Python Data Structures and Algorithms

Binarizing data

To binarize a given feature set, we make use of a threshold. If any value within a given dataset is greater than the threshold, the value is replaced by 1. If the value is less than the threshold 1, we will replace it:

    results = preprocessing.Binarizer(50.0).fit(data).transform(data)     print(results) 

An instance of Binarizer is created with the argument 50.0. 50.0 is the threshold that will be used in the binarizing algorithm:

[[ 1.  0.  0.] [ 0.  1.  1.] [ 0.  1.  0.]] 

All values in the data that are less than 50 will have 0 in their stead. The opposite also holds true.