R中的Neuralnet包：非规范化数据

Question

我试图预测股票市场的价格，并使用R＆＃34; Neuralnet＆＃34;包。如何对数据进行非规范化并最终找到实际价格。这是算法：

 library("quantmod")
 library("neuralnet")

 startDate <- as.Date('2009-01-01')
 endDate   <- as.Date('2014-01-01')
 getSymbols("^AAPL",src="yahoo",from=startDate,to=endDate)

 # DataSet
 RSI3 <- RSI(Op(AAPL),n=3)
 EMA5 <- EMA(Op(AAPL),n=5)
 EMAcross <- Op(AAPL)-EMA5
 MACD <- MACD(Op(AAPL),fast = 12, slow = 26, signal = 9)
 MACDsignal <- MACD[,2]
 BB  <- BBands(Op(AAPL),n=20,sd=2)
 BBp <- BB[,4]
 Price   <- Cl(AAPL)-Op(AAPL)
 DataSet <- data.frame(RSI3,EMAcross,MACDsignal,BBp,Price)
 DataSet <- DataSet[-c(1:33),]
 colnames(DataSet) <- c("RSI3","EMAcross","MACDsignal","BollingerB","Price")

 # Normalize function
 Normalized     <- function(x) {(x-min(x))/(max(x)-min(x))}
 NormalizedData <- as.data.frame(lapply(DataSet,Normalized))
 # Training and test sets
 TrainingSet <- NormalizedData[1:816,]
 TestSet     <- NormalizedData[817:1225 ,]
 # ANN
 nn1 <- neuralnet(Price~RSI3+EMAcross+MACDsignal+BollingerB,data=TrainingSet, hidden=3, learningrate=.001,algorithm="backprop")

 predictedPrice=compute(nn1,TestSet[,1:4])