Passenger Title and survival rate
Was it coincidence that upper-class Rose survived and third-class passenger Jack not? Let's have a look...
You have access to a new train and test set named train_new
and test_new
. These data sets contain a new column with the name Title
(referring to Miss, Mr, etc.). Title
is another example of feature engineering: it's a new variable that possibly improves the model.
This exercise is part of the course
Kaggle R Tutorial on Machine Learning
Exercise instructions
- Finish the command to create a decision tree
my_tree_five
: make sure to include theTitle
variable, and to create the tree based ontrain_new
. - Visualize
my_tree_five
withfancyRpartPlot()
. Notice thatTitle
appears in one of the nodes. - Finish the
predict()
call to createmy_prediction
: the function should usemy_tree_five
andtest_new
to make predictions. - The code that creates a data frame
my_solution
and writes it to a CSV file is included: these steps make the solution ready for a submission on Kaggle.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# train_new and test_new are available in the workspace
# Finish the command
my_tree_five <- rpart(Survived ~ Pclass + Sex + Age + SibSp + Parch + Fare + Embarked + ___,
data = ___, method = "class")
# Visualize my_tree_five
# Make prediction
my_prediction <- predict(___, ___, type = "class")
# Make results ready for submission
my_solution <- data.frame(PassengerId = test_new$PassengerId, Survived = my_prediction)
write.csv(my_solution, file = "my_solution.csv", row.names = FALSE)