Praktikum Missing Value dan Outlier

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.4.3

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

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

##
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
##
## filter, lag

## The following objects are masked from 'package:stats':
##
## intersect, setdiff, setequal, union

library(tidyr)

## Warning: package 'tidyr' was built under R version 4.4.3

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.4.3

data("airquality")

airquality

head(airquality)

summary(airquality)

##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
## 

is.na(airquality)

##        Ozone Solar.R  Wind  Temp Month   Day
##   [1,] FALSE   FALSE FALSE FALSE FALSE FALSE
##   [2,] FALSE   FALSE FALSE FALSE FALSE FALSE
##   [3,] FALSE   FALSE FALSE FALSE FALSE FALSE
##   [4,] FALSE   FALSE FALSE FALSE FALSE FALSE
##   [5,]  TRUE    TRUE FALSE FALSE FALSE FALSE
##   [6,] FALSE    TRUE FALSE FALSE FALSE FALSE
##   [7,] FALSE   FALSE FALSE FALSE FALSE FALSE
##   [8,] FALSE   FALSE FALSE FALSE FALSE FALSE
##   [9,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [10,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [11,] FALSE    TRUE FALSE FALSE FALSE FALSE
##  [12,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [13,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [14,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [15,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [16,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [17,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [18,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [19,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [20,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [21,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [22,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [23,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [24,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [25,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [26,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [27,]  TRUE    TRUE FALSE FALSE FALSE FALSE
##  [28,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [29,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [30,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [31,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [32,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [33,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [34,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [35,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [36,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [37,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [38,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [39,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [40,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [41,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [42,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [43,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [44,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [45,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [46,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [47,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [48,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [49,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [50,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [51,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [52,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [53,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [54,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [55,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [56,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [57,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [58,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [59,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [60,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [61,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [62,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [63,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [64,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [65,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [66,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [67,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [68,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [69,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [70,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [71,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [72,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [73,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [74,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [75,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [76,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [77,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [78,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [79,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [80,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [81,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [82,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [83,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [84,]  TRUE   FALSE FALSE FALSE FALSE FALSE
##  [85,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [86,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [87,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [88,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [89,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [90,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [91,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [92,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [93,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [94,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [95,] FALSE   FALSE FALSE FALSE FALSE FALSE
##  [96,] FALSE    TRUE FALSE FALSE FALSE FALSE
##  [97,] FALSE    TRUE FALSE FALSE FALSE FALSE
##  [98,] FALSE    TRUE FALSE FALSE FALSE FALSE
##  [99,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [100,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [101,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [102,]  TRUE   FALSE FALSE FALSE FALSE FALSE
## [103,]  TRUE   FALSE FALSE FALSE FALSE FALSE
## [104,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [105,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [106,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [107,]  TRUE   FALSE FALSE FALSE FALSE FALSE
## [108,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [109,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [110,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [111,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [112,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [113,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [114,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [115,]  TRUE   FALSE FALSE FALSE FALSE FALSE
## [116,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [117,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [118,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [119,]  TRUE   FALSE FALSE FALSE FALSE FALSE
## [120,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [121,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [122,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [123,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [124,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [125,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [126,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [127,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [128,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [129,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [130,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [131,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [132,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [133,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [134,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [135,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [136,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [137,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [138,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [139,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [140,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [141,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [142,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [143,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [144,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [145,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [146,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [147,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [148,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [149,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [150,]  TRUE   FALSE FALSE FALSE FALSE FALSE
## [151,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [152,] FALSE   FALSE FALSE FALSE FALSE FALSE
## [153,] FALSE   FALSE FALSE FALSE FALSE FALSE

colSums(is.na(airquality))

##   Ozone Solar.R    Wind    Temp   Month     Day 
##      37       7       0       0       0       0

# Visualisasi missing values
library(VIM) # Library untuk visualisasi missing values

## Warning: package 'VIM' was built under R version 4.4.3

## Loading required package: colorspace

## Loading required package: grid

## VIM is ready to use.

## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues

## 
## Attaching package: 'VIM'

## The following object is masked from 'package:datasets':
## 
##     sleep

## Loading required package: colorspace

## Loading required package: grid

## VIM is ready to use.

## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues

##
## Attaching package: 'VIM'

## The following object is masked from 'package:datasets':
##
## sleep

aggr(airquality, numbers = TRUE, prop = FALSE)

# Mengganti missing values dengan median di setiap kolom
airquality$Ozone[is.na(airquality$Ozone)] <- median(airquality$Ozone, na.rm = TRUE)
airquality$Solar.R[is.na(airquality$Solar.R)] <- median(airquality$Solar.R, na.rm = TRUE)

airquality

colSums(is.na(airquality))

##   Ozone Solar.R    Wind    Temp   Month     Day 
##       0       0       0       0       0       0

# Menggunakan metode IQR untuk mendeteksi outlier pada kolom Ozone
Q1 <- quantile(airquality$Ozone, 0.25)
Q3 <- quantile(airquality$Ozone, 0.75)
IQR <- Q3 - Q1
# Batas bawah dan atas
lower_bound <- Q1 - 1.5 * IQR
upper_bound <- Q3 + 1.5 * IQR

# Menandai outlier dengan kondisi apakah nilainya di luar batas bawah atau atas
outliersa <- airquality$Ozone < lower_bound
outliers <- airquality$Ozone > upper_bound
sum(outliersa)

## [1] 0

## [1] 0

sum(outliers)

## [1] 15

## [1] 15

# Visualisasi boxplot untuk melihat outlier pada kolom Ozone
boxplot(airquality$Ozone, main = "Boxplot Ozone", col = "pink")

# Menangani outlier dengan winsorizing (mengganti nilai ekstrem dengan batas)
airquality$Ozone[outliers] <- ifelse(airquality$Ozone[outliers] < lower_bound, lower_bound, upper_bound)

# Cek jumlah duplikasi dalam dataset
sum(duplicated(airquality)) # Menghitung jumlah baris yang duplikat

## [1] 0

## [1] 0

# Hapus duplikasi jika ada
airquality <- airquality[!duplicated(airquality), ] # Menyaring hanya baris unik

# Cek ulang data setelah preprocessing
summary(airquality) # Menampilkan ringkasan statistik setelah preprocessing

##      Ozone          Solar.R           Wind             Temp      
##  Min.   : 1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.:21.00   1st Qu.:120.0   1st Qu.: 7.400   1st Qu.:72.00  
##  Median :31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   :37.29   Mean   :186.8   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.:46.00   3rd Qu.:256.0   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :83.50   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0