electricsheepafrica/africa-lake-chad-basin-key-figures

---
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
- complex-emergency-conflict-security
- hxl
- internally-displaced-persons-idp
- refugees
- cmr
- tcd
- nga
pretty_name: "Lake Chad Basin - Key figures"
dataset_info:
splits:
- name: train
num_examples: 132
- name: test
num_examples: 33
---

# Lake Chad Basin - Key figures

**Publisher:** OCHA West and Central Africa (ROWCA) · **Source:** [HDX](https://data.humdata.org/dataset/lake-chad-basin-key-figures) · **License:** `cc-by-igo` · **Updated:** 2025-08-27

---

## Abstract

This collection of datasets is related to the Lake Chad Basin crisis visualization. The collection includes key crisis figures, Number of IDPs and refugees; number of incidents by location; Accessible territories; and data on funding.

Each row in this dataset represents country-level aggregates. Temporal coverage is indicated by the `date` column(s). Geographic scope: **CMR, TCD, NGA**.

*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)** | 165 |
| **Columns** | 9 (5 numeric, 3 categorical, 1 datetime) |
| **Train split** | 132 rows |
| **Test split** | 33 rows |
| **Geographic scope** | CMR, TCD, NGA |
| **Publisher** | OCHA West and Central Africa (ROWCA) |
| **HDX last updated** | 2025-08-27 |

---

## Variables

**Geographic** — `country` (TCD, CMR, NER), `displaced_people` (range 0.0–2100000.0).

**Temporal** — `date`.

**Outcome / Measurement** — `people_in_affected_areas` (range 491000.0–15000000.0).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-08).

**Other** — `people_in_need` (range 257000.0–10600000.0), `sam_children` (range 10809.0–2695754992.0), `food_insecure_people_3` (range 0.0–5248327.0).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-lake-chad-basin-key-figures")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `date` | datetime64[ns] | 0.6% | |
| `country` | object | 0.0% | TCD, CMR, NER |
| `people_in_affected_areas` | float64 | 34.5% | 491000.0 – 15000000.0 (mean 4602333.3333) |
| `displaced_people` | float64 | 0.6% | 0.0 – 2100000.0 (mean 550395.5549) |
| `people_in_need` | float64 | 27.3% | 257000.0 – 10600000.0 (mean 2508102.0667) |
| `sam_children` | float64 | 27.3% | 10809.0 – 2695754992.0 (mean 38031393.3667) |
| `food_insecure_people_3` | float64 | 0.6% | 0.0 – 5248327.0 (mean 1183509.2561) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-08 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `people_in_affected_areas` | 491000.0 | 15000000.0 | 4602333.3333 | 2500000.0 |
| `displaced_people` | 0.0 | 2100000.0 | 550395.5549 | 247991.0 |
| `people_in_need` | 257000.0 | 10600000.0 | 2508102.0667 | 660617.5 |
| `sam_children` | 10809.0 | 2695754992.0 | 38031393.3667 | 31000.0 |
| `food_insecure_people_3` | 0.0 | 5248327.0 | 1183509.2561 | 340000.0 |

---

## 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`. 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 West and Central Africa (ROWCA) 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: `people_in_affected_areas`, `people_in_need`, `sam_children`.
- This dataset spans 3 countries; geographic and methodological inconsistencies across national boundaries may affect cross-country comparability.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/lake-chad-basin-key-figures) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_lake_chad_basin_key_figures,
title = {Lake Chad Basin - Key figures},
author = {OCHA West and Central Africa (ROWCA)},
year = {2025},
url = {https://data.humdata.org/dataset/lake-chad-basin-key-figures},
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.*