In the first lecture Bagging notebook there is this markdown cell
Bagging in scikit-learn
Scikit-learn implements the bagging procedure as a “meta-estimator”, that is an estimator that wraps another estimator: it takes a base model that is cloned several times and trained independently on each bootstrap sample.
The following code snippet shows how to build a bagging ensemble of decision trees. We set n_estimtators=100` instead of 3 in our manual implementation above to get a stronger smoothing effect.
There´s one letter “t” too much. 