Decision tree
In the last three chapters, you've learned a range of techniques that help you tackle many aspects of the machine learning interview. In this chapter, you'll be introduced to various ways to make sure any model you're asked to create or discuss in a machine learning interview is generalizable, evaluated correctly, and properly selected from among other possible models.
In this exercise, you will delve into hyperparameter tuning for a decision tree on the loan_data dataset.
Here you'll tune min_samples_split, which is the minimum number of samples required to create an additional binary split, and max_depth, which is how deep you want to grow the tree. The deeper a tree, the more splits and therefore captures more information about the data.
The feature matrix X and the target label y have been imported for you.
Note that you're once again performing all of the steps in the machine learning pipeline!
This exercise is part of the course
Practicing Machine Learning Interview Questions in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Import modules
from sklearn.tree import ____
from sklearn.metrics import accuracy_score
# Train/test split
X_train, X_test, y_train, y_test = train_test_split(____, ____, test_size=0.30, random_state=123)
# Instantiate, Fit, Predict
loans_clf = ____()
loans_clf.____(____, ____)
y_pred = loans_clf.____(____)
# Evaluation metric
print("Decision Tree Accuracy: {}".format(____(____,____)))