Hi, I’m noob to machine learning, just I was going through Google’s Machine Learning recipes videos, in which I came up with something called as DecisionTreeClassifier. The things which I didn’t understood there is that he used an example of deciding a fruit based on features.
The features used in the example are as follows : Weight, Texture
The code is as follows :
from sklearn import tree # Here 0 indicates texture (bumpy) and 1 indicates texture (plain) features = [[ 140, 1 ] [ 130, 1 ] [ 150, 0 ] [ 170, 0 ]] # Here 0 indicates fruit (orange) and 1 indicates fruit (apple) labels = [0, 0, 1, 1] clf = tree.DecisionTreeClassifier() clf = clf.fit(features, labels) print clf.predict([[150, 0]])
My question is that,
Where the machine is actually learning and where the learnt data is saved?
And on what bases machine is deciding the fruit type?