library(tidyverse)

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

## Warning: package 'ggplot2' was built under R version 4.4.2

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

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

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

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

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

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

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

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

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(datasets)
data(airquality)
airquality <- tibble::as.tibble(airquality)

## Warning: `as.tibble()` was deprecated in tibble 2.0.0.
## ℹ Please use `as_tibble()` instead.
## ℹ The signature and semantics have changed, see `?as_tibble`.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

library(dplyr)

class(airquality)

## [1] "tbl_df"     "tbl"        "data.frame"

view(airquality)

head(airquality)

## # A tibble: 6 × 6
##   Ozone Solar.R  Wind  Temp Month   Day
##   <int>   <int> <dbl> <int> <int> <int>
## 1    41     190   7.4    67     5     1
## 2    36     118   8      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

glimpse(airquality)

## Rows: 153
## Columns: 6
## $ Ozone   <int> 41, 36, 12, 18, NA, 28, 23, 19, 8, NA, 7, 16, 11, 14, 18, 14, …
## $ Solar.R <int> 190, 118, 149, 313, NA, NA, 299, 99, 19, 194, NA, 256, 290, 27…
## $ Wind    <dbl> 7.4, 8.0, 12.6, 11.5, 14.3, 14.9, 8.6, 13.8, 20.1, 8.6, 6.9, 9…
## $ Temp    <int> 67, 72, 74, 62, 56, 66, 65, 59, 61, 69, 74, 69, 66, 68, 58, 64…
## $ Month   <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,…
## $ Day     <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,…

Data Filtering

Mengambil kualitas udara dengan temperatur lebih dari 60.0 fahrenheit

filtered_airquality <- filter(airquality, Temp > 60.0)
head(filtered_airquality)

## # A tibble: 6 × 6
##   Ozone Solar.R  Wind  Temp Month   Day
##   <int>   <int> <dbl> <int> <int> <int>
## 1    41     190   7.4    67     5     1
## 2    36     118   8      72     5     2
## 3    12     149  12.6    74     5     3
## 4    18     313  11.5    62     5     4
## 5    28      NA  14.9    66     5     6
## 6    23     299   8.6    65     5     7

Mengambil data dari Ozone, Solar.r, Wind, Temp, Month, Day

airquality %>% filter(Month==5)

## # A tibble: 31 × 6
##    Ozone Solar.R  Wind  Temp Month   Day
##    <int>   <int> <dbl> <int> <int> <int>
##  1    41     190   7.4    67     5     1
##  2    36     118   8      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
##  7    23     299   8.6    65     5     7
##  8    19      99  13.8    59     5     8
##  9     8      19  20.1    61     5     9
## 10    NA     194   8.6    69     5    10
## # ℹ 21 more rows

airquality %>% select(Ozone, Solar.R, Wind, Temp, Month, Day)

## # A tibble: 153 × 6
##    Ozone Solar.R  Wind  Temp Month   Day
##    <int>   <int> <dbl> <int> <int> <int>
##  1    41     190   7.4    67     5     1
##  2    36     118   8      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
##  7    23     299   8.6    65     5     7
##  8    19      99  13.8    59     5     8
##  9     8      19  20.1    61     5     9
## 10    NA     194   8.6    69     5    10
## # ℹ 143 more rows

airquality %>% select(-Solar.R, -Day)

## # A tibble: 153 × 4
##    Ozone  Wind  Temp Month
##    <int> <dbl> <int> <int>
##  1    41   7.4    67     5
##  2    36   8      72     5
##  3    12  12.6    74     5
##  4    18  11.5    62     5
##  5    NA  14.3    56     5
##  6    28  14.9    66     5
##  7    23   8.6    65     5
##  8    19  13.8    59     5
##  9     8  20.1    61     5
## 10    NA   8.6    69     5
## # ℹ 143 more rows

Data Arranging

Mengurutkan berdasarkan peubah Wind dari nilai terkecil

airquality %>% arrange(Wind)

## # A tibble: 153 × 6
##    Ozone Solar.R  Wind  Temp Month   Day
##    <int>   <int> <dbl> <int> <int> <int>
##  1    NA      59   1.7    76     6    22
##  2   118     225   2.3    94     8    29
##  3    73     183   2.8    93     9     3
##  4   168     238   3.4    81     8    25
##  5   122     255   4      89     8     7
##  6   135     269   4.1    84     7     1
##  7    NA      91   4.6    76     6    23
##  8    64     175   4.6    83     7     5
##  9    66      NA   4.6    87     8     6
## 10    91     189   4.6    93     9     4
## # ℹ 143 more rows

Mengurutkan berdasaran peubah Wind dari nilai terbesar

airquality %>% arrange(desc(Wind))

## # A tibble: 153 × 6
##    Ozone Solar.R  Wind  Temp Month   Day
##    <int>   <int> <dbl> <int> <int> <int>
##  1    37     284  20.7    72     6    17
##  2     8      19  20.1    61     5     9
##  3     6      78  18.4    57     5    18
##  4    11     320  16.6    73     5    22
##  5    NA      66  16.6    57     5    25
##  6    14      20  16.6    63     9    25
##  7    NA     242  16.1    67     6     3
##  8    21     259  15.5    77     8    21
##  9    32      92  15.5    84     9     6
## 10    21     259  15.5    76     9    12
## # ℹ 143 more rows

Data Reshaping

Mengubah data dari format wide ke long

long_airquality <- pivot_longer(airquality, cols = c(Ozone, Solar.R, Wind, Temp, Month, Day), names_to = "Measurement", values_to = "Value")
head(long_airquality)

## # A tibble: 6 × 2
##   Measurement Value
##   <chr>       <dbl>
## 1 Ozone        41  
## 2 Solar.R     190  
## 3 Wind          7.4
## 4 Temp         67  
## 5 Month         5  
## 6 Day           1

Data Merging

Menambahkan contoh data eksternal

additional_data <- data.frame(Month = c(5, 6, 7, 8, 9), Info = c("Type A", "Type B", "Type C", "Type D", "Type E"))
merged_airquality <- left_join(airquality, additional_data, by = "Month")
head(merged_airquality)

## # A tibble: 6 × 7
##   Ozone Solar.R  Wind  Temp Month   Day Info  
##   <int>   <int> <dbl> <int> <dbl> <int> <chr> 
## 1    41     190   7.4    67     5     1 Type A
## 2    36     118   8      72     5     2 Type A
## 3    12     149  12.6    74     5     3 Type A
## 4    18     313  11.5    62     5     4 Type A
## 5    NA      NA  14.3    56     5     5 Type A
## 6    28      NA  14.9    66     5     6 Type A

Data Aggregating

Menghitung rata-rata Temp tiap bulan

airquality %>% group_by(Month) %>% summarize (mean=mean(Temp))

## # A tibble: 5 × 2
##   Month  mean
##   <int> <dbl>
## 1     5  65.5
## 2     6  79.1
## 3     7  83.9
## 4     8  84.0
## 5     9  76.9

Feature Engineering (Variable Trnasformation)

Menambah peubah baru

airquality %>% filter(Month==6)

## # A tibble: 30 × 6
##    Ozone Solar.R  Wind  Temp Month   Day
##    <int>   <int> <dbl> <int> <int> <int>
##  1    NA     286   8.6    78     6     1
##  2    NA     287   9.7    74     6     2
##  3    NA     242  16.1    67     6     3
##  4    NA     186   9.2    84     6     4
##  5    NA     220   8.6    85     6     5
##  6    NA     264  14.3    79     6     6
##  7    29     127   9.7    82     6     7
##  8    NA     273   6.9    87     6     8
##  9    71     291  13.8    90     6     9
## 10    39     323  11.5    87     6    10
## # ℹ 20 more rows

airqualitybaru <- airquality %>% select(-Month, -Day) %>% mutate(quality=Ozone-Wind)
airqualitybaru

## # A tibble: 153 × 5
##    Ozone Solar.R  Wind  Temp quality
##    <int>   <int> <dbl> <int>   <dbl>
##  1    41     190   7.4    67  33.6  
##  2    36     118   8      72  28    
##  3    12     149  12.6    74  -0.600
##  4    18     313  11.5    62   6.5  
##  5    NA      NA  14.3    56  NA    
##  6    28      NA  14.9    66  13.1  
##  7    23     299   8.6    65  14.4  
##  8    19      99  13.8    59   5.2  
##  9     8      19  20.1    61 -12.1  
## 10    NA     194   8.6    69  NA    
## # ℹ 143 more rows

engineered_airquality <- mutate(airquality, Impact_Solar_Ozone = Ozone * Solar.R)
head(engineered_airquality)

## # A tibble: 6 × 7
##   Ozone Solar.R  Wind  Temp Month   Day Impact_Solar_Ozone
##   <int>   <int> <dbl> <int> <int> <int>              <int>
## 1    41     190   7.4    67     5     1               7790
## 2    36     118   8      72     5     2               4248
## 3    12     149  12.6    74     5     3               1788
## 4    18     313  11.5    62     5     4               5634
## 5    NA      NA  14.3    56     5     5                 NA
## 6    28      NA  14.9    66     5     6                 NA

Membuat variabel baru yang merupakan hasil perkalian Ozone dengan Solar.r

Pengguaan 2 Fungsi Bersamaan

Menyaring data airquality untuk mendapatkan nilai wind lebih besar dari 10.0 mph, kemudian mengurutkan hasilnya berdasarkan Ozone secara descending.

result1 <- airquality %>%
  filter(Wind > 10.0) %>%
  arrange(desc(Ozone))
result1

## # A tibble: 72 × 6
##    Ozone Solar.R  Wind  Temp Month   Day
##    <int>   <int> <dbl> <int> <int> <int>
##  1    89     229  10.3    90     8     8
##  2    71     291  13.8    90     6     9
##  3    63     220  11.5    85     7    20
##  4    52      82  12      86     7    27
##  5    45     252  14.9    81     5    29
##  6    44     192  11.5    86     8    12
##  7    44     190  10.3    78     8    20
##  8    44     236  14.9    81     9    11
##  9    40     314  10.9    83     7     6
## 10    39     323  11.5    87     6    10
## # ℹ 62 more rows

Membuat kolom baru yang merupakan hasil pengurangan Ozone dengan Wind yang disebut sebagai quality, lalu memilih hanya beberapa kolom tertentu untuk ditampilkan

result2 <- airquality %>%
  mutate(Quality = Ozone - Wind) %>%
  select(Ozone, Temp, Month)

head(result2)

## # A tibble: 6 × 3
##   Ozone  Temp Month
##   <int> <int> <int>
## 1    41    67     5
## 2    36    72     5
## 3    12    74     5
## 4    18    62     5
## 5    NA    56     5
## 6    28    66     5

Tugas Sesi UAS (Data Wrangling)

Abdullah Zeith Alfarizy

2024-12-06

Data Filtering

Mengambil kualitas udara dengan temperatur lebih dari 60.0 fahrenheit

Mengambil data dari Ozone, Solar.r, Wind, Temp, Month, Day

Data Arranging

Mengurutkan berdasarkan peubah Wind dari nilai terkecil

Mengurutkan berdasaran peubah Wind dari nilai terbesar

Data Reshaping

Mengubah data dari format wide ke long

Data Merging

Menambahkan contoh data eksternal

Data Aggregating

Menghitung rata-rata Temp tiap bulan

Feature Engineering (Variable Trnasformation)

Menambah peubah baru

Membuat variabel baru yang merupakan hasil perkalian Ozone dengan Solar.r

Pengguaan 2 Fungsi Bersamaan

Menyaring data airquality untuk mendapatkan nilai wind lebih besar dari 10.0 mph, kemudian mengurutkan hasilnya berdasarkan Ozone secara descending.

Membuat kolom baru yang merupakan hasil pengurangan Ozone dengan Wind yang disebut sebagai quality, lalu memilih hanya beberapa kolom tertentu untuk ditampilkan