0

I need help with understanding how to know similarities between dataframes in a multiple density plot. I'm currently working on a project and my task is to determine which dataframe is the most similar one to a chosen dataframe. Well, I don't think I can post my company data here, so i just found a density plot which most likely can help me. Let's say 'Waseca' is the chosen datframe. Which dataframe is the most similar one with 'Waseca'? If it's possible, can you help me with a python script to do so? Please note that my dataframes have different shapes. thanks a lot.density plot

Well, my senior told me just to see and look which one is the similar one, but since I'm a beginner I can't be so sure about my visual analysis. So I do think that calculation might help me to get an accurate answer. I did tried some scripts but it doesn't seem to work, but unfortunately i deleted that script :(

lauisjjang
  • 1
  • 2
  • See [KL-divergence](https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence) and compute it with [`scipy.stats.entropy`](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.entropy.html) – paime Mar 07 '23 at 07:42
  • As this is not primarily script-related, you should ask this question on CrossValidated: https://stats.stackexchange.com/ – Mr. T Mar 07 '23 at 07:44
  • if you don;t have data, only have picture, maybe you can compare pixel – Para Mar 07 '23 at 08:08

0 Answers0