无法在R中进行每日时间序列分析

Question

The following is my data,

 day       sum
2015-03-05   44           
2015-03-06   46           
2015-03-06   48           
2015-03-07   48           
2015-03-08   58           
2015-03-09   58           
2015-03-10   66           
2015-03-11   68           
2015-03-12   85           
2015-03-13   94           
2015-03-14   98           
2015-03-15  102           
2015-03-16  102           
2015-03-17  104           
2015-03-17  114 

The type of variables used are as follows,

typeof(x)
[1] "list"

typeof(x$day)
[1] "double"

typeof(x$sum)
[1] "integer"

class(x$day)
[1] "Date"

I want to predict, for a particular future date, what would be the sum.

The following are my findings,

When I use ts(x), the values of the dates are changing as follows,

day

16464              

16465              

16466

16467

16468

16469

16470

16471

16472

When I use ets, following is the output,

fit <- ets(x)
Error in ets(ana) : y should be a univariate time series

I am able to plot the dates with the sum and getting the graphs perfectly. But, I am not able to make any analysis after this point. I want to predict, for a particular future date, what would be the sum. I tried regression analysis also, but it doesn't work with this variable. Can anybody please help me how to proceed further?

Thanks

Answer 1

If you "correct" the duplicated days, you will be able to do this:

library(xts)
dates=as.Date(x$day,"%Y-%m-%d")
xs=xts(x$sum,dates)
plot(xs)
library("forecast")
class(xs)
fit <- ets(xs)
plot(forecast(fit))