electricsheepafrica/africa-ethiopia-coronavirus-covid-19-subnational-cases

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- n<1K
source_datasets:
- original
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- affected-population
- covid-19
- disease
- epidemics-outbreaks
- fatalities
- health
- hxl
- eth
pretty_name: "Ethiopia: Coronavirus(COVID-19) Subnational Cases"
dataset_info:
splits:
- name: train
num_examples: 112
- name: test
num_examples: 28
---

# Ethiopia: Coronavirus(COVID-19) Subnational Cases

**Publisher:** OCHA Ethiopia · **Source:** [HDX](https://data.humdata.org/dataset/ethiopia-coronavirus-covid-19-subnational-cases) · **License:** `cc-by` · **Updated:** 2026-01-16

---

## Abstract

This dataset contains the number of confirmed cases, recoveries and deaths by admin 1 due to the Coronavirus pandemic in Ethiopia.

Each row in this dataset represents geolocated point observations. Temporal coverage is indicated by the `date_as_of` column(s). Geographic scope: **ETH**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Geolocated point observations |
| **Rows (total)** | 141 |
| **Columns** | 21 (17 numeric, 3 categorical, 1 datetime) |
| **Train split** | 112 rows |
| **Test split** | 28 rows |
| **Geographic scope** | ETH |
| **Publisher** | OCHA Ethiopia |
| **HDX last updated** | 2026-01-16 |

---

## Variables

**Geographic** — `tigray` (range 0.0–31.0), `cumulative_total` (range 62.0–309639.0), `newly_recovered` (range 0.0–473.0), `daily_death` (range 0.0–11.0), `cumulative_total_covid_19_cases` (range 1.0–5846.0) and 1 others.

**Temporal** — `date_as_of`.

**Outcome / Measurement** — `case_in_last_24_hours` (range 0.0–399.0), `total_patients_in_treatment_centers` (range 1.0–3646.0), `total_recovered` (range 0.0–4814.0), `total_deaths` (range 0.0–139.0).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-07).

**Other** — `addis_ababa` (range 0.0–232.0), `somali` (range 0.0–133.0), `oromia` (range 0.0–22.0), `afar` (range 0.0–11.0), `amhara` (range 0.0–33.0) and 3 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-ethiopia-coronavirus-covid-19-subnational-cases")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `date_as_of` | datetime64[ns] | 0.7% | |
| `case_in_last_24_hours` | float64 | 16.3% | 0.0 – 399.0 (mean 67.7966) |
| `addis_ababa` | float64 | 44.0% | 0.0 – 232.0 (mean 50.6456) |
| `somali` | float64 | 64.5% | 0.0 – 133.0 (mean 8.26) |
| `oromia` | float64 | 58.2% | 0.0 – 22.0 (mean 5.1017) |
| `afar` | float64 | 76.6% | 0.0 – 11.0 (mean 2.3939) |
| `amhara` | float64 | 62.4% | 0.0 – 33.0 (mean 5.7736) |
| `snnp` | float64 | 78.7% | 0.0 – 7.0 (mean 2.1) |
| `tigray` | float64 | 66.7% | 0.0 – 31.0 (mean 4.2553) |
| `test_in_last_24_hours` | float64 | 25.5% | 59.0 – 6911.0 (mean 2792.9429) |
| `cumulative_total` | float64 | 25.5% | 62.0 – 309639.0 (mean 99036.4476) |
| `total_patients_in_treatment_centers` | float64 | 24.1% | 1.0 – 3646.0 (mean 789.4579) |
| `patients_in_intensive_care` | float64 | 25.5% | 0.0 – 39.0 (mean 11.6381) |
| `newly_recovered` | float64 | 15.6% | 0.0 – 473.0 (mean 33.4454) |
| `total_recovered` | float64 | 15.6% | 0.0 – 4814.0 (mean 626.6303) |
| `daily_death` | float64 | 14.9% | 0.0 – 11.0 (mean 1.1167) |
| `total_deaths` | float64 | 17.7% | 0.0 – 139.0 (mean 24.1897) |
| `cumulative_total_covid_19_cases` | float64 | 23.4% | 1.0 – 5846.0 (mean 1076.8333) |
| `of_daily_cases2` | object | 24.1% | 0%, 1%, 2% |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-07 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `case_in_last_24_hours` | 0.0 | 399.0 | 67.7966 | 12.5 |
| `addis_ababa` | 0.0 | 232.0 | 50.6456 | 14.0 |
| `somali` | 0.0 | 133.0 | 8.26 | 4.0 |
| `oromia` | 0.0 | 22.0 | 5.1017 | 3.0 |
| `afar` | 0.0 | 11.0 | 2.3939 | 2.0 |
| `amhara` | 0.0 | 33.0 | 5.7736 | 2.0 |
| `snnp` | 0.0 | 7.0 | 2.1 | 2.0 |
| `tigray` | 0.0 | 31.0 | 4.2553 | 2.0 |
| `test_in_last_24_hours` | 59.0 | 6911.0 | 2792.9429 | 2926.0 |
| `cumulative_total` | 62.0 | 309639.0 | 99036.4476 | 62300.0 |
| `total_patients_in_treatment_centers` | 1.0 | 3646.0 | 789.4579 | 93.0 |
| `patients_in_intensive_care` | 0.0 | 39.0 | 11.6381 | 1.0 |
| `newly_recovered` | 0.0 | 473.0 | 33.4454 | 4.0 |
| `total_recovered` | 0.0 | 4814.0 | 626.6303 | 106.0 |
| `daily_death` | 0.0 | 11.0 | 1.1167 | 0.0 |

---

## 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`. 4 column(s) with >80% missing values were removed: `dire_dawa`, `harar`, `benish`, `gambela`. 6 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 OCHA Ethiopia 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: `addis_ababa`, `somali`, `oromia`, `afar`, `amhara`, `snnp`, `tigray`, `test_in_last_24_hours`....
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/ethiopia-coronavirus-covid-19-subnational-cases) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_ethiopia_coronavirus_covid_19_subnational_cases,
title = {Ethiopia: Coronavirus(COVID-19) Subnational Cases},
author = {OCHA Ethiopia},
year = {2026},
url = {https://data.humdata.org/dataset/ethiopia-coronavirus-covid-19-subnational-cases},
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.*