阿里云AI-深度学习糖尿病预测

import tensorflow as tf

trainCount=10000
inputNodeCount=8
validateCount=50
sampleCount=200
testCount=10
outputNodeCount=1
ossPath="oss://myhaspl-ai.oss-cn-beijing-internal.aliyuncs.com/"
localPath="./"
dataPath=ossPath

g=tf.Graph()
with g.as_default():

def getWeights(shape,wname):
weights=tf.Variable(tf.truncated_normal(shape,stddev=0.1),name=wname)
return weights

def getBias(shape,bname):
biases=tf.Variable(tf.constant(0.1,shape=shape),name=bname)
return biases

def inferenceInput(x):
layer1=tf.nn.relu(tf.add(tf.matmul(x,w1),b1))
result=tf.add(tf.matmul(layer1,w2),b2)
return result

def inference(x):
yp=inferenceInput(x)
return tf.sigmoid(yp)

def loss():
yp=inferenceInput(x)
return tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y,logits=yp))

def train(learningRate,trainLoss,trainStep):
trainOp=tf.train.AdamOptimizer(learningRate).minimize(trainLoss,global_step=trainStep)
return trainOp

def evaluate(x):
return tf.cast(inference(x)>0.5,tf.float32)

def accuracy(x,y,count):
yp=evaluate(x)
return tf.reduce_mean(tf.cast(tf.equal(yp,y),tf.float32))

def inputFromFile(fileName,skipLines=1):
#生成文件名队列
fileNameQueue=tf.train.string_input_producer([fileName])
#生成记录键值对
reader=tf.TextLineReader(skip_header_lines=skipLines)
key,value=reader.read(fileNameQueue)
return value

def getTestData(fileName,skipLines=1,n=10):
#生成文件名队列
testFileNameQueue=tf.train.string_input_producer([fileName])
#生成记录键值对
testReader=tf.TextLineReader(skip_header_lines=skipLines)
testKey,testValue=testReader.read(testFileNameQueue)
testRecordDefaults=[[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.]]
testDecoded=tf.decode_csv(testValue,record_defaults=testRecordDefaults)
pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age,outcome=tf.train.shuffle_batch(testDecoded,batch_size=n,capacity=1000,min_after_dequeue=1)
testFeatures=tf.transpose(tf.stack([pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age]))
testY=tf.transpose([outcome])
return (testFeatures,testY)

def getNextBatch(n,values):
recordDefaults=[[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.]]
decoded=tf.decode_csv(values,record_defaults=recordDefaults)
pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age,outcome=tf.train.shuffle_batch(decoded,batch_size=n,capacity=1000,min_after_dequeue=1)
features=tf.transpose(tf.stack([pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age]))
y=tf.transpose([outcome])
return (features,y)

with tf.name_scope("inputSample"):
samples=inputFromFile(dataPath+"diabetes.csv",1)
inputDs=getNextBatch(sampleCount,samples)
with tf.name_scope("validateSamples"):
validateInputs=getNextBatch(validateCount,samples)

with tf.name_scope("testSamples"):
testInputs=getTestData(dataPath+"diabetes_test.csv")

with tf.name_scope("inputDatas"):
x=tf.placeholder(dtype=tf.float32,shape=[None,inputNodeCount],name="input_x")
y=tf.placeholder(dtype=tf.float32,shape=[None,outputNodeCount],name="input_y")

with tf.name_scope("Variable"):
w1=getWeights([inputNodeCount,12],"w1")
b1=getBias((),"b1")
w2=getWeights([12,outputNodeCount],"w2")
b2=getBias((),"b2")
trainStep=tf.Variable(0,dtype=tf.int32,name="tcount",trainable=False)

with tf.name_scope("train"):
trainLoss=loss()
trainOp=train(0.005,trainLoss,trainStep)
init=tf.global_variables_initializer()

with tf.Session(graph=g) as sess:
sess.run(init)

coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
logStr=""
while trainStep.eval()<trainCount:

sampleX,sampleY=sess.run(inputDs)
sess.run(trainOp,feed_dict={x:sampleX,y:sampleY})
nowStep=sess.run(trainStep)
if nowStep%500==0:
validate_acc=sess.run(accuracy(sampleX,sampleY,sampleCount))
logStr=logStr+"%d次后=>正确率%g"%(nowStep,validate_acc)+"\n"
print ".",
if nowStep>trainCount:
break