electricsheepafrica/africa-ethiopia-populated-places-geonames

---
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-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- populated-places-settlements
- population
- eth
pretty_name: "Ethiopia - Populated Places GeoNames"
dataset_info:
splits:
- name: train
num_examples: 12420
- name: test
num_examples: 3105
---

# Ethiopia - Populated Places GeoNames

**Publisher:** 3iS · **Source:** [HDX](https://data.humdata.org/dataset/ethiopia-populated-places-geonames) · **License:** `cc-by` · **Updated:** 2025-05-05

---

## Abstract

This dataset represents populated places in Ethiopia at the locality level, including villages, kebeles, towns, and other administrative divisions. Each entry is associated with XY coordinates and is integrated with Ethiopian administrative boundaries. The data originates from the National Geospatial-Intelligence Agency (NGA) and is accessible through their GeoNames platform(https://geonames.nga.mil/geonames/GNSData/).The dataset includes various types of populated areas such as: villages, kebeles and towns. This dataset is crucial for various applications, including urban planning to assist in the development of infrastructure and services based on population distribution, for research, and on disaster management to support humanitarian efforts by identifying populated areas during crises.

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2025-05-05. Geographic scope: **ETH**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Demographics and population |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 15,525 |
| **Columns** | 32 (7 numeric, 24 categorical, 0 datetime) |
| **Train split** | 12,420 rows |
| **Test split** | 3,105 rows |
| **Geographic scope** | ETH |
| **Publisher** | 3iS |
| **HDX last updated** | 2025-05-05 |

---

## Variables

**Geographic** — `lat_dd` (range 3.5047–14.7792), `long_dd` (range 33.0167–47.7833), `mgrs_x` (range 33.0167–47.7833), `mgrs_y` (range 3.5047–14.7792), `admin3name` and 10 others.

**Identifier / Metadata** — `fid` (range 0.0–15524.0), `full_name` (Dir?, Goro, Gora), `sort_name` (HARO, DIRE, SIRE), `fid_2` (range 0.0–1140.0), `objectid` (range 1.0–1563.0) and 2 others.

**Other** — `nt` (N, V, D), `desig_cd` (PPL, PPLA, PPLL), `fc` (P), `cc_ft` (ETH), `adm1` (ET-OR, ET-AM, ET-TI) and 5 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-ethiopia-populated-places-geonames")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `fid` | int64 | 0.0% | 0.0 – 15524.0 (mean 7762.0) |
| `full_name` | object | 0.0% | Dir?, Goro, Gora |
| `nt` | object | 0.0% | N, V, D |
| `lat_dd` | float64 | 0.0% | 3.5047 – 14.7792 (mean 9.7853) |
| `long_dd` | float64 | 0.0% | 33.0167 – 47.7833 (mean 38.9741) |
| `desig_cd` | object | 0.0% | PPL, PPLA, PPLL |
| `fc` | object | 0.0% | P |
| `cc_ft` | object | 0.0% | ETH |
| `adm1` | object | 0.0% | ET-OR, ET-AM, ET-TI |
| `generic` | object | 0.0% | , Bota, El |
| `full_nm_nd` | object | 0.0% | Haro, Dire, Goro |
| `sort_gen` | object | 0.0% | , BOTA, EL |
| `sort_name` | object | 0.0% | HARO, DIRE, SIRE |
| `mgrs` | object | 0.0% | |
| `mgrs_x` | float64 | 0.0% | 33.0167 – 47.7833 (mean 38.9741) |
| `mgrs_y` | float64 | 0.0% | 3.5047 – 14.7792 (mean 9.7853) |
| `mod_dt_ft` | datetime64[ns, UTC] | 0.0% | |
| `fid_2` | int64 | 0.0% | 0.0 – 1140.0 (mean 452.5688) |
| `objectid` | int64 | 0.0% | 1.0 – 1563.0 (mean 466.5208) |
| `admin3name` | object | 0.0% | |
| `admin3pcod` | object | 0.0% | |
| `admin3refn` | object | 0.0% | |
| `admin3altn` | object | 0.0% | |
| `admin3al_1` | object | 0.0% | |
| `admin2name` | object | 0.0% | |
| `admin2pcod` | object | 0.0% | |
| `admin1name` | object | 0.0% | |
| `admin1pcod` | object | 0.0% | |
| `admin0name` | object | 0.0% | |
| `admin0pcod` | object | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `fid` | 0.0 | 15524.0 | 7762.0 | 7762.0 |
| `lat_dd` | 3.5047 | 14.7792 | 9.7853 | 9.5361 |
| `long_dd` | 33.0167 | 47.7833 | 38.9741 | 38.85 |
| `mgrs_x` | 33.0167 | 47.7833 | 38.9741 | 38.85 |
| `mgrs_y` | 3.5047 | 14.7792 | 9.7853 | 9.5361 |
| `fid_2` | 0.0 | 1140.0 | 452.5688 | 442.0 |
| `objectid` | 1.0 | 1563.0 | 466.5208 | 449.0 |

---

## 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) 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 3iS 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/ethiopia-populated-places-geonames) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_ethiopia_populated_places_geonames,
title = {Ethiopia - Populated Places GeoNames},
author = {3iS},
year = {2025},
url = {https://data.humdata.org/dataset/ethiopia-populated-places-geonames},
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.*