Now let's join the numerical and categorical pipelines.
Join the two pipeline and save it in a variable named preprocess_pipeline:
from sklearn.pipeline import FeatureUnion
<< your code goes here >> = FeatureUnion(transformer_list=[
("num_pipeline", num_pipeline),
("cat_pipeline", cat_pipeline),
])
Fit the training data in this pipeline:
X_train = preprocess_pipeline.fit_transform(<< your code goes here >>)
Save the labels in y_train:
<< your code goes here >> = train_data["Survived"]
Loading comments...