This is a decision tree built on the Titanic dataset.
The algorithm went through the data and decided that for the first split, the Sex attribute was the most appropriate, as it found that the value Female lead to a large percentage of correctly predicted examples. You can see the number of examples affected by this decision when you hover the mouse pointer over the box with the Yes or No label.
For Sex=Male, new rules have been found by repeatedly splitting the data using the same algorithm. This gave you a decision tree that classifies data by going through a list of decisions. If you had a second Titanic and sank it, you could use this tree to predict the survival of passengers.
The Age = ? decision is an indicator that you have missing data (indicated with ? here) in your example set, and that a rule using this property was found: If the age is missing, more people didn't survive.
Newbie
Answers
This is a decision tree built on the Titanic dataset.
The algorithm went through the data and decided that for the first split, the Sex attribute was the most appropriate, as it found that the value Female lead to a large percentage of correctly predicted examples. You can see the number of examples affected by this decision when you hover the mouse pointer over the box with the Yes or No label.
For Sex=Male, new rules have been found by repeatedly splitting the data using the same algorithm. This gave you a decision tree that classifies data by going through a list of decisions. If you had a second Titanic and sank it, you could use this tree to predict the survival of passengers.
The Age = ? decision is an indicator that you have missing data (indicated with ? here) in your example set, and that a rule using this property was found: If the age is missing, more people didn't survive.
Regards,
Balázs