How to train xgboost model to get 0/1?

Question

Python

Good afternoon, dear toaster users!
I wondered how, having data in the format dd.mm.yyyy for 6 months (10+ thousand lines), to get a prediction for the next month using xgboost black box, I take the first steps, I found a lot of complex tasks on the Internet, with many variables, everything is different in this task , please share examples of a simple forecast in the format dd.mm.yyyy! if someone is ready on a commercial basis, then of course I will immerse, but the knowledge is yours, so I will understand everything! thanks in advance,

Answer 1

You cannot fit the solution of a machine learning problem into one comment.
First, write down that there is an object for which predictions are made, what features it has (input data), what is the output data. After that, try to understand what problem you are solving - classification, regression, clustering. Take the simplest algorithm that solves the problem and try to use it with any library that you have any knowledge of. Select metrics that evaluate the quality of the algorithm. Then try another algorithm. Compare them to each other.
When all this is as easy as writing questions in a toaster, try xgboost.

Answer 2

found good material on the topic here
a key question arose, so as not to produce topics, there is a csv file, in some lines there is a "-" sign, which means that it does not need to be taken into account in statistics, how to prepare a database in this case? how to indicate that cells that contain - should not be perceived?