June 2020
Intermediate to advanced
382 pages
11h 39m
English
Let's instantiate the random forest algorithm and use it to train our model using the training data.
There are two key hyperparameters that we'll be looking at here:
n_estimators
max_depth
The n_estimators hyperparameter controls how many individual decision trees are built and the max_depth hyperparameter controls how deep each of these individual decision trees can go.
So, in other words, a decision tree can keep splitting and splitting until it has a node that represents every given example in the training set. By setting max_depth, we constrain how many levels of splits it can make. This controls the complexity of the model and determines how closely it fits the training ...