def lenseTest():
fr = open("lenses.txt")
lenses = [inst.strip().split("\t") for inst in fr.readlines() ]
lenseLabels = ['age', 'prescript', 'astigmatic', 'tearRate']
lensesTree = createTree(lenses, lenseLabels[:])
print lensesTree
import treeplotter
treeplotter.createPlot(lensesTree)
nazwaKlasy = klasyfikuj(drugi[key], etykiety, test)
else:
nazwaKlasy = drugi[key]
return nazwaKlasy
def zapiszDrzewo(wejscie, nazwaPliku):
import pickle
fw = open(nazwaPliku, 'w')
pickle.dump(wejscie, fw) #zapis do pliku
fw.close()
def otworzDrzewo(nazwaPliku):
import pickle
fr = open(nazwaPliku)
return pickle.load(fr) #odczyt z pliku
myDat = []
myDat, etykiety = utworzZbiorDanych()
print(myDat)
print(liczenieEntropii(myDat))
print(wyborNajlepszejCechy(myDat))
myTree = stworzDrzewo(myDat, etykiety)
print(myTree)
import treeplotter
print(treeplotter.getNumLeafs(myTree))
print(treeplotter.getTreeDepth(myTree))
treeplotter.createPlot(myTree)
Returns:
lensesTree: 预测隐形眼镜决策树
'''
def contactLensesType():
#fr = open('lenses.txt')
with open('lenses.txt') as fr:
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ['age', 'prescript', 'astigmatic', 'teatRate']
lensesTree = createTree(lenses, lensesLabels)
return lensesTree
if __name__ == '__main__':
myDat, labels = createDataSet()
print(calcShannonEnt(myDat))
print(splitDataSet(myDat, 0, 1))
print(chooseBestFeatureToSplit(myDat))
print(createTree(myDat, labels))
import treeplotter
myTree = treeplotter.retrieveTree(0)
print(classify(myTree, labels, [1, 1]))
storeTree(myTree, 'classifierStorge.txt')
print(grabTree('classifierStorge.txt'))
print(contactLensesType())
treeplotter.createPlot(contactLensesType())
def classify(inputTree, featLabels, testVec):
firstStr = inputTree.keys()[0]
secondDict = inputTree[firstStr]
featIndex = featLabels.index(firstStr)
key = testVec[featIndex]
valueOfFeat = secondDict[key]
if isinstance(valueOfFeat, dict):
classLabel = classify(valueOfFeat, featLabels, testVec)
else:
classLabel = valueOfFeat
return classLabel
def storeTree(inputTree, filename):
import pickle
fw = open(filename, 'w')
pickle.dump(inputTree, fw)
fw.close()
def grabTree(filename):
import pickle
fr = open(filename)
return pickle.load(fr)
ds, l = createDataSet()
tree = createTree(ds, l)
treeplotter.createPlot(tree)
def grabTree(filename):
import pickle
fr = open(filename)
return pickle.load(fr)
# # yun xing
# mydata,mylabels=creatDataSet()
# print mydata,mylabels
# mydata[0][-1]='maybe'
# result=calcShannonEnt(mydata)
# result=spiltDataSet(mydata,0,1)
# mytree=createTree(mydata,mylabels)
# print mytree
# mytree=treeplotter.retrieveTree(0)
# result=classify(mytree,mylabels,[1,0])
# print result
# def add(a,b):
# a+=1
# b+=2
# return a,b
# print add(1,2)
# 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)
treeplotter.createPlot(lensesTree)
myTree = {}
myTree = {bestFeatLabel: {}}
del (labels[bestFeat])
featValues = [example[bestFeat] for example in dataset]
uniqueVals = set(featValues)
for value in uniqueVals:
subLabels = labels[:]
myTree[bestFeatLabel][value] = createTree(split_dataset.splitDataSet(dataset, bestFeat, value), subLabels)
return myTree
if __name__ == "__main__":
dataset = [
["omer", "demircan", "kocaeli"],
["eray", "arslan", "sakarya"],
["ss", "dd", "izmir"],
["yunus", "kocyigit", "kocaeli"],
["omer", "demircan", "kocaeli"],
["eray", "arslan", "sakarya"],
["ss", "dd", "izmir"],
["yunus", "kocyigit", "kocaeli"],
["omer", "demircan", "kocaeli"],
["eray", "arslan", "sakarya"],
["ss", "dd", "izmir"],
["yunus", "kocyigit", "kocaeli"],
]
tree = createTree(dataset, ["ad", "soyad", "sehir"])
myTree = treeplotter.retrieveTree(0)
treeplotter.createPlot(myTree)