def test_treeNums(self):
dataSet, labels = trees.createDataSet()
print("\n dataSet == %s" % (dataSet))
tree = trees.createTree(dataSet, labels)
print("\n tree == %s" % (tree))
leafs = treePlotter.getNumLeafs(tree)
depth = treePlotter.getTreeDepth(tree)
print("\n leafs == %s depth == %s " % (leafs, depth))
def createPlot(self, inTree):
fig = plt.figure()
axprops = dict(xticks=[], yticks=[])
treePlotter.createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)
treePlotter.plotTree.totalW = float(treePlotter.getNumLeafs(inTree))
treePlotter.plotTree.totalD = float(treePlotter.getTreeDepth(inTree))
treePlotter.plotTree.x0ff = -0.5 / treePlotter.plotTree.totalW
treePlotter.plotTree.y0ff = 1.0
treePlotter.plotTree(inTree, (0.5, 1.0), '')
return fig
print shannonEnt
#split dataset
print '-------------- split dataset --------------------'
print splitDataSet(myDat,0,1)
print splitDataSet(myDat,0,0)
#get best feature
print '-------------- best feature --------------------'
print 'best feature:' ,chooseBestFeatureToSplit(myDat)
print 'createTree ', createTree(myDat,labels)
#plot trees
print '-------------- plot-trees --------------------'
myTree = tp.retrieveTree(0)
print 'myTree ', myTree
print 'labels', labels
print 'numLeafs ', tp.getNumLeafs(myTree)
print 'treeDepth ', tp.getTreeDepth(myTree)
#tp.createPlot(myTree)
#update dict and plot again
#myTree['no surfacing'][3] = 'maybe'
#tp.createPlot(myTree)
#classify
print '-------------- classify --------------------'
myDat, labels = createDataSet()
print 'labels', labels
myTree = tp.retrieveTree(0)
print 'myTree ', myTree
print '[1,0]: ', classify(myTree, labels, [1,0])
print '[1,1]: ', classify(myTree, labels, [1,1])
# 测试创建树 reload(trees) myDat, labels = trees.createDataSet() myTree = trees.createTree(myDat, labels) myTree # 测试matplotlib import treePlotter treePlotter.createPlot() # 测试获取叶子数量及树深度的函数 reload(treePlotter) treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) treePlotter.getNumLeafs(myTree) treePlotter.getTreeDepth(myTree) # 绘制树 reload(treePlotter) myTree=treePlotter.retrieveTree(0) treePlotter.createPlot(myTree) # 变更字典，重新绘制 myTree['no surfacing'][3]='maybe' myTree treePlotter.createPlot(myTree) # 测试分类函数 myDat, labels = trees.createDataSet() labels
import treePlotter as tp print tp.retrieveTree(0) print tp.retrieveTree(1) myTree = tp.retrieveTree(0) print tp.getNumLeafs(myTree) print tp.getTreeDepth(myTree) # tp.createPlot(myTree) tp.createPlot(tp.retrieveTree(1))
@author: weixw
"""
import myTrees as mt
import treePlotter as tp
# 测试
dataSet, feature_names = mt.createDataSet()
# copy函数：新开辟一块内存，然后将list的所有值复制到新开辟的内存中
feature_names1 = feature_names.copy()
# createTree函数中将labels1的值改变了，所以在分类测试时不能用labels1
myTree = mt.createTree(dataSet, feature_names)
# 保存树到本地
mt.storeTree(myTree, 'myTree.txt')
# 在本地磁盘获取树
myTree = mt.grabTree('myTree.txt')
print(u"决策树结构：%s" % myTree)
# 绘制决策树
print(u"绘制决策树：")
tp.createPlot(myTree)
numLeafs = tp.getNumLeafs(myTree)
treeDepth = tp.getTreeDepth(myTree)
print(u"叶子节点数目：%d" % numLeafs)
print(u"树深度：%d" % treeDepth)
# 测试分类 简单样本数据3列
labelResult = mt.classify(myTree, feature_names, [1, 1])
print(u"[1,1] 测试结果为：%s" % labelResult)
labelResult = mt.classify(myTree, feature_names, [1, 0])
print(u"[1,0] 测试结果为：%s" % labelResult)
print shannonEnt
#split dataset
print '-------------- split dataset --------------------'
print splitDataSet(myDat, 0, 1)
print splitDataSet(myDat, 0, 0)
#get best feature
print '-------------- best feature --------------------'
print 'best feature:', chooseBestFeatureToSplit(myDat)
print 'createTree ', createTree(myDat, labels)
#plot trees
print '-------------- plot-trees --------------------'
myTree = tp.retrieveTree(0)
print 'myTree ', myTree
print 'labels', labels
print 'numLeafs ', tp.getNumLeafs(myTree)
print 'treeDepth ', tp.getTreeDepth(myTree)
#tp.createPlot(myTree)
#update dict and plot again
#myTree['no surfacing'][3] = 'maybe'
#tp.createPlot(myTree)
#classify
print '-------------- classify --------------------'
myDat, labels = createDataSet()
print 'labels', labels
myTree = tp.retrieveTree(0)
print 'myTree ', myTree
print '[1,0]: ', classify(myTree, labels, [1, 0])
print '[1,1]: ', classify(myTree, labels, [1, 1])
#lensesLabels = ["年龄组" , "规定", "闪光", "泪液扫除率"] lensesLabels = ['age' , 'prescript', 'astigmatic', 'tearRate'] lensesTree = tr.createTree(lenses,lensesLabels) print(lensesTree) tp.createPlot(lensesTree) dataSet, labels = tr.createDataSet() shannonEnt = tr.calcShannonEnt(dataSet) print(shannonEnt) print(tp.retrieveTree(1)) myTree = tp.retrieveTree(0) numLeafs = tp.getNumLeafs(myTree) treeDepth = tp.getTreeDepth(myTree) print(numLeafs) print(treeDepth) myTree = tp.retrieveTree(0) tp.createPlot(myTree) myTree['no surfacing'][3] = 'maybe' tp.createPlot(myTree) myDat,labels = tr.createDataSet() print(labels) myTree = tp.retrieveTree(0)
}
}
}, {
'no surfacing': {
0: 'no',
1: {
'flippers': {
0: {
'head': {
0: 'no',
1: 'yes'
}
},
1: 'no'
}
}
}
}]
return listOfTrees[i]
# createPlot(thisTree)
if __name__ == "__main__":
import treePlotter
myTree = treePlotter.retrieveTree(0)
print("\ntreePlotter.getTreeDepth:\n", treePlotter.getTreeDepth(myTree))
print("\ntreePlotter.getNumLeafs:\n", treePlotter.getNumLeafs(myTree))
print("\nmyTree:\n", myTree)
createPlot(myTree)
1) # [[1, 'yes'], [1, 'yes'], [0, 'no']]
splittedDat = DT.splitDataSet(myDat, 0, 0) # [[1, 'no'], [1, 'no']]
bestFeature = DT.chooseBestFeatureToSplit(myDat) # 0
myTree = DT.createTree(
myDat, labels
) # {'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
import treePlotter as TP
# TP.createPlot()
myTree = TP.retrieveTree(
0) #{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
n = TP.getNumLeafs(myTree) # 3
d = TP.getTreeDepth(myTree) # 2
TP.createPlot(myTree)
# classify
myDat, labels = DT.createDataSet()
myTree = TP.retrieveTree(
0) # {'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
class1 = DT.classify(myTree, labels, [1, 0]) # no
class2 = DT.classify(myTree, labels, [1, 1]) # yes
# storing the tree pickeld form
DT.storeTree(myTree, 'data/classifierStorage.txt')
grabedTree = DT.grabTree(
'data/classifierStorage.txt'
fig.clf()
createPlot.ax1 = plt.subplot(111, frameon=False) #绘制子图
plotNode('a decision node', (0.5, 0.1), (0.1, 0.5), decisionNode)
plotNode('a leaf node', (0.8, 0.1), (0.3, 0.8), leafNode)
plt.show()
# 绘制树型的示例程序
createPlot()
# 统计叶子个数和树的层数
import treePlotter
myTree = treePlotter.retrieveTree(0) # 直接从上面的结果导入树结构
print('叶子节点数：', treePlotter.getNumLeafs(myTree)) # 统计叶子节点个数，以计算x轴长度
print('树的层数：', treePlotter.getTreeDepth(myTree)) # 统计树的层数，以计算y轴高度
# 绘制完整的决策树模型
print('绘制完整的决策树模型')
treePlotter.createPlot(myTree)
### 应用数据构造决策树并用于预测
import W_tree
import treePlotter
myDat, labels = W_tree.createDataSet()
myTree = treePlotter.retrieveTree(0)
print('[1,0]的分类结果是', W_tree.classify(myTree, labels, [1, 0])) # [1,0]的分类结果是 no
print('[1,1]的分类结果是', W_tree.classify(myTree, labels,
[1, 1])) # [1,1]的分类结果是 yes
import treePlotter treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) print(treePlotter.getNumLeafs(myTree)) print(treePlotter.getTreeDepth(myTree))
__author__ = 'Wei Yin' import treePlotter treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) treePlotter.getNumLeafs(myTree) treePlotter.getTreeDepth(myTree) treePlotter.createPlot(myTree)
import trees import treePlotter myDat, labels = trees.createDataSet() print myDat print trees.calcShannonEnt(myDat) print trees.splitDataSet(myDat, 0, 1) print trees.splitDataSet(myDat, 0, 0) print trees.splitDataSet(myDat, 1, 1) print trees.chooseBestFeatureToSplit(myDat) print trees.createTree(myDat, labels) treePlotter.createPlot() print 'createPlot over' print treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) print treePlotter.getNumLeafs(myTree) print treePlotter.getTreeDepth(myTree)
import treePlotter
import tree
myDat, labels = tree.createDataSet()
myTree = tree.createTree(myDat, labels)
print('myTree = ', myTree)
print('treePlotter.getNumLeafs(myTree) = ', treePlotter.getNumLeafs(myTree))
print('treePlotter.getTreeDepth(myTree) = ', treePlotter.getTreeDepth(myTree))
treePlotter.createPlot(myTree)
trees.splitDataSet(myDat, 0, 1) trees.splitDataSet(myDat, 0, 0) print "选择最好的数据集划分方式:", trees.chooseBestFeatureToSplit(myDat) #3.1.3 递归构建决策树 myDat, labels = trees.createDataSet() myTree = trees.createTree(myDat, labels) print "myTree:", myTree #3.2.1 Matplotlib注解 treePlotter.createPlot() #3.2.2 构造注解树 treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) print "获取叶节点的数目:", treePlotter.getNumLeafs(myTree) print "获取树的层数:", treePlotter.getTreeDepth(myTree) treePlotter.createPlot(myTree) myTree['no surfacing'][3] = 'maybe' print "myTree:", myTree treePlotter.createPlot(myTree) #3.3.1 测试算法：使用决策树执行分类 myDat, labels = trees.createDataSet() print "labels:", labels myTree = treePlotter.retrieveTree(0) print "myTree:", myTree print "分类1:", trees.classify(myTree, labels, [1, 0]) print "分类2:", trees.classify(myTree, labels, [1, 1]) #3.3.2 决策树的存储
import treePlotter
if __name__ == '__main__':
print treePlotter.retrieveTree(1)
myTree = treePlotter.retrieveTree(1)
print treePlotter.getNumLeafs(myTree)
print treePlotter.getTreeDepth(myTree)
print tree.calcShannonEnt([[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'yes'],
[0, 1, 'yes'], [0, 1, 'yes']])
print tree.splitDataSet(
[[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'no'], [0, 1, 'no'], [0, 1, 'no']],
0, 1)
print tree.chooseBestFeatureToSplit([[1, 1, 'yes'], [1, 1, 'yes'],
[1, 0, 'no'], [0, 1, 'no'], [0, 1, 'no']])
print tree.createTree(
[[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'no'], [0, 1, 'no'], [0, 1, 'no']],
['No Surfacing?', 'Flippers?'])
t = {'No Surfacing?': {0: 'no', 1: {'Flippers?': {0: 'no', 1: 'yes'}}}}
print treePlotter.getNumLeafs(t)
print treePlotter.getTreeDepth(t)
treePlotter.createPlot(t)
print tree.classify(
{'No Surfacing?': {
0: 'no',
1: {
'Flippers?': {
0: 'no',
1: 'yes'
}
}
}}, ['No Surfacing?', 'Flippers?'], [1, 0])
