Winter Week 3 Blog Post Chongxian Chen

This week Jake collect some data. I used excel to convert the file into csv file. The data includes the stats for more than 300 schools in NCAA including detailed data such as field goal and field goal percentage. The data will be great to use as training set. We will also be needing single match data and result to be both as training set and test set for our classification model. Since single match with result will have a true(win)/false(loss) result that we can verify the accuracy of our model.

The difficulty I have in this week is trying to understand the mathematical background of classification model. And what file format to save our data. With our TA's help, I figured that both .txt and .csv file will be sufficient to save the data.

Next week we will collect more data includes single matches in NCAA and use scikit to train and test the model.