electricsheepafrica/africa-displacement-libya

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- conflict-violence
- displacement
- forced-displacement
- internally-displaced-persons-idp
- lby
pretty_name: "Libya IOM Displacement Tracking Matrix (DTM) from API"
dataset_info:
splits:
- name: train
num_examples: 2142
- name: test
num_examples: 535
---

# Libya IOM Displacement Tracking Matrix (DTM) from API

**Publisher:** International Organization for Migration (IOM) · **Source:** [HDX](https://data.humdata.org/dataset/lby-iom-dtm-from-api) · **License:** `hdx-other` · **Updated:** 2026-04-27

---

## Abstract

This dataset comes from the International Organization for Migration (IOM)'s displacement tracking matrix (DTM) [publicly accessible API](https://dtm.iom.int/data-and-analysis/dtm-api). This API allows the humanitarian community, academia, media, government, and non-governmental organizations to utilize the data collected by DTM. The DTM API only provides non-sensitive IDP figures, aggregated at the country, Admin 1 (states, provinces, or equivalent), and Admin 2 (smaller subnational administrative areas) levels. For more detailed information, please see the [country-specific DTM datasets on HDX](https://data.humdata.org/dataset/?dataseries_name=IOM%20-%20DTM%20Baseline%20Assessment&dataseries_name=IOM%20-%20DTM%20Event%20and%20Flow%20Tracking&dataseries_name=IOM%20-%20DTM%20Site%20and%20Location%20Assessment&organization=international-organization-for-migration&q=&sort=last_modified%20desc&ext_page_size=25).

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

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Conflict and security |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 2,678 |
| **Columns** | 21 (6 numeric, 14 categorical, 1 datetime) |
| **Train split** | 2,142 rows |
| **Test split** | 535 rows |
| **Geographic scope** | LBY |
| **Publisher** | International Organization for Migration (IOM) |
| **HDX last updated** | 2026-04-27 |

---

## Variables

**Geographic** — `admin0name` (Libya), `admin0pcode` (LBY), `admin1name` (West, East, South), `admin1pcode` (LY02, LY01, LY03), `admin2name` (Misrata, Tripoli, Almargeb) and 7 others.

**Temporal** — `reportingdate`, `monthreportingdate` (range 1.0–12.0).

**Outcome / Measurement** — `roundnumber` (range 1.0–52.0).

**Identifier / Metadata** — `id` (range 5.0–150091.0), `numpresentidpind` (range 2.0–401836.0), `esa_source`, `esa_processed`.

**Other** — `operation` (Libya Crisis), `operationstatus`.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-displacement-libya")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `id` | float64 | 8.6% | 5.0 – 150091.0 (mean 66774.6407) |
| `operation` | object | 0.0% | Libya Crisis |
| `admin0name` | object | 0.0% | Libya |
| `admin0pcode` | object | 0.0% | LBY |
| `admin1name` | object | 8.6% | West, East, South |
| `admin1pcode` | object | 8.6% | LY02, LY01, LY03 |
| `admin2name` | object | 27.1% | Misrata, Tripoli, Almargeb |
| `admin2pcode` | object | 27.1% | LY0214, LY0211, LY0210 |
| `adminlevel` | int64 | 0.0% | 0.0 – 2.0 (mean 1.6438) |
| `numpresentidpind` | int64 | 0.0% | 2.0 – 401836.0 (mean 12617.5463) |
| `reportingdate` | datetime64[ns] | 0.0% | |
| `yearreportingdate` | int64 | 0.0% | 2016.0 – 2024.0 (mean 2019.2565) |
| `monthreportingdate` | int64 | 0.0% | 1.0 – 12.0 (mean 6.6613) |
| `roundnumber` | int64 | 0.0% | 1.0 – 52.0 (mean 26.1751) |
| `displacementreason` | object | 0.0% | Conflict, Insecurity, Conflict; Insecurity |
| `idporiginadmin1name` | object | 0.0% | Not available, West, East |
| `idporiginadmin1pcode` | object | 0.0% | Not available, LY02, LY01 |
| `assessmenttype` | object | 0.0% | |
| `operationstatus` | object | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `id` | 5.0 | 150091.0 | 66774.6407 | 56676.0 |
| `adminlevel` | 0.0 | 2.0 | 1.6438 | 2.0 |
| `numpresentidpind` | 2.0 | 401836.0 | 12617.5463 | 2500.0 |
| `yearreportingdate` | 2016.0 | 2024.0 | 2019.2565 | 2019.0 |
| `monthreportingdate` | 1.0 | 12.0 | 6.6613 | 6.0 |
| `roundnumber` | 1.0 | 52.0 | 26.1751 | 26.0 |

---

## 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`. 2 column(s) with >80% missing values were removed: `numbermales`, `numberfemales`. 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 International Organization for Migration (IOM) 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: `admin2name`, `admin2pcode`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/lby-iom-dtm-from-api) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_displacement_libya,
title = {Libya IOM Displacement Tracking Matrix (DTM) from API},
author = {International Organization for Migration (IOM)},
year = {2026},
url = {https://data.humdata.org/dataset/lby-iom-dtm-from-api},
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.*