electricsheepafrica/africa-srf-2014

--- 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 task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - education - health - humanitarian-needs-overview-hno - nutrition - population - shelter - water-sanitation-and-hygiene-wash - som pretty_name: "Somalia beneficiary figures (targeted and reached) by month, Jan - Dec 2014" dataset_info: splits: - name: train num_examples: 1880 - name: test num_examples: 470 --- # Somalia beneficiary figures (targeted and reached) by month, Jan - Dec 2014 **Publisher:** OCHA Somalia · **Source:** [HDX](https://data.humdata.org/dataset/srf-2014) · **License:** `cc-by-igo` · **Updated:** 2023-11-15 --- ## Abstract 2014 response data for Somalia. (Single Reporting Format) The data shows targets and response by cluster per month. The data is sourced from the humanitarian clusters in Somalia. Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `date` column(s). Geographic scope: **SOM**. *Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).* --- ## Dataset Characteristics | | | |---|---| | **Domain** | Public health | | **Unit of observation** | First-level administrative unit observations | | **Rows (total)** | 2,350 | | **Columns** | 14 (3 numeric, 10 categorical, 1 datetime) | | **Train split** | 1,880 rows | | **Test split** | 470 rows | | **Geographic scope** | SOM | | **Publisher** | OCHA Somalia | | **HDX last updated** | 2023-11-15 | --- ## Variables **Geographic** — `region` (Awdal, Lower Juba, Nugaal), `category` (FSC, Wash, Education), `end_year_target` (550, 6,000, 0), `cumulative_reached_to_date` (0, 600, 3,265), `cumulative_reached_num_to_date` (range 0.0–1427330.0). **Temporal** — `date`, `month_num` (range 1.0–12.0), `month` (December, April, May), `current_target_to_date` (0, 3,000, 1,500), `percent_current_target_reached_to_date` (0%, 6%, 4%) and 1 others. **Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-08). **Other** — `metric` (Number of people receiving primary and/or basic secondary health care services, Number of people targeted through interventions geared towards improving access to food and safety nets, Number of people targeted through livelihood investment and assets activities). --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-srf-2014") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `region` | object | 0.0% | Awdal, Lower Juba, Nugaal | | `date` | datetime64[ns] | 0.0% | | | `month_num` | int64 | 0.0% | 1.0 – 12.0 (mean 6.9677) | | `month` | object | 0.0% | December, April, May | | `category` | object | 0.0% | FSC, Wash, Education | | `metric` | object | 0.0% | Number of people receiving primary and/or basic secondary health care services, Number of people targeted through interventions geared towards improving access to food and safety nets, Number of people targeted through livelihood investment and assets activities | | `end_year_target` | object | 0.0% | 550, 6,000, 0 | | `current_target_to_date` | object | 0.0% | 0, 3,000, 1,500 | | `cumulative_reached_to_date` | object | 25.5% | 0, 600, 3,265 | | `cumulative_reached_num_to_date` | float64 | 0.0% | 0.0 – 1427330.0 (mean 45403.4732) | | `percent_current_target_reached_to_date` | object | 0.0% | 0%, 6%, 4% | | `ratio_of_current_target_reached_to_date` | float64 | 0.0% | 0.0 – 13.89 (mean 0.6117) | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-08 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `month_num` | 1.0 | 12.0 | 6.9677 | 7.0 | | `cumulative_reached_num_to_date` | 0.0 | 1427330.0 | 45403.4732 | 1948.0 | | `ratio_of_current_target_reached_to_date` | 0.0 | 13.89 | 0.6117 | 0.25 | --- ## 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`. 1 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 Somalia 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: `cumulative_reached_to_date`. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/srf-2014) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_srf_2014, title = {Somalia beneficiary figures (targeted and reached) by month, Jan - Dec 2014}, author = {OCHA Somalia}, year = {2023}, url = {https://data.humdata.org/dataset/srf-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.*--- annotations_creators: - 无注释 language_creators: - 现成采集 language: - 英语（en） license: 知识共享署名4.0（CC BY 4.0） multilinguality: - 单语言 size_categories: - 1000 < 样本数 < 10000 source_datasets: - 原创数据集 task_categories: - 表格分类 task_ids: - 无 tags: - 非洲 - 人道主义 - HDX - 电羊非洲（Electric Sheep Africa） - 教育 - 卫生 - 人道主义需求概览（humanitarian-needs-overview-hno） - 营养 - 人口 - 住所 - 水、环境卫生与个人卫生（WASH, water-sanitation-and-hygiene-wash） - 索马里（SOM） pretty_name: "2014年1-12月索马里受益人群月度统计（目标人数与实际覆盖人数）" dataset_info: splits: - name: train num_examples: 1880 - name: test num_examples: 470 --- # 2014年1-12月索马里受益人群月度统计（目标人数与实际覆盖人数） **发布方：** 联合国人道主义事务协调厅索马里办事处（OCHA Somalia） · **数据源：** [人类数据交换平台（HDX）](https://data.humdata.org/dataset/srf-2014) · **许可证：** `cc-by-igo` · **更新时间：** 2023-11-15 --- ## 摘要 本数据集包含2014年索马里人道主义响应的单报告格式（Single Reporting Format, SRF）数据，展示了各事务集群月度目标与响应情况，数据源自索马里人道主义事务集群。 数据集内每一行代表一级行政单元的观测记录，时间范围由`date`（日期）列标识，地理覆盖范围为**索马里（SOM）**。 *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。* --- ## 数据集特征 | | | |---|---| | **领域** | 公共卫生 | | **观测单元** | 一级行政单元观测记录 | | **总行数** | 2350 | | **列数** | 14列（3列数值型、10列分类型、1列日期型） | | **训练集划分** | 1880行 | | **测试集划分** | 470行 | | **地理覆盖范围** | 索马里（SOM） | | **发布方** | 联合国人道主义事务协调厅索马里办事处（OCHA Somalia） | | **HDX最后更新时间** | 2023-11-15 --- ## 变量说明 ### 地理变量 `region`（地区：奥达勒、下朱巴、努加尔）、`category`（类别：FSC、Wash、教育）、`end_year_target`（年度目标值：550、6000、0）、`cumulative_reached_to_date`（累计覆盖人数至当前：0、600、3265）、`cumulative_reached_num_to_date`（累计覆盖人数数值：范围0.0–1427330.0）。 ### 时间变量 `date`（日期）、`month_num`（月份序号：范围1.0–12.0）、`month`（月份：12月、4月、5月）、`current_target_to_date`（当期至当前目标值：0、3000、1500）、`percent_current_target_reached_to_date`（当期目标完成百分比：0%、6%、4%）及1个其他变量。 ### 标识符/元数据变量 `esa_source`（数据来源：HDX）、`esa_processed`（处理时间：2026-04-08）。 ### 其他变量 `metric`（统计指标：接受初级和/或基础中等医疗服务的人数、通过改善粮食获取与安全网的干预措施覆盖的目标人数、通过生计投资与资产活动覆盖的目标人数）。 --- ## 快速使用示例 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-srf-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 | 缺失率 | 取值范围/示例值 | |---|---|---|---| | `region` | 字符型（object） | 0.0% | 奥达勒、下朱巴、努加尔 | | `date` | 日期时间型（datetime64[ns]） | 0.0% | 无 | | `month_num` | 整型（int64） | 0.0% | 1.0 – 12.0（均值6.9677） | | `month` | 字符型（object） | 0.0% | 12月、4月、5月 | | `category` | 字符型（object） | 0.0% | FSC、Wash、教育 | | `metric` | 字符型（object） | 0.0% | 接受初级和/或基础中等医疗服务的人数、通过改善粮食获取与安全网的干预措施覆盖的目标人数、通过生计投资与资产活动覆盖的目标人数 | | `end_year_target` | 字符型（object） | 0.0% | 550、6000、0 | | `current_target_to_date` | 字符型（object） | 0.0% | 0、3000、1500 | | `cumulative_reached_to_date` | 字符型（object） | 25.5% | 0、600、3265 | | `cumulative_reached_num_to_date` | 浮点型（float64） | 0.0% | 0.0 – 1427330.0（均值45403.4732） | | `percent_current_target_reached_to_date` | 字符型（object） | 0.0% | 0%、6%、4% | | `ratio_of_current_target_reached_to_date` | 浮点型（float64） | 0.0% | 0.0 – 13.89（均值0.6117） | | `esa_source` | 字符型（object） | 0.0% | HDX | | `esa_processed` | 字符型（object） | 0.0% | 2026-04-08 | --- ## 数值型变量统计 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `month_num` | 1.0 | 12.0 | 6.9677 | 7.0 | | `cumulative_reached_num_to_date` | 0.0 | 1427330.0 | 45403.4732 | 1948.0 | | `ratio_of_current_target_reached_to_date` | 0.0 | 13.89 | 0.6117 | 0.25 | --- ## 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。所有列名均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`。根据解析成功率（阈值>85%），将1列从字符串类型转换为数值型或日期时间型。采用固定随机种子（42）将数据集以80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式。 --- ## 数据集局限性 - 数据源自联合国人道主义事务协调厅索马里办事处，未经过电羊非洲的独立验证。 - 自动化清洗无法修正原始数据收集中的错报值、定义不一致或抽样偏差问题。 - 以下列存在超过20%的缺失值，在建模时需谨慎使用：`cumulative_reached_to_date`。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/srf-2014)查看发布方提供的方法说明与注意事项。 --- ## 引用格式 bibtex @dataset{hdx_africa_srf_2014, title = {2014年1-12月索马里受益人群月度统计（目标人数与实际覆盖人数）}, author = {联合国人道主义事务协调厅索马里办事处（OCHA Somalia）}, year = {2023}, url = {https://data.humdata.org/dataset/srf-2014}, note = {由电羊非洲（Electric Sheep Africa）重新打包以适配机器学习（https://huggingface.co/electricsheepafrica)} } --- *[电羊非洲（Electric Sheep Africa）——非洲机器学习数据集基础设施，尼日利亚拉各斯。]*