electricsheepafrica/africa-fewsnet-staple-food-price-data-for-ethiopia-weekly-6041

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 100K<n<1M
source_datasets:
- original
task_categories:
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- eastern-africa
- economics
- food-security
- indicators
- markets
- eth
pretty_name: "Ethiopia Weekly FEWS NET Staple Food Price Data"
dataset_info:
splits:
- name: train
num_examples: 84930
- name: test
num_examples: 21232
---

# Ethiopia Weekly FEWS NET Staple Food Price Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_ethiopia_weekly_6041) · **License:** `cc-by` · **Updated:** 2026-03-28

---

## Abstract

Ethiopia Weekly staple food price data collected by FEWS NET since 2019.

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

*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)** | 106,163 |
| **Columns** | 17 (3 numeric, 13 categorical, 1 datetime) |
| **Train split** | 84,930 rows |
| **Test split** | 21,232 rows |
| **Geographic scope** | ETH |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-03-28 |

---

## Variables

**Geographic** — `country` (Ethiopia), `admin_1` (Oromia, Somali, South Ethiopia), `longitude` (range 34.3515–45.3418), `latitude` (range 4.8934–14.0605), `price_type` (Retail, Wage) and 2 others.

**Temporal** — `period_date`.

**Outcome / Measurement** — `value` (range 1.0–324202.8).

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

**Other** — `market` (Addis Ababa, Merkato, Nazareth, Adama, Bahir Dar), `cpcv2` (P23520AA, R01701BD, R01122AC), `product` (Refined sugar, Beans (Haricot), Maize Grain (White)), `unit` (kg, ea, L).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-fewsnet-staple-food-price-data-for-ethiopia-weekly-6041")
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% | Ethiopia |
| `market` | object | 0.0% | Addis Ababa, Merkato, Nazareth, Adama, Bahir Dar |
| `admin_1` | object | 0.0% | Oromia, Somali, South Ethiopia |
| `longitude` | float64 | 0.0% | 34.3515 – 45.3418 (mean 39.5143) |
| `latitude` | float64 | 0.0% | 4.8934 – 14.0605 (mean 8.7939) |
| `cpcv2` | object | 0.0% | P23520AA, R01701BD, R01122AC |
| `product` | object | 0.0% | Refined sugar, Beans (Haricot), Maize Grain (White) |
| `source_document` | object | 0.0% | Famine Early Warning Systems Network (FEWS NET), Ethiopia, Price (weekly) |
| `period_date` | datetime64[ns] | 0.0% | |
| `price_type` | object | 0.0% | Retail, Wage |
| `product_source` | object | 0.0% | Local, Import |
| `unit` | object | 0.0% | kg, ea, L |
| `unit_type` | object | 0.0% | Weight, Item, Volume |
| `currency` | object | 0.0% | |
| `value` | float64 | 24.5% | 1.0 – 324202.8 (mean 2096.4237) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `longitude` | 34.3515 | 45.3418 | 39.5143 | 39.0367 |
| `latitude` | 4.8934 | 14.0605 | 8.7939 | 8.541 |
| `value` | 1.0 | 324202.8 | 2096.4237 | 65.8 |

---

## 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 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`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_ethiopia_weekly_6041) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_fewsnet_staple_food_price_data_for_ethiopia_weekly_6041,
title = {Ethiopia Weekly FEWS NET Staple Food Price Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_ethiopia_weekly_6041},
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.*