I have the following data:
df=data.frame(store=c('A','A','A','A','B','B','B','B'),
Date=c('2017-01-01','2017-01-02','2017-01-03','2017-01-04','2017-01-01','2017-01-02','2017-01-03','2017-01-04'),
sales=c('15','37','29','18','16','22','5','6'))
df
store Date sales
1 A 2017-01-01 15
2 A 2017-01-02 37
3 A 2017-01-03 29
4 A 2017-01-04 18
5 B 2017-01-01 16
6 B 2017-01-02 22
7 B 2017-01-03 5
8 B 2017-01-04 6
I would like to convert it into a time series format as below:
Date A B
1 2017-01-01 15 16
2 2017-01-02 37 22
3 2017-01-03 29 5
4 2017-01-04 18 6
I need to run auto.arima(from forecast package) iteratively on time series A & B.Hence i require the data frame to be the ts format.