def test_classify(self): my_data, labels = trees.createDataSet() my_tree = treePlotter.retrieveTree(0) print(trees.classify(my_tree, labels, [1, 0])) print(trees.classify(my_tree, labels, [1, 1]))
def test_createDataSet(self): # 获得数据集和标签 my_data, labels = trees.createDataSet() print(my_data) # 计算数据集的信息熵 print(trees.calcShannonEnt(my_data))
def test_createTree(self): my_data, labels = trees.createDataSet() my_tree = trees.createTree(my_data, labels) print(my_tree)
def test_chooseBestFeatureToSplit(self): my_data, labels = trees.createDataSet() print(trees.chooseBestFeatureToSplit(my_data)) print(my_data)
def test_splitDataSet(self): my_data, labels = trees.createDataSet() print(my_data) print(trees.splitDataSet(my_data, 0, 1)) print(trees.splitDataSet(my_data, 0, 0))
def test_calcShannonEnt(self): my_data, labels = trees.createDataSet() # 增加一个新的分类 'maybe' ,观察信息熵的变化 my_data[0][-1] = 'maybe' print(trees.calcShannonEnt(my_data))