electricsheepafrica/african-regional-energy-statistics-2014

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- energy
- facilities-infrastructure
- dza
- ago
- ben
- bwa
- bfa
pretty_name: "African Regional Energy Statistics, 2014"
dataset_info:
splits:
- name: train
num_examples: 13614
- name: test
num_examples: 3403
---

# African Regional Energy Statistics, 2014

**Publisher:** African Development Bank Group · **Source:** [HDX](https://data.humdata.org/dataset/african-regional-energy-statistics-2014) · **License:** `cc-by` · **Updated:** 2023-05-02

---

## Abstract

African Regional Energy Statistics, 2000 - 2014

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2023-05-02. Geographic scope: **DZA, AGO, BEN, BWA, BFA, BDI, CPV, CMR, and 50 others**.

*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)** | 17,018 |
| **Columns** | 9 (4 numeric, 5 categorical, 0 datetime) |
| **Train split** | 13,614 rows |
| **Test split** | 3,403 rows |
| **Geographic scope** | DZA, AGO, BEN, BWA, BFA, BDI, CPV, CMR, and 50 others |
| **Publisher** | African Development Bank Group |
| **HDX last updated** | 2023-05-02 |

---

## Variables

**Geographic** — `region` (range 1.0–10516.0), `regionname` (Africa, Southern Africa, South Africa).

**Temporal** — `date` (range 2000.0–2014.0).

**Outcome / Measurement** — `value` (range -4102281.0–8985871.2198).

**Identifier / Metadata** — `indicatorname` (Total production of electricity, GWh, Final consumption of electricity, GWh, Final consumption of oil, 1000 tonnes), `esa_source` (HDX), `esa_processed` (2026-04-18).

**Other** — `indicator` (range 102.0–21773673.0), `unit` (thousand tonnes, GWh, terajoules (TJ)).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/african-regional-energy-statistics-2014")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `indicator` | int64 | 0.0% | 102.0 – 21773673.0 (mean 6088314.0264) |
| `indicatorname` | object | 0.0% | Total production of electricity, GWh, Final consumption of electricity, GWh, Final consumption of oil, 1000 tonnes |
| `region` | int64 | 0.0% | 1.0 – 10516.0 (mean 8612.1383) |
| `regionname` | object | 0.0% | Africa, Southern Africa, South Africa |
| `unit` | object | 0.0% | thousand tonnes, GWh, terajoules (TJ) |
| `date` | int64 | 0.0% | 2000.0 – 2014.0 (mean 2007.2201) |
| `value` | float64 | 0.0% | -4102281.0 – 8985871.2198 (mean 24953.5928) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-18 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `indicator` | 102.0 | 21773673.0 | 6088314.0264 | 504.0 |
| `region` | 1.0 | 10516.0 | 8612.1383 | 10303.0 |
| `date` | 2000.0 | 2014.0 | 2007.2201 | 2007.0 |
| `value` | -4102281.0 | 8985871.2198 | 24953.5928 | 655.0 |

---

## 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`. 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 African Development Bank Group and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- This dataset spans 58 countries; geographic and methodological inconsistencies across national boundaries may affect cross-country comparability.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/african-regional-energy-statistics-2014) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_african_regional_energy_statistics_2014,
title = {African Regional Energy Statistics, 2014},
author = {African Development Bank Group},
year = {2023},
url = {https://data.humdata.org/dataset/african-regional-energy-statistics-2014},
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.*

### 数据集元数据
标注创建者：
- 无标注（no-annotation）
语言数据采集方式：
- 公开采集（found）
语言：
- 英语（en）
许可协议：CC BY 4.0
多语言属性：
- 单语言（monolingual）
数据规模：
- 10K<n<100K
原始数据集来源：
- 原始数据集（original）
任务类别：
- 表格分类（tabular-classification）
- 表格回归（tabular-regression）
任务子类别：无
标签：
- 非洲（africa）
- 人道主义（humanitarian）
- HDX
- Electric Sheep Africa
- 能源（energy）
- 设施与基础设施（facilities-infrastructure）
- DZA
- AGO
- BEN
- BWA
- BFA
数据集别名："2014年非洲区域能源统计数据集"
数据集信息：
数据划分：
- 名称：训练集（train）
样本数：13614
- 名称：测试集（test）
样本数：3403

# 2014年非洲区域能源统计数据集

**发布方**：非洲开发银行集团 · **数据源**：[HDX](https://data.humdata.org/dataset/african-regional-energy-statistics-2014) · **许可协议**：`CC BY` · **最后更新时间**：2023-05-02

---

## 摘要

2000-2014年非洲区域能源统计数据集

本数据集的每一行均代表一级行政单元的观测数据。该数据最后一次在HDX平台更新于2023年5月2日。地理覆盖范围：**DZA、AGO、BEN、BWA、BFA、BDI、CPV、CMR及另外50个国家**。

*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。*

---

## 数据集特征

| | |
|---|---|
| **领域** | 人道主义与发展数据 |
| **观测单元** | 一级行政单元观测数据 |
| **总数据行数** | 17018 |
| **列数** | 9（4个数值型列、5个分类型列、0个日期时间型列） |
| **训练集划分** | 13614行 |
| **测试集划分** | 3403行 |
| **地理覆盖范围** | DZA、AGO、BEN、BWA、BFA、BDI、CPV、CMR及另外50个国家 |
| **发布方** | 非洲开发银行集团 |
| **HDX平台最后更新时间** | 2023-05-02 |

---

## 变量说明

**地理类变量**：`region`（取值范围1.0–10516.0）、`regionname`（取值如：非洲、南部非洲、南非）。
**时间类变量**：`date`（取值范围2000.0–2014.0）。
**结果/测量类变量**：`value`（取值范围-4102281.0–8985871.2198）。
**标识/元数据类变量**：`indicatorname`（取值如：电力总产量（GWh）、电力最终消费量（GWh）、石油最终消费量（千吨））、`esa_source`（取值为HDX）、`esa_processed`（取值为2026-04-18）。
**其他变量**：`indicator`（取值范围102.0–21773673.0）、`unit`（取值如：千吨、GWh、太焦耳（TJ））。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/african-regional-energy-statistics-2014")
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 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `indicator` | int64 | 0.0% | 102.0 – 21773673.0（均值6088314.0264） |
| `indicatorname` | object | 0.0% | 电力总产量（GWh）、电力最终消费量（GWh）、石油最终消费量（千吨） |
| `region` | int64 | 0.0% | 1.0 – 10516.0（均值8612.1383） |
| `regionname` | object | 0.0% | 非洲、南部非洲、南非 |
| `unit` | object | 0.0% | 千吨、GWh、太焦耳（TJ） |
| `date` | int64 | 0.0% | 2000.0 – 2014.0（均值2007.2201） |
| `value` | float64 | 0.0% | -4102281.0 – 8985871.2198（均值24953.5928） |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-18 |

---

## 数值统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `indicator` | 102.0 | 21773673.0 | 6088314.0264 | 504.0 |
| `region` | 1.0 | 10516.0 | 8612.1383 | 10303.0 |
| `date` | 2000.0 | 2014.0 | 2007.2201 | 2007.0 |
| `value` | -4102281.0 | 8985871.2198 | 24953.5928 | 655.0 |

---

## 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。列名均转换为小写并标准化为蛇形命名法（snake_case）。常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。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压缩的Parquet格式文件。

---

## 数据集局限性

- 本数据源自非洲开发银行集团，未由Electric Sheep Africa进行独立验证。
- 自动化清洗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。
- 本数据集覆盖58个国家，各国间的地理与方法学差异可能影响跨国比较的有效性。
- 如需查看发布方提供的方法学说明与免责声明，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/african-regional-energy-statistics-2014)。

---

## 引用格式

bibtex
@dataset{hdx_african_regional_energy_statistics_2014,
title = {African Regional Energy Statistics, 2014},
author = {African Development Bank Group},
year = {2023},
url = {https://data.humdata.org/dataset/african-regional-energy-statistics-2014},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}

---

*[Electric Sheep Africa](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。*