time series - R-Weekly Forecast -


when use ts <- ts(df, frequency=52, start=c(2007,1)) , print it, got results shown below, instead of 2007.01, 2007.02, 2007.52 ...., got 2007.000, 2007.019, ....which gets 1/52=0.019 mathematically correct not easy interpret, there way label date data frame or @ least 2007 wk1, 2007 wk2 ...

time series:

start = c(2007, 1)

end = c(2014, 11)

frequency = 52

week, amount

2007.000, 645575.4

2007.019, 2185193.2

2007.038, 1016711.8

2007.058, 1894056.4

2007.077, 2317517.6

2007.096, 2522955.8

2007.115, 2266107.3

fit <- auto.arima(dmsales[[2]])
fcast<-forecast(fit,h=input$ahead)
dfcast<-data.frame(fcast)
b<-data.frame(seq(as.date(dmsales[[3]]+7), = "week", length.out = input$ahead))
ffcast<-as.data.frame(cbind(b,dfcast$point.forecast,dfcast$lo.95,dfcast$hi.95))
names(ffcast)<-c("week","forecast","lo-95","hi-95")


Comments

Popular posts from this blog

aws api gateway - SerializationException in posting new Records via Dynamodb Proxy Service in API -

asp.net - Problems sending emails from forum -