denguedatasets

The denguedasets package provide a curated collection of open-access dengue fever surveillance and climate datasets for epidemiological research and machine learning. Includes surveillance records, climatic co-variates, and mortality indicators from Bangladesh, the Philippines, Taiwan, Sri Lanka, Brazil, Colombia, Pakistan, India, Peru, Indonesia, and Sierra Leone, spanning case counts, deaths, case-fatality rates, and associated meteorological variables (temperature, humidity, precipitation) suitable for spatiotemporal analysis, outbreak prediction, machine learning, and time-series modeling from Kaggle."

You can install the denguedatasets package from PyPI

pip install denguedatasets

import denguedatasets as dd

import denguedatasets as dd

# List all available datasets
dd.list_datasets()

# Inspect metadata (source, license, description) before loading
dd.dataset_info("dengue_taiwan")

# Load a dataset as a pandas DataFrame
df = dd.load_dataset("dengue_taiwan")
df.head()

# Describe dataset
df = dd.describe("dengue_taiwan")
print(df)

load_dataset accepts any keyword argument supported by pandas.read_csv, forwarded directly:

df = dd.load_dataset("dengue_brazil", sep=";", encoding="latin-1")

Full details for each dataset (original source URL, license text, original filename, and description) are documented in datasets.md.

Run denguedasets.list_datasets or dd.list_datasets (using dd as alias) to see the full list of availabale datasets.

The datasets included in denguedasets are provided strictly for educational, research, and informational purposes. Every dataset bundled with this package originates from a public Kaggle dataset. Each retains its original license as declared by its publisher (see the table above and datasets.md); this package does not relicense the underlying data. Users redistributing or publishing derived work should check the individual dataset license before reuse.

The author of denguedasets makes no warranties, express or implied, regarding the accuracy, completness, or suitability of any datasets for a particular purpose. Users are solely responsible for ensuring that their use of these datasets complies with applicable laws, regulations, and ethical guidelines.

Anu finding, conclusions, or decisions derived from the use of these datasets are the soloe responsibility of the user. The author shall not be held liable for any direct, indirect, or consequential damages arising from the use or misuse of the datasets included in this package.

git clone https://github.com/fdzul/denguedatasets-py.git
cd denguedatasets_py
pip install -e ".[dev]"
pytest -v

If you use this package in your research, please cite it as:

Dzul Manzanilla, F.A. & Correa Morales, F. (2026). denguedatasets: A curated collection of open-access dengue fever datasets for epidemiological research (Version 0.1.0) [Software]. https://github.com/fdzul/denguedatasets-py

• Felipe A. Dzul Manzanilla — ORCID: 0000-0002-2085-9141 — Instituto Nacional de Salud Pública (INSP), Mexico
• Fabián Correa Morales — ORCID: 0000-0002-6193-1242 — Centro Nacional de Programas Preventivos y Control de Enfermedades (CENAPRECE), Mexico

The denguedatasets library es release under GNU General Public License v3.0 (GPL-3.0), which ensures that all source code and derived works remain free and open-source. See LICENSE for details. Individual datasets retain their own original licenses as documented in datasets.md.