華為雲隨筆(END)-深度學習糖尿病預測(2)
阿新 • • 發佈:2018-12-13
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Sat Sep 15 10:54:53 2018
@author: myhaspl
@email:[email protected]
糖尿病預測(多層)
csv格式:懷孕次數、葡萄糖、血壓、面板厚度,胰島素,bmi,糖尿病血統函式,年齡,結果
"""
import tensorflow as tf
import os
trainCount=10000
inputNodeCount=8
validateCount=50
sampleCount=200
testCount=10
outputNodeCount= 1
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):
#生成檔名佇列
fileNameQueue=tf.train.string_input_producer([fileName])
#生成記錄鍵值對
reader=tf.TextLineReader(skip_header_lines=skipLines)
key,value=reader.read(fileNameQueue)
return value
def getTestData(fileName,skipLines=1,n=10):
#生成檔名佇列
testFileNameQueue=tf.train.string_input_producer([fileName])
#生成記錄鍵值對
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("s3://myhaspl/tf_learn/diabetes.csv",1)
inputDs=getNextBatch(sampleCount,samples)
with tf.name_scope("validateSamples"):
validateInputs=getNextBatch(validateCount,samples)
with tf.name_scope("testSamples"):
testInputs=getTestData("s3://myhaspl/tf_learn/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)
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))
print "%d次後=>正確率%g"%(nowStep,validate_acc)
if nowStep>trainCount:
break
testInputX,testInputY=sess.run(testInputs)
print "測試樣本正確率%g"%sess.run(accuracy(testInputX,testInputY,testCount))
print testInputX,testInputY
print sess.run(evaluate(testInputX))
coord.request_stop()
coord.join(threads)
500次後=>正確率0.67
1000次後=>正確率0.75
1500次後=>正確率0.81
2000次後=>正確率0.75
2500次後=>正確率0.775
3000次後=>正確率0.765
3500次後=>正確率0.84
4000次後=>正確率0.85
4500次後=>正確率0.77
5000次後=>正確率0.78
5500次後=>正確率0.775
6000次後=>正確率0.835
6500次後=>正確率0.84
7000次後=>正確率0.785
7500次後=>正確率0.805
8000次後=>正確率0.765
8500次後=>正確率0.83
9000次後=>正確率0.835
9500次後=>正確率0.78
10000次後=>正確率0.775
測試樣本正確率0.7
[[1.00e+01 1.01e+02 7.60e+01 4.80e+01 1.80e+02 3.29e+01 1.71e-01 6.30e+01]
[3.00e+00 7.80e+01 5.00e+01 3.20e+01 8.80e+01 3.10e+01 2.48e-01 2.60e+01]
[2.00e+00 1.22e+02 7.00e+01 2.70e+01 0.00e+00 3.68e+01 3.40e-01 2.70e+01]
[2.00e+00 8.80e+01 5.80e+01 2.60e+01 1.60e+01 2.84e+01 7.66e-01 2.20e+01]
[1.00e+01 1.01e+02 7.60e+01 4.80e+01 1.80e+02 3.29e+01 1.71e-01 6.30e+01]
[2.00e+00 1.22e+02 7.00e+01 2.70e+01 0.00e+00 3.68e+01 3.40e-01 2.70e+01]
[1.00e+00 8.90e+01 6.60e+01 2.30e+01 9.40e+01 2.81e+01 1.67e-01 2.10e+01]
[6.00e+00 1.48e+02 7.20e+01 3.50e+01 0.00e+00 3.36e+01 6.27e-01 5.00e+01]
[1.00e+00 9.30e+01 7.00e+01 3.10e+01 0.00e+00 3.04e+01 3.15e-01 2.30e+01]
[2.00e+00 1.22e+02 7.00e+01 2.70e+01 0.00e+00 3.68e+01 3.40e-01 2.70e+01]] [[0.]
[1.]
[0.]
[0.]
[0.]
[0.]
[0.]
[1.]
[0.]
[0.]]
[[1.]
[0.]
[0.]
[0.]
[1.]
[0.]
[0.]
[1.]
[0.]
[0.]]
感覺華為雲中提供的深度學習服務,就是給你提供一個強大的伺服器,然後,你自己編寫程式碼。可能還提供了一些更多的功能