electricsheepafrica/africa-northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state

--- annotations_creators: - no-annotation language_creators: - found language: - en license: cc-by-4.0 multilinguality: - monolingual size_categories: - 1K<n<10K source_datasets: - original task_categories: - tabular-classification - tabular-regression task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - affected-population - displacement - hxl - internally-displaced-persons-idp - populated-places-settlements - returnees - nga pretty_name: "Northeast Nigeria - Displacement for Borno, Adamawa, and Yobe States (BAY State)" dataset_info: splits: - name: train num_examples: 1380 - name: test num_examples: 345 --- # Northeast Nigeria - Displacement for Borno, Adamawa, and Yobe States (BAY State) **Publisher:** OCHA Nigeria · **Source:** [HDX](https://data.humdata.org/dataset/northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state) · **License:** `cc-by-igo` · **Updated:** 2025-02-04 --- ## Abstract Northeast Nigeria displacement datasets by rounds of assessment from the in country IOM/DTM. Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2025-02-04. Geographic scope: **NGA**. *Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).* --- ## Dataset Characteristics | | | |---|---| | **Domain** | Forced displacement and migration | | **Unit of observation** | Subnational administrative unit observations | | **Rows (total)** | 1,726 | | **Columns** | 10 (2 numeric, 8 categorical, 0 datetime) | | **Train split** | 1,380 rows | | **Test split** | 345 rows | | **Geographic scope** | NGA | | **Publisher** | OCHA Nigeria | | **HDX last updated** | 2025-02-04 | --- ## Variables **Geographic** — `state_name` (BORNO, ADAMAWA, YOBE), `state_pcode` (NG008, NG002, NG036), `lga_name` (MAIDUGURI, JERE, CHIBOK), `lga_pcode` (NG008021, NG008013, NG008006), `ward_name` (MAISANDARI, DUSUMAN, OLD MAIDUGURI) and 1 others. **Demographic** — `households` (range 1.0–21124.0), `individuals` (range 8.0–73012.0). **Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-17). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `state_name` | object | 0.0% | BORNO, ADAMAWA, YOBE | | `state_pcode` | object | 0.0% | NG008, NG002, NG036 | | `lga_name` | object | 0.0% | MAIDUGURI, JERE, CHIBOK | | `lga_pcode` | object | 0.0% | NG008021, NG008013, NG008006 | | `ward_name` | object | 0.0% | MAISANDARI, DUSUMAN, OLD MAIDUGURI | | `ward_pcode` | object | 0.0% | NG008021013, NG008013004, NG008013011 | | `households` | float64 | 0.1% | 1.0 – 21124.0 (mean 271.869) | | `individuals` | float64 | 0.1% | 8.0 – 73012.0 (mean 1308.5942) | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-17 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `households` | 1.0 | 21124.0 | 271.869 | 65.0 | | `individuals` | 8.0 | 73012.0 | 1308.5942 | 355.0 | --- ## 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`. 12 exact duplicate rows were removed. 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 OCHA Nigeria 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/northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_northeast_nigeria_displacement_for_borno_adamawa_and_yobe_states_bay_state, title = {Northeast Nigeria - Displacement for Borno, Adamawa, and Yobe States (BAY State)}, author = {OCHA Nigeria}, year = {2025}, url = {https://data.humdata.org/dataset/northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state}, 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（no-annotation） language_creators: - 现有语料采集（found） language: - 英语（en） license: - CC BY 4.0（cc-by-4.0） multilinguality: - 单语（monolingual） size_categories: - 1000<n≤10000（1K<n<10K） source_datasets: - 原创数据集（original） task_categories: - 表格分类（tabular-classification） - 表格回归（tabular-regression） task_ids: - 无 tags: - 非洲（africa） - 人道主义（humanitarian） - HDX（hdx） - Electric Sheep Africa（electric-sheep-africa） - 受影响人口（affected-population） - 流离失所（displacement） - HXL（hxl） - 国内流离失所者（internally-displaced-persons-idp） - 聚居地与定居点（populated-places-settlements） - 返回者（returnees） - 尼日利亚（nga） pretty_name: "尼日利亚东北部——博尔诺州、阿达马瓦州和约贝州流离失所情况数据集（BAY州）" dataset_info: splits: - name: train num_examples: 1380 - name: test num_examples: 345 --- # 尼日利亚东北部——博尔诺州、阿达马瓦州和约贝州流离失所情况数据集（BAY州） **发布方：** 尼日利亚人道主义事务协调厅（OCHA Nigeria） · **来源：** [HDX（hdx）](https://data.humdata.org/dataset/northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state) · **许可证：** `cc-by-igo` · **更新时间：** 2025-02-04 --- ## 摘要 本数据集基于尼日利亚境内国际移民组织/流离失所监测中心（IOM/DTM）的多轮评估结果，涵盖尼日利亚东北部流离失所情况。 数据集中每一行代表一个次国家级行政单元的观测记录。本数据集最近一次在HDX平台的更新时间为2025-02-04。地理覆盖范围：**尼日利亚（NGA）**。 *本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为可供机器学习使用的Parquet格式。* --- ## 数据集特征 | | | |---|---| | **研究领域** | 强迫流离失所与移民 | | **观测单元** | 次国家级行政单元观测记录 | | **总数据行数** | 1,726 | | **字段总数** | 10（2个数值型字段，8个分类型字段，0个日期时间型字段） | | **训练集划分** | 1,380条数据 | | **测试集划分** | 345条数据 | | **地理覆盖范围** | 尼日利亚（NGA） | | **发布方** | 尼日利亚人道主义事务协调厅（OCHA Nigeria） | | **HDX平台最后更新时间** | 2025-02-04 | --- ## 字段说明 ### 地理类字段 `state_name`（州名：博尔诺、阿达马瓦、约贝）、`state_pcode`（州编码：NG008、NG002、NG036）、`lga_name`（地方政府区名：迈杜古里、杰雷、奇博克）、`lga_pcode`（地方政府区编码：NG008021、NG008013、NG008006）、`ward_name`（选区名：迈桑达里、杜苏曼、旧迈杜古里）及1个额外字段。 ### 人口统计类字段 `households`（家庭户数，取值范围1.0~21124.0）、`individuals`（人口数，取值范围8.0~73012.0）。 ### 标识符与元数据字段 `esa_source`（数据来源：HDX）、`esa_processed`（数据处理时间：2026-04-17）。 --- ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据结构 | 字段名 | 数据类型 | 缺失率 | 取值范围/示例值 | |---|---|---|---| | `state_name` | 字符串型 | 0.0% | 博尔诺、阿达马瓦、约贝 | | `state_pcode` | 字符串型 | 0.0% | NG008、NG002、NG036 | | `lga_name` | 字符串型 | 0.0% | 迈杜古里、杰雷、奇博克 | | `lga_pcode` | 字符串型 | 0.0% | NG008021、NG008013、NG008006 | | `ward_name` | 字符串型 | 0.0% | 迈桑达里、杜苏曼、旧迈杜古里 | | `ward_pcode` | 字符串型 | 0.0% | NG008021013、NG008013004、NG008013011 | | `households` | 浮点型 | 0.1% | 1.0 – 21124.0（均值271.869） | | `individuals` | 浮点型 | 0.1% | 8.0 – 73012.0（均值1308.5942） | | `esa_source` | 字符串型 | 0.0% | HDX | | `esa_processed` | 字符串型 | 0.0% | 2026-04-17 | --- ## 数值型字段统计 | 字段名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `households` | 1.0 | 21124.0 | 271.869 | 65.0 | | `individuals` | 8.0 | 73012.0 | 1308.5942 | 355.0 | --- ## 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。字段名统一转换为小写蛇形命名法。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。删除了12条完全重复的数据行。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。本数据集采用固定随机种子（42）按80/20的比例划分为训练集与测试集，并以Snappy压缩格式保存为Parquet文件。 --- ## 局限性说明 - 本数据集源自尼日利亚人道主义事务协调厅，未由Electric Sheep Africa进行独立验证。 - 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。 - 如需查看发布方提供的官方方法论说明与免责声明，请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state)。 --- ## 引用格式 bibtex @dataset{hdx_africa_northeast_nigeria_displacement_for_borno_adamawa_and_yobe_states_bay_state, title = {尼日利亚东北部——博尔诺州、阿达马瓦州和约贝州流离失所情况数据集（BAY州）}, author = {尼日利亚人道主义事务协调厅（OCHA Nigeria）}, year = {2025}, url = {https://data.humdata.org/dataset/northeast-nigeria-displacement-for-borno-adamawa-and-yobe-states-bay-state}, note = {由Electric Sheep Africa重新打包以适配机器学习任务（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。*