1 Mengimport dan memilih data yang ingin digunakan

library("x12")
library(readxl)
library(DT)

data <- read_xlsx("CNYIDR.xlsx")
datatable(data)

data1 <- data.frame("Tanggal" = data$Tanggal, 
                    "Kurs" = data$Terakhir) 

data1$Tanggal <- format(as.Date(data1$Tanggal, '%Y-%m-%d'), "%m-%Y")

## Warning in as.POSIXlt.POSIXct(x, tz = tz): unknown timezone '%Y-%m-%d'

datatable(data1)

data_CNY_IDR <-ts(rev(data1$Kurs),start=c(2015,10),frequency = 12)
data_CNY_IDR

##          Jan     Feb     Mar     Apr     May     Jun     Jul     Aug     Sep
## 2015                                                                        
## 2016 2093.69 2039.05 2055.04 2035.74 2073.34 1986.41 1973.15 1985.48 1954.69
## 2017 1938.14 1940.75 1933.39 1932.29 1956.01 1964.61 1980.06 2024.28 2024.50
## 2018 2127.12 2169.21 2191.78 2196.08 2166.59 2162.30 2113.14 2154.98 2168.94
## 2019 2083.27 2099.42 2120.54 2115.04 2065.93 2056.46 2035.15 1980.64 1984.89
## 2020 1967.74 2050.53 2300.89 2098.55 2041.40 2006.82 2082.89 2125.70 2184.92
## 2021 2180.23 2198.45 2215.61 2230.46 2240.59 2244.57 2237.70 2207.86 2209.45
##          Oct     Nov     Dec
## 2015 2164.38 2161.55 2122.34
## 2016 1924.88 1966.62 1938.97
## 2017 2043.09 2043.98 2084.68
## 2018 2178.40 2053.06 2088.93
## 2019 1992.87 2004.52 1992.94
## 2020 2184.21 2140.75 2150.60
## 2021

2 Lag sebelum dilakukan X-12-ARIMA

par(mfrow=c(1,2)) 
acf(data_CNY_IDR, lag.max = 48, main = "Sample ACF for the mean monthly CNY/IDR series")
pacf(data_CNY_IDR, lag.max = 48, main = "Sample PACF for the mean monthly CNY/IDR series")

3 Lag setelah dilakukan X-12-ARIMA

CNY_IDR_diff <-  diff(data_CNY_IDR)

par(mfrow=c(1,2)) 
acf(CNY_IDR_diff)
pacf(CNY_IDR_diff)

4 X-12-ARIMA dengan x12 Package

data_CNY_IDR_X12 <- x12(data_CNY_IDR)
plot(data_CNY_IDR_X12,original=T,trend=T,sa=T)

#data_CNY_IDR_X12

data_CNY_IDR_STL <- stl(data_CNY_IDR, t.window=15, s.window="periodic", robust=TRUE)
plot(data_CNY_IDR_STL)

library(forecast)

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

forecasts<-forecast(data_CNY_IDR_STL, method = "naive")
plot(forecasts, ylab="Kurs")

window(forecasts$mean,start=c(2021,10),end=c(2022,3))

##           Jan      Feb      Mar Apr May Jun Jul Aug Sep      Oct      Nov
## 2021                                                    2213.993 2202.144
## 2022 2204.200 2222.441 2232.764                                          
##           Dec
## 2021 2199.742
## 2022