def test_classify():
mydat, labels = creatDataSet()
import treePlotter
myTree = treePlotter.retrieveTree(0)
print(myTree)
print(classify(myTree, labels, [1, 0]))
print(classify(myTree, labels, [1, 1]))
def test_store_tree():
mydat, labels = creatDataSet()
import treePlotter
myTree = treePlotter.retrieveTree(0)
print(myTree)
storeTree(myTree, 'classifierStorage.txt')
grabTree('classifierStorage.txt')
def test():
dataSet, labels = createDataSet()
# sdataSet = splitDataSet(dataSet, 0, 1)
# ent = calcShannonEnt(dataSet)
# bestFeature = chooseBestFeatureToSplit(dataSet)
# myTree = createTree(dataSet, labels)
myTree = treePlotter.retrieveTree(0)
print(classify(myTree, labels, [1, 1]))
def main7():
'''
生成决策树并存储为.txt
从.txt文件导入决策树
'''
import treePlotter
myDat, labels = createDataSet()
myTree = treePlotter.retrieveTree(0)
print classify(myTree, labels, [1, 0])
storeTree(myTree, 'classifierStorage.txt')
print grabTree('classifierStorage.txt')
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))
classLabel = secondDict[key]
return classLabel
def storeTreee(inputTree, filename):
"""存储树"""
import pickle
with open(filename, 'wb') as f:
pickle.dump(inputTree, f)
def grabTree(filename):
"""读取树"""
import pickle
with open(filename, 'rb') as f:
return pickle.load(f)
if __name__ == '__main__':
# myDat, labels = createDataSet()
# print(labels)
myTree = tp.retrieveTree(0)
print(myTree)
# result = classify(myTree, labels, [1, 1])
# print(result)
# storeTreee(myTree, 'classifierStorage.txt')
tree = grabTree('classifierStorage.txt')
print(tree)
#
fr = open('lensesCN.txt')
lenses = [unicode(inst, 'utf-8').strip().strip().split('\t') for inst in fr.readlines()]
#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)
splittedDat = DT.splitDataSet(myDat, 0,
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(
fig = plt.figure(1, facecolor='white')
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,
def test1():
mydat, labels = createDataSet()
myTree = treePlotter.retrieveTree(0)
print(myTree)
print(classify(myTree, labels, [1, 1]))
import pickle
fr = open(filename)
return pickle.load(fr)
if __name__ == "__main__":
myDat, labels = createDataSet()
# print clacShannonEnt(myDat)
# print splitDataSet(myDat, 0, 1)
# print splitDataSet(myDat, 0, 0)
# print chooseBestFeatureToSplit(myDat)
# myTree = createTree(myDat, labels)
# print myTree
from treePlotter import retrieveTree, createPlot
#
myTree = retrieveTree(0)
# print myTree
# print classify(myTree, labels, [1, 0])
# print classify(myTree, labels, [1, 1])
# storeTree(myTree, 'classifierStorage.txt')
# print grabTree('classifierStorage.txt')
fr = open('lenses.txt')
lenses = [inst.strip().split("\t") for inst in fr.readlines()]
lensesLabels = ['age', 'prescript', 'astigmatic', 'tearRate']
lensesTree = createTree(lenses, lensesLabels)
print lensesTree
createPlot(lensesTree)
import trees
import treePlotter
treePlotter.retrieveTree(1)
myTree = treePlotter.retrieveTree(0)
fr = open('lenses.txt')
lenses=[inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels=['age', 'prescript', 'astigmatix', 'tearRate']
lensesTree = trees.createTree(lenses, lensesLabels)
treePlotter.createPlot(lensesTree)
def testDumpAndLoadDecisionTree():
myTree = treePlotter.retrieveTree(0)
storeTree(myTree, 'classTree.txt')
print(grabTree('classTree.txt'))
firstStr = inputTree.keys()[0]
secondDict = inputTree[firstStr]
featIndex = featLabels.index(firstStr) #将标签字符串转换为索引
for key in secondDict.keys():
if testVec[featIndex] == key:
if type(secondDict[key]).__name__ == 'dict':
classLabel = classify(secondDict[key], featLabels, testVec)
else:
classLabel = secondDict[key]
return classLabel
myDat, labels = createDataSet()
#myTree = createTree(myDat,labels)
print(labels)
print(treePlotter.retrieveTree(1))
print(treePlotter.retrieveTree(0))
myTree = treePlotter.retrieveTree(0)
print(classify(myTree, labels, [1, 0]))
print(classify(myTree, labels, [1, 1]))
#treePlotter.createPlot()
print('-------隐形眼镜数据-----')
fr = open('/Users/wakemeup/Documents/MLiA/ch03/lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ['age', 'prescript', 'astigmatic', 'tearRate']
lensesTree = createTree(lenses, lensesLabels)
print(lensesTree)
import pickle
fw = open(filename, 'wb')
pickle.dump(inputTree, fw)
fw.close()
def grabTree(filename):
import pickle
fr = open(filename, 'rb')
return pickle.load(fr)
if __name__ == "__main__":
myDat, labels = createDataSet()
print(labels)
myTrees = tplt.retrieveTree(0)
print(myTrees)
print(classify(myTrees, labels, [1, 0]))
print(classify(myTrees, labels, [1, 1]))
storeTree(myTrees, "classifierStorage.txt")
print("Saved!")
gt = grabTree("classifierStorage.txt")
print("Loaded!")
print(gt)
fr = open("lenses.txt")
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ["age", "prescript", "astigmatic", "tearRate"]
lenseTree = createTree(lenses, lensesLabels)
print(lenseTree)
tplt.createPlot(lenseTree)
# -*- coding: utf-8 -*-
# 求使数据集熵最大的列
import trees
ds, ls = trees.createDataSet()
trees.chooseBestFeatureToSplit(ds)
# 创建决策树
import trees
ds, ls = trees.createDataSet()
trees.createTree(ds, ls)
# 绘制树
import treePlotter
mt = treePlotter.retrieveTree(0)
treePlotter.createPlot(mt)
# 利用决策树判断分类
import trees
import treePlotter
it = treePlotter.retrieveTree(0)
ds, ls = trees.createDataSet()
trees.classify(it, ls, [0, 0])
# 序列化与反序列化决策树
import trees
import treePlotter
it = treePlotter.retrieveTree(0)
trees.storeTree(it, 'classifierStorage.txt')
ot = trees.grabTree('classifierStorage.txt')
def main():
dataSet, labels = createDataSet()
myTree = treePlotter.retrieveTree()
print classify(myTree, labels, [1, 0])
print classify(myTree, labels, [1, 1])
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel:{}}
del(labels[bestFeat]) #delete the best feature , so it can find the next best feature
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals:
subLabels = labels[:] #copy all of labels, so trees don't mess up existing labels
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
return myTree
#决策树的存储
def storeTree( inputTree, filename ):
import json
with open( filename, 'w') as f:
f.write(json.dumps(inputTree))
def grabTree( filename ):
import json
f = open( filename)
return json.loads(f.read())
# dataSet, labels = createDataSet()
# tree = createTree(dataSet, labels)
# storeTree(tree,'classifierStorage.txt')
import treePlotter
myTree = treePlotter.retrieveTree(0)
treePlotter.createPlot(myTree)
# plt.xlabel('count')
# plt.ylabel('result')
# plt.title('Hahaha Goooood!!!')
# fig.savefig('plot.svg')
# import matplotlib
# matplotlib.use('Agg')
# import matplotlib.pyplot as plt
# fig = plt.figure(1, facecolor='white')
# fig.clf()
# ax = plt.subplot(111, frameon=True)
# # ax.scatter([.2, .5], [.1, .5])
# plt.figure(1, figsize=(3,3))
# ax = plt.subplot(111)
# ax.annotate("Test", xy=(0.2, 0.2), xycoords='data', xytext=(0.8, 0.8),
# textcoords='data', size=20, va="center", ha="center",
# bbox=dict(boxstyle="round4", fc="w"),
# arrowprops=dict(arrowstyle="-|>",
# connectionstyle="arc3,rad=-0.2", fc="w"), )
# ax.annotate("This is my text", xy=(0.2, 0.1), xycoords='data',
# xytext=(0.4, 0.3), textcoords='data', ha='center', va='center',
# arrowprops=dict(arrowstyle="->", connectionstyle="arc3"), )
# fig.savefig('plot.svg')
# import textPlotter
# textPlotter.createPlot()
import treePlotter
treePlotter.createPlot(treePlotter.retrieveTree(0))
#输出手动创建的数据集，计算香农熵
myDat,labels=trees.createDataSet()
print "myDat 数据集是：",myDat
print "\nlabels 标签是:",labels
rawCalc =trees.calcShannonEnt(myDat)
print "\ncalcShannonEnt(myDat) 数据集的原始熵是：",rawCalc
print "\ntrees.splitDataSet( myDat,1,1)将数据集的按 特征[1]=1(即 flippers==1) 提取出来的矩阵是:",trees.splitDataSet(myDat,1,1)
#
bestLabel = trees.chooseBestFeatureToSplit(myDat)
print "\nchooseBestFeatureToSplit(myDat) 数据集的bestLabel最好特征的[下标]是：",bestLabel,"\tlabels[bestLabel]最好特征是：",labels[bestLabel]
#
myTree = trees.createTree(myDat,labels)
print "\ntrees.createTree(myDat,labels) 根据数据集创建的树是:", myTree
#读取预先存储的树[0] 并绘制图形
print "\n读取预先存储的树[0] 并绘制出第一个图形:"
myTree0 = treePlotter.retrieveTree(0)
treePlotter.createPlot(myTree0)
#读取预先存储的树[1] 并绘制图形
print "\n读取预先存储的树[1] 并绘制出第二个图形:"
myTree1 = treePlotter.retrieveTree(1)
treePlotter.createPlot(myTree1)
#change one date in "no surfacing"
#and print
'''
myTree['no surfacing'][3] = 'maybe'
print('after change is:')
print myTree
treePlotter.createPlot(myTree)rag
'''
#calculate shannonEnt
print '-------------- calculate shannonEnt --------------------'
shannonEnt = calcShannonEnt(myDat)
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)
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
if __name__ == '__main__':
print treePlotter.retrieveTree(1)
myTree = treePlotter.retrieveTree(1)
print treePlotter.getNumLeafs(myTree)
print treePlotter.getTreeDepth(myTree)
# -*- coding:utf-8 -*-
import trees
import treePlotter
def createDataSet():
dataSet = [
[1, 1, 'yes'],
[1, 1, 'yes'],
[1, 0, 'no'],
[0, 1, 'no'],
[0, 1, 'no']
]
labels = ['no surfacing', 'flippers']
return dataSet, labels
myDat, labels = createDataSet()
print myDat
# print trees.calcShannonEnt(myDat) #熵越高，则混合的数据越多，如果增加maybe分类myDat[0][-1]='maybe'，则信息熵更高了
# print trees.splitDataSet(myDat, 0, 1) # 循环dataSet对象，对于每一个循环值，索引为0的值看是否和1相等，如果相等，返回后边的值
# print trees.chooseBestFeatureToSplit(myDat)
# print trees.createTree(myDat, labels)
myTree = treePlotter.retrieveTree(0) # 这是生成的决策树
print trees.classify(myTree, labels, [1, 1])
