electricsheepafrica/africa-learning-levels-in-tanzania-2014

---
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
- tza
pretty_name: "Learning levels in Tanzania (2014)"
dataset_info:
splits:
- name: train
num_examples: 26155
- name: test
num_examples: 6538
---

# Learning levels in Tanzania (2014)

**Publisher:** Uwezo at Twaweza East Africa (inactive) · **Source:** [HDX](https://data.humdata.org/dataset/learning-levels-in-tanzania-2014) · **License:** `cc-by` · **Updated:** 2025-02-19

---

## Abstract

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

Each row in this dataset represents subnational administrative unit observations. Data was last updated on HDX on 2025-02-19. Geographic scope: **TZA**.

*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)** | 32,694 |
| **Columns** | 117 (90 numeric, 27 categorical, 0 datetime) |
| **Train split** | 26,155 rows |
| **Test split** | 6,538 rows |
| **Geographic scope** | TZA |
| **Publisher** | Uwezo at Twaweza East Africa (inactive) |
| **HDX last updated** | 2025-02-19 |

---

## Variables

**Geographic** — `id_district` (range 101.0–2103.0), `id_districtname` (Geita, Kahama, Bariadi), `id_regionname` (Shinyanga, Mwanza, Rukwa), `mealsperday` (range 1.0–3.0), `asset_bicycle` and 12 others.

**Demographic** — `id_hh` (range 1001.0–1340020.0), `id_village` (range 1.0–1340.0), `hhno` (range 1.0–32.0), `answering_person` (range 1.0–3.0), `hh_gender` (range 1.0–2.0) and 14 others.

**Outcome / Measurement** — `income_source` (Farming, Own business, Casual wage).

**Identifier / Metadata** — `id_database` (TZ14), `water_source`, `esa_source`, `esa_processed`.

**Other** — `use_tele` (range 0.0–1.0), `house_wall` (Mud, Stone/Bricks, Iron sheet), `house_lighting` (Paraffin, Electricity, Solar), `asset_water` (range 0.0–1.0), `asset_toilet` (range 0.0–1.0) and 71 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-learning-levels-in-tanzania-2014")
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% | TZ14 |
| `id_district` | int64 | 0.0% | 101.0 – 2103.0 (mean 1213.165) |
| `id_districtname` | object | 0.0% | Geita, Kahama, Bariadi |
| `id_hh` | int64 | 0.0% | 1001.0 – 1340020.0 (mean 725191.168) |
| `id_regionname` | object | 0.0% | Shinyanga, Mwanza, Rukwa |
| `id_village` | int64 | 0.0% | 1.0 – 1340.0 (mean 725.1811) |
| `hhno` | int64 | 0.0% | 1.0 – 32.0 (mean 10.0338) |
| `answering_person` | float64 | 3.6% | 1.0 – 3.0 (mean 1.5521) |
| `hh_gender` | float64 | 5.7% | 1.0 – 2.0 (mean 1.2881) |
| `hh_age` | float64 | 6.4% | 0.0 – 108.0 (mean 45.31) |
| `hh_edu` | object | 26.9% | Some primary, Some secondary, Post secondary |
| `use_tele` | float64 | 42.9% | 0.0 – 1.0 (mean 0.905) |
| `household_visited` | float64 | 3.8% | 0.0 – 1.0 (mean 0.098) |
| `hh_males` | float64 | 1.9% | 1.0 – 23.0 (mean 3.5244) |
| `hh_females` | float64 | 0.6% | 1.0 – 25.0 (mean 3.6198) |
| `hh_size` | int64 | 0.0% | 1.0 – 42.0 (mean 7.0401) |
| `house_wall` | object | 1.5% | Mud, Stone/Bricks, Iron sheet |
| `house_lighting` | object | 0.0% | Paraffin, Electricity, Solar |
| `asset_water` | int64 | 0.0% | 0.0 – 1.0 (mean 0.3096) |
| `asset_toilet` | int64 | 0.0% | 0.0 – 1.0 (mean 0.8243) |
| `mealsperday` | float64 | 3.0% | 1.0 – 3.0 (mean 2.494) |
| `asset_tv` | int64 | 0.0% | 0.0 – 1.0 (mean 0.1636) |
| `asset_radio` | int64 | 0.0% | 0.0 – 1.0 (mean 0.5791) |
| `asset_phone` | int64 | 0.0% | 0.0 – 1.0 (mean 0.6065) |
| `asset_computer` | int64 | 0.0% | 0.0 – 1.0 (mean 0.0202) |
| `asset_car` | int64 | 0.0% | 0.0 – 1.0 (mean 0.0261) |
| `asset_bicycle` | int64 | 0.0% | |
| `asset_motorbike` | int64 | 0.0% | |
| `asset_cart` | int64 | 0.0% | |
| `asset_cattle` | int64 | 0.0% | |
| `asset_sheep_goat` | int64 | 0.0% | |
| `asset_donkey` | int64 | 0.0% | |
| `asset_camel` | int64 | 0.0% | |
| `h108_favourites` | object | 62.0% | RADIO, TV, radio |
| `fav_radio` | object | 39.2% | TBC, RFA, 1 |
| `fav_tv` | object | 76.5% | ITV, TBC, 0 |
| `income_source` | object | 7.6% | Farming, Own business, Casual wage |
| `water_source` | object | 18.2% | |
| `treat_water` | object | 4.2% | |
| `eat_fruit` | int64 | 0.0% | |
| `hhld_books` | object | 58.2% | |
| `h202` | float64 | 4.3% | |
| `h203` | float64 | 4.8% | |
| `h204` | float64 | 4.9% | |
| `h205` | float64 | 4.8% | |
| `h206` | float64 | 9.1% | |
| `h207_1` | int64 | 0.0% | |
| `h208` | float64 | 4.4% | |
| `h301` | float64 | 7.9% | |
| `h302` | object | 3.6% | |
| `h401` | float64 | 3.0% | |
| `h402` | float64 | 58.3% | |
| `h403` | float64 | 20.4% | |
| `h404` | float64 | 3.2% | |
| `h405` | float64 | 3.6% | |
| `h1201` | float64 | 2.7% | |
| `h1202` | float64 | 2.2% | |
| `h1309_deparch_hh` | float64 | 1.3% | |
| `h1309_deparch_mm` | float64 | 1.3% | |
| `h207_4` | int64 | 0.0% | |
| `h207_2` | int64 | 0.0% | |
| `drink_juice` | int64 | 0.0% | |
| `eat_veg` | int64 | 0.0% | |
| `drink_milk` | int64 | 0.0% | |
| `h207_3` | int64 | 0.0% | |
| `childslno` | int64 | 0.0% | |
| `age` | int64 | 0.0% | |
| `gender` | object | 0.0% | |
| `mothers_age` | float64 | 11.0% | |
| `mothers_edu` | object | 17.0% | |
| `preschool` | int64 | 0.0% | |
| `wenttopreschool` | int64 | 0.0% | |
| `grade` | float64 | 30.1% | |
| `tuition` | int64 | 0.0% | |
| `schoolmatch` | int64 | 0.0% | |
| `neverenrolled` | int64 | 0.0% | |
| `dropout` | int64 | 0.0% | |
| `testsample` | float64 | 22.5% | |
| `english` | object | 9.1% | |
| `english1` | float64 | 61.6% | |
| `english2` | float64 | 63.8% | |
| `swahili` | object | 10.5% | |
| `swahili1` | float64 | 46.2% | |
| `swahili2` | float64 | 48.7% | |
| `math` | object | 10.4% | |
| `matheveryday` | float64 | 14.0% | |
| `bonus1` | float64 | 15.0% | |
| `bonus2` | float64 | 15.5% | |
| `left_eye` | float64 | 7.9% | |
| `right_eye` | float64 | 8.1% | |
| `districtnameold` | object | 0.0% | |
| `regioncodenew` | int64 | 0.0% | |
| `regionnamenew` | object | 0.0% | |
| `wardcode` | int64 | 0.0% | |
| `hh_edu_raw` | float64 | 13.3% | |
| `hh_children` | int64 | 0.0% | |
| `asset_elec` | int64 | 0.0% | |
| `mothers_edu_raw` | float64 | 15.6% | |
| `enr_ans` | int64 | 0.0% | |
| `schooltype` | object | 20.4% | |
| `h303` | float64 | 7.7% | |
| `district_nohhlds` | int64 | 0.0% | |
| `weight` | float64 | 0.0% | |
| `nohhldsinea` | int64 | 0.0% | |
| `noeasindistrict` | int64 | 0.0% | |
| `nodistricts` | int64 | 0.0% | |
| `english_imputed` | object | 0.0% | |
| `english1_imputed` | int64 | 0.0% | |
| `english2_imputed` | int64 | 0.0% | |
| `swahili_imputed` | object | 0.0% | |
| `swahili1_imputed` | int64 | 0.0% | |
| `swahili2_imputed` | int64 | 0.0% | |
| `math_imputed` | object | 0.0% | |
| `bonus1_imputed` | int64 | 0.0% | |
| `bonus2_imputed` | int64 | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id_district` | 101.0 | 2103.0 | 1213.165 | 1302.0 |
| `id_hh` | 1001.0 | 1340020.0 | 725191.168 | 778015.0 |
| `id_village` | 1.0 | 1340.0 | 725.1811 | 778.0 |
| `hhno` | 1.0 | 32.0 | 10.0338 | 10.0 |
| `answering_person` | 1.0 | 3.0 | 1.5521 | 2.0 |
| `hh_gender` | 1.0 | 2.0 | 1.2881 | 1.0 |
| `hh_age` | 0.0 | 108.0 | 45.31 | 43.0 |
| `use_tele` | 0.0 | 1.0 | 0.905 | 1.0 |
| `household_visited` | 0.0 | 1.0 | 0.098 | 0.0 |
| `hh_males` | 1.0 | 23.0 | 3.5244 | 3.0 |
| `hh_females` | 1.0 | 25.0 | 3.6198 | 3.0 |
| `hh_size` | 1.0 | 42.0 | 7.0401 | 6.0 |
| `asset_water` | 0.0 | 1.0 | 0.3096 | 0.0 |
| `asset_toilet` | 0.0 | 1.0 | 0.8243 | 1.0 |
| `mealsperday` | 1.0 | 3.0 | 2.494 | 3.0 |

---

## 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: `completed`, `dropout_year`, `dropout_class`, `h402other`. 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: `hh_edu`, `use_tele`, `h108_favourites`, `fav_radio`, `fav_tv`, `hhld_books`, `h402`, `h403`....
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/learning-levels-in-tanzania-2014) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_learning_levels_in_tanzania_2014,
title = {Learning levels in Tanzania (2014)},
author = {Uwezo at Twaweza East Africa (inactive)},
year = {2025},
url = {https://data.humdata.org/dataset/learning-levels-in-tanzania-2014},
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.*