def demo():
print '... demo'
myDat, featNames = createDataSet()
print myDat
shannonEnt = decisionTree.calcShannonEnt(myDat)
print '当前数据集的熵是: ', shannonEnt
print '... 测试拆分数据集'
print decisionTree.splitDataSet(myDat, 0, 1)
print '... 测试最佳特征选择'
bestFeature = decisionTree.chooseBestFeatureToSplit(myDat)
print '最好的分类特征是 %s' % bestFeature
print '... 测试决策树的生成'
myTree = decisionTree.createTree(myDat, featNames)
print '生成的决策树是: \n', myTree
print '... 测试SortedCount'
classList = ['a', 'b', 'b', 'c', 'e']
print decisionTree.majorityCnt(classList)
# print '... 测试绘制树节点'
# plotDecisionTree.createPlot()
print '... 测试绘制决策树'
myTree = plotDecisionTree.retrieveTree(0)
leafNums = decisionTree.getNumLeafs(myTree)
treeDepth = decisionTree.getTreeDepth(myTree)
print myTree
print '叶子数量:%d, 树高度:%d' % (leafNums, treeDepth)
# plotDecisionTree.createPlot(myTree)
print '... 预测'
featNames = ['no surfacing', 'flippers', 'fish']
print decisionTree.classify(myTree, featNames, [1, 1])
print '... 测试和读取决策树存储'
decisionTree.storeTree(myTree, 'classfierStorage.txt')
print decisionTree.grabTree('classfierStorage.txt')
print '... 测试中文情况的决策树读取和存储'
cnTree = plotDecisionTree.retrieveTree(2)
print '存储前的决策树: \n', cnTree
# 对于中文来说,正常的print只能打印出utf-8编码格式
# 但是可以递归的打印字典 就可以输出中文
decisionTree.storeTree(cnTree, 'cnTree.txt')
print decisionTree.grabTree('cnTree.txt')
def randomForest(dataSet,
labels,
num_trees=2,
max_depth=None,
by='random',
max_features='log2'):
decisionTrees = []
for i in range(num_trees):
subDataSet = subSample(dataSet)
tree = createTree(subDataSet,
labels[:],
max_depth=max_depth,
by=by,
max_features=max_features)
decisionTrees.append(tree)
return decisionTrees
from decisionTree import createDataSet
from decisionTree import createTree
import matplotlib.pyplot as plt
dataSet, labels = createDataSet()
#决策树
decisionTree = createTree(dataSet, labels)
#决策节点样式为锯齿框
decisionNode = dict(boxstyle="sawtooth", fc="0.8")
#叶结点样式
leafNode = dict(boxstyle="round4", fc="0.8")
#箭头样式
arrow_args = dict(arrowstyle="<-")
def plotNode(nodeTxt, centerPt, parentPt, nodeType):
createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords="axes fraction",xytext=centerPt,\
textcoords="axes fraction", va="center", ha="center", bbox=nodeType, arrowprops=arrow_args)
def createPlot():
fig = plt.figure(1, facecolor="white")
fig.clf()
createPlot.ax1 = plt.subplot(111, frameon=False)
plotNode("decisionNode", (0.5, 0.1), (0.1, 0.5), decisionNode)
plotNode('leafNode', (0.8, 0.1), (0.3, 0.8), leafNode)
plt.show()
def getNumLeafs(myTree):
numLeafs = 0
for key in myTree:
# coding:utf-8
# 对隐形眼镜的分类
import decisionTree
import plotDecisionTree
import trees
fr = open('lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
fr.close()
print type(lenses)
for i in range(len(lenses)):
print lenses[i]
print '... end lenses'
lensesFeatName = ['age', 'prescript', 'astigmatic', 'tearRate', 'lenses type']
lensesTree = decisionTree.createTree(lenses, lensesFeatName)
print lensesTree
plotDecisionTree.createPlot(lensesTree)
#!/usr/bin/env python import decisionTree as dt def createDataset() : dataset = [[1, 1], [1, 1], [1, 0], [0, 1], [0, 1]] labels = ['yes', 'yes', 'no', 'no', 'no'] return (dataset, labels) if __name__ == '__main__' : (dataset, labels) = createDataset() labelName = ["no surface", "flipper"] tree = dt.createTree(dataset, labels, labelName) print(tree) labelName = ["no surface", "flipper"] label = dt.classify(tree, labelName, [0,0]) print(label)
