Apply the Decision Tree model on the two data sets respectively.
Apply the K-NN model on the two data sets respectively.
Apply the Naive Bayes model on the two data sets respectively.
(Note: Please divide the dataset into a training set with 80% data and a test set with 20% data)

Based on the first step, we can get six training models. Use Confusion Matrix to evaluate these six models and analyze their pros and cons.

Horizontal comparison: Compare the performance of the same training model on different data sets.
Longitudinal comparison: Compare the performance of different training models on the same data set.

P1 : Decision Tree (training + evaluating + horizontal comparison) & Longitudinal comparison (Dota 2 data set) & Report’s 1 , 2 , 3 , 4.1 ,5.1 ,6.1.1 , 6.2.1
P2 : K-NN (training + evaluating + horizontal comparison) & Longitudinal comparison (LoL data set) & Report’s 4.2 ,5.2 ,6.1.2 , 6.2.2
P3 : Naïve Bayes (training + evaluating + horizontal comparison) & Report’s 4.3 ,5.3 ,6.1.3 & Report’s Conclusion part

https://archive.ics.uci.edu/ml/datasets/Dota2+Games+Results
https://www.kaggle.com/bobbyscience/league-of-legends-diamond-ranked-games-10-min