electricsheepafrica/africa-north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018

---
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
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- geodata
- needs-assessment
- severity
- shelter
- nga
pretty_name: "North East Nigeria Shelter and NFI Needs Severity Mapping by LGA as of June 2018"
dataset_info:
splits:
- name: train
num_examples: 52
- name: test
num_examples: 13
---

# North East Nigeria Shelter and NFI Needs Severity Mapping by LGA as of June 2018

**Publisher:** iMMAP Inc. · **Source:** [HDX](https://data.humdata.org/dataset/north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018) · **License:** `cc-by` · **Updated:** 2024-09-13

---

## Abstract

Dataset covers Shelter and Non-food Items needs severity mapping by Local Government Area (LGA) as of June 2018. Dataset covers Borno, Yobe and Adamawa, the three crisis-affected states; Shelter needs severity mapping by Local Government Area (LGA) as of June 2018. Dataset covers Borno, Yobe and Adamawa, the three crisis-affected states; Non-food Items needs severity mapping by Local Government Area (LGA) as of June 2018. The zipped shapefile covers Borno, Yobe and Adamawa, the three crisis-affected states; and a CSV dataset containing Shelter and Non-food Items (NFI) needs severity mapping combined, by Local Government Area (LGA) as of June 2018, covering the three crisis-affected states of Borno, Yobe and Adamawa.

Each row in this dataset represents subnational administrative unit observations. Temporal coverage is indicated by the `date`, `validon` column(s). Geographic scope: **NGA**.

*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)** | 65 |
| **Columns** | 16 (5 numeric, 9 categorical, 2 datetime) |
| **Train split** | 52 rows |
| **Test split** | 13 rows |
| **Geographic scope** | NGA |
| **Publisher** | iMMAP Inc. |
| **HDX last updated** | 2024-09-13 |

---

## Variables

**Geographic** — `admin2name` (Bade, Toungo, Yola North), `admin2pcod` (NG036001, NG002019, NG002020), `admin2refn` (Bade, Toungo, Yola North), `admin1name` (Borno, Adamawa, Yobe), `admin1pcod` (NG008, NG002, NG036) and 2 others.

**Temporal** — `date`.

**Identifier / Metadata** — `validon`, `validto` (range 0.0–0.0), `esa_source` (HDX), `esa_processed` (2026-04-08).

**Other** — `shape_leng` (range 0.2743–5.2851), `shape_area` (range 0.0052–0.494), `nfineeds` (range 0.0–29344.0), `shelterneeds` (range 0.0–41386.0).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `admin2name` | object | 0.0% | Bade, Toungo, Yola North |
| `admin2pcod` | object | 0.0% | NG036001, NG002019, NG002020 |
| `admin2refn` | object | 0.0% | Bade, Toungo, Yola North |
| `admin1name` | object | 0.0% | Borno, Adamawa, Yobe |
| `admin1pcod` | object | 0.0% | NG008, NG002, NG036 |
| `admin0name` | object | 0.0% | Nigeria |
| `admin0pcod` | object | 0.0% | NG |
| `date` | datetime64[ns] | 0.0% | |
| `validon` | datetime64[ns] | 0.0% | |
| `validto` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `shape_leng` | float64 | 0.0% | 0.2743 – 5.2851 (mean 2.1746) |
| `shape_area` | float64 | 0.0% | 0.0052 – 0.494 (mean 0.1973) |
| `nfineeds` | int64 | 0.0% | 0.0 – 29344.0 (mean 3015.9385) |
| `shelterneeds` | int64 | 0.0% | 0.0 – 41386.0 (mean 3996.7692) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `validto` | 0.0 | 0.0 | 0.0 | 0.0 |
| `shape_leng` | 0.2743 | 5.2851 | 2.1746 | 2.1857 |
| `shape_area` | 0.0052 | 0.494 | 0.1973 | 0.1761 |
| `nfineeds` | 0.0 | 29344.0 | 3015.9385 | 1095.0 |
| `shelterneeds` | 0.0 | 41386.0 | 3996.7692 | 1662.0 |

---

## 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`. 4 column(s) with >80% missing values were removed: `admin2altn`, `admin2al_1`, `unnamed_16`, `unnamed_17`. 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 iMMAP Inc. 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/north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_north_east_nigeria_shelter_and_nfi_needs_severity_mapping_by_lga_as_of_june_2018,
title = {North East Nigeria Shelter and NFI Needs Severity Mapping by LGA as of June 2018},
author = {iMMAP Inc.},
year = {2024},
url = {https://data.humdata.org/dataset/north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018},
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
- 语言创建方式：采集获取
- 语言：英语
- 许可协议：CC BY 4.0
- 多语言类型：单语言
- 样本规模：少于1000条
- 源数据集类型：原始数据集
- 任务类别：表格分类、其他
- 任务子类别：无
- 标签：非洲、人道主义、人道主义数据交换（HDX）、Electric Sheep Africa、地理数据、需求评估、严重程度、住房、尼日利亚（NGA）
- 美观名称：2018年6月尼日利亚东北部地方政府区域住房与非食品物品需求严重程度映射

# 2018年6月尼日利亚东北部地方政府区域（LGA）住房与非食品物品（NFI）需求严重程度映射

**发布方**：iMMAP公司 · **来源**：[人道主义数据交换（HDX）](https://data.humdata.org/dataset/north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018) · **许可协议**：`CC BY` · **最后更新时间**：2024-09-13

---

## 摘要
本数据集涵盖2018年6月按地方政府区域（Local Government Area，简称LGA）划分的住房与非食品物品需求严重程度映射数据，覆盖博尔诺州、约贝州和阿达马瓦州这三个受危机影响的州。其中，住房需求严重程度映射与非食品物品需求严重程度映射均覆盖上述三州。打包后的形状文件（shapefile）涵盖上述三州；另有CSV格式数据集，整合了2018年6月按地方政府区域划分的住房与非食品物品（Non-Food Items，简称NFI）需求严重程度映射数据，同样覆盖博尔诺州、约贝州和阿达马瓦州。
本数据集的每一行代表一个次国家级行政单元的观测数据。时间覆盖范围由`date`、`validon`字段标识。地理范围：**尼日利亚（NGA）**。
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
| 指标 | 详情 |
|---|---|
| **领域** | 粮食安全与营养 |
| **观测单元** | 次国家级行政单元 |
| **总样本行数** | 65 |
| **字段总数** | 16个（5个数值型、9个分类型、2个日期时间型） |
| **训练集划分** | 52行 |
| **测试集划分** | 13行 |
| **地理范围** | 尼日利亚（NGA） |
| **发布方** | iMMAP公司 |
| **HDX最后更新时间** | 2024-09-13 |

---

## 字段分类
- **地理类字段**：`admin2name`（巴德、通古、约拉北）、`admin2pcod`（NG036001、NG002019、NG002020）、`admin2refn`（巴德、通古、约拉北）、`admin1name`（博尔诺、阿达马瓦、约贝）、`admin1pcod`（NG008、NG002、NG036）及另外2个字段。
- **时间类字段**：`date`。
- **标识符/元数据字段**：`validon`、`validto`（取值范围0.0–0.0）、`esa_source`（HDX）、`esa_processed`（2026-04-08）。
- **其他字段**：`shape_leng`（取值范围0.2743–5.2851）、`shape_area`（取值范围0.0052–0.494）、`nfineeds`（取值范围0.0–29344.0）、`shelterneeds`（取值范围0.0–41386.0）。

---

## 快速上手示例
python
from datasets import load_dataset

# 加载数据集
ds = load_dataset("electricsheepafrica/africa-north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018")
# 将训练集转换为Pandas DataFrame
train = ds["train"].to_pandas()
# 将测试集转换为Pandas DataFrame
test = ds["test"].to_pandas()

# 打印训练集形状
print(train.shape)
# 查看训练集前5行数据
train.head()

---

## 字段架构
| 字段名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `admin2name` | 字符串型 | 0.0% | 巴德、通古、约拉北 |
| `admin2pcod` | 字符串型 | 0.0% | NG036001、NG002019、NG002020 |
| `admin2refn` | 字符串型 | 0.0% | 巴德、通古、约拉北 |
| `admin1name` | 字符串型 | 0.0% | 博尔诺、阿达马瓦、约贝 |
| `admin1pcod` | 字符串型 | 0.0% | NG008、NG002、NG036 |
| `admin0name` | 字符串型 | 0.0% | 尼日利亚 |
| `admin0pcod` | 字符串型 | 0.0% | NG |
| `date` | 日期时间型 | 0.0% | 无 |
| `validon` | 日期时间型 | 0.0% | 无 |
| `validto` | 整型 | 0.0% | 0.0 – 0.0（均值0.0） |
| `shape_leng` | 浮点型 | 0.0% | 0.2743 – 5.2851（均值2.1746） |
| `shape_area` | 浮点型 | 0.0% | 0.0052 – 0.494（均值0.1973） |
| `nfineeds` | 整型 | 0.0% | 0.0 – 29344.0（均值3015.9385） |
| `shelterneeds` | 整型 | 0.0% | 0.0 – 41386.0（均值3996.7692） |
| `esa_source` | 字符串型 | 0.0% | HDX |
| `esa_processed` | 字符串型 | 0.0% | 2026-04-08 |

---

## 数值型字段统计摘要
| 字段名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `validto` | 0.0 | 0.0 | 0.0 | 0.0 |
| `shape_leng` | 0.2743 | 5.2851 | 2.1746 | 2.1857 |
| `shape_area` | 0.0052 | 0.494 | 0.1973 | 0.1761 |
| `nfineeds` | 0.0 | 29344.0 | 3015.9385 | 1095.0 |
| `shelterneeds` | 0.0 | 41386.0 | 3996.7692 | 1662.0 |

---

## 数据整理流程
原始数据通过CKAN应用程序编程接口从HDX下载，并转换为Parquet格式。字段名称统一转换为小写，并遵循蛇形命名法（snake_case）进行标准化。常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。移除了4个缺失值占比超过80%的字段：`admin2altn`、`admin2al_1`、`unnamed_16`、`unnamed_17`。基于解析成功率（阈值为85%），将2个字段从字符串类型转换为数值型或日期时间型。数据集以固定随机种子（42）按80/20的比例划分为训练集与测试集，并以Snappy压缩的Parquet格式保存。

---

## 数据集局限性
- 本数据集源自iMMAP公司，尚未由Electric Sheep Africa进行独立验证。
- 自动化数据清洗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条款，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018)。

---

## 引用格式
bibtex
@dataset{hdx_africa_north_east_nigeria_shelter_and_nfi_needs_severity_mapping_by_lga_as_of_june_2018,
title = {2018年6月尼日利亚东北部地方政府区域住房与非食品物品需求严重程度映射},
author = {iMMAP公司},
year = {2024},
url = {https://data.humdata.org/dataset/north-east-nigeria-shelter-and-nfi-needs-severity-mapping-by-lga-as-of-june-2018},
note = {由Electric Sheep Africa重新打包以适配机器学习应用 (https://huggingface.co/electricsheepafrica)}
}

---

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