electricsheepafrica/africa-hdx-hapi-humanitarian-needs

---
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:
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- humanitarian-needs-overview-hno
- people-in-need-pin
- afg
- bfa
- cmr
- tcd
- col
pretty_name: "HDX HAPI - Affected People: Humanitarian Needs"
dataset_info:
splits:
- name: train
num_examples: 217
- name: test
num_examples: 54
---

# HDX HAPI - Affected People: Humanitarian Needs

**Publisher:** HDX Humanitarian API Data · **Source:** [HDX](https://data.humdata.org/dataset/hdx-hapi-humanitarian-needs) · **License:** `cc-by-igo` · **Updated:** 2026-02-13

---

## Abstract

This dataset contains data obtained from the
[HDX Humanitarian API](https://hapi.humdata.org/) (HDX HAPI),
which provides standardized humanitarian indicators designed
for seamless interoperability from multiple sources.
The data facilitates automated workflows and visualizations
to support humanitarian decision making.
For more information, please see the HDX HAPI
[landing page](https://data.humdata.org/hapi)
and
[documentation](https://hdx-hapi.readthedocs.io/en/latest/).

Warnings typically indicate corrections have been made to
the data or show things to look out for. Rows with only warnings
are considered complete, and are made available via the API.
Errors usually mean that the data is incomplete or unusable.
Rows with any errors are not present in the API but are included
here for transparency.

Each row in this dataset represents geolocated point observations. Temporal coverage is indicated by the `reference_period_start`, `reference_period_end` column(s). Geographic scope: **AFG, BFA, CMR, TCD, COL, COD, SLV, GTM, and 13 others**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Demographics and population |
| **Unit of observation** | Geolocated point observations |
| **Rows (total)** | 272 |
| **Columns** | 14 (2 numeric, 10 categorical, 2 datetime) |
| **Train split** | 217 rows |
| **Test split** | 54 rows |
| **Geographic scope** | AFG, BFA, CMR, TCD, COL, COD, SLV, GTM, and 13 others |
| **Publisher** | HDX Humanitarian API Data |
| **HDX last updated** | 2026-02-13 |

---

## Variables

**Geographic** — `location_code` (COD, CAF, TCD), `admin_level` (range 0.0–0.0), `population_status` (TGT, INN, all), `population` (range 33445.0–237500000.0), `dataset_hdx_id` (8326ed53-8f3a-47f9-a2aa-83ab4ecee476) and 1 others.

**Temporal** — `reference_period_start`, `reference_period_end`.

**Identifier / Metadata** — `sector_code` (Intersectoral, EDU, FSC), `sector_name` (Intersectoral, Education, Food Security), `esa_source` (HDX), `esa_processed` (2026-04-07).

**Other** — `has_hrp` (Y), `in_gho` (Y).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-hdx-hapi-humanitarian-needs")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `location_code` | object | 0.0% | COD, CAF, TCD |
| `has_hrp` | object | 0.0% | Y |
| `in_gho` | object | 0.0% | Y |
| `admin_level` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `sector_code` | object | 0.0% | Intersectoral, EDU, FSC |
| `sector_name` | object | 0.0% | Intersectoral, Education, Food Security |
| `population_status` | object | 0.0% | TGT, INN, all |
| `population` | int64 | 0.0% | 33445.0 – 237500000.0 (mean 6504748.7868) |
| `reference_period_start` | datetime64[ns] | 0.0% | |
| `reference_period_end` | datetime64[ns] | 0.0% | |
| `dataset_hdx_id` | object | 0.0% | 8326ed53-8f3a-47f9-a2aa-83ab4ecee476 |
| `resource_hdx_id` | object | 0.0% | edb91329-0e6b-4ebc-b6cb-051b2a11e536 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-07 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `admin_level` | 0.0 | 0.0 | 0.0 | 0.0 |
| `population` | 33445.0 | 237500000.0 | 6504748.7868 | 2078939.5 |

---

## 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`. 9 column(s) with >80% missing values were removed: `provider_admin1_name`, `provider_admin2_name`, `admin1_code`, `admin1_name`, `admin2_code`, `admin2_name`.... 2 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 HDX Humanitarian API Data and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- This dataset spans 21 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/hdx-hapi-humanitarian-needs) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_hdx_hapi_humanitarian_needs,
title = {HDX HAPI - Affected People: Humanitarian Needs},
author = {HDX Humanitarian API Data},
year = {2026},
url = {https://data.humdata.org/dataset/hdx-hapi-humanitarian-needs},
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.*