Repositories¶

The core of the scikit-datasets package consist in fetching functions to obtain data from several repositories, containing both multivariate and functional data.

The subpackage repositories contains a module per available repository. For repositories that contain data in a regular format, that module has a fetch function that returns data in a standardized format. For modules such as cran, where data is in a non-regular format, specific functions are provided to return the data.

The available repositories are described next.

Aneurisk¶

The Aneurisk dataset repository

URL: http://ecm2.mathcs.emory.edu/aneuriskweb/index

fetch([name, data_home, return_X_y])

CRAN¶

The main repository of R packages.

URL: https://cran.r-project.org/

`fetch_package`(package_name, *[, ...])	Fetch all datasets from a R package.
`fetch_dataset`(dataset_name, package_name, *)	Fetch an R dataset.

Forex¶

The foreign exchange market (Forex).

URL: https://theforexapi.com/

fetch([start, end, currency_1, currency_2, ...])

Fetch Forex datasets.

Keel¶

The KEEL-dataset repository.

URL: https://sci2s.ugr.es/keel/datasets.php

Fetch Keel dataset.

Keras¶

The Keras example datasets.

URL: https://keras.io/api/datasets

Fetch Keras dataset.

LIBSVM¶

The LIBSVM data repository.

URL: https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/

Fetch LIBSVM dataset.

Rätsch¶

The Gunnar Rätsch benchmark datasets.

URL: https://github.com/tdiethe/gunnar_raetsch_benchmark_datasets/

Fetch Gunnar Raetsch's dataset.

scikit-learn¶

The scikit-learn example datasets.

URL: https://scikit-learn.org/stable/datasets.html

fetch(name, *[, return_X_y])

Fetch Scikit-learn dataset.

UCI¶

The University of California Irvine (CRAN) repository.

URL: https://archive.ics.uci.edu

Fetch UCI dataset.

UCR¶

The UCR/UEA time series classification archive.

URL: https://www.timeseriesclassification.com

Fetch UCR dataset.