Training with bootstrapping
Let's now build a "weak" decision tree classifier and train it on a sample of the training set drawn with replacement. This will help you understand what happens on every iteration of a bagging ensemble.
To take a sample, you'll use pandas' .sample() method, which has a replace parameter. For example, the following line of code samples with replacement from the whole DataFrame df:
df.sample(frac=1.0, replace=True, random_state=42)
This exercise is part of the course
Ensemble Methods in Python
Exercise instructions
- Take a sample drawn with replacement (
replace=True) from the whole (frac=1.0) training set,X_train. - Build a decision tree classifier using the parameter
max_depth = 4. - Fit the model to the sampled training data.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Take a sample with replacement
X_train_sample = X_train.____(____, ____, random_state=42)
y_train_sample = y_train.loc[X_train_sample.index]
# Build a "weak" Decision Tree classifier
clf = ____(____, random_state=500)
# Fit the model to the training sample
____