electricsheepafrica/africa-indice-composite-de-developpement-local-maroc-2014

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- developement
- morocco
pretty_name: "Indice Composite de Développement Local Maroc 2014"
dataset_info:
splits:
- name: train
num_examples: 1230
- name: test
num_examples: 307
---

# Indice Composite de Développement Local Maroc 2014

**Publisher:** TAFRA · **Source:** [OpenAfrica](https://open.africa/dataset/indice-composite-de-developpement-local-maroc-2014) · **License:** `cc-by` · **Updated:** 2024-02-05

---

## Abstract

Données relatives à l’Indice Composite de Développement local 2014. Les données ont été collectées du site web de l’Observatoire National du Développement Humain http://www.ondh.ma/fr/publications/cartographie-developpement-local-multidimensionnel-niveau-et-deficits.

Data related to the Local Development Composite Index 2014.The data was collected from the l’Observatoire National du Développement Humain.website http://www.ondh.ma/fr/publications/cartographie-developpement-local-multidimensionnel-niveau-et-deficits.

Each row in this dataset represents first-level administrative unit observations. Data was last updated on OpenAfrica on 2024-02-05. Geographic scope: **Africa (multiple countries)**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 1,538 |
| **Columns** | 17 (11 numeric, 6 categorical, 0 datetime) |
| **Train split** | 1,230 rows |
| **Test split** | 307 rows |
| **Geographic scope** | Africa (multiple countries) |
| **Publisher** | TAFRA |
| **OpenAfrica last updated** | 2024-02-05 |

---

## Variables

**Geographic** — `idregion` (range 606.0–621.0), `idwilaya` (range 2.0–18.0), `region` (Souss - Massa - Drâa, Marrakech - Tensift - Al-haouz, Taza - Al Hoceima - Taounate), `wilaya` (Souss - Massa - Drâa, Marrakech - Tensift - Al-haouz, Taza - Al Hoceima - Taounate).

**Identifier / Metadata** — `idprefprov` (range 241.0–323.0), `idcommune` (range 635.0–2172.0), `prefprov` (Taroudannt, Essaouira, Taounate), `esa_source` (HDX), `esa_processed` (2026-04-27).

**Other** — `commune` (Oulad Aissa, Laatamna, Ait Ouallal), `icdl` (range 0.314–0.858), `compedu` (range 0.216–0.868), `compsante` (range 0.09–0.727), `compeco` (range 0.0–1.0) and 3 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-indice-composite-de-developpement-local-maroc-2014")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `idregion` | int64 | 0.0% | 606.0 – 621.0 (mean 613.5858) |
| `idwilaya` | int64 | 0.0% | 2.0 – 18.0 (mean 9.645) |
| `idprefprov` | int64 | 0.0% | 241.0 – 323.0 (mean 285.459) |
| `idcommune` | int64 | 0.0% | 635.0 – 2172.0 (mean 1403.5) |
| `region` | object | 0.0% | Souss - Massa - Drâa, Marrakech - Tensift - Al-haouz, Taza - Al Hoceima - Taounate |
| `wilaya` | object | 0.0% | Souss - Massa - Drâa, Marrakech - Tensift - Al-haouz, Taza - Al Hoceima - Taounate |
| `prefprov` | object | 0.0% | Taroudannt, Essaouira, Taounate |
| `commune` | object | 0.0% | Oulad Aissa, Laatamna, Ait Ouallal |
| `icdl` | float64 | 0.4% | 0.314 – 0.858 (mean 0.6045) |
| `compedu` | float64 | 0.3% | 0.216 – 0.868 (mean 0.5688) |
| `compsante` | float64 | 0.4% | 0.09 – 0.727 (mean 0.4125) |
| `compeco` | float64 | 0.3% | 0.0 – 1.0 (mean 0.1769) |
| `comphabitat` | float64 | 0.3% | 0.154 – 0.739 (mean 0.309) |
| `compssoc` | float64 | 0.3% | 0.006 – 0.82 (mean 0.4035) |
| `compnvie` | float64 | 0.3% | 0.015 – 0.998 (mean 0.5027) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-27 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `idregion` | 606.0 | 621.0 | 613.5858 | 615.0 |
| `idwilaya` | 2.0 | 18.0 | 9.645 | 11.0 |
| `idprefprov` | 241.0 | 323.0 | 285.459 | 288.5 |
| `idcommune` | 635.0 | 2172.0 | 1403.5 | 1403.5 |
| `icdl` | 0.314 | 0.858 | 0.6045 | 0.591 |
| `compedu` | 0.216 | 0.868 | 0.5688 | 0.578 |
| `compsante` | 0.09 | 0.727 | 0.4125 | 0.413 |
| `compeco` | 0.0 | 1.0 | 0.1769 | 0.1275 |
| `comphabitat` | 0.154 | 0.739 | 0.309 | 0.307 |
| `compssoc` | 0.006 | 0.82 | 0.4035 | 0.4365 |
| `compnvie` | 0.015 | 0.998 | 0.5027 | 0.504 |

---

## Curation

Raw data was downloaded from OpenAfrica 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: `idsouspref`, `souspref`. 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 TAFRA and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- Refer to the [original HDX dataset page](https://open.africa/dataset/indice-composite-de-developpement-local-maroc-2014) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{openafrica_africa_indice_composite_de_developpement_local_maroc_2014,
title = {Indice Composite de Développement Local Maroc 2014},
author = {TAFRA},
year = {2024},
url = {https://open.africa/dataset/indice-composite-de-developpement-local-maroc-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.*