python在医学领域应用_吴裕雄 python 人工智能——基于神经网络算法在智能医疗诊断中的应用探索代码简要展示...

#决策树

importosimportsysimporttimeimportoperatorimportcx_Oracleimportnumpy as npimportpandas as pdfrom math importlogimporttensorflow as tf

conn=cx_Oracle.connect('doctor/admin@localhost:1521/tszr')

cursor=conn.cursor()#获取数据集

defgetdata(surgery,surgeryChest):

sql= "select feature1,feature2,feature3,feature4,feature5,trainLable from menzhenZ where surgery='%s' and surgeryChest='%s'" %(surgery,surgeryChest)

cursor.execute(sql)

rows=cursor.fetchall()

dataset=[]for row inrows:

temp=[]

temp.append(row[0])

temp.append(row[1])

temp.append(row[2])

temp.append(row[3])

temp.append(row[4])

temp.append(row[5])

dataset.append(temp)

lables=[]

lables.append("呼吸急促")

lables.append("持续性脉搏加快")

lables.append("畏寒")

lables.append("血压降低")

lables.append("咳血")returndataset,lablesdefgettestdata(surgery,surgeryChest):

sql= "select feature1,feature2,feature3,feature4,feature5,trainLable from testZ where surgery='%s' and surgeryChest='%s'" %(surgery,surgeryChest)

cursor.execute(sql)

rows=cursor.fetchall()

testdataset=[]

testlables=[]for row inrows:

temp=[]

temp.append(row[0])

temp.append(row[1])

temp.append(row[2])

temp.append(row[3])

temp.append(row[4])

testdataset.append(temp)

testlables.append(row[5])returntestdataset,testlables#计算熵值

defcalcShannonEnt(dataSet):

numEntries=len(dataSet)

labelCounts={}for featVec indataSet:

currentLabel= featVec[-1]if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] =0

labelCounts[currentLabel]+= 1shannonEnt= 0.0

for key inlabelCounts:

prob= float(labelCounts[key])/numEntries

shannonEnt-= prob * log(prob,2)returnshannonEnt#按照给定特征划分数据集

defsplitDataSet(dataSet, axis, value):

retDataSet=[]for featVec indataSet:if featVec[axis] ==value:

reducedFeatVec=featVec[:axis]

reducedFeatVec.extend(featVec[axis+1:])

retDataSet.append(reducedFeatVec)returnretDataSet#选择最好的属性

defchooseBestFeatureToSplit(dataSet):

numFeatures= len(dataSet[0]) - 1baseEntropy=calcShannonEnt(dataSet)

bestInfoGain= 0.0bestFeature= -1

for i inrange(numFeatures):

featList= [example[i] for example indataSet]

uniqueVals=set(featList)

newEntropy= 0.0

for value inuniqueVals:

subDataSet=splitDataSet(dataSet, i, value)

prob= len(subDataSet)/float(len(dataSet))

newEntropy+= prob *calcShannonEnt(subDataSet)

infoGain= baseEntropy -newEntropyif (infoGain >bestInfoGain):

bestInfoGain=infoGain

bestFeature=ireturnbestFeature#统计机制

defmajorityCnt(classList):

classCount={}for vote inclassList:if vote not in classCount.keys(): classCount[vote] =0

classCount[vote]+= 1sortedClassCount= sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)returnsortedClassCount[0][0]#创建决策树

defcreateTree(dataSet,labels):

classList= [example[-1] for example indataSet]if classList.count(classList[0]) ==len(classList):returnclassList[0]if len(dataSet[0]) == 1:returnmajorityCnt(classList)

bestFeat=chooseBestFeatureToSplit(dataSet)

bestFeatLabel=labels[bestFeat]

myTree={bestFeatLabel:{}}

temp=[]for i inlabels:if i !=labels[bestFeat]:

temp.append(i)

labels=temp

featValues= [example[bestFeat] for example indataSet]

uniqueVals=set(featValues)for value inuniqueVals:

subLabels=labels[:]

myTree[bestFeatLabel][value]=createTree(splitDataSet(dataSet, bestFeat, value),subLabels)returnmyTree#使用决策树模型分类

defclassify(inputTree,featLabels,testVec):for i ininputTree.keys():

firstStr=ibreaksecondDict=inputTree[firstStr]

featIndex=featLabels.index(firstStr)

key=testVec[featIndex]

valueOfFeat=secondDict[key]ifisinstance(valueOfFeat, dict):

classLabel=classify(valueOfFeat, featLabels, testVec)else: classLabel =valueOfFeatreturnclassLabel#启动和检测模型

defdatingClassTest():

dataSet,labels= getdata("外科","胸外科")

myTree=createTree(dataSet,labels)

testdataset,testlables= gettestdata("外科","胸外科")

errorCount= 0.0start=time.time()for i inrange(np.shape(testdataset)[0]):

classifierResult=classify(myTree,labels,testdataset[i])print("the classifier came back with: %s, the real answer is: %s" %(classifierResult, testlables[i]))if (classifierResult !=testlables[i]):

errorCount+= 1.0end=time.time()print("错误率: %.2f%%" % (errorCount/float(np.shape(testdataset)[0])*100))print("准确率: %.2f%%" % ((1.0-errorCount/float(np.shape(testdataset)[0]))*100))print("训练和预测一共耗时: %.2f 秒" % (end-start))

datingClassTest()