However in the above decision of tree which it is significant that there the "parents visiting" node came on the top of the tree. Whether we don't know exactly the reason for this and we didn't see the example weekends from that the tree was produced but still number of weekends the parents visited was relatively high but every weekend they did visit and there was a trip to the cinema. Let assume in following example that the parents have visited every fortnight for a year but on each occasion the family visited the cinema. Because there is no evidence in favour of doing anything rather than watching a film the parents visit. As given that there we are learning rules from examples because if the parents visit then the decision is already made. Thus we can put this at the top of the decision tree but disregard all the examples when the parents visited while constructing the rest of the tree. Do not having to think about a set of examples that will make the construction job easier.
In fact this kind of thinking underlies the ID3 algorithm for learning decisions trees that we will describe more formally below. Moreover the reasoning is a little more subtle like in our example it would also take with account the examples where the parents did not visit yet.