electricsheepafrica/africa-fewsnet-staple-food-price-data-for-djibouti-weekly-269

---
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-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- eastern-africa
- economics
- food-security
- indicators
- markets
- dji
pretty_name: "Djibouti Weekly FEWS NET Staple Food Price Data"
dataset_info:
splits:
- name: train
num_examples: 852
- name: test
num_examples: 213
---

# Djibouti Weekly FEWS NET Staple Food Price Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_djibouti_weekly_269) · **License:** `cc-by` · **Updated:** 2026-04-01

---

## Abstract

Djibouti Weekly staple food price data collected by FEWS NET since 2004.

Each row in this dataset represents country-level aggregates. Temporal coverage is indicated by the `period_date` column(s). Geographic scope: **DJI**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 1,065 |
| **Columns** | 17 (3 numeric, 13 categorical, 1 datetime) |
| **Train split** | 852 rows |
| **Test split** | 213 rows |
| **Geographic scope** | DJI |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-04-01 |

---

## Variables

**Geographic** — `country` (Djibouti), `longitude` (range 43.1485–43.1485), `latitude` (range 11.59–11.59), `price_type` (Retail), `unit_type` (Weight, Volume) and 1 others.

**Temporal** — `period_date`.

**Outcome / Measurement** — `value` (range 80.0–405.0).

**Identifier / Metadata** — `fnid` (DJ0000M005), `source_document` (Famine Early Warning Systems Network (FEWS NET), Djibouti, Price), `product_source` (Local, Import), `esa_source`, `esa_processed`.

**Other** — `market` (Djibouti City), `cpcv2` (P33341AA, P23161AA, P23110AA), `product` (Kerosene, Rice (Milled), Wheat Flour), `unit` (kg, L).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-fewsnet-staple-food-price-data-for-djibouti-weekly-269")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `country` | object | 0.0% | Djibouti |
| `fnid` | object | 0.0% | DJ0000M005 |
| `market` | object | 0.0% | Djibouti City |
| `longitude` | float64 | 0.0% | 43.1485 – 43.1485 (mean 43.1485) |
| `latitude` | float64 | 0.0% | 11.59 – 11.59 (mean 11.59) |
| `cpcv2` | object | 0.0% | P33341AA, P23161AA, P23110AA |
| `product` | object | 0.0% | Kerosene, Rice (Milled), Wheat Flour |
| `source_document` | object | 0.0% | Famine Early Warning Systems Network (FEWS NET), Djibouti, Price |
| `period_date` | datetime64[ns] | 0.0% | |
| `price_type` | object | 0.0% | Retail |
| `product_source` | object | 0.0% | Local, Import |
| `unit` | object | 0.0% | kg, L |
| `unit_type` | object | 0.0% | Weight, Volume |
| `currency` | object | 0.0% | |
| `value` | float64 | 5.2% | 80.0 – 405.0 (mean 148.407) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `longitude` | 43.1485 | 43.1485 | 43.1485 | 43.1485 |
| `latitude` | 11.59 | 11.59 | 11.59 | 11.59 |
| `value` | 80.0 | 405.0 | 148.407 | 140.0 |

---

## 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`. 1 column(s) with >80% missing values were removed: `admin_1`. 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 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.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_djibouti_weekly_269) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_fewsnet_staple_food_price_data_for_djibouti_weekly_269,
title = {Djibouti Weekly FEWS NET Staple Food Price Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_djibouti_weekly_269},
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.*