall Indicators at Subnational Level"
dataset_info:
splits:
- name: train
num_examples: 27384
- name: test
num_examples: 6846
---

# Sierra Leone: Rainfall Indicators at Subnational Level

**Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/sle-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: **SLE**.

*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)** | 34,230 |
| **Columns** | 17 (12 numeric, 4 categorical, 1 datetime) |
| **Train split** | 27,384 rows |
| **Test split** | 6,846 rows |
| **Geographic scope** | SLE |
| **Publisher** | WFP - World Food Programme |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `n_pixels` (range 3.0–741.0).

**Temporal** — `date`.

**Identifier / Metadata** — `adm_id` (range 900443.0–1006463.0), `pcode` (SL01, SL0502, SL0401), `esa_source` (HDX), `esa_processed` (2026-04-08).

**Other** — `adm_level` (range 1.0–2.0), `rfh` (range 0.3936–787.6667), `rfh_avg` (range 0.669–335.6889), `r1h` (range 1.6968–1701.6667), `r1h_avg` (range 2.3823–914.5444) and 6 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sle-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 1.7619) |
| `adm_id` | int64 | 0.0% | 900443.0 – 1006463.0 (mean 981214.9048) |
| `pcode` | object | 0.0% | SL01, SL0502, SL0401 |
| `n_pixels` | float64 | 0.0% | 3.0 – 741.0 (mean 226.4762) |
| `rfh` | float64 | 0.0% | 0.3936 – 787.6667 (mean 75.557) |
| `rfh_avg` | float64 | 0.0% | 0.669 – 335.6889 (mean 75.3881) |
| `r1h` | float64 | 0.1% | 1.6968 – 1701.6667 (mean 226.9214) |
| `r1h_avg` | float64 | 0.1% | 2.3823 – 914.5444 (mean 226.398) |
| `r3h` | float64 | 0.5% | 7.6961 – 3646.0 (mean 683.0364) |
| `r3h_avg` | float64 | 0.5% | 11.4716 – 2389.1 (mean 681.0995) |
| `rfq` | float64 | 0.0% | 17.1071 – 640.8437 (mean 99.5748) |
| `r1q` | float64 | 0.1% | 22.9156 – 382.4611 (mean 99.1716) |
| `r3q` | float64 | 0.5% | 27.3344 – 333.653 (mean 99.4682) |
| `version` | object | 0.0% | final, prelim, forecast |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `adm_level` | 1.0 | 2.0 | 1.7619 | 2.0 |
| `adm_id` | 900443.0 | 1006463.0 | 981214.9048 | 1006453.0 |
| `n_pixels` | 3.0 | 741.0 | 226.4762 | 181.0 |
| `rfh` | 0.3936 | 787.6667 | 75.557 | 51.5701 |
| `rfh_avg` | 0.669 | 335.6889 | 75.3881 | 50.8438 |
| `r1h` | 1.6968 | 1701.6667 | 226.9214 | 164.3903 |
| `r1h_avg` | 2.3823 | 914.5444 | 226.398 | 162.074 |
| `r3h` | 7.6961 | 3646.0 | 683.0364 | 536.6228 |
| `r3h_avg` | 11.4716 | 2389.1 | 681.0995 | 537.6967 |
| `rfq` | 17.1071 | 640.8437 | 99.5748 | 95.8535 |
| `r1q` | 22.9156 | 382.4611 | 99.1716 | 96.5084 |
| `r3q` | 27.3344 | 333.653 | 99.4682 | 98.3965 |

---

## 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/sle-rainfall-subnational) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_sle_rainfall_subnational,
title = {Sierra Leone: Rainfall Indicators at Subnational Level},
author = {WFP - World Food Programme},
year = {2026},
url = {https://data.humdata.org/dataset/sle-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:
- 语料来源：公开抓取
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:
- 表格回归
- 其他
task_ids: []
tags:
- 非洲
- 人道主义
- HDX
- Electric Sheep Africa
- 气候与天气
- 环境
- 塞拉利昂（SLE）
pretty_name: "塞拉利昂：次国家级降雨指标"
dataset_info:
splits:
- name: train
num_examples: 27384
- name: test
num_examples: 6846

# 塞拉利昂：次国家级降雨指标

**发布方**：世界粮食计划署（WFP - World Food Programme）· **数据来源**：[HDX](https://data.humdata.org/dataset/sle-rainfall-subnational) · **许可协议**：`cc-by` · **更新时间**：2026-04-03

---

## 摘要

本数据集包含旬度降雨指标，由气候灾害小组红外降水卫星影像结合野外台站数据（Climate Hazards Group InfraRed Precipitation, CHIRPS）版本2，以及CHIRPS-GEFS短期降雨预报数据计算得到，并按次国家级行政单元进行聚合。

包含的指标（每旬）：

- 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`）
- 降雨量距平百分比 [%]（`rfq`）
- 1个月降雨量距平百分比 [%]（`r1q`）
- 3个月降雨量距平百分比 [%]（`r3q`）

用于聚合的行政单元基于世界粮食计划署（WFP）数据，每个单元均配有Pcode编码。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（原`type`列，经标准化重命名）标识该数据为预报、初步观测还是最终观测产品。

预报于每月6日、16日、26日发布，覆盖未来10天（旬），并于每月1日、11日、21日更新为改进版本。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，随后由最终观测数据替代——最终观测数据于月中（13日或23日）发布，覆盖上月的全部三个旬。详情如下：

发布日期 | 预报类型 | 覆盖旬段
- 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预报相关信息，请访问：https://www.chc.ucsb.edu/data/chirps-gefs

如需进一步了解细节，请参阅方法学章节。

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`列标识。地理覆盖范围：**塞拉利昂（SLE）**。

*本数据集由[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 |
| **总数据行数** | 34,230 |
| **列数** | 17列（12列数值型、4列分类型、1列日期型） |
| **训练集划分** | 27,384行 |
| **测试集划分** | 6,846行 |
| **地理覆盖范围** | 塞拉利昂（SLE） |
| **发布方** | 世界粮食计划署（WFP） |
| **HDX最后更新时间** | 2026-04-03 |

---

## 变量说明

**地理相关字段**：`n_pixels`（取值范围3.0–741.0）。
**时间相关字段**：`date`。
**标识符/元数据字段**：`adm_id`（取值范围900443.0–1006463.0）、`pcode`（示例值：SL01、SL0502、SL0401）、`esa_source`（HDX）、`esa_processed`（2026-04-08）。
**其他字段**：`adm_level`（取值范围1.0–2.0）、`rfh`（0.3936–787.6667）、`rfh_avg`（0.669–335.6889）、`r1h`（1.6968–1701.6667）、`r1h_avg`（2.3823–914.5444）及另外6个字段。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sle-rainfall-subnational")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据Schema

| 列名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `date` | datetime64[ns] | 0.0% | 无 |
| `adm_level` | int64 | 0.0% | 1.0 – 2.0（均值1.7619） |
| `adm_id` | int64 | 0.0% | 900443.0 – 1006463.0（均值981214.9048） |
| `pcode` | object | 0.0% | SL01、SL0502、SL0401 |
| `n_pixels` | float64 | 0.0% | 3.0 – 741.0（均值226.4762） |
| `rfh` | float64 | 0.0% | 0.3936 – 787.6667（均值75.557） |
| `rfh_avg` | float64 | 0.0% | 0.669 – 335.6889（均值75.3881） |
| `r1h` | float64 | 0.1% | 1.6968 – 1701.6667（均值226.9214） |
| `r1h_avg` | float64 | 0.1% | 2.3823 – 914.5444（均值226.398） |
| `r3h` | float64 | 0.5% | 7.6961 – 3646.0（均值683.0364） |
| `r3h_avg` | float64 | 0.5% | 11.4716 – 2389.1（均值681.0995） |
| `rfq` | float64 | 0.0% | 17.1071 – 640.8437（均值99.5748） |
| `r1q` | float64 | 0.1% | 22.9156 – 382.4611（均值99.1716） |
| `r3q` | float64 | 0.5% | 27.3344 – 333.653（均值99.4682） |
| `version` | object | 0.0% | final、prelim、forecast（即最终、初步、预报） |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## 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 | 1.7619 | 2.0 |
| `adm_id` | 900443.0 | 1006463.0 | 981214.9048 | 1006453.0 |
| `n_pixels` | 3.0 | 741.0 | 226.4762 | 181.0 |
| `rfh` | 0.3936 | 787.6667 | 75.557 | 51.5701 |
| `rfh_avg` | 0.669 | 335.6889 | 75.3881 | 50.8438 |
| `r1h` | 1.6968 | 1701.6667 | 226.9214 | 164.3903 |
| `r1h_avg` | 2.3823 | 914.5444 | 226.398 | 162.074 |
| `r3h` | 7.6961 | 3646.0 | 683.0364 | 536.6228 |
| `r3h_avg` | 11.4716 | 2389.1 | 681.0995 | 537.6967 |
| `rfq` | 17.1071 | 640.8437 | 99.5748 | 95.8535 |
| `r1q` | 22.9156 | 382.4611 | 99.1716 | 96.5084 |
| `r3q` | 27.3344 | 333.653 | 99.4682 | 98.3965 |

---

## 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并标准化为蛇形命名法（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。

---

## 局限性说明

- 数据源自世界粮食计划署（WFP），未由Electric Sheep Africa（ESA）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条款，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/sle-rainfall-subnational)。

---

## 引用格式

bibtex
@dataset{hdx_africa_sle_rainfall_subnational,
title = {Sierra Leone: Rainfall Indicators at Subnational Level},
author = {WFP - World Food Programme},
year = {2026},
url = {https://data.humdata.org/dataset/sle-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。*