electricsheepafrica/africa-daily-cross-border-trade-for-ethiopia-6824
收藏资源简介:
--- 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 - eastern-africa - trade - eth pretty_name: "Ethiopia Daily FEWS NET Cross Border Trade Data" dataset_info: splits: - name: train num_examples: 38785 - name: test num_examples: 9696 --- # Ethiopia Daily FEWS NET Cross Border Trade Data **Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/daily_cross_border_trade_for_ethiopia_6824) · **License:** `cc-by` · **Updated:** 2026-03-30 --- ## Abstract Ethiopia Daily cross border trade data collected by FEWS NET since 2010. Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `start_date`, `period_date` column(s). Geographic scope: **ETH**. *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)** | 48,482 | | **Columns** | 38 (5 numeric, 31 categorical, 2 datetime) | | **Train split** | 38,785 rows | | **Test split** | 9,696 rows | | **Geographic scope** | ETH | | **Publisher** | FEWS NET | | **HDX last updated** | 2026-03-30 | --- ## Variables **Geographic** — `reporting_country` (Ethiopia, Somalia, Kenya), `reporting_country_code` (ET, SO, KE), `source_country_code` (ET, SO, SD), `destination_country_code` (SD, ET, SS), `flow_type` and 8 others. **Temporal** — `start_date`, `period_date`, `value_one_month_ago` (range 0.0–1372872.0), `pct_change_from_one_month_ago` (range -99.9889–178287.6501). **Outcome / Measurement** — `value` (range 0.0–1372872.0). **Identifier / Metadata** — `source` (Ethiopia, Somalia, Sudan), `indicator_name` (TradeFlowQuantity), `source_organization`, `source_document`, `dataseries_name` and 4 others. **Other** — `border_point` (Gambella, Kurmuk, Moyale), `destination` (Sudan, Ethiopia, South Sudan), `cpcv2` (P23520AA, P23161AA, R01122AC), `product` (Refined sugar, Rice (Milled), Maize Grain (White)), `collection_status` and 6 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-daily-cross-border-trade-for-ethiopia-6824") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() ``` --- ## Schema | Column | Type | Null % | Range / Sample Values | |---|---|---|---| | `reporting_country` | object | 0.0% | Ethiopia, Somalia, Kenya | | `reporting_country_code` | object | 0.0% | ET, SO, KE | | `border_point` | object | 0.0% | Gambella, Kurmuk, Moyale | | `source` | object | 0.0% | Ethiopia, Somalia, Sudan | | `source_country_code` | object | 0.0% | ET, SO, SD | | `destination` | object | 0.0% | Sudan, Ethiopia, South Sudan | | `destination_country_code` | object | 0.0% | SD, ET, SS | | `cpcv2` | object | 0.0% | P23520AA, P23161AA, R01122AC | | `product` | object | 0.0% | Refined sugar, Rice (Milled), Maize Grain (White) | | `indicator_name` | object | 0.0% | TradeFlowQuantity | | `start_date` | datetime64[ns] | 0.0% | | | `period_date` | datetime64[ns] | 0.0% | | | `value` | float64 | 0.0% | 0.0 – 1372872.0 (mean 1920.4796) | | `flow_type` | object | 0.0% | | | `trade_type` | object | 0.0% | | | `collection_status` | object | 0.0% | | | `source_organization` | object | 0.0% | | | `source_document` | object | 0.0% | | | `dataseries_name` | object | 0.0% | | | `dataseries` | int64 | 0.0% | 6544175.0 – 7402469.0 (mean 6669150.9641) | | `unit` | object | 0.0% | | | `unit_type` | object | 0.0% | | | `unit_name` | object | 0.0% | | | `status` | object | 0.0% | | | `common_unit` | object | 0.0% | | | `common_unit_quantity` | float64 | 0.0% | 0.0 – 384000000.0 (mean 162639.9936) | | `reporting_country_geographic_group` | object | 0.0% | | | `reporting_country_fewsnet_region` | object | 0.0% | | | `source_geographic_group` | object | 0.0% | | | `source_fewsnet_region` | object | 0.0% | | | `destination_geographic_group` | object | 0.0% | | | `destination_fewsnet_region` | object | 2.7% | | | `value_one_month_ago` | float64 | 70.6% | 0.0 – 1372872.0 (mean 1735.3038) | | `pct_change_from_one_month_ago` | float64 | 70.6% | -99.9889 – 178287.6501 (mean 451.8913) | | `collection_schedule` | object | 0.0% | | | `data_usage_policy` | object | 0.0% | | | `esa_source` | object | 0.0% | | | `esa_processed` | object | 0.0% | | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `value` | 0.0 | 1372872.0 | 1920.4796 | 0.0 | | `dataseries` | 6544175.0 | 7402469.0 | 6669150.9641 | 6614111.0 | | `common_unit_quantity` | 0.0 | 384000000.0 | 162639.9936 | 0.0 | | `value_one_month_ago` | 0.0 | 1372872.0 | 1735.3038 | 400.0 | | `pct_change_from_one_month_ago` | -99.9889 | 178287.6501 | 451.8913 | 225.9259 | --- ## 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`. 10 column(s) with >80% missing values were removed: `id`, `value_one_year_ago`, `value_two_years_ago`, `value_three_years_ago`, `value_four_years_ago`, `value_five_years_ago`.... 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 FEWS NET 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: `value_one_month_ago`, `pct_change_from_one_month_ago`. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/daily_cross_border_trade_for_ethiopia_6824) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_daily_cross_border_trade_for_ethiopia_6824, title = {Ethiopia Daily FEWS NET Cross Border Trade Data}, author = {FEWS NET}, year = {2026}, url = {https://data.humdata.org/dataset/daily_cross_border_trade_for_ethiopia_6824}, 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: - 采集所得 language: - 英语 license: CC-BY 4.0 multilinguality: - 单语言 size_categories: - 10000 < n < 100000 source_datasets: - 原创数据集 task_categories: - 表格分类 - 表格回归 task_ids: [] tags: - 非洲 - 人道主义 - 人道主义数据交换(Humanitarian Data Exchange,HDX) - Electric Sheep Africa - 东非 - 贸易 - 埃塞俄比亚(ETH) pretty_name: "埃塞俄比亚每日FEWS NET跨境贸易数据集" dataset_info: splits: - name: 训练集 num_examples: 38785 - name: 测试集 num_examples: 9696 --- # 埃塞俄比亚每日FEWS NET跨境贸易数据集 **发布方:饥荒早期预警系统网络(Famine Early Warning Systems Network,FEWS NET)** · **来源:[人道主义数据交换(Humanitarian Data Exchange,HDX)](https://data.humdata.org/dataset/daily_cross_border_trade_for_ethiopia_6824)** · **许可证:`cc-by`** · **更新时间:2026-03-30** --- ## 摘要 埃塞俄比亚每日跨境贸易数据由饥荒早期预警系统网络(FEWS NET)自2010年起收集。 数据集中每一行代表一级行政单元的观测样本。时间覆盖范围由`start_date`(开始日期)与`period_date`(周期日期)列标识。地理覆盖范围:**埃塞俄比亚(ETH)**。 *本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet列存格式。* --- ## 数据集特征 | | | |---|---| | **领域** | 人道主义与发展数据 | | **观测单元** | 一级行政单元观测样本 | | **总样本行数** | 48,482 | | **列数** | 38列(5个数值型、31个分类型、2个日期时间型) | | **训练集划分** | 38,785行 | | **测试集划分** | 9,696行 | | **地理覆盖范围** | ETH(埃塞俄比亚) | | **发布方** | FEWS NET | | **HDX最后更新时间** | 2026-03-30 --- ## 变量 **地理类变量** — `reporting_country`(埃塞俄比亚、索马里、肯尼亚)、`reporting_country_code`(ET、SO、KE)、`source_country_code`(ET、SO、SD)、`destination_country_code`(SD、ET、SS)、`flow_type`及另外8个变量。 **时间类变量** — `start_date`、`period_date`、`value_one_month_ago`(取值范围0.0–1372872.0)、`pct_change_from_one_month_ago`(取值范围-99.9889–178287.6501)。 **结果/测量变量** — `value`(取值范围0.0–1372872.0)。 **标识符/元数据变量** — `source`(埃塞俄比亚、索马里、苏丹)、`indicator_name`(TradeFlowQuantity)、`source_organization`、`source_document`、`dataseries_name`及另外4个变量。 **其他变量** — `border_point`(甘贝拉、库尔穆克、莫亚莱)、`destination`(苏丹、埃塞俄比亚、南苏丹)、`cpcv2`(P23520AA、P23161AA、R01122AC)、`product`(精制糖、碾米、白玉米籽粒)、`collection_status`及另外6个变量。 --- ## 快速上手 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-daily-cross-border-trade-for-ethiopia-6824") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 数据结构(Schema) | 列名 | 数据类型 | 空值占比 | 取值范围/示例值 | |---|---|---|---| | `reporting_country` | 字符串(object) | 0.0% | 埃塞俄比亚、索马里、肯尼亚 | | `reporting_country_code` | 字符串(object) | 0.0% | ET、SO、KE | | `border_point` | 字符串(object) | 0.0% | 甘贝拉、库尔穆克、莫亚莱 | | `source` | 字符串(object) | 0.0% | 埃塞俄比亚、索马里、苏丹 | | `source_country_code` | 字符串(object) | 0.0% | ET、SO、SD | | `destination` | 字符串(object) | 0.0% | 苏丹、埃塞俄比亚、南苏丹 | | `destination_country_code` | 字符串(object) | 0.0% | SD、ET、SS | | `cpcv2` | 字符串(object) | 0.0% | P23520AA、P23161AA、R01122AC | | `product` | 字符串(object) | 0.0% | 精制糖、碾米、白玉米籽粒 | | `indicator_name` | 字符串(object) | 0.0% | TradeFlowQuantity | | `start_date` | 日期时间型(datetime64[ns]) | 0.0% | 无 | | `period_date` | 日期时间型(datetime64[ns]) | 0.0% | 无 | | `value` | 浮点型(float64) | 0.0% | 0.0 – 1372872.0(均值1920.4796) | | `flow_type` | 字符串(object) | 0.0% | 无 | | `trade_type` | 字符串(object) | 0.0% | 无 | | `collection_status` | 字符串(object) | 0.0% | 无 | | `source_organization` | 字符串(object) | 0.0% | 无 | | `source_document` | 字符串(object) | 0.0% | 无 | | `dataseries_name` | 字符串(object) | 0.0% | 无 | | `dataseries` | 整型(int64) | 0.0% | 6544175.0 – 7402469.0(均值6669150.9641) | | `unit` | 字符串(object) | 0.0% | 无 | | `unit_type` | 字符串(object) | 0.0% | 无 | | `unit_name` | 字符串(object) | 0.0% | 无 | | `status` | 字符串(object) | 0.0% | 无 | | `common_unit` | 字符串(object) | 0.0% | 无 | | `common_unit_quantity` | 浮点型(float64) | 0.0% | 0.0 – 384000000.0(均值162639.9936) | | `reporting_country_geographic_group` | 字符串(object) | 0.0% | 无 | | `reporting_country_fewsnet_region` | 字符串(object) | 0.0% | 无 | | `source_geographic_group` | 字符串(object) | 0.0% | 无 | | `source_fewsnet_region` | 字符串(object) | 0.0% | 无 | | `destination_geographic_group` | 字符串(object) | 0.0% | 无 | | `destination_fewsnet_region` | 字符串(object) | 2.7% | 无 | | `value_one_month_ago` | 浮点型(float64) | 70.6% | 0.0 – 1372872.0(均值1735.3038) | | `pct_change_from_one_month_ago` | 浮点型(float64) | 70.6% | -99.9889 – 178287.6501(均值451.8913) | | `collection_schedule` | 字符串(object) | 0.0% | 无 | | `data_usage_policy` | 字符串(object) | 0.0% | 无 | | `esa_source` | 字符串(object) | 0.0% | 无 | | `esa_processed` | 字符串(object) | 0.0% | 无 | --- ## 数值型变量统计摘要 | 列名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `value` | 0.0 | 1372872.0 | 1920.4796 | 0.0 | | `dataseries` | 6544175.0 | 7402469.0 | 6669150.9641 | 6614111.0 | | `common_unit_quantity` | 0.0 | 384000000.0 | 162639.9936 | 0.0 | | `value_one_month_ago` | 0.0 | 1372872.0 | 1735.3038 | 400.0 | | `pct_change_from_one_month_ago` | -99.9889 | 178287.6501 | 451.8913 | 225.9259 | --- ## 数据整理流程 原始数据通过CKAN应用程序编程接口(API)从HDX下载,并转换为Parquet列存格式。列名统一转换为小写,并采用蛇形命名法(snake_case)进行标准化。常见缺失值标记(`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`)被统一替换为`NaN`。删除了10列缺失值占比超过80%的字段:`id`、`value_one_year_ago`、`value_two_years_ago`、`value_three_years_ago`、`value_four_years_ago`、`value_five_years_ago`等。根据解析成功率(阈值>85%),将2列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,并保存为Snappy压缩格式的Parquet文件。 --- ## 数据集局限性 - 数据源自FEWS NET,未经过Electric Sheep Africa的独立验证。 - 自动化清洗流程无法修正原始数据采集阶段的错报值、定义不一致或采样偏差问题。 - 以下两列缺失值占比超过20%,在建模过程中需谨慎使用:`value_one_month_ago`与`pct_change_from_one_month_ago`。 - 如需查看发布方的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/daily_cross_border_trade_for_ethiopia_6824)。 --- ## 引用 bibtex @dataset{hdx_africa_daily_cross_border_trade_for_ethiopia_6824, title = {埃塞俄比亚每日FEWS NET跨境贸易数据集}, author = {FEWS NET}, year = {2026}, url = {https://data.humdata.org/dataset/daily_cross_border_trade_for_ethiopia_6824}, note = {由Electric Sheep Africa重新打包以适配机器学习场景,详见https://huggingface.co/electricsheepafrica} } --- *[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施提供商,总部位于尼日利亚拉各斯。*



