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

---
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
- eastern-africa
- trade
- dji
pretty_name: "Djibouti Daily FEWS NET Cross Border Trade Data"
dataset_info:
splits:
- name: train
num_examples: 4019
- name: test
num_examples: 1004
---

# Djibouti Daily FEWS NET Cross Border Trade Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/daily_cross_border_trade_for_djibouti_6824) · **License:** `cc-by` · **Updated:** 2026-04-01

---

## Abstract

Djibouti 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: **DJI**.

*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)** | 5,024 |
| **Columns** | 38 (5 numeric, 31 categorical, 2 datetime) |
| **Train split** | 4,019 rows |
| **Test split** | 1,004 rows |
| **Geographic scope** | DJI |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-04-01 |

---

## Variables

**Geographic** — `reporting_country` (Djibouti, Somalia, Ethiopia), `reporting_country_code` (DJ, SO, ET), `source_country_code` (ET, DJ, SO), `destination_country_code` (DJ, SO, ET), `flow_type` and 8 others.

**Temporal** — `start_date`, `period_date`, `value_one_month_ago` (range 0.0667–32200.0), `pct_change_from_one_month_ago` (range -98.5082–51861.6026).

**Outcome / Measurement** — `value` (range 0.0–128800.0).

**Identifier / Metadata** — `source` (Ethiopia, Djibouti, Somalia), `indicator_name` (TradeFlowQuantity), `source_organization`, `source_document`, `dataseries_name` and 4 others.

**Other** — `border_point` (Galafi, Loyado, Galila), `destination` (Djibouti, Somalia, Ethiopia), `cpcv2` (R01704AA, R01142AA, P21549AA), `product` (Lentils, Sorghum, Refined Vegetable Oil), `collection_status` and 6 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-daily-cross-border-trade-for-djibouti-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% | Djibouti, Somalia, Ethiopia |
| `reporting_country_code` | object | 0.0% | DJ, SO, ET |
| `border_point` | object | 0.0% | Galafi, Loyado, Galila |
| `source` | object | 0.0% | Ethiopia, Djibouti, Somalia |
| `source_country_code` | object | 0.0% | ET, DJ, SO |
| `destination` | object | 0.0% | Djibouti, Somalia, Ethiopia |
| `destination_country_code` | object | 0.0% | DJ, SO, ET |
| `cpcv2` | object | 0.0% | R01704AA, R01142AA, P21549AA |
| `product` | object | 0.0% | Lentils, Sorghum, Refined Vegetable Oil |
| `indicator_name` | object | 0.0% | TradeFlowQuantity |
| `start_date` | datetime64[ns] | 0.0% | |
| `period_date` | datetime64[ns] | 0.0% | |
| `value` | float64 | 0.0% | 0.0 – 128800.0 (mean 1435.2386) |
| `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 – 7402473.0 (mean 6656381.8545) |
| `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 – 6440000.0 (mean 68177.6354) |
| `reporting_country_geographic_group` | object | 0.0% | |
| `reporting_country_fewsnet_region` | object | 0.0% | |
| `source_geographic_group` | object | 0.0% | |
| `source_fewsnet_region` | object | 1.4% | |
| `destination_geographic_group` | object | 0.0% | |
| `destination_fewsnet_region` | object | 1.7% | |
| `value_one_month_ago` | float64 | 69.9% | 0.0667 – 32200.0 (mean 1089.9519) |
| `pct_change_from_one_month_ago` | float64 | 69.9% | -98.5082 – 51861.6026 (mean 356.0909) |
| `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 | 128800.0 | 1435.2386 | 0.0 |
| `dataseries` | 6544175.0 | 7402473.0 | 6656381.8545 | 6615898.0 |
| `common_unit_quantity` | 0.0 | 6440000.0 | 68177.6354 | 0.0 |
| `value_one_month_ago` | 0.0667 | 32200.0 | 1089.9519 | 100.0 |
| `pct_change_from_one_month_ago` | -98.5082 | 51861.6026 | 356.0909 | 225.3135 |

---

## 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_djibouti_6824) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_daily_cross_border_trade_for_djibouti_6824,
title = {Djibouti Daily FEWS NET Cross Border Trade Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/daily_cross_border_trade_for_djibouti_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.*