latamdata-py: Python Package for Latin American Research Datasets

April 3, 2026 · View on GitHub

DOI ORCID License: CC0 GitHub release CI codecov Docs Open In Colab

Part of the Open Research Collection — 1,273+ datasets · Author: Juan Moisés de la Serna Tuya · UNIR


Overview

latamdata-py is a Python package that provides one-line access to 38+ open research datasets from Latin America, covering neuroscience, mental health, epidemiology, and social determinants of health.

All datasets are free, open, and available under CC0 or CC-BY-4.0 licenses.


Installation

pip install latamdata-py

Requirements: Python 3.8+ · pandas · requests


Quick Start

import latamdata as ld

# List all available datasets
ld.list_datasets()

# Load a dataset as a pandas DataFrame
df = ld.load("alzheimer-latam")
print(df.head())

# Get metadata for a specific dataset
ld.info("mental-health-specialists")

Available Datasets

Dataset IDTitleTopicDOI
alzheimer-latamAlzheimer's Disease in Latin America (2000–2050)Neuroscience10.7910/DVN/UVHABW
mental-health-specialistsMental Health Specialists in Ibero-America (2000–2026)Mental Health10.5281/zenodo.18984813
generative-ai-researchGenerative AI in Academic Research (2022–2025)AI & Education
psychological-wellbeing-latamPsychological Wellbeing of Researchers in Latin AmericaMental Health
global-mental-healthGlobal Mental Health StatisticsEpidemiology
ai-educational-impact-latamAI Educational Impact in Latin AmericaAI & Education
mental-health-lockdownMental Health and Lockdown DatasetMental Health
adhd-latamADHD in Latin America — GBD 1990–2026Neuroscience

Use ld.list_datasets() to see the full list of 38+ datasets at runtime.


API Reference

latamdata.load(dataset_name, **kwargs)

Load a dataset as a pandas DataFrame.

df = ld.load("alzheimer-latam")
ParameterTypeDescription
dataset_namestrDataset identifier (see table above)
**kwargsExtra arguments passed to pandas.read_csv()

latamdata.list_datasets()

Returns a DataFrame with all available datasets (name, title, DOI, keywords).

latamdata.info(dataset_name)

Returns a dict with metadata for a single dataset (title, URL, DOI, description, keywords).


Citation

If you use latamdata-py in your research, please cite:

@software{serna_tuya_2026_latamdata,
  author    = {Serna Tuya, Juan Moisés},
  title     = {latamdata-py: One-line access to 38 open research datasets from Latin America},
  year      = {2026},
  version   = {1.0.0},
  doi       = {10.5281/zenodo.19145316},
  url       = {https://github.com/juanmoisesd/latamdata-py}
}

License

Code: MIT · Data: CC0 1.0 Universal


Juan Moisés de la Serna Tuya · UNIR · Harvard Dataverse