electricsheepafrica/africa-daily-cross-border-trade-for-kenya-6824

---
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
- ken
pretty_name: "Kenya Daily FEWS NET Cross Border Trade Data"
dataset_info:
splits:
- name: train
num_examples: 31952
- name: test
num_examples: 7988
---

# Kenya Daily FEWS NET Cross Border Trade Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/daily_cross_border_trade_for_kenya_6824) · **License:** `cc-by` · **Updated:** 2026-03-30

---

## Abstract

Kenya 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: **KEN**.

*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)** | 39,940 |
| **Columns** | 38 (5 numeric, 31 categorical, 2 datetime) |
| **Train split** | 31,952 rows |
| **Test split** | 7,988 rows |
| **Geographic scope** | KEN |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-03-30 |

---

## Variables

**Geographic** — `reporting_country` (Kenya, Tanzania, United Republic of, Somalia), `reporting_country_code` (KE, TZ, SO), `source_country_code` (TZ, KE, ET), `destination_country_code` (KE, TZ, SO), `flow_type` and 8 others.

**Temporal** — `start_date`, `period_date`, `value_one_month_ago` (range 0.0889–48462142.25), `pct_change_from_one_month_ago` (range -99.9167–614741.6667).

**Outcome / Measurement** — `value` (range 0.0–193848569.0).

**Identifier / Metadata** — `source` (Tanzania, United Republic of, Kenya, Ethiopia), `indicator_name` (TradeFlowQuantity), `source_organization`, `source_document`, `dataseries_name` and 4 others.

**Other** — `border_point` (Taveta, Moyale, Tarakea), `destination` (Kenya, Tanzania, United Republic of, Somalia), `cpcv2` (R01122AC, P23161AA, R01701AA), `product` (Maize Grain (White), Rice (Milled), Beans (mixed)), `collection_status` and 6 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-daily-cross-border-trade-for-kenya-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% | Kenya, Tanzania, United Republic of, Somalia |
| `reporting_country_code` | object | 0.0% | KE, TZ, SO |
| `border_point` | object | 0.0% | Taveta, Moyale, Tarakea |
| `source` | object | 0.0% | Tanzania, United Republic of, Kenya, Ethiopia |
| `source_country_code` | object | 0.0% | TZ, KE, ET |
| `destination` | object | 0.0% | Kenya, Tanzania, United Republic of, Somalia |
| `destination_country_code` | object | 0.0% | KE, TZ, SO |
| `cpcv2` | object | 0.0% | R01122AC, P23161AA, R01701AA |
| `product` | object | 0.0% | Maize Grain (White), Rice (Milled), Beans (mixed) |
| `indicator_name` | object | 0.0% | TradeFlowQuantity |
| `start_date` | datetime64[ns] | 0.0% | |
| `period_date` | datetime64[ns] | 0.0% | |
| `value` | float64 | 0.0% | 0.0 – 193848569.0 (mean 147452.5806) |
| `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% | 6544288.0 – 7402479.0 (mean 6659592.5972) |
| `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 – 737810000.0 (mean 401073.4535) |
| `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 | 0.0% | |
| `value_one_month_ago` | float64 | 74.0% | 0.0889 – 48462142.25 (mean 128202.8483) |
| `pct_change_from_one_month_ago` | float64 | 74.0% | -99.9167 – 614741.6667 (mean 642.2668) |
| `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 | 193848569.0 | 147452.5806 | 0.0 |
| `dataseries` | 6544288.0 | 7402479.0 | 6659592.5972 | 6614009.0 |
| `common_unit_quantity` | 0.0 | 737810000.0 | 401073.4535 | 0.0 |
| `value_one_month_ago` | 0.0889 | 48462142.25 | 128202.8483 | 255.25 |
| `pct_change_from_one_month_ago` | -99.9167 | 614741.6667 | 642.2668 | 241.4925 |

---

## 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_kenya_6824) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_daily_cross_border_trade_for_kenya_6824,
title = {Kenya Daily FEWS NET Cross Border Trade Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/daily_cross_border_trade_for_kenya_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:
- 无标注（no-annotation）
language_creators:
- 爬取获取（found）
language:
- 英语（en）
license: cc-by-4.0
multilinguality:
- 单语言（monolingual）
size_categories:
- 10K<n<100K
source_datasets:
- 原创数据集（original）
task_categories:
- 表格分类（tabular-classification）
- 表格回归（tabular-regression）
task_ids: []
tags:
- 非洲（africa）
- 人道主义（humanitarian）
- HDX（hdx）
- Electric Sheep Africa（electric-sheep-africa）
- 东非（eastern-africa）
- 贸易（trade）
- ken（肯尼亚）
pretty_name: "肯尼亚每日FEWS NET跨境贸易数据集"

dataset_info:
splits:
- name: train
num_examples: 31952
- name: test
num_examples: 7988

# 肯尼亚每日FEWS NET跨境贸易数据集

**发布方**：FEWS NET · **来源**：[HDX](https://data.humdata.org/dataset/daily_cross_border_trade_for_kenya_6824) · **许可协议**：`cc-by` · **更新时间**：2026-03-30

---

## 摘要

肯尼亚每日跨境贸易数据由FEWS NET自2010年起收集。

本数据集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`、`period_date`列标识。地理范围：**肯尼亚（KEN）**。

*本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的Parquet（Parquet）格式。*

---

## 数据集特征

| | |
|---|---|
| **领域** | 人道主义与发展数据 |
| **观测单元** | 一级行政单元观测样本 |
| **总行数** | 39,940 |
| **列数** | 38（5个数值列、31个分类列、2个日期时间列） |
| **训练集划分** | 31,952条数据 |
| **测试集划分** | 7,988条数据 |
| **地理范围** | 肯尼亚（KEN） |
| **发布方** | FEWS NET |
| **HDX最后更新时间** | 2026-03-30 |

---

## 变量

**地理类变量**：`reporting_country`（肯尼亚、坦桑尼亚联合共和国、索马里）、`reporting_country_code`（KE、TZ、SO）、`source_country_code`（TZ、KE、ET）、`destination_country_code`（KE、TZ、SO）、`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0.0889–48462142.25）、`pct_change_from_one_month_ago`（取值范围-99.9167–614741.6667）。
**结果/测量类变量**：`value`（取值范围0.0–193848569.0）。
**标识符/元数据类变量**：`source`（坦桑尼亚联合共和国、肯尼亚、埃塞俄比亚）、`indicator_name`（TradeFlowQuantity）、`source_organization`、`source_document`、`dataseries_name`及另外4个变量。
**其他类变量**：`border_point`（塔韦塔、莫亚莱、塔拉基亚）、`destination`（肯尼亚、坦桑尼亚联合共和国、索马里）、`cpcv2`（R01122AC、P23161AA、R01701AA）、`product`（白玉米籽粒、精米、混合豆类）、`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-kenya-6824")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据Schema

| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `reporting_country` | object | 0.0% | 肯尼亚、坦桑尼亚联合共和国、索马里 |
| `reporting_country_code` | object | 0.0% | KE、TZ、SO |
| `border_point` | object | 0.0% | 塔韦塔、莫亚莱、塔拉基亚 |
| `source` | object | 0.0% | 坦桑尼亚联合共和国、肯尼亚、埃塞俄比亚 |
| `source_country_code` | object | 0.0% | TZ、KE、ET |
| `destination` | object | 0.0% | 肯尼亚、坦桑尼亚联合共和国、索马里 |
| `destination_country_code` | object | 0.0% | KE、TZ、SO |
| `cpcv2` | object | 0.0% | R01122AC、P23161AA、R01701AA |
| `product` | object | 0.0% | 白玉米籽粒、精米、混合豆类 |
| `indicator_name` | object | 0.0% | TradeFlowQuantity |
| `start_date` | datetime64[ns] | 0.0% | 无 |
| `period_date` | datetime64[ns] | 0.0% | 无 |
| `value` | float64 | 0.0% | 0.0 – 193848569.0（均值147452.5806） |
| `flow_type` | object | 0.0% | 无 |
| `trade_type` | object | 0.0% | 无 |
| `collection_status` | object | 0.0% | 无 |
| `source_organization` | object | 0.0% | 无 |
| `source_document` | object | 0.0% | 无 |
| `dataseries_name` | object | 0.0% | 无 |
| `dataseries` | int64 | 0.0% | 6544288.0 – 7402479.0（均值6659592.5972） |
| `unit` | object | 0.0% | 无 |
| `unit_type` | object | 0.0% | 无 |
| `unit_name` | object | 0.0% | 无 |
| `status` | object | 0.0% | 无 |
| `common_unit` | object | 0.0% | 无 |
| `common_unit_quantity` | float64 | 0.0% | 0.0 – 737810000.0（均值401073.4535） |
| `reporting_country_geographic_group` | object | 0.0% | 无 |
| `reporting_country_fewsnet_region` | object | 0.0% | 无 |
| `source_geographic_group` | object | 0.0% | 无 |
| `source_fewsnet_region` | object | 0.0% | 无 |
| `destination_geographic_group` | object | 0.0% | 无 |
| `destination_fewsnet_region` | object | 0.0% | 无 |
| `value_one_month_ago` | float64 | 74.0% | 0.0889 – 48462142.25（均值128202.8483） |
| `pct_change_from_one_month_ago` | float64 | 74.0% | -99.9167 – 614741.6667（均值642.2668） |
| `collection_schedule` | object | 0.0% | 无 |
| `data_usage_policy` | object | 0.0% | 无 |
| `esa_source` | object | 0.0% | 无 |
| `esa_processed` | object | 0.0% | 无 |

---

## 数值统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `value` | 0.0 | 193848569.0 | 147452.5806 | 0.0 |
| `dataseries` | 6544288.0 | 7402479.0 | 6659592.5972 | 6614009.0 |
| `common_unit_quantity` | 0.0 | 737810000.0 | 401073.4535 | 0.0 |
| `value_one_month_ago` | 0.0889 | 48462142.25 | 128202.8483 | 255.25 |
| `pct_change_from_one_month_ago` | -99.9167 | 614741.6667 | 642.2668 | 241.4925 |

---

## 数据整理流程

原始数据通过CKAN API（CKAN API）从HDX下载，并转换为Parquet（Parquet）格式。列名被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`。移除了10个缺失率超过80%的列：`id`、`value_one_year_ago`、`value_two_years_ago`、`value_three_years_ago`、`value_four_years_ago`、`value_five_years_ago`…… 根据解析成功率（>85%阈值），将2列从字符串类型转换为数值或日期时间类型。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（Snappy）压缩的Parquet格式。

---

## 局限性

- 本数据集源自FEWS NET，未经过Electric Sheep Africa的独立验证。
- 自动化清洗无法修正原始收集过程中出现的错报值、定义不一致或采样偏差问题。
- 以下列的缺失率超过20%，在建模时需谨慎使用：`value_one_month_ago`、`pct_change_from_one_month_ago`。
- 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/daily_cross_border_trade_for_kenya_6824)以获取发布方提供的方法论说明与注意事项。

---

## 引用

bibtex
@dataset{hdx_africa_daily_cross_border_trade_for_kenya_6824,
title = {肯尼亚每日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_kenya_6824},
note = {由Electric Sheep Africa（https://huggingface.co/electricsheepafrica）重新打包以适配机器学习需求}
}

---

*[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。*