electricsheepafrica/africa-climate-botswana

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- baseline-population
- climate-weather
- conflict-violence
- education
- hazards-and-risk
- health
- indicators
- poverty
- bwa
pretty_name: "HDX HAPI Data for Botswana"
dataset_info:
splits:
- name: train
num_examples: 6208
- name: test
num_examples: 1552
---

# HDX HAPI Data for Botswana

**Publisher:** HDX Humanitarian API Data · **Source:** [HDX](https://data.humdata.org/dataset/hdx-hapi-bwa) · **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: **BWA**.

*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)** | 7,761 |
| **Columns** | 16 (3 numeric, 7 categorical, 2 datetime) |
| **Train split** | 6,208 rows |
| **Test split** | 1,552 rows |
| **Geographic scope** | BWA |
| **Publisher** | HDX Humanitarian API Data |
| **HDX last updated** | 2026-02-18 |

---

## Variables

**Geographic** — `origin_location_code` (BWA, ZWE, COD), `asylum_location_code` (BWA, CAN, GBR), `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-botswana")
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% | BWA, ZWE, COD |
| `origin_has_hrp` | bool | 0.0% | |
| `origin_in_gho` | bool | 0.0% | |
| `asylum_location_code` | object | 0.0% | BWA, CAN, GBR |
| `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 – 2253.0 (mean 21.9277) |
| `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 | 2253.0 | 21.9277 | 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-bwa) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_climate_botswana,
title = {HDX HAPI Data for Botswana},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-bwa},
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: 现有资源采集
language: 英语
license: 其他协议
multilinguality: 单语言
size_categories: 1000 < 样本量 < 10000
source_datasets: 原创数据集
task_categories: 表格分类、其他任务
task_ids: 无
tags: 非洲、人道主义、HDX、电羊非洲（Electric Sheep Africa）、基线人口、气候与天气、冲突与暴力、教育、灾害与风险、卫生、指标、贫困、博茨瓦纳（BWA）
pretty_name: "博茨瓦纳HDX人道主义API数据集"
dataset_info:
数据集划分:
- 名称: 训练集
样本数: 6208
- 名称: 测试集
样本数: 1552

# 博茨瓦纳HDX人道主义API数据集
**发布方**：HDX人道主义API数据 · **来源**：[HDX](https://data.humdata.org/dataset/hdx-hapi-bwa) · **授权协议**：`hdx-other` · **更新时间**：2026-02-18

---

## 摘要
本数据集包含从[人道主义数据交换（Humanitarian Data Exchange，HDX）人道主义API（HDX HAPI）](https://hapi.humdata.org/)获取的数据，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操作，以辅助人道主义决策制定。如需更多信息，请访问HDX HAPI的[落地页](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地理定位的点位观测值。时间覆盖范围由`reference_period_start`、`reference_period_end`列标识。地理覆盖范围：**博茨瓦纳（BWA）**。
*本数据集已由[电羊非洲（Electric Sheep Africa）](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的Parquet格式（Parquet）。*

---

## 数据集特征
| | |
|---|---|
| **领域** | 公共卫生 |
| **观测单元** | 地理定位点位观测值 |
| **总行数** | 7761 |
| **列数** | 16列（3个数值型、7个分类型、2个日期时间型） |
| **训练集划分** | 6208行 |
| **测试集划分** | 1552行 |
| **地理覆盖范围** | 博茨瓦纳（BWA） |
| **发布方** | HDX人道主义API数据 |
| **HDX最后更新时间** | 2026-02-18 |

---

## 变量
### 地理相关变量
`origin_location_code`（取值：博茨瓦纳BWA、津巴布韦ZWE、刚果民主共和国COD）、`asylum_location_code`（取值：博茨瓦纳BWA、加拿大CAN、英国GBR）、`asylum_has_hrp`、`asylum_in_gho`、`population_group`（取值：难民REF、寻求庇护者ASY、流离失所者OOC）及另外2个变量。
### 时间相关变量
`reference_period_start`、`reference_period_end`。
### 人口统计相关变量
`gender`（取值：女f、男m、全体all）、`age_range`（取值：全体all、0-4岁、5-11岁）、`min_age`（取值范围：0.0–60.0）。
### 标识符/元数据变量
`esa_source`（取值：HDX）、`esa_processed`（取值：2026-04-21）。
### 其他变量
`origin_has_hrp`、`origin_in_gho`。

---

## 快速上手
python
from datasets import load_dataset

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

print(train.shape)
train.head()

---

## 数据结构
| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `origin_location_code` | 字符型 | 0.0% | BWA、ZWE、COD |
| `origin_has_hrp` | 布尔型 | 0.0% | 无 |
| `origin_in_gho` | 布尔型 | 0.0% | 无 |
| `asylum_location_code` | 字符型 | 0.0% | BWA、CAN、GBR |
| `asylum_has_hrp` | 布尔型 | 0.0% | 无 |
| `asylum_in_gho` | 布尔型 | 0.0% | 无 |
| `population_group` | 字符型 | 0.0% | REF、ASY、OOC |
| `gender` | 字符型 | 0.0% | f、m、all |
| `age_range` | 字符型 | 0.0% | all、0-4、5-11 |
| `min_age` | 浮点型 | 23.1% | 0.0 – 60.0（平均值19.0） |
| `max_age` | 浮点型 | 38.5% | 4.0 – 59.0（平均值22.75） |
| `population` | 整型 | 0.0% | 0.0 – 2253.0（平均值21.9277） |
| `reference_period_start` | 日期时间型 | 0.0% | 无 |
| `reference_period_end` | 日期时间型 | 0.0% | 无 |
| `esa_source` | 字符型 | 0.0% | HDX |
| `esa_processed` | 字符型 | 0.0% | 2026-04-21 |

---

## 数值型变量统计摘要
| 列名 | 最小值 | 最大值 | 平均值 | 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 | 2253.0 | 21.9277 | 0.0 |

---

## 数据整理流程
原始数据通过CKAN API（Comprehensive Knowledge Archive Network API）从HDX下载并转换为Parquet格式（Parquet）。列名统一转换为小写并标准化为蛇形命名法（snake_case）。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）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80/20比例划分为训练集与测试集，并保存为Snappy压缩（Snappy）的Parquet格式文件。

---

## 数据集局限性
- 数据源自HDX人道主义API数据，未经过电羊非洲（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、定义不一致或抽样偏差问题。
- 以下列的缺失率超过20%，在建模过程中需谨慎使用：`min_age`、`max_age`。
- 如需了解发布方的方法说明与注意事项，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/hdx-hapi-bwa)。

---

## 引用格式
bibtex
@dataset{hdx_africa_climate_botswana,
title = {HDX HAPI Data for Botswana},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-bwa},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}

---

*[电羊非洲（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。*