We'll talk in more detail on Monday. A running tally of my thoughts on reading the methods/results.
You need to present properly formatted tables and graphs, not screenshots of output
Don't just present variable labels. They should be given meaningful names and explain what each variable represents
Why do you choose ID, DATE, YEAR, DISTRICT, AND PRIMARY TYPE as your variables of interest? They should connect back to some theory or hypothesis
Justify data transformations. For example, why convert the continuous time column to a binned categorical variable?
Consider line graphs for visualizing data over time
Why do some districts in Chicago have higher crime rates than others? Is there a spatial component here? Are those districts located near one another? Graphing this using a map could be useful (if you know how to do this)
Is the outcome of interest a continuous measure? If so, this is random forest regression not classification. I don't know how a confusion matrix would be relevant here. Are you sure you performed regression and not classification?
We'll talk in more detail on Monday. A running tally of my thoughts on reading the methods/results.