electricsheepafrica/africa-learning-levels-in-uganda-2015

---
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:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- uga
pretty_name: "Learning levels in Uganda (2015)"
dataset_info:
splits:
- name: train
num_examples: 131303
- name: test
num_examples: 32825
---

# Learning levels in Uganda (2015)

**Publisher:** Uwezo at Twaweza East Africa (inactive) · **Source:** [HDX](https://data.humdata.org/dataset/learning-levels-in-uganda-2015) · **License:** `cc-by` · **Updated:** 2025-02-19

---

## Abstract

These datasets contains data relevant to learner achievement in Uganda. This ranges from school enrollment, socioeconomic indicators, school infrastructure among others.

Each row in this dataset represents subnational administrative unit observations. Temporal coverage is indicated by the `date` column(s). Geographic scope: **UGA**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Water, sanitation and hygiene (wash) |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 164,129 |
| **Columns** | 130 (62 numeric, 67 categorical, 1 datetime) |
| **Train split** | 131,303 rows |
| **Test split** | 32,825 rows |
| **Geographic scope** | UGA |
| **Publisher** | Uwezo at Twaweza East Africa (inactive) |
| **HDX last updated** | 2025-02-19 |

---

## Variables

**Geographic** — `id_district` (range 101.0–426.0), `id_districtname` (Koboko, Pallisa, Kaabong), `id_regionname` (Eastern, North, Western), `county_code1` (range 1.0–5.0), `county` (KIBOGA, BUKOTO, KOBOKO) and 19 others.

**Temporal** — `date`.

**Demographic** — `id_hh` (range 1001.0–3360020.0), `id_village` (range 1.0–3360.0), `no_of_hhs` (range 12.0–808.0), `males` (range 23.0–990.0), `females` (range 11.0–1136.0) and 16 others.

**Identifier / Metadata** — `id_database` (UG15), `parishcode` (range 1.0–94.0), `parish_name` (CENTRAL WARD, LOROO, AMUDAT), `ea_code` (range 1.0–95.0), `eacode` (range 10101.0–4261000000.0) and 6 others.

**Other** — `sample_no` (range 1.0–30.0), `house_wall`, `house_lighting`, `asset_toilet`, `eat_veg` and 68 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-learning-levels-in-uganda-2015")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `id_database` | object | 0.0% | UG15 |
| `id_district` | int64 | 0.0% | 101.0 – 426.0 (mean 268.3714) |
| `id_districtname` | object | 0.0% | Koboko, Pallisa, Kaabong |
| `id_hh` | int64 | 0.0% | 1001.0 – 3360020.0 (mean 1698053.7879) |
| `id_regionname` | object | 0.0% | Eastern, North, Western |
| `id_village` | int64 | 0.0% | 1.0 – 3360.0 (mean 1698.0435) |
| `county_code1` | int64 | 0.0% | 1.0 – 5.0 (mean 1.2955) |
| `county` | object | 0.0% | KIBOGA, BUKOTO, KOBOKO |
| `parishcode` | int64 | 0.0% | 1.0 – 94.0 (mean 3.559) |
| `subcounty_code` | int64 | 0.0% | 1.0 – 29.0 (mean 4.9305) |
| `subcounty_name` | object | 0.0% | KARITA, MALONGO, KIRYANDONGO |
| `parish_name` | object | 0.0% | CENTRAL WARD, LOROO, AMUDAT |
| `locationcode` | int64 | 0.0% | 1.0 – 94.0 (mean 4.8976) |
| `location` | object | 0.0% | MASAKA, KAVULE, AGULE |
| `ea_code` | int64 | 0.0% | 1.0 – 95.0 (mean 7.1056) |
| `eacode` | float64 | 0.1% | 10101.0 – 4261000000.0 (mean 2682383775.3687) |
| `village_estate` | object | 0.0% | MASAKA, AYILO, KASAMBYA |
| `urban_code` | int64 | 0.0% | 1.0 – 2.0 (mean 1.1216) |
| `no_of_hhs` | int64 | 0.0% | 12.0 – 808.0 (mean 100.631) |
| `males` | int64 | 0.0% | 23.0 – 990.0 (mean 240.0212) |
| `females` | int64 | 0.0% | 11.0 – 1136.0 (mean 255.5044) |
| `sample_no` | int64 | 0.0% | 1.0 – 30.0 (mean 15.2208) |
| `validationcode` | int64 | 0.0% | 22010.0 – 999023.0 (mean 540592.1559) |
| `date` | datetime64[ns] | 49.4% | |
| `hhno` | int64 | 0.0% | 1.0 – 50.0 (mean 10.2612) |
| `answering_person` | object | 1.4% | HH head, Spouse, Other adult |
| `hh_gender` | object | 2.0% | Female, Male |
| `hh_age` | float64 | 11.1% | 16.0 – 120.0 (mean 39.4212) |
| `hh_edu_raw` | float64 | 3.0% | 1.0 – 5.0 (mean 2.0719) |
| `household_visited` | int64 | 0.0% | 0.0 – 1.0 (mean 0.0316) |
| `home_language` | object | 0.6% | |
| `hh_size` | float64 | 0.3% | 1.0 – 50.0 (mean 7.1386) |
| `hh_males` | float64 | 0.9% | |
| `hh_females` | float64 | 2.1% | |
| `house_wall` | object | 0.3% | |
| `house_lighting` | object | 0.0% | |
| `asset_toilet` | object | 0.0% | |
| `mealsperday` | object | 1.2% | |
| `eat_veg` | object | 0.8% | |
| `eat_fruit` | object | 0.7% | |
| `drink_milk` | object | 1.4% | |
| `asset_tv` | int64 | 0.0% | |
| `asset_radio` | int64 | 0.0% | |
| `asset_computer` | int64 | 0.0% | |
| `asset_phone` | int64 | 0.0% | |
| `asset_car` | int64 | 0.0% | |
| `asset_motorbike` | int64 | 0.0% | |
| `asset_bicycle` | int64 | 0.0% | |
| `asset_cattle` | int64 | 0.0% | |
| `asset_sheep_goat` | int64 | 0.0% | |
| `h107other` | object | 69.3% | |
| `water_source` | object | 0.8% | |
| `water_source_distance` | object | 1.7% | |
| `treat_water` | object | 56.4% | |
| `h201_1` | int64 | 0.0% | |
| `h201_2` | int64 | 0.0% | |
| `h201_3` | int64 | 0.0% | |
| `h201_4` | int64 | 0.0% | |
| `h201_5` | int64 | 0.0% | |
| `h201_6` | int64 | 0.0% | |
| `h201_7` | int64 | 0.0% | |
| `h301a_1` | float64 | 21.8% | |
| `h301a_2` | float64 | 61.7% | |
| `h301c_1` | float64 | 20.2% | |
| `h301c_2` | float64 | 46.8% | |
| `h302a` | object | 1.0% | |
| `h302b` | object | 1.6% | |
| `h302c` | object | 2.1% | |
| `h302d` | object | 2.0% | |
| `h302e` | object | 1.9% | |
| `h303` | object | 0.0% | |
| `h304` | float64 | 39.1% | |
| `h305` | float64 | 39.4% | |
| `h306` | object | 0.0% | |
| `h307` | object | 0.0% | |
| `h1600` | object | 27.6% | |
| `h1700` | float64 | 27.0% | |
| `childno` | int64 | 0.0% | |
| `age` | int64 | 0.0% | |
| `gender` | object | 0.0% | |
| `biological_parents` | float64 | 3.9% | |
| `h600` | float64 | 13.5% | |
| `disability` | object | 8.9% | |
| `mothers_toschool` | object | 13.5% | |
| `preschool` | object | 0.0% | |
| `schooltype` | object | 48.3% | |
| `tuition` | object | 0.0% | |
| `schoolmatch` | object | 0.0% | |
| `completed_primary` | object | 0.0% | |
| `completed_secondary` | object | 0.0% | |
| `neverenrolled` | object | 30.9% | |
| `dropout` | object | 30.9% | |
| `h1100` | float64 | 55.0% | |
| `attendyesterday` | object | 47.2% | |
| `mathteachyesterday` | object | 55.2% | |
| `testsample` | object | 43.8% | |
| `english` | object | 42.6% | |
| `locallanguage` | object | 71.1% | |
| `math` | object | 42.9% | |
| `ethnomath1` | object | 43.8% | |
| `ethnomath2` | object | 43.9% | |
| `bonus1` | object | 42.4% | |
| `bonus2` | object | 42.2% | |
| `bonus3` | object | 42.3% | |
| `right_eye` | object | 41.1% | |
| `left_eye` | object | 41.1% | |
| `asset_elec` | int64 | 0.0% | |
| `asset_water` | int64 | 0.0% | |
| `mothers_edu_raw` | float64 | 39.1% | |
| `mothers_edu` | object | 39.1% | |
| `grade` | float64 | 49.5% | |
| `enr_ans` | float64 | 30.9% | |
| `hh_edu` | object | 22.9% | |
| `hh_children` | int64 | 0.0% | |
| `weight` | float64 | 0.0% | |
| `district_nohhlds` | int64 | 0.0% | |
| `noschooldata` | int64 | 0.0% | |
| `district_name` | object | 0.0% | |
| `nohhldsinea` | int64 | 0.0% | |
| `noeasindistrict` | int64 | 0.0% | |
| `nodistricts` | int64 | 0.0% | |
| `english_imputed` | object | 39.3% | |
| `english1_imputed` | object | 39.3% | |
| `english2_imputed` | object | 39.3% | |
| `math_imputed` | object | 39.3% | |
| `bonus1_imputed` | object | 39.3% | |
| `bonus2_imputed` | object | 39.3% | |
| `bonus3_imputed` | object | 39.3% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id_district` | 101.0 | 426.0 | 268.3714 | 301.0 |
| `id_hh` | 1001.0 | 3360020.0 | 1698053.7879 | 1702007.0 |
| `id_village` | 1.0 | 3360.0 | 1698.0435 | 1702.0 |
| `county_code1` | 1.0 | 5.0 | 1.2955 | 1.0 |
| `parishcode` | 1.0 | 94.0 | 3.559 | 3.0 |
| `subcounty_code` | 1.0 | 29.0 | 4.9305 | 4.0 |
| `locationcode` | 1.0 | 94.0 | 4.8976 | 4.0 |
| `ea_code` | 1.0 | 95.0 | 7.1056 | 6.0 |
| `eacode` | 10101.0 | 4261000000.0 | 2682383775.3687 | 3011000000.0 |
| `urban_code` | 1.0 | 2.0 | 1.1216 | 1.0 |
| `no_of_hhs` | 12.0 | 808.0 | 100.631 | 96.0 |
| `males` | 23.0 | 990.0 | 240.0212 | 229.0 |
| `females` | 11.0 | 1136.0 | 255.5044 | 245.0 |
| `sample_no` | 1.0 | 30.0 | 15.2208 | 15.0 |
| `validationcode` | 22010.0 | 999023.0 | 540592.1559 | 531711.0 |

---

## 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`. 28 column(s) with >80% missing values were removed: `ea_code1`, `whichyear`, `h107_donkey`, `h107_camel`, `h107_pig`, `h201_8other`.... 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 Uwezo at Twaweza East Africa (inactive) 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: `date`, `h107other`, `treat_water`, `h301a_1`, `h301a_2`, `h301c_1`, `h301c_2`, `h304`....
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/learning-levels-in-uganda-2015) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_learning_levels_in_uganda_2015,
title = {Learning levels in Uganda (2015)},
author = {Uwezo at Twaweza East Africa (inactive)},
year = {2025},
url = {https://data.humdata.org/dataset/learning-levels-in-uganda-2015},
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.*