electricsheepafrica/africa-eth-requirements-and-funding-data

---
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:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- covid-19
- funding
- humanitarian-financial-tracking-service-fts
- eth
pretty_name: "Ethiopia - Requirements and Funding Data"
dataset_info:
splits:
- name: train
num_examples: 48
- name: test
num_examples: 12
---

# Ethiopia - Requirements and Funding Data

**Publisher:** OCHA Financial Tracking System (FTS) · **Source:** [HDX](https://data.humdata.org/dataset/eth-requirements-and-funding-data) · **License:** `cc-by-igo` · **Updated:** 2026-04-03

---

## Abstract

FTS publishes data on humanitarian funding flows as reported by donors and recipient organizations. It presents all humanitarian funding to a country and funding that is specifically reported or that can be specifically mapped against funding requirements stated in humanitarian response plans. The data comes from OCHA's [Financial Tracking Service](https://fts.unocha.org/) and is encoded as utf-8.

Each row in this dataset represents country-level aggregates. 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** | Country-level aggregates |
| **Rows (total)** | 61 |
| **Columns** | 14 (6 numeric, 6 categorical, 2 datetime) |
| **Train split** | 48 rows |
| **Test split** | 12 rows |
| **Geographic scope** | ETH |
| **Publisher** | OCHA Financial Tracking System (FTS) |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `countrycode` (ETH), `typeid` (range 4.0–2170.0), `typename` (Regional response plan, Humanitarian response plan, Other), `year` (range 2000.0–2028.0).

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

**Outcome / Measurement** — `percentfunded` (range 2.0–76.0).

**Identifier / Metadata** — `id` (range 54.0–1527.0), `name` (Not specified, Ethiopia Humanitarian Response Plan 2021, Ethiopia: 2006 Govt-UN Joint Emergency Flood Appeal for Somali Region), `code` (RREG26a, RREG26, OETH0607), `esa_source` (HDX), `esa_processed` (2026-04-04).

**Other** — `requirements` (range 7502719.0–3994813508.0), `funding` (range 1197605.0–1710540760.0).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-eth-requirements-and-funding-data")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `countrycode` | object | 0.0% | ETH |
| `id` | float64 | 47.5% | 54.0 – 1527.0 (mean 929.6875) |
| `name` | object | 0.0% | Not specified, Ethiopia Humanitarian Response Plan 2021, Ethiopia: 2006 Govt-UN Joint Emergency Flood Appeal for Somali Region |
| `code` | object | 47.5% | RREG26a, RREG26, OETH0607 |
| `typeid` | float64 | 47.5% | 4.0 – 2170.0 (mean 135.4375) |
| `typename` | object | 47.5% | Regional response plan, Humanitarian response plan, Other |
| `startdate` | datetime64[ns] | 47.5% | |
| `enddate` | datetime64[ns] | 47.5% | |
| `year` | int64 | 0.0% | 2000.0 – 2028.0 (mean 2016.9344) |
| `requirements` | float64 | 54.1% | 7502719.0 – 3994813508.0 (mean 741579799.2857) |
| `funding` | int64 | 0.0% | 1197605.0 – 1710540760.0 (mean 337450325.6721) |
| `percentfunded` | float64 | 54.1% | 2.0 – 76.0 (mean 41.0357) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-04 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 54.0 | 1527.0 | 929.6875 | 1060.5 |
| `typeid` | 4.0 | 2170.0 | 135.4375 | 111.0 |
| `year` | 2000.0 | 2028.0 | 2016.9344 | 2020.0 |
| `requirements` | 7502719.0 | 3994813508.0 | 741579799.2857 | 258889628.5 |
| `funding` | 1197605.0 | 1710540760.0 | 337450325.6721 | 200894617.0 |
| `percentfunded` | 2.0 | 76.0 | 41.0357 | 40.0 |

---

## 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`. 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 Financial Tracking System (FTS) and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- The following columns have >20% missing values and should be treated with caution in modelling: `id`, `code`, `typeid`, `typename`, `startdate`, `enddate`, `requirements`, `percentfunded`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/eth-requirements-and-funding-data) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_eth_requirements_and_funding_data,
title = {Ethiopia - Requirements and Funding Data},
author = {OCHA Financial Tracking System (FTS)},
year = {2026},
url = {https://data.humdata.org/dataset/eth-requirements-and-funding-data},
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

在构建埃塞俄比亚人道主义需求与资金数据集的过程中，原始数据源自联合国人道主义事务协调厅的财务追踪服务，通过HDX平台以CKAN API获取。数据经过系统性的清洗与标准化处理，包括将列名转换为蛇形命名法，统一缺失值标记为NaN，并依据解析成功率将字符串列转换为数值或日期时间类型。最终，数据集被划分为训练集与测试集，采用固定随机种子确保可复现性，并以Snappy压缩的Parquet格式存储，为机器学习应用提供结构化的数据基础。

特点

该数据集聚焦于埃塞俄比亚的人道主义援助领域，涵盖国家层面的聚合数据，包含需求金额、资金到位情况及资助比例等关键变量。其特点在于整合了地理、时间与财务维度，如起始日期、结束日期及年度信息，同时标注了计划类型与代码等元数据。值得注意的是，部分列存在较高比例的缺失值，例如需求与资助比例字段，这要求使用者在建模时谨慎处理。数据集规模相对紧凑，总计61行观测，分为48行训练样本与12行测试样本，适用于小规模的分析与预测任务。

使用方法

使用该数据集时，可通过Hugging Face的datasets库直接加载，并转换为Pandas DataFrame以进行后续分析。数据集适用于表格分类或回归任务，例如预测资助比例或分析资金分配模式。在建模过程中，建议优先处理缺失值较多的列，并参考原始HDX页面的方法论说明以确保数据解读的准确性。此外，利用时间序列特征如起始与结束日期，可深入探究人道主义响应的动态变化，为政策制定与资源优化提供数据驱动的见解。

背景与挑战

背景概述

该数据集由联合国人道主义事务协调厅（OCHA）的财务追踪服务（FTS）于2026年发布，并由Electric Sheep Africa机构进行机器学习格式的整理与发布。其核心研究问题聚焦于埃塞俄比亚人道主义援助资金需求与到位情况的量化分析，旨在通过结构化数据揭示人道主义响应计划中的资金缺口与分配效率。作为人道主义与发展数据领域的关键资源，该数据集为政策制定者、研究机构及非政府组织提供了实证基础，以评估援助资金流动的透明度与效果，对提升全球人道主义行动的精准性与问责性具有显著影响力。

当前挑战

该数据集旨在解决人道主义援助资金追踪与需求预测的领域挑战，具体包括资金流动的实时性不足、数据报告标准不一导致的跨计划可比性困难，以及资金缺口评估的复杂性。在构建过程中，数据集面临原始数据缺失值比例较高（如需求金额、资金百分比等关键字段缺失率超过20%）、自动化清洗难以纠正原始报告中的定义不一致或误报问题，以及数据采样偏差等挑战，这些因素可能影响机器学习模型在资金需求预测或分类任务中的稳健性与准确性。

常用场景

经典使用场景

在非洲人道主义援助领域，该数据集通过提供埃塞俄比亚的人道主义资金需求与资助数据，为研究人员和政策制定者构建了关键的分析基础。其经典使用场景聚焦于利用机器学习方法，对资金缺口进行预测建模，例如通过历史需求与资助比例数据训练回归模型，以评估未来援助计划的资金充足性。这类分析有助于揭示资金分配的时间趋势和响应计划类型间的差异，为优化人道主义资源调度提供数据驱动的见解。

衍生相关工作

围绕该数据集衍生的经典研究工作，主要集中在人道主义数据分析与机器学习交叉领域。学者们利用其时间序列特征，开发了基于历史资金模式的预测模型，用于预警未来资金缺口风险。同时，结合其他社会经济指标，研究团队开展了资金分配公平性与影响评估的复合分析，探索援助资金如何更有效地缓解脆弱性。这些工作不仅丰富了人道主义信息学的实证案例库，也为开发自动化资金监控工具和决策支持系统提供了核心数据基础。

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研究焦点。基于埃塞俄比亚需求与资金数据集，学者们正探索利用机器学习模型预测资金缺口，优化资源分配策略。结合时间序列分析与回归技术，研究旨在揭示人道主义响应计划中资金流动的时序规律，以应对气候变化与公共卫生危机等复合型挑战。此类工作不仅提升了援助效率的透明度，也为区域可持续发展政策提供了量化依据，推动人道主义行动向精准化、智能化转型。