electricsheepafrica/africa-ifrc-appeals-data-for-ethiopia

---
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
- funding
- eth
pretty_name: "Ethiopia - IFRC Appeals"
dataset_info:
splits:
- name: train
num_examples: 40
- name: test
num_examples: 10
---

# Ethiopia - IFRC Appeals

**Publisher:** International Federation of Red Cross and Red Crescent Societies (IFRC) · **Source:** [HDX](https://data.humdata.org/dataset/ifrc-appeals-data-for-ethiopia) · **License:** `cc-by-igo` · **Updated:** 2026-04-10

---

## Abstract

The International Federation of Red Cross and Red Crescent Societies (IFRC) is the world’s largest humanitarian network. Our secretariat supports local Red Cross and Red Crescent action in more than 192 countries, bringing together almost 15 million volunteers for the good of humanity.

We launch Emergency Appeals for big and complex disasters affecting lots of people who will need long-term support to recover. We also support Red Cross and Red Crescent Societies to respond to lots of small and medium-sized disasters worldwide—through our Disaster Response Emergency Fund (DREF) and in other ways.

There is also a [global dataset](https://data.humdata.org/dataset/global-ifrc-appeals-data).

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2026-04-10. 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** | First-level administrative unit observations |
| **Rows (total)** | 50 |
| **Columns** | 41 (14 numeric, 19 categorical, 0 datetime) |
| **Train split** | 40 rows |
| **Test split** | 10 rows |
| **Geographic scope** | ETH |
| **Publisher** | International Federation of Red Cross and Red Crescent Societies (IFRC) |
| **HDX last updated** | 2026-04-10 |

---

## Variables

**Geographic** — `dtype_id` (range 1.0–24.0), `dtype_name` (Flood, Population Movement, Epidemic), `dtype_translation_module_original_language` (en), `atype` (range 0.0–1.0), `atype_display` (DREF, Emergency Appeal) and 18 others.

**Temporal** — `start_date`, `end_date`, `real_data_update`.

**Outcome / Measurement** — `amount_requested` (range 0.0–30579088.0), `amount_funded` (range 0.0–9717481.9257).

**Identifier / Metadata** — `aid` (range 8.0–19878.0), `name` (Ethiopia - Floods, Ethiopia - Drought, Ethiopia - Population Movement), `code` (MDRET041, MDRET001, MDRET011), `id` (range 19.0–4415.0), `esa_source` and 1 others.

**Other** — `status` (range 0.0–1.0), `sector` (Country cluster for Ethiopia and Djibouti), `created_at`, `modified_at`, `event` (range 40.0–7704.0) and 2 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-ifrc-appeals-data-for-ethiopia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `aid` | int64 | 0.0% | 8.0 – 19878.0 (mean 9656.6) |
| `name` | object | 0.0% | Ethiopia - Floods, Ethiopia - Drought, Ethiopia - Population Movement |
| `dtype_id` | int64 | 0.0% | 1.0 – 24.0 (mean 10.82) |
| `dtype_name` | object | 0.0% | Flood, Population Movement, Epidemic |
| `dtype_translation_module_original_language` | object | 0.0% | en |
| `atype` | int64 | 0.0% | 0.0 – 1.0 (mean 0.42) |
| `atype_display` | object | 0.0% | DREF, Emergency Appeal |
| `status` | int64 | 0.0% | 0.0 – 1.0 (mean 0.84) |
| `status_display` | object | 0.0% | Closed, Active |
| `code` | object | 0.0% | MDRET041, MDRET001, MDRET011 |
| `sector` | object | 0.0% | Country cluster for Ethiopia and Djibouti |
| `amount_requested` | float64 | 0.0% | 0.0 – 30579088.0 (mean 2839368.64) |
| `amount_funded` | float64 | 0.0% | 0.0 – 9717481.9257 (mean 1104239.3461) |
| `start_date` | datetime64[ns, UTC] | 0.0% | |
| `end_date` | datetime64[ns, UTC] | 0.0% | |
| `real_data_update` | datetime64[ns, UTC] | 2.0% | |
| `created_at` | datetime64[ns, UTC] | 0.0% | |
| `modified_at` | datetime64[ns, UTC] | 0.0% | |
| `event` | float64 | 6.0% | 40.0 – 7704.0 (mean 2877.4468) |
| `needs_confirmation` | bool | 0.0% | |
| `country_iso` | object | 0.0% | ET |
| `country_iso3` | object | 0.0% | ETH |
| `country_id` | int64 | 0.0% | 65.0 – 65.0 (mean 65.0) |
| `country_record_type` | int64 | 0.0% | 1.0 – 1.0 (mean 1.0) |
| `country_record_type_display` | object | 0.0% | Country |
| `country_region` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `country_independent` | bool | 0.0% | |
| `country_is_deprecated` | bool | 0.0% | |
| `country_fdrs` | object | 0.0% | |
| `country_name` | object | 0.0% | |
| `country_society_name` | object | 0.0% | |
| `country_translation_module_original_language` | object | 0.0% | |
| `region_name` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `region_id` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `region_region_name` | object | 0.0% | |
| `region_label` | object | 0.0% | |
| `region_translation_module_original_language` | object | 0.0% | |
| `id` | int64 | 0.0% | 19.0 – 4415.0 (mean 2352.5) |
| `initial_num_beneficiaries` | int64 | 0.0% | 0.0 – 1000000.0 (mean 138600.18) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `aid` | 8.0 | 19878.0 | 9656.6 | 8756.0 |
| `dtype_id` | 1.0 | 24.0 | 10.82 | 12.0 |
| `atype` | 0.0 | 1.0 | 0.42 | 0.0 |
| `status` | 0.0 | 1.0 | 0.84 | 1.0 |
| `amount_requested` | 0.0 | 30579088.0 | 2839368.64 | 488993.5 |
| `amount_funded` | 0.0 | 9717481.9257 | 1104239.3461 | 419589.18 |
| `event` | 40.0 | 7704.0 | 2877.4468 | 1679.0 |
| `country_id` | 65.0 | 65.0 | 65.0 | 65.0 |
| `country_record_type` | 1.0 | 1.0 | 1.0 | 1.0 |
| `country_region` | 0.0 | 0.0 | 0.0 | 0.0 |
| `region_name` | 0.0 | 0.0 | 0.0 | 0.0 |
| `region_id` | 0.0 | 0.0 | 0.0 | 0.0 |
| `id` | 19.0 | 4415.0 | 2352.5 | 2073.5 |
| `initial_num_beneficiaries` | 0.0 | 1000000.0 | 138600.18 | 43600.0 |

---

## 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) with >80% missing values were removed: `dtype_summary`, `country_average_household_size`. 5 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 International Federation of Red Cross and Red Crescent Societies (IFRC) 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/ifrc-appeals-data-for-ethiopia) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_ifrc_appeals_data_for_ethiopia,
title = {Ethiopia - IFRC Appeals},
author = {International Federation of Red Cross and Red Crescent Societies (IFRC)},
year = {2026},
url = {https://data.humdata.org/dataset/ifrc-appeals-data-for-ethiopia},
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

在构建这一数据集的过程中，原始数据源自国际红十字与红新月会联合会（IFRC）通过人道主义数据交换平台（HDX）发布的埃塞俄比亚紧急呼吁记录。数据经过Electric Sheep Africa团队的精心整理，利用CKAN API获取原始资料后，进行了系统的数据清洗与标准化处理。具体步骤包括将列名统一转换为蛇形命名法，将常见的缺失值标记规范为NaN，并移除了缺失率超过80%的列。此外，基于超过85%的解析成功率，将部分字符串列转换为数值或日期时间类型，最终以Snappy压缩的Parquet格式保存，并按照80:20的比例划分训练集与测试集，确保了数据在机器学习任务中的直接可用性。

特点

该数据集聚焦于人道主义援助领域，以埃塞俄比亚的一级行政区划为观测单元，涵盖了洪水、人口流动、流行病等多种灾害类型下的紧急呼吁记录。其核心特征在于包含了41个变量，其中14个为数值型，19个为分类变量，细致记录了每次呼吁的请求金额、已获资助金额、受益人数量及时间跨度等关键指标。数据集规模精炼，总计50条观测，分为40条训练样本与10条测试样本，地理范围严格限定于埃塞俄比亚，为研究特定区域的人道主义资金流动与灾害响应模式提供了高度聚焦且结构化的数据基础。

使用方法

在机器学习应用中，该数据集适用于表格分类与回归任务，例如预测呼吁状态或估算资金需求。使用者可通过Hugging Face的datasets库便捷加载，利用提供的Python代码片段将数据转换为Pandas DataFrame以进行后续分析。数据已预先划分为训练集与测试集，便于直接用于模型训练与评估。鉴于其包含丰富的分类与数值特征，建议在建模前进行适当的特征工程，并注意数据源自IFRC的原始报告，可能存在定义不一致或报告偏差，需参考原始HDX页面了解详细的方法学说明与注意事项。

背景与挑战

背景概述

在当代人道主义援助领域，数据驱动的决策支持系统日益成为提升应急响应效率的关键工具。由国际红十字与红新月会联合会（IFRC）发布的埃塞俄比亚紧急呼吁数据集，作为全球人道主义数据交换平台的重要组成部分，于2026年4月由Electric Sheep Africa团队进行机器学习友好型重构。该数据集聚焦于埃塞俄比亚境内由洪水、人口流动及流行病等灾害引发的紧急事件，核心研究问题在于通过量化分析不同灾害类型的资金需求与到位情况，揭示人道主义援助资源的配置模式与缺口，为灾害风险管理与韧性建设提供实证依据。其结构化记录涵盖了事件特征、时间维度及资金流动等多维变量，为人道主义信息学与计算社会科学领域的模型开发奠定了数据基础。

当前挑战

该数据集致力于解决人道主义援助资源分配预测与效果评估这一复杂领域问题，其核心挑战在于灾害事件的高度异质性与动态性导致资金需求与到位金额之间存在显著非线性关系，且受地缘政治、社会经济等多重隐变量干扰，使得传统回归模型难以捕捉深层因果机制。在数据构建过程中，原始采集面临报告延迟、定义不一致及部分字段缺失率较高等固有局限，例如关键变量`dtype_summary`因信息不足而被移除。尽管经过自动化清洗与格式标准化，但数据固有的报告偏差与未经验证的原始值仍可能引入噪声，制约了模型在真实场景中的泛化能力与可靠性。

常用场景

经典使用场景

在灾害响应与人道主义援助领域，该数据集为机器学习模型提供了结构化训练样本，支持对埃塞俄比亚地区紧急呼吁事件进行预测与分类。研究人员利用其包含的灾害类型、资金请求与资助金额、时间跨度等特征，构建回归或分类模型，旨在预测未来灾害事件的资金需求或评估援助效率。这类应用有助于优化资源分配策略，提升人道主义行动的响应速度与精准度。

衍生相关工作

围绕该数据集，已衍生出多项经典研究工作，包括基于机器学习的灾害资金需求预测模型、援助效果评估框架，以及跨区域灾害模式比较分析。这些工作通常整合时序分析与空间统计方法，探索灾害响应中的关键影响因素。部分研究进一步将此类数据与气候、社会经济指标融合，构建更全面的风险预警系统。

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。基于埃塞俄比亚红十字会与红新月会国际联合会呼吁数据集，学者们正探索利用机器学习模型预测灾害响应资金缺口，优化资源分配策略。结合气候变迁与人口流动等多元变量，研究致力于构建动态风险评估框架，以提升紧急援助的时效性与精准度。此类工作不仅呼应全球人道数据伙伴关系的倡议，也为脆弱地区的韧性建设提供了量化依据，推动人道行动向智能化、预见性转型。