electricsheepafrica/africa-hrp-projects-eth

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- humanitarian-response-plan-hrp
- who-is-doing-what-and-where-3w-4w-5w
- eth
pretty_name: "Ethiopia: Response Plan projects"
dataset_info:
splits:
- name: train
num_examples: 200
- name: test
num_examples: 50
---

# Ethiopia: Response Plan projects

**Publisher:** OCHA Humanitarian Programme Cycle Tools (HPC Tools) · **Source:** [HDX](https://data.humdata.org/dataset/hrp-projects-eth) · **License:** `cc-by-igo` · **Updated:** 2026-04-03

---

## Abstract

Projects proposed, in progress, or completed as part of the annual Ethiopia Humanitarian Response Plans (HRPs) or other Humanitarian Programme Cycle plans. The original data is available on https://hpc.tools

**Important:** some projects in Ethiopia might be missing, and others might not apply specifically to Ethiopia. See _Caveats_ under the _Additional information_ tab.

Each row in this dataset represents time-series observations. Temporal coverage is indicated by the `startdate`, `enddate` column(s). Geographic scope: **ETH**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Time-series observations |
| **Rows (total)** | 251 |
| **Columns** | 13 (1 numeric, 10 categorical, 2 datetime) |
| **Train split** | 200 rows |
| **Test split** | 50 rows |
| **Geographic scope** | ETH |
| **Publisher** | OCHA Humanitarian Programme Cycle Tools (HPC Tools) |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `locations` (ETH, EGY, LBY).

**Temporal** — `startdate`, `enddate`.

**Identifier / Metadata** — `name` (Ethiopia: ACT Alliance/Ethiopian Orthodox Church-Development and Inter-Church Aid Commission (Education response), Uganda: ACT Alliance / Lutheran World Federation (Protection - Gender-Based Violence response), Egypt: United Nations High Commissioner for Refugees (Protection - Gender-Based Violence response)), `versioncode` (RRSDN24-EDU-213166-1, RRSDN24-PRO-220173-1, RRSDN24-PRO-213244-1), `response_plan_code` (RRSDN24), `esa_source` (HDX), `esa_processed` (2026-04-04).

**Other** — `currentrequestedfunds` (range 5000.0–32130390.0), `objective` (International Rescue Committee - Protection response for Sudan Regional Plan in Libya, Cooperazione E Sviluppo - CESVI - Protection response for Sudan Regional Plan in Libya, ACT Alliance / Lutheran World Federation - Protection response for Sudan Regional Plan in Uganda), `globalclusters` (Health, Early Recovery, Protection), `organizations` (United Nations High Commissioner for Refugees, United Nations Children's Fund, International Organization for Migration), `plans` (Sudan Emergency: Regional Refugee Response Plan 2024).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-hrp-projects-eth")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `name` | object | 0.0% | Ethiopia: ACT Alliance/Ethiopian Orthodox Church-Development and Inter-Church Aid Commission (Education response), Uganda: ACT Alliance / Lutheran World Federation (Protection - Gender-Based Violence response), Egypt: United Nations High Commissioner for Refugees (Protection - Gender-Based Violence response) |
| `versioncode` | object | 0.0% | RRSDN24-EDU-213166-1, RRSDN24-PRO-220173-1, RRSDN24-PRO-213244-1 |
| `currentrequestedfunds` | int64 | 0.0% | 5000.0 – 32130390.0 (mean 2010167.0876) |
| `objective` | object | 0.0% | International Rescue Committee - Protection response for Sudan Regional Plan in Libya, Cooperazione E Sviluppo - CESVI - Protection response for Sudan Regional Plan in Libya, ACT Alliance / Lutheran World Federation - Protection response for Sudan Regional Plan in Uganda |
| `startdate` | datetime64[ns] | 0.0% | |
| `enddate` | datetime64[ns] | 0.0% | |
| `globalclusters` | object | 0.0% | Health, Early Recovery, Protection |
| `locations` | object | 0.0% | ETH, EGY, LBY |
| `organizations` | object | 0.0% | United Nations High Commissioner for Refugees, United Nations Children's Fund, International Organization for Migration |
| `plans` | object | 0.0% | Sudan Emergency: Regional Refugee Response Plan 2024 |
| `response_plan_code` | object | 0.0% | RRSDN24 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-04 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `currentrequestedfunds` | 5000.0 | 32130390.0 | 2010167.0876 | 740000.0 |

---

## 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: `partners`. 2 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 OCHA Humanitarian Programme Cycle Tools (HPC Tools) 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/hrp-projects-eth) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_hrp_projects_eth,
title = {Ethiopia: Response Plan projects},
author = {OCHA Humanitarian Programme Cycle Tools (HPC Tools)},
year = {2026},
url = {https://data.humdata.org/dataset/hrp-projects-eth},
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.*

搜集汇总

数据集介绍

构建方式

在非洲人道主义数据领域，该数据集源自联合国人道主义事务协调厅的人道主义计划周期工具，原始数据通过HDX平台的CKAN接口获取。数据经过系统化清洗流程，包括统一缺失值标记为NaN格式，将列名标准化为蛇形命名法，并移除了缺失率超过80%的合作伙伴字段。时间序列数据经过类型转换处理，字符串字段依据超过85%的解析成功率被转换为数值或日期时间类型。最终数据集采用固定随机种子进行80/20划分，形成训练集与测试集，并以Snappy压缩的Parquet格式存储，确保了机器学习任务的数据可用性。

特点

该数据集呈现显著的人道主义行动时空特征，包含251条时间序列观测记录，涵盖埃塞俄比亚及其周边区域的人道主义响应项目。数据维度包含13个字段，其中地理信息覆盖ETH、EGY、LBY三个国家代码，时间维度通过起始日期和结束日期精确记录项目周期。资金需求字段展现出从5000到3213万美元的广泛分布，平均值为201万美元。项目分类体系包含健康、早期恢复、保护等全球集群标签，执行机构涉及联合国难民署、儿童基金会等国际组织，形成了多层次的人道主义行动档案。

使用方法

在机器学习应用场景中，研究者可通过HuggingFace数据集库直接加载该资源，使用标准接口调用训练集与测试集。数据加载后可通过to_pandas方法转换为DataFrame格式进行后续分析。该数据集适用于时间序列预测、资金需求建模、人道主义项目分类等任务，地理编码字段支持空间分析，机构与集群标签可用于网络关系研究。需要注意的是，原始数据存在部分项目缺失或地理归属模糊的情况，建议结合HDX平台的方法论说明进行交叉验证，以确保分析结论的稳健性。

背景与挑战

背景概述

在全球化人道主义响应领域，数据驱动的决策支持系统日益成为优化资源配置与行动协调的核心工具。'africa-hrp-projects-eth'数据集由联合国人道主义事务协调厅（OCHA）的人道主义计划周期工具（HPC Tools）于2026年发布，并由Electric Sheep Africa机构重新整理为机器学习可用格式。该数据集聚焦于埃塞俄比亚年度人道主义响应计划（HRPs）及其他相关计划中的项目提案、执行与完成情况，旨在通过时间序列观测记录，系统追踪人道主义干预措施的资金需求、目标机构与地理分布。其核心研究问题在于揭示人道主义项目在复杂危机环境中的动态演变规律，为政策制定者与研究人员提供量化分析基础，从而提升人道主义行动的透明度与效能。

当前挑战

该数据集致力于解决人道主义项目监测与评估领域的核心挑战，即如何在多机构、跨地域的复杂协作网络中，实现对项目进展与资金流动的精准追踪与标准化表征。构建过程中面临多重技术障碍：原始数据来源于分散的报告系统，存在定义不一致与采样偏差风险；自动化清洗流程虽能统一缺失值标记，却难以纠正原始收集中的误报或概念歧义。此外，数据集规模有限（总计251条观测记录），且部分项目可能缺失或未严格限定于埃塞俄比亚地理范围，这些因素均可能制约模型训练的泛化能力与结论的普适性。

常用场景

经典使用场景

在非洲人道主义援助领域，该数据集为研究人员提供了埃塞俄比亚人道主义响应计划项目的结构化时间序列数据。其经典使用场景聚焦于分析援助项目的资金分配、实施进度与地理分布，通过机器学习模型预测资金需求或评估项目成效，从而优化人道主义资源的配置策略。

衍生相关工作

围绕该数据集衍生的经典工作包括基于时间序列的援助资金预测模型、多智能体仿真系统用于模拟人道主义供应链，以及自然语言处理技术对项目目标文本进行聚类分析。这些研究不仅拓展了计算社会科学在人道主义领域的应用边界，也为后续区域性的危机响应数据平台开发提供了方法论借鉴。

数据集最近研究

最新研究方向

在非洲人道主义援助领域，数据驱动的决策支持正成为前沿探索的核心。针对africa-hrp-projects-eth这类结构化的人道主义响应计划项目数据集，当前研究聚焦于利用时间序列与多源异构特征，开发预测性模型以优化资源分配与危机响应效能。学者们结合自然语言处理技术，从项目目标与集群分类中提取语义模式，旨在识别援助项目的协同效应与潜在缺口。随着全球气候变化与地区冲突加剧，此类数据集为评估跨区域难民响应计划的可持续影响提供了量化基础，推动了人道主义行动向智能化和前瞻性方向演进。