实验：由上面的学习，我们可以知道ID3的核心应该是在决策树各个结点上，

Experiment: From the above study, we can know that the core of ID3 should be at each node of the decision tree, select features for the corresponding information gain criteria, and build the tree recursively. The specific method is: starting from the root node, calculate the information gain of all possible features for the node, select the feature with the largest information gain as the feature of the node, and establish child nodes from different values ​​of the feature; then The above method is called recursively on the child nodes to construct a decision tree; until the information gain of all features is very small or no features can be selected, a decision tree is finally obtained. <br>The training set is as follows:

Experiment: From the above study, we can know that the core of ID3 should be in the decision tree at each node, the corresponding information gain criteria to select characteristics, recursively build the tree. The specific method is: starting with the root node (root node), calculating the information gain of all possible features, selecting the feature with the largest information gain as the node feature, establishing the child node by the different values of the feature, then calling the above method on the sub-junction recursively, building the decision tree, until the information gain of all features is small or no features to be selected, and finally a decision tree is obtained.<br>The training set is as follows:

Experiment: from the above learning, we can know that the core of ID3 should be to select the characteristics of the corresponding information gain criteria on each node of the decision tree and construct the tree recursively. The specific method is: from the root node (root Node) first, calculate the information gain of all possible features for the node, select the feature with the largest information gain as the feature of the node, and establish the sub node according to the different values of the feature; then call the above methods recursively for the sub node to build the decision tree; until the information gain of all features is small or there is no feature to choose, finally get a decision tree.<br>The training set is as follows: