tree.py
from math import log
import operator
def createdataset():
dataset = [[1, 1, 'yes'],
[1, 1, 'yes'],
[1, 0, 'no'],
[0, 1, 'no'],
[0, 1, 'no']]#資料集
labels = ['no su***cing','flippers']
#change to discrete values
return dataset, labels
#計算熵
def calcshannonent(dataset):
numentries = len(dataset)#樣本容量
labelcounts = {}#建立乙個空字典
for featvec in dataset: #遍歷資料集
currentlabel = featvec[-1]#取類標記，根據資料集的資料格式選取
if currentlabel not in labelcounts.keys(): labelcounts[currentlabel] = 0
labelcounts[currentlabel] += 1#如果取的類標記不在字典裡，就新增進去，再將字典內容加一
shannonent = 0.0#定義熵
for key in labelcounts:
prob = float(labelcounts[key])/numentries
shannonent -= prob * log(prob,2) #log base 2#按公式計算熵
return shannonent
#劃分資料集
def splitdataset(dataset, axis, value):
retdataset = #為了不修改原始資料，建立乙個新的列表物件
for featvec in dataset:#遍歷資料集
if featvec[axis] == value:#如果該例項的值等於需要的值
reducedfeatvec = featvec[:axis]#取出在axis前面的值
reducedfeatvec.extend(featvec[axis+1:])#取出在axis後面的值
return retdataset
def choosebestfeaturetosplit(dataset):
numfeatures = len(dataset[0]) - 1 #the last column is used for the labels
baseentropy = calcshannonent(dataset)#計算熵
bestinfogain = 0.0; bestfeature = -1
for i in range(numfeatures): #iterate over all the features
featlist = [example[i] for example in dataset]#create a list of all the examples of this feature
uniquevals = set(featlist) #get a set of unique values
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 #calculate the info gain; ie reduction in entropy
if (infogain > bestinfogain): #compare this to the best gain so far
bestinfogain = infogain #if better than current best, set to best
bestfeature = i
return bestfeature #returns an integer
def majoritycnt(classlist):
classcount={}
for vote in classlist:
if vote not in classcount.keys(): classcount[vote] = 0
classcount[vote] += 1
sortedclasscount = sorted(classcount.iteritems(), 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[:] #copy all of labels, so trees don't mess up existing labels
mytree[bestfeatlabel][value] = createtree(splitdataset(dataset, bestfeat, value),sublabels)
return mytree
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)
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 ...