Feature Extraction/ Processing

source https://scikit-learn.org/stable/modules/feature_extraction.html

Scale the data

sklearn.preprocessing.MinMaxScaler

from sklearn.preprocessing import MinMaxScaler

mm = MinMaxScaler()

x_train = mm.fit_transform(x_train)
x_test = mm.transform(x_test)

Text data will be very sparse
we can scale them into (0,1) range