Datasets

You are here: Home Resources Datasets

Astronomical datasets provided by educators to exercise statistical and computational methods

Data mining datasets, University of Edinburgh Twenty-four datasets from a wide range of fields including the SuperCOSMOS Sky Survey Object Catalogue and Volcanoes on Venus.

Datasets for textbook Statistics, Data Mining, and Machine Learning in Astronomy (Z. Ivezic, A. Connolly, J. VanderPlas, A. Gray, 2013) Seventeen datasets from the Sloan Digital Sky Survey and other astronomical surveys with Python codes illustrating statistical analysis, classification and graphics.

Datasets for textbook Modern Statistical Methods for Astronomy with R Applications (E. D. Feigelson & G. J. Babu, Cambridge University Press, 2012)  Nineteen datasets from several branches of astronomy with R codes illustrating  univariate distributions, measurement errors, censoring and truncation, nonlinear regression, multivariate analysis, clustering and classification, spatial point processes, and time series analysis with graphics.

Datasets for R exercises and graphics (University of Birmingham) Several datasets from extragalactic astronomy prepared by Alastair Sanderson for online tutorials on the R statistical software environment with graphics.

Time series of variable stars (University of California Berkeley) Visible band lightcurves of 137 classes of variable stars, serving as training sets for classification of lightcurves generated by wide-field multi-epoch surveys.  From Berkeley’s Center for Time Domain Informatics.

Time series of X-ray sources (Naval Research Lab) A variety of Poissonian and Gaussian time series from X-ray astronomy including: quasar, BL Lac object, supernova, accretion binary star systems, gamma-ray burst, and sunspots.