#pipelines

Question 1: Select all that apply

Which statements about machine learning pipelines (a chain of preprocessing steps ending with a model, as in scikit-learn's Pipeline) are true? Select all that apply.

A single pipeline can contain scaling of numeric features, one-hot encoding of categorical features and a final model1
Once a pipeline ends with a model, you can call fit, predict and score on the whole pipeline2
A pipeline can also take care of splitting the data into training and test sets3
The order of the steps in a pipeline matters4
When a pipeline is cross-validated, its transformers are fit on each training fold and only applied (transform) to the validation fold5

Timed test