electricsheepafrica/africa-climate-tunisia

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- baseline-population
- climate-weather
- conflict-violence
- education
- funding
- hazards-and-risk
- health
- indicators
- tun
pretty_name: "HDX HAPI Data for Tunisia"
dataset_info:
splits:
- name: train
num_examples: 18699
- name: test
num_examples: 4674
---

# HDX HAPI Data for Tunisia

**Publisher:** HDX Humanitarian API Data · **Source:** [HDX](https://data.humdata.org/dataset/hdx-hapi-tun) · **License:** `hdx-other` · **Updated:** 2026-02-18

---

## Abstract

This dataset contains data obtained from the
[HDX Humanitarian API](https://hapi.humdata.org/) (HDX HAPI),
which provides standardized humanitarian indicators designed
for seamless interoperability from multiple sources.
The data facilitates automated workflows and visualizations
to support humanitarian decision making.
For more information, please see the HDX HAPI
[landing page](https://data.humdata.org/hapi)
and
[documentation](https://hdx-hapi.readthedocs.io/en/latest/).

Each row in this dataset represents geolocated point observations. Temporal coverage is indicated by the `reference_period_start`, `reference_period_end` column(s). Geographic scope: **TUN**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Geolocated point observations |
| **Rows (total)** | 23,374 |
| **Columns** | 16 (3 numeric, 7 categorical, 2 datetime) |
| **Train split** | 18,699 rows |
| **Test split** | 4,674 rows |
| **Geographic scope** | TUN |
| **Publisher** | HDX Humanitarian API Data |
| **HDX last updated** | 2026-02-18 |

---

## Variables

**Geographic** — `origin_location_code` (TUN, CIV, IRQ), `asylum_location_code` (TUN, CAN, CHE), `asylum_has_hrp`, `asylum_in_gho`, `population_group` (REF, ASY, OOC) and 2 others.

**Temporal** — `reference_period_start`, `reference_period_end`.

**Demographic** — `gender` (f, m, all), `age_range` (all, 0-4, 5-11), `min_age` (range 0.0–60.0).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-21).

**Other** — `origin_has_hrp`, `origin_in_gho`.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-climate-tunisia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `origin_location_code` | object | 0.0% | TUN, CIV, IRQ |
| `origin_has_hrp` | bool | 0.0% | |
| `origin_in_gho` | bool | 0.0% | |
| `asylum_location_code` | object | 0.0% | TUN, CAN, CHE |
| `asylum_has_hrp` | bool | 0.0% | |
| `asylum_in_gho` | bool | 0.0% | |
| `population_group` | object | 0.0% | REF, ASY, OOC |
| `gender` | object | 0.0% | f, m, all |
| `age_range` | object | 0.0% | all, 0-4, 5-11 |
| `min_age` | float64 | 23.1% | 0.0 – 60.0 (mean 19.0) |
| `max_age` | float64 | 38.5% | 4.0 – 59.0 (mean 22.75) |
| `population` | int64 | 0.0% | 0.0 – 6219.0 (mean 17.7626) |
| `reference_period_start` | datetime64[ns] | 0.0% | |
| `reference_period_end` | datetime64[ns] | 0.0% | |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-21 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `min_age` | 0.0 | 60.0 | 19.0 | 12.0 |
| `max_age` | 4.0 | 59.0 | 22.75 | 14.0 |
| `population` | 0.0 | 6219.0 | 17.7626 | 0.0 |

---

## 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 HDX Humanitarian API Data 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: `min_age`, `max_age`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/hdx-hapi-tun) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_climate_tunisia,
title = {HDX HAPI Data for Tunisia},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-tun},
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:
- 无标注
language_creators:
- 采集获取
language:
- 英语
license:
- 其他
multilinguality:
- 单语言
size_categories:
- 10000条至100000条之间
source_datasets:
- 原创数据集
task_categories:
- 表格分类、其他
task_ids:
- 无
tags:
- 非洲
- 人道主义
- HDX
- Electric Sheep Africa
- 基线人口
- 气候与天气
- 冲突与暴力
- 教育
- 资助
- 灾害与风险
- 健康
- 指标
- 突尼斯（TUN）
pretty_name: "突尼斯HDX HAPI数据集"
dataset_info:
splits:
- name: 训练集
num_examples: 18699
- name: 测试集
num_examples: 4674

# 突尼斯HDX HAPI数据集

**发布方**：HDX人道主义应用程序编程接口（HDX Humanitarian API）数据 · **来源**：[HDX](https://data.humdata.org/dataset/hdx-hapi-tun) · **许可证**：`hdx-other` · **更新时间**：2026-02-18

---

## 摘要
本数据集的数据源自[HDX人道主义应用程序编程接口（HDX Humanitarian API，简称HDX HAPI）](https://hapi.humdata.org/)，该接口提供标准化的人道主义指标，旨在实现多源数据的无缝互操作。本数据集支持自动化工作流与可视化流程，以辅助人道主义决策制定。如需了解更多信息，请访问HDX HAPI的[首页](https://data.humdata.org/hapi)与[官方文档](https://hdx-hapi.readthedocs.io/en/latest/)。

本数据集的每一行均代表一个带地理定位的点位观测数据。时间覆盖范围由`reference_period_start`（参考周期开始时间）与`reference_period_end`（参考周期结束时间）列标注。地理覆盖范围：**突尼斯（TUN）**。

*本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的Parquet格式（Parquet format）。*

---

## 数据集特征
| | |
|---|---|
| **研究领域** | 公共卫生 |
| **观测单元** | 带地理定位的点位观测数据 |
| **总样本行数** | 23374 |
| **列数** | 16列（其中3列为数值型、7列为分类型、2列为日期时间型） |
| **训练集拆分** | 18699条数据 |
| **测试集拆分** | 4674条数据 |
| **地理覆盖范围** | 突尼斯（TUN） |
| **发布方** | HDX人道主义应用程序编程接口数据 |
| **HDX最后更新时间** | 2026-02-18 |

---

## 变量说明
### 地理类变量
`origin_location_code`（来源地位置代码，取值为TUN、CIV、IRQ）、`asylum_location_code`（庇护地位置代码，取值为TUN、CAN、CHE）、`asylum_has_hrp`（庇护地是否处于人道主义响应计划区域）、`asylum_in_gho`（庇护地是否纳入全球卫生观察数据库）、`population_group`（人口群体，取值为REF、ASY、OOC）及另外2个变量。
### 时间类变量
`reference_period_start`（参考周期开始时间）、`reference_period_end`（参考周期结束时间）。
### 人口统计类变量
`gender`（性别，取值为f、m、all）、`age_range`（年龄区间，取值为all、0-4、5-11）、`min_age`（最小年龄，取值范围0.0~60.0）。
### 标识符/元数据类变量
`esa_source`（数据来源，取值为HDX）、`esa_processed`（数据处理时间，取值为2026-04-21）。
### 其他变量
`origin_has_hrp`（来源地是否处于人道主义响应计划区域）、`origin_in_gho`（来源地是否纳入全球卫生观察数据库）。

---

## 快速上手
python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-climate-tunisia")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据Schema
| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `origin_location_code` | 字符串对象 | 0.0% | TUN, CIV, IRQ |
| `origin_has_hrp` | 布尔型 | 0.0% | |
| `origin_in_gho` | 布尔型 | 0.0% | |
| `asylum_location_code` | 字符串对象 | 0.0% | TUN, CAN, CHE |
| `asylum_has_hrp` | 布尔型 | 0.0% | |
| `asylum_in_gho` | 布尔型 | 0.0% | |
| `population_group` | 字符串对象 | 0.0% | REF, ASY, OOC |
| `gender` | 字符串对象 | 0.0% | f, m, all |
| `age_range` | 字符串对象 | 0.0% | all, 0-4, 5-11 |
| `min_age` | 64位浮点型 | 23.1% | 0.0 – 60.0（均值为19.0） |
| `max_age` | 64位浮点型 | 38.5% | 4.0 – 59.0（均值为22.75） |
| `population` | 64位整型 | 0.0% | 0.0 – 6219.0（均值为17.7626） |
| `reference_period_start` | 纳秒级日期时间型 | 0.0% | |
| `reference_period_end` | 纳秒级日期时间型 | 0.0% | |
| `esa_source` | 字符串对象 | 0.0% | HDX |
| `esa_processed` | 字符串对象 | 0.0% | 2026-04-21 |

---

## 数值型变量统计摘要
| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `min_age` | 0.0 | 60.0 | 19.0 | 12.0 |
| `max_age` | 4.0 | 59.0 | 22.75 | 14.0 |
| `population` | 0.0 | 6219.0 | 17.7626 | 0.0 |

---

## 数据整理流程
原始数据通过CKAN应用程序编程接口（CKAN API）从HDX下载，并转换为Parquet格式。列名统一转为小写并标准化为蛇形命名法（snake_case）。常见的缺失值标记（`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2列从字符串类型转换为数值型或日期时间型。本数据集以固定随机种子（42）按照80/20的比例划分为训练集与测试集，并保存为采用Snappy压缩的Parquet格式文件。

---

## 数据集局限性
- 本数据源自HDX人道主义应用程序编程接口数据，未经过Electric Sheep Africa的独立验证。
- 自动化清洗流程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。
- 以下列存在超过20%的缺失值，在建模时需谨慎使用：`min_age`、`max_age`。
- 如需了解发布方的方法说明与免责声明，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/hdx-hapi-tun)。

---

## 引用格式
bibtex
@dataset{hdx_africa_climate_tunisia,
title = {HDX HAPI Data for Tunisia},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-tun},
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。*