> xreg.train<- data.frame(is.holiday=jholidays.xts["::2015-11-30"],year=year(date.train),month=as.factor(month(date.train)),day=day(date.train),wd=weekdays(date.train))%>%dummy.data.frame%>%select(-month1,-wd“ϊ—j“ϊ)%>%as.matrix

> fit.arimax.cal<- auto.arima(call.train.ts,seasonal=T,trace=Txreg=xreg.train)#arimaxƒ‚ƒfƒ‹‚ΜƒtƒBƒbƒeƒBƒ“ƒO


 ARIMA(2,0,2) with non-zero mean : 11402.32
 ARIMA(0,0,0) with non-zero mean : 11664.95
 ARIMA(1,0,0) with non-zero mean : 11402.53
 ARIMA(0,0,1) with non-zero mean : 11451.06
 ARIMA(0,0,0) with zero mean     : 11665.87
 ARIMA(1,0,2) with non-zero mean : 11401.18
 ARIMA(1,0,1) with non-zero mean : 11403.75
 ARIMA(1,0,3) with non-zero mean : 11401.67
 ARIMA(2,0,3) with non-zero mean : 11404.22
 ARIMA(1,0,2) with zero mean     : 11400.29
 ARIMA(0,0,2) with zero mean     : 11417.95
 ARIMA(2,0,2) with zero mean     : 11401.2
 ARIMA(1,0,1) with zero mean     : 11403.12
 ARIMA(1,0,3) with zero mean     : 11400.76
 ARIMA(0,0,1) with zero mean     : 11450.95
 ARIMA(2,0,3) with zero mean     : 11403.14

 Best model: ARIMA(1,0,2) with zero mean     


> summary(fit.arimax.cal)
Series: call.train.ts 
ARIMA(1,0,2) with zero mean     

Coefficients:
         ar1      ma1      ma2  is.holiday    year    month2    month3    month4    month5    month6    month7    month8   month9  month10
      0.7803  -0.2321  -0.1964   -379.1346  1.5137  195.9081  272.9902  -24.2703  -88.6687  -25.0078  277.1681  224.4410  76.2821   3.7991
s.e.  0.0837   0.0973   0.0656     42.8611  0.0387   96.4907   99.5181  101.4300  100.2031  101.4180  101.1563  101.2811  92.3923  91.6773
       month11   month12      day   wd‰Ξ—j“ϊ  wd‹ΰ—j“ϊ  wdŒŽ—j“ϊ   wd…—j“ϊ  wd“y—j“ϊ   wd–Ψ—j“ϊ
      147.3163  414.5067  -1.1747  -104.1835   61.3693   22.6069  -127.6002  157.4556  -130.2834
s.e.   93.0474   94.0236   1.5022    31.7203   31.6301   26.3375    32.3830   25.5789    32.3576

sigma^2 estimated as 59126:  log likelihood=-5675.48
AIC=11398.96   AICc=11400.47   BIC=11512.01

Training set error measures:
                     ME    RMSE     MAE        MPE     MAPE       MASE        ACF1
Training set -0.4521637 243.158 172.401 -0.5560798 5.406263 0.05535613 0.007784234


#ˆΘ‰Ί‚ͺ—\‘ͺŒ‹‰Κi”²ˆj
Forecasts:
         Point Forecast    Lo 80    Hi 80    Lo 95    Hi 95
70934401       3529.367 3217.748 3840.987 3052.786 4005.948
71020801       3404.598 3049.215 3759.980 2861.087 3948.108
71107201       3385.364 3022.739 3747.989 2830.777 3939.951
71193601       3563.843 3196.878 3930.809 3002.618 4125.068

#ˆΘ‰Ί‚ͺ—\‘ͺŠJŽn“ϊ‚Μ‘O“ϊ‚ά‚Ε‚Μƒf[ƒ^i”²ˆj
2015/11/26	3557
2015/11/27	3416
2015/11/28	3329
2015/11/29	3001
2015/11/30	3446