moving average

library(ggplot2)
library(tidyquant)

## Warning: package 'tidyquant' was built under R version 4.4.2

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

## Warning: package 'xts' was built under R version 4.4.2

## Warning: package 'PerformanceAnalytics' was built under R version 4.4.2

## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.10 ──
## ✔ PerformanceAnalytics 2.0.8      ✔ TTR                  0.24.4
## ✔ quantmod             0.4.26     ✔ xts                  0.14.1

## ── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date()                 masks base::as.Date()
## ✖ zoo::as.Date.numeric()         masks base::as.Date.numeric()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary()            masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(rstatix)

## 
## Attaching package: 'rstatix'
## 
## The following object is masked from 'package:stats':
## 
##     filter

library(lubridate)

## Warning: package 'lubridate' was built under R version 4.4.2

## 
## Attaching package: 'lubridate'
## 
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(forecast)
library(dplyr)

## 
## ######################### Warning from 'xts' package ##########################
## #                                                                             #
## # The dplyr lag() function breaks how base R's lag() function is supposed to  #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or       #
## # source() into this session won't work correctly.                            #
## #                                                                             #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop           #
## # dplyr from breaking base R's lag() function.                                #
## #                                                                             #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning.  #
## #                                                                             #
## ###############################################################################
## 
## Attaching package: 'dplyr'
## 
## The following objects are masked from 'package:xts':
## 
##     first, last
## 
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## 
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)

data("airquality")

df = airquality
df |> freq_table(5)

## # A tibble: 5 × 3
##   Month     n  prop
##   <int> <int> <dbl>
## 1     5    31  20.3
## 2     6    30  19.6
## 3     7    31  20.3
## 4     8    31  20.3
## 5     9    30  19.6

length(df$Month)

## [1] 153

library(zoo)
head(df)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

# Moving average with K = 3
colnames(df)

## [1] "Ozone"   "Solar.R" "Wind"    "Temp"    "Month"   "Day"

df <- df |> mutate(
  temp3 =rollmean(Temp, k=4,
                         fill=NA,
                  align = "right")
  )

## Show results
head(df, 4)

##   Ozone Solar.R Wind Temp Month Day temp3
## 1    41     190  7.4   67     5   1    NA
## 2    36     118  8.0   72     5   2    NA
## 3    12     149 12.6   74     5   3    NA
## 4    18     313 11.5   62     5   4 68.75

df$No = 1:nrow(df)
ggplot(df, aes(No, Temp)) +
  geom_line()+
  geom_ma(ma_fun = SMA, n=4, color="green")+
  geom_ma(ma_fun = SMA, n=10, color="red")

library(forecast)
colnames(df)

## [1] "Ozone"   "Solar.R" "Wind"    "Temp"    "Month"   "Day"     "temp3"  
## [8] "No"

df |> freq_table(5)

## # A tibble: 5 × 3
##   Month     n  prop
##   <int> <int> <dbl>
## 1     5    31  20.3
## 2     6    30  19.6
## 3     7    31  20.3
## 4     8    31  20.3
## 5     9    30  19.6

nrow(df)

## [1] 153

## Change datat to times series
myts <- ts(df$Temp, start=c(2017, 1), end=c(2024, 12), frequency=12)
summary(myts)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   56.00   68.75   79.00   76.42   83.25   93.00

## 
# Fit an ARIMA model to the data
model <- auto.arima(myts)
# Generate forecasts for the next 10 time points
forecast_values <- forecast(model, h = 10)

plot(forecast_values)

library(ggfortify)

## Warning: package 'ggfortify' was built under R version 4.4.2

## Registered S3 methods overwritten by 'ggfortify':
##   method                 from    
##   autoplot.Arima         forecast
##   autoplot.acf           forecast
##   autoplot.ar            forecast
##   autoplot.bats          forecast
##   autoplot.decomposed.ts forecast
##   autoplot.ets           forecast
##   autoplot.forecast      forecast
##   autoplot.stl           forecast
##   autoplot.ts            forecast
##   fitted.ar              forecast
##   fortify.ts             forecast
##   residuals.ar           forecast

autoplot(forecast_values)