Dataset for machine learning MK stellar classification

Question

I would like to create program for automatic Morgan-Keenan stellar classification using machine learning. For that, I need dataset of stars with known absolute magnitude, temperature and luminosity type (0, Ia, Ib, ..., VII). I found some datasets, (e. g. kaggle.com), however they contain only few hundreds stars and not all star types are represented.

Is there any large enough dataset (at least 1000 stars) in which all types of stars are represented, from hypergiants to dwarfs, and with all the information mentioned?

Answer 1

That I know there is the XHIP catalog via VizieR and you can enter a range in UMag (or B- and V-band) for example of -20 .. 20. Check the box SpType and Tc to get also the spectral type and temperature (double check the literature for the quantities you need)

On the column on the left titled Preferences, set the quantity max to unlimited (it's the number of data) and the box just below indicates the format to download the data, if you want *.csv select CDS Portal and click on Submit.

You will be redirected on the CDS portal and simply click on Save and then on MyData, it will show you a list of the dataset you saved and you can select the format of your file (csv, fits, etc.) and then download.

With the simple range of the V absolute magnitude between -20 and 20 you get more then 100k stars

Edited: I noticed that downloading the data through the CDS portal does not give you the quantities that you check, but some fixed one. Maybe I can suggest to select ascii text/plain and then download the page.