Compulsory Task I

Follow these steps:

$$ Create a Decision Tree that can predict the survival of passengers on the

Titanic. Make sure not to impose any restrictions on the depth of the tree.

$$ Use the decision$\_$tree$\_$titanic.ipynb file provided, which has the

titanic.csv dataset loaded $($sourced here$)$ to complete the task.

$$ Select relevant variables from the data and split the data into a training,

development, and test set.

$$ Train a decision tree and make a plot of it$.$

$$ Compute your model$$s accuracy on the development set.

$$ Try building your model with different values of the max$\_$depth $[2-10].$ At

each step, create a plot of your tree and store the accuracies on both the

training and development data.

$$ Plot a line of your training accuracies and another of your development

accuracies in the same graph. Write down what shape the lines have and

what this shape means.

$$ Report the accuracy of your final model on the test data.