# Preparing and combining datasets for predictions

I am trying to create and train a model to predict the winner of a professional DOTA match. This model is only for "fun" and shouldn't be used for professional purposes but is clearly for learning.

I know that a very important part of ML is to prepare your data. In my case, I have two sets of data that I am not quite sure how to combine.

First, i have a dataset of the teams overall performance that looks something like this:

Other than that, I have individual match performance:

I also have data or match that shows individual skill level for the players per match:

Now my question is, how do I prepare my data to be put into the model? How can I combine such very different datasets into a dataset that is usable for training a model on it?

My end goal is to input two teams and predict a match winner