python code for the comments steps in part 1 and 2 thank you!!!

Remember in part 1 we bnned wins (df [] ) to a categorcal varable - that was tor making the analyss a classitcation problem. Sometmes we also using binning for dimensionality reduction purposes. For instance, the feature year (df [ 'yearID' ] ) has more than 100 distinct values, so its dimensionality will be 100+. A lot of machine learning algorithms do not like high-dimensional features, so it is a common practice to bin high-dimensional features. Rule of thumb: if a categorical feature has more than 5 categories, you should consider bin it. In the block below, you are going to create your own function (assign_label) and apply it to your data ( df ). When a categorical variable is low-dimensional, we shoud create dummy variables for that. pandas provides a function called get_dummies ( ) for that. [18] 1 \# define the "assign_label" function An alternative way of binning the yearID feature is to bin it by decade, then create dummy variables based on dacades. This can be done using following code