def createTree(atom_csv, undefined_percentage): #输入为处理过的可达集、优先级字典
title, dataSet = csvOperation.readCsv(atom_csv)
#add 0822 for only one class 可能返回字符串，而不是字典
classList = [example[-1] for example in dataSet]
if len(set(classList)) == 1:
return '(' + title[-1] + ' = ' + classList[0] + ')'
else:
myTree = id3.createTree(
dataSet, title[:-1], undefined_percentage
) #0726,修改函数id3.createTree，加入优先级判定依据，即undefined_percentage
return myTree
import id3
import entropy
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 entropy.entropy(myDat)
#print id3.chooseBestFeatureToSplit(myDat)
tree = id3.createTree(myDat,labels)
print tree
import id3
import entropy
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 entropy.entropy(myDat)
#print id3.chooseBestFeatureToSplit(myDat)
tree = id3.createTree(myDat, labels)
print tree
def train(self):
if not (self.dataSet and self.labels):
return dict()
self.tree = id3.createTree(self.dataSet,self.labels)
import id3
import id3plot
import pickle
if __name__ == "__main__" :
# myDat,labels = id3.createDataSet()
# print myDat
# shan = id3.calcShannonEnt(myDat)
# print shan
# myTree = id3.createTree(myDat,labels)
# print myTree
# id3plot.createPlot(myTree)
data, labels = id3.createDataSetFromTXT("dataset.txt")
print "data is ", data
print "label is", labels
#计算给定数据集的香农熵
shan = id3.calcShannonEnt(data)
print shan
#选择最好的数据集划分方式
col = id3.chooseBestFeatureToSplit(data)
print col
Tree = id3.createTree(data, labels)
print Tree
id3plot.createPlot(Tree)
import id3
import id3plot
import pickle
if __name__ == "__main__":
# myDat,labels = id3.createDataSet()
# print myDat
# shan = id3.calcShannonEnt(myDat)
# print shan
# myTree = id3.createTree(myDat,labels)
# print myTree
# id3plot.createPlot(myTree)
data, labels = id3.createDataSetFromTXT("dataset.txt")
print "data is ", data
print "label is", labels
#计算给定数据集的香农熵
shan = id3.calcShannonEnt(data)
print shan
#选择最好的数据集划分方式
col = id3.chooseBestFeatureToSplit(data)
print col
Tree = id3.createTree(data, labels)
print Tree
id3plot.createPlot(Tree)
convert_list = getConvertList(origin_title, left_list)
#print(convert_list)
right_list = getRight(atom_list[:])
#print(right_list)
atom_dataset = dataSetToAtomDataSet(origin_dataSet, convert_list,
right_list, origin_title)
#print(atom_dataset)
newtitle, newdataset = creatAtomCsv(atom_list[:], atom_dataset[:],
origin_dataSet)
creatCsv(newtitle, newdataset)
#decision tree part
title, dataSet = readCsv('atom.csv')
print(title[:-1])
myTree = id3.createTree(dataSet, title[:-1])
treePlotter.createPlot(myTree)
'''
#recive some message like n[1] = T & n[2] = C
title,dataSet = readCsv('atom.csv')
message = 'n[1] = T'
message_vec = toVec(title[:-1],message)
print(message_vec)
'''
'''
#test 18 5 11
title,dataSet = readCsv('atom.csv')
myTree = id3.createTree(dataSet,title[:-1])
message = 'n[1] = T & n[2] = T & x = true'
message_vec = toVec(title[:-1],message)
result = id3.classify2(myTree,title[:-1],message_vec)
