electricsheepafrica/africa-rd-congo-donnees-epidemiologiques

---
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-classification
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- disease
- epidemics-outbreaks
- cod
pretty_name: "Democratic Republic of Congo : Epidemioliogical cases and deaths (Données épidémiologiques)"
dataset_info:
splits:
- name: train
num_examples: 22628
- name: test
num_examples: 5657
---

# Democratic Republic of Congo : Epidemioliogical cases and deaths (Données épidémiologiques)

**Publisher:** OCHA Democratic Republic of the Congo (DRC) · **Source:** [HDX](https://data.humdata.org/dataset/rd-congo-donnees-epidemiologiques) · **License:** `cc-by` · **Updated:** 2025-05-05

---

## Abstract

The file provides information on the cases, deaths, ... of the various pathologies on the extent of the national territory.
Le fichier renseigne sur les cas, décès, ... des différentes pathologies sur l'étendue du territoire national.

Each row in this dataset represents tabular records. Temporal coverage is indicated by the `debutsem` column(s). Geographic scope: **COD**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Epidemiology and disease surveillance |
| **Unit of observation** | Tabular records |
| **Rows (total)** | 28,286 |
| **Columns** | 26 (18 numeric, 7 categorical, 1 datetime) |
| **Train split** | 22,628 rows |
| **Test split** | 5,657 rows |
| **Geographic scope** | COD |
| **Publisher** | OCHA Democratic Republic of the Congo (DRC) |
| **HDX last updated** | 2025-05-05 |

---

## Variables

**Geographic** — `pays` (RDC), `uniquekey` (range 1.0–2757.0).

**Demographic** — `pop` (range 0.0–1232023.0).

**Outcome / Measurement** — `totalcas` (range 0.0–7974.0), `totaldeces` (range 0.0–981.3).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-15).

**Other** — `num` (RDCHUEPAW, RDCHUEFAR, RDCHUEABA), `prov` (KINSHASA, ITURI, NORD-KIVU), `zs` (MIABI, KASANSA, BINZA-OZONE), `numsem` (range 1.0–8.0), `debutsem` and 14 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-rd-congo-donnees-epidemiologiques")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `num` | object | 0.0% | RDCHUEPAW, RDCHUEFAR, RDCHUEABA |
| `pays` | object | 0.0% | RDC |
| `prov` | object | 0.0% | KINSHASA, ITURI, NORD-KIVU |
| `zs` | object | 0.0% | MIABI, KASANSA, BINZA-OZONE |
| `pop` | float64 | 0.4% | 0.0 – 1232023.0 (mean 201445.4852) |
| `numsem` | int64 | 0.0% | 1.0 – 8.0 (mean 4.3945) |
| `debutsem` | datetime64[ns] | 0.0% | |
| `maladie` | object | 0.0% | IRA, PALUDISME SUSP, PALUDISME CONF |
| `c328tnn` | float64 | 29.0% | 0.0 – 651.0 (mean 2.9648) |
| `dtnn` | float64 | 29.1% | 0.0 – 3.0 (mean 0.0036) |
| `c011mois` | float64 | 2.1% | 0.0 – 3847.0 (mean 44.8348) |
| `d011mois` | float64 | 6.2% | 0.0 – 7.0 (mean 0.0375) |
| `c1259mois` | float64 | 1.3% | 0.0 – 2060.0 (mean 76.6688) |
| `d1259mois` | float64 | 5.7% | 0.0 – 9.0 (mean 0.0657) |
| `c515ans` | float64 | 3.7% | 0.0 – 3330.0 (mean 64.449) |
| `d515ans` | float64 | 7.7% | 0.0 – 218.0 (mean 0.0247) |
| `cp15ans` | float64 | 3.6% | 0.0 – 3449.0 (mean 101.7957) |
| `dp15ans` | float64 | 7.6% | 0.0 – 16.0 (mean 0.0286) |
| `totalcas` | float64 | 0.0% | 0.0 – 7974.0 (mean 259.9026) |
| `totaldeces` | float64 | 0.2% | 0.0 – 981.3 (mean 5.1334) |
| `letal` | float64 | 4.7% | 0.0 – 100.0 (mean 0.7896) |
| `attaq` | float64 | 2.5% | 0.0 – 999.7 (mean 139.6562) |
| `recstatus` | float64 | 3.2% | 1.0 – 1.0 (mean 1.0) |
| `uniquekey` | float64 | 3.2% | 1.0 – 2757.0 (mean 679.2195) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-15 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `pop` | 0.0 | 1232023.0 | 201445.4852 | 182300.0 |
| `numsem` | 1.0 | 8.0 | 4.3945 | 4.0 |
| `c328tnn` | 0.0 | 651.0 | 2.9648 | 0.0 |
| `dtnn` | 0.0 | 3.0 | 0.0036 | 0.0 |
| `c011mois` | 0.0 | 3847.0 | 44.8348 | 11.0 |
| `d011mois` | 0.0 | 7.0 | 0.0375 | 0.0 |
| `c1259mois` | 0.0 | 2060.0 | 76.6688 | 20.0 |
| `d1259mois` | 0.0 | 9.0 | 0.0657 | 0.0 |
| `c515ans` | 0.0 | 3330.0 | 64.449 | 14.0 |
| `d515ans` | 0.0 | 218.0 | 0.0247 | 0.0 |
| `cp15ans` | 0.0 | 3449.0 | 101.7957 | 20.0 |
| `dp15ans` | 0.0 | 16.0 | 0.0286 | 0.0 |
| `totalcas` | 0.0 | 7974.0 | 259.9026 | 58.0 |
| `totaldeces` | 0.0 | 981.3 | 5.1334 | 0.0 |
| `letal` | 0.0 | 100.0 | 0.7896 | 0.0 |

---

## 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`. 772 exact duplicate rows were removed. 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 Democratic Republic of the Congo (DRC) 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: `c328tnn`, `dtnn`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/rd-congo-donnees-epidemiologiques) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_rd_congo_donnees_epidemiologiques,
title = {Democratic Republic of Congo : Epidemioliogical cases and deaths (Données épidémiologiques)},
author = {OCHA Democratic Republic of the Congo (DRC)},
year = {2025},
url = {https://data.humdata.org/dataset/rd-congo-donnees-epidemiologiques},
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.*