def calcshannonent(dataset):
numentries = len(dataset)
labelcounts = {}
for featvec in dataset:
currentlabel = featvec[-1]
if currentlabel not in labelcounts.keys():
labelcounts[currentlabel] = 0
labelcounts[currentlabel] += 1
shannonent = 0.0
for key in labelcounts:
prob = float(labelcounts[key])/numentries
shannonent -= prob * log(prob,2)
return shannonent
def splitdataset(dataset, axis, value):
# 抽取出第axis+1位屬性為value的所有元素，並去除value屬性
retdataset =
for featvec in dataset:
if featvec[axis] == value:
reducefeatvec = featvec[:axis]
reducefeatvec.extend(featvec[axis+1:])
return retdataset
def choosebestfeaturetosplit(dataset):
numfeatures = len(dataset[0]) - 1
baseentropy = calcshannonent(dataset)
bestinfogain = 0.0
bestfeature = -1
for i in range(numfeatures):
featlist = [example[i] for example in dataset]
# 將dataset中的資料按行依次放入example中，然後取得example中的example[i]元素，放入列表featlist中
uniquevals = set(featlist)
newentropy = 0.0
for value in uniquevals:
subdataset = splitdataset(dataset, i, value)
prob = len(subdataset)/float(len(dataset))
newentropy += prob * calcshannonent(subdataset)
infogain = baseentropy - newentropy
if (infogain > bestinfogain):
bestinfogain = infogain
bestfeature = i
return bestfeature
def majoritycnt(classlist):
classcount = {}
for vote in classlist:
if vote not in classcount.keys():
classcount[vote] = 0
classcount[vote] += 1
sortedclasscount = sorted(classcount.items(),key=operator.itemgetter(1),reverse=true)
return sortedclasscount[0][0]
def createtree(dataset,labels):
classlist = [example[-1] for example in dataset]
if classlist.count(classlist[0]) == len(classlist):
return classlist[0] # stop splitting when all of the classes are equal
if len(dataset[0]) == 1: # stop splitting when there are no more features in dataset
return majoritycnt(classlist)
bestfeat = choosebestfeaturetosplit(dataset)
bestfeatlabel = labels[bestfeat]
mytree = }
del(labels[bestfeat])
featvalues = [example[bestfeat] for example in dataset]
uniquevals = set(featvalues)
for value in uniquevals:
sublabels = labels[:]
mytree[bestfeatlabel][value] = createtree(splitdataset(dataset, bestfeat, value),sublabels)
return mytree
def classify(inputtree,featlabels,testvec):
firststr = list(inputtree.keys())[0]
seconddict = inputtree[firststr]
featindex = featlabels.index(firststr)
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
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)
機器學習實戰 決策樹
決策樹 2 python語言在函式中傳遞的是列表的引用，在函式內部對列表物件的修改，將會影響該列表物件的整個生存週期。為了消除這個不良影響，我們需要在函式的開始宣告乙個新列表物件。在本節中，指的是在劃分資料集函式中，傳遞的引數dataset列表的引用，為了不影響dataset我們重新宣告了乙個ret...
機器學習實戰決策樹
這幾天一直在學習機器學習實戰python 實現，在程式清單的3 6 獲取及誒單數程式，書上的程式是這樣的 def getnumleafs mytree numleafs 0.0 firststr list dict.keys mytree 0 seconddict mytree firststr p...
機器學習實戰 決策樹
class sklearn.tree.decisiontreeclassifier criterion gini splitter best max depth none,min samples split 2,min samples leaf 1,min weight fraction leaf ...