def Pruning_the_Tree(): print '>>Pruning the Tree' reload(treepredict) tree=treepredict.buildtree(treepredict.my_data) print '------------------' treepredict.prune(tree,0.1) treepredict.printtree(tree) treepredict.prune(tree,1.0) treepredict.printtree(tree)
["d", "France", "yes", "23", "Basic"],
]
train_flowers = data.read_filedata("..//data//train_data.txt", "ALL", ",", [0, 1, 2, 3])
test_flowers = data.read_filedata("..//data//test_data.txt", "ALL", ",", [0, 1, 2, 3])
tree = DecisionTree(train_flowers)
treepredict.buildtree(tree)
tree.printTree()
right = 0
wrong = 0
for flower in test_flowers:
result = treepredict.predic(tree, flower)
if flower[-1] in result:
if right == 49:
pass
right += 1
else:
wrong += 1
print "正确预测：" + str(right) + "个"
print "错误预测：" + str(wrong) + "个"
print "-------------------------------------------------------------------"
treepredict.prune(tree, 0.95)
tree.printTree()
gender = doc2.getElementsByTagName('gender')[0].firstChild.data
age = doc2.getElementsByTagName('age')[0].firstChild.data
loc = doc2.getElementsByTagName('location')[0].firstChild.data[0:2]
# 将州转换成地区
for r, s in stateregions.items():
if loc in s: region = r
if region != None:
result.append((gender, int(age), region, rating))
except:
pass
return result
l1 = getrandomratings(500)
print len(l1)
pdata = getpeopledata(l1)
print pdata[0]
import treepredict
hottree = treepredict.buildtree(pdata, scoref=treepredict.variance)
treepredict.prune(hottree, 0.5)
treepredict.drawtree(hottree, 'hottree.jpg')
south = treepredict.mdclassify((None, None, 'south'), hottree)
midat = treepredict.mdclassify((None, None, 'Mid Atlantic'), hottree)
print south[10] / sum(south.values())
print midat[10] / sum(midat.values())
# #测试divideSet # print treepredict.divideSet(data.my_data, 2, "yes") # #测试经过训练后，基尼不纯度和熵的变化 # print treepredict.giniImpurity(data.my_data) # print treepredict.entropy(data.my_data) # set1,set2=treepredict.divideSet(data.my_data, 2, "yes") # print treepredict.giniImpurity(set1) # print treepredict.entropy(set1) #测试buildTree tree=treepredict.buildTree(data.my_data) draw=DrawTree.DrawTree(tree,'treeview.jpg') draw.drawTree() # #使用classify函数进行预测 # tree=treepredict.buildTree(data.my_data) # print treepredict.classify(['(direct)','USA','yes',5], tree) #尝试剪枝函数，并绘图 tree=treepredict.buildTree(data.my_data) treepredict.prune(tree, 1.0) draw=DrawTree.DrawTree(tree,'treeview2.jpg') draw.drawTree() # #使用mdclassify函数进行预测 tree=treepredict.buildTree(data.my_data) print treepredict.classify(['(direct)','USA','yes',5], tree) print treepredict.mdclassify(['google',None,'yes',None], tree) print treepredict.mdclassify(['google','France',None,None], tree)
#print doc.toxml()
gender = doc.getElementsByTagName('gender')[0].firstChild.data
age = doc.getElementsByTagName('age')[0].firstChild.data
loc = doc.getElementsByTagName('location')[0].firstChild.data
region = None
for r, s in stateregions.iteritems():
if loc[0:2] in s: region = r
if region:
result.append((gender, int(age), region, rating))
except:
pass
return result
if __name__ == '__main__':
d = getrandomratings(50)
# hu, all results are always of the same gender?
pdata = getpeopledata(d)
print pdata
import drawtree
import treepredict
tree = treepredict.buildtree(pdata, treepredict.variance)
treepredict.prune(tree, 0.5)
drawtree.drawtree(tree, 'hottree.png')
print 'Wrote hottree.png'
url = "http://services.hotornot.com/rest/?app_key=%s" % api_key
url += "&method=MeetMe.getProfile&emid=%s&get_keywords=true" % emid
# 得到所有关于此人的详细信息
try:
rating = int(float(rating) + 0.5)
doc2 = xml.dom.minidom.parseString(
urllib.request.urlopen(url).read())
gender = doc2.getElementsByTagName('gender')[0].firstChild.data
age = doc2.getElementsByTagName('age')[0].firstChild.data
loc = doc2.getElementsByTagName('location')[0].firstChild.data[0:2]
# 将州转换为地区
for r, s in stateregions.items():
if loc in s: region = r
if region != None:
result.append((gender, int(age), region, rating))
except:
pass
return result
if __name__ == '__main__': #只有在执行当前模块时才会运行此函数
l1 = getrandomratings(500)
print(len(l1))
pdata = getpeopledata(l1)
print(pdata)
tree = treepredict.buildtree(pdata, scoref=treepredict.variance) #创建决策树
treepredict.prune(tree, 0.5) #剪支
treepredict.drawtree(tree, 'hot.jpg')