electricsheepafrica/africa-climate-mozambique

---
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
- displacement
- economics
- education
- food-security
- funding
- moz
pretty_name: "HDX HAPI Data for Mozambique"
dataset_info:
splits:
- name: train
num_examples: 1219
- name: test
num_examples: 304
---

# HDX HAPI Data for Mozambique

**Publisher:** HDX Humanitarian API Data · **Source:** [HDX](https://data.humdata.org/dataset/hdx-hapi-moz) · **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 subnational administrative unit observations. Temporal coverage is indicated by the `reference_period_start`, `reference_period_end` column(s). Geographic scope: **MOZ**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 1,524 |
| **Columns** | 18 (3 numeric, 11 categorical, 2 datetime) |
| **Train split** | 1,219 rows |
| **Test split** | 304 rows |
| **Geographic scope** | MOZ |
| **Publisher** | HDX Humanitarian API Data |
| **HDX last updated** | 2026-02-18 |

---

## Variables

**Geographic** — `location_code` (MOZ), `provider_admin1_name` (Nampula, Cabo Delgado, Niassa), `provider_admin2_name` (Dondo, Nhamatanda, Nicoadala), `admin1_code` (MZ07, MZ01, MZ08), `admin1_name` (Nampula, Cabo Delgado, Niassa) and 5 others.

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

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed`.

**Other** — `has_hrp`, `in_gho`, `operation` (Cabo Delgado Conflict, Cyclone Idai, Cyclone Kenneth), `reporting_round` (range 1.0–22.0).

---

## Quick Start

```python
from datasets import load_dataset

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

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `location_code` | object | 0.0% | MOZ |
| `has_hrp` | bool | 0.0% | |
| `in_gho` | bool | 0.0% | |
| `provider_admin1_name` | object | 3.4% | Nampula, Cabo Delgado, Niassa |
| `provider_admin2_name` | object | 16.2% | Dondo, Nhamatanda, Nicoadala |
| `admin1_code` | object | 3.4% | MZ07, MZ01, MZ08 |
| `admin1_name` | object | 3.4% | Nampula, Cabo Delgado, Niassa |
| `admin2_code` | object | 16.2% | MZ0907, MZ0913, MZ1122 |
| `admin2_name` | object | 16.2% | Dondo, Nhamatanda, Nicoadala |
| `admin_level` | int64 | 0.0% | 0.0 – 2.0 (mean 1.8038) |
| `operation` | object | 0.0% | Cabo Delgado Conflict, Cyclone Idai, Cyclone Kenneth |
| `assessment_type` | object | 0.0% | BA, SA |
| `population` | int64 | 0.0% | 2.0 – 1028743.0 (mean 28988.8563) |
| `reporting_round` | int64 | 0.0% | 1.0 – 22.0 (mean 13.2008) |
| `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% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `admin_level` | 0.0 | 2.0 | 1.8038 | 2.0 |
| `population` | 2.0 | 1028743.0 | 28988.8563 | 2218.5 |
| `reporting_round` | 1.0 | 22.0 | 13.2008 | 13.0 |

---

## 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.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/hdx-hapi-moz) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_climate_mozambique,
title = {HDX HAPI Data for Mozambique},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-moz},
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:
- 无注释
language_creators:
- 爬取获取
language:
- 英语（en）
license:
- 其他
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
task_ids: []
tags:
- 非洲
- 人道主义
- HDX（Humanitarian Data Exchange，人道主义数据交换平台）
- electric-sheep-africa
- baseline-population
- 气候-天气
- 冲突-暴力
- 流离失所
- 经济学
- 教育
- 粮食安全
- 资助
- moz
pretty_name: "莫桑比克HDX HAPI数据集"
dataset_info:
splits:
- name: 训练集
num_examples: 1219
- name: 测试集
num_examples: 304
---
# 莫桑比克HDX HAPI数据集

**发布方：** HDX人道主义API数据集 · **来源：** [HDX（Humanitarian Data Exchange，人道主义数据交换平台）](https://data.humdata.org/dataset/hdx-hapi-moz) · **许可证：** `hdx-other` · **最后更新：** 2026-02-18

---

## 摘要

本数据集源自[HDX人道主义API（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[着陆页](https://data.humdata.org/hapi)与[官方文档](https://hdx-hapi.readthedocs.io/en/latest/)。

本数据集的每一行代表一条次国家级行政单元观测记录。时间覆盖范围由`reference_period_start`（参考周期起始）、`reference_period_end`（参考周期结束）两列标注。地理覆盖范围：**莫桑比克（MOZ）**。

*本数据集已由[Electric Sheep Africa（电羊非洲）](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式。*

---

## 数据集特征

| 类别 | 详情 |
|---|---|
| **研究领域** | 粮食安全与营养 |
| **观测单元** | 次国家级行政单元观测记录 |
| **总记录数** | 1524条 |
| **字段总数** | 18个（3个数值型、11个分类型、2个日期时间型） |
| **训练集划分** | 1219条记录 |
| **测试集划分** | 304条记录 |
| **地理覆盖范围** | 莫桑比克（MOZ） |
| **发布方** | HDX人道主义API数据集 |
| **HDX平台最后更新时间** | 2026-02-18 |

---

## 字段说明

**地理类字段**：`location_code`（MOZ）、`provider_admin1_name`（楠普拉省、德尔加杜角省、尼亚萨省）、`provider_admin2_name`（敦多镇、恩马塔坦达镇、尼科阿达拉镇）、`admin1_code`（MZ07、MZ01、MZ08）、`admin1_name`（楠普拉省、德尔加杜角省、尼亚萨省）及另外5个字段。
**时间类字段**：`reference_period_start`（参考周期起始）、`reference_period_end`（参考周期结束）。
**标识符/元数据字段**：`esa_source`（HDX）、`esa_processed`。
**其他字段**：`has_hrp`、`in_gho`、`operation`（德尔加杜角冲突、伊代气旋、肯尼斯气旋）、`reporting_round`（取值范围1.0–22.0）。

---

## 快速上手

以下为快速加载与使用本数据集的示例代码：
python
from datasets import load_dataset

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

print(train_df.shape)
train_df.head()

---

## 字段结构

| 字段名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `location_code` | 字符串（object） | 0.0% | MOZ |
| `has_hrp` | 布尔型（bool） | 0.0% | 无 |
| `in_gho` | 布尔型（bool） | 0.0% | 无 |
| `provider_admin1_name` | 字符串（object） | 3.4% | 楠普拉省、德尔加杜角省、尼亚萨省 |
| `provider_admin2_name` | 字符串（object） | 16.2% | 敦多镇、恩马塔坦达镇、尼科阿达拉镇 |
| `admin1_code` | 字符串（object） | 3.4% | MZ07、MZ01、MZ08 |
| `admin1_name` | 字符串（object） | 3.4% | 楠普拉省、德尔加杜角省、尼亚萨省 |
| `admin2_code` | 字符串（object） | 16.2% | MZ0907、MZ0913、MZ1122 |
| `admin2_name` | 字符串（object） | 16.2% | 敦多镇、恩马塔坦达镇、尼科阿达拉镇 |
| `admin_level` | 64位整型（int64） | 0.0% | 0.0 – 2.0（均值1.8038） |
| `operation` | 字符串（object） | 0.0% | 德尔加杜角冲突、伊代气旋、肯尼斯气旋 |
| `assessment_type` | 字符串（object） | 0.0% | BA、SA |
| `population` | 64位整型（int64） | 0.0% | 2.0 – 1028743.0（均值28988.8563） |
| `reporting_round` | 64位整型（int64） | 0.0% | 1.0 – 22.0（均值13.2008） |
| `reference_period_start` | 日期时间型（datetime64[ns]） | 0.0% | 无 |
| `reference_period_end` | 日期时间型（datetime64[ns]） | 0.0% | 无 |
| `esa_source` | 字符串（object） | 0.0% | HDX |
| `esa_processed` | 字符串（object） | 0.0% | 无 |

---

## 数值统计摘要

| 字段名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `admin_level` | 0.0 | 2.0 | 1.8038 | 2.0 |
| `population` | 2.0 | 1028743.0 | 28988.8563 | 2218.5 |
| `reporting_round` | 1.0 | 22.0 | 13.2008 | 13.0 |

---

## 数据整理流程

原始数据通过CKAN API从HDX平台下载，并转换为Parquet格式。所有字段名均转换为小写并标准化为蛇形命名法（snake_case）。将常见的缺失值标记（`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个字段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，并以Snappy压缩格式保存为Parquet文件。

---

## 数据集局限性

- 本数据集源自HDX人道主义API数据集，未经过Electric Sheep Africa（电羊非洲）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。
- 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-moz)。

---

## 引用格式

以下为该数据集的标准引用格式：
bibtex
@dataset{hdx_africa_climate_mozambique,
title = {HDX HAPI Data for Mozambique},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-moz},
note = {由Electric Sheep Africa（电羊非洲）重新打包为机器学习可用格式，详见https://huggingface.co/electricsheepafrica}
}

---

*[Electric Sheep Africa（电羊非洲）](https://huggingface.co/electricsheepafrica) — 非洲的机器学习数据集基础设施。尼日利亚拉各斯。*