Pengertian Manipulasi Data

Manipulasi data, manipulasi data dapat diartikan sebagai proses perubahan data sesuai dengan aturan yang kita terapkan. Manfaat manipulasi data dapat kita gunakan untuk melakukan prediksi data. Dengan adanya prediksi tersebut kita dapat membuat rencana untuk mencegah hal-hal yang tidak kita inginkan.

Import Data dari Excel

library(readxl)
## Warning: package 'readxl' was built under R version 4.1.2
inflowbali <- read_excel(path = "D:/1. PERKULIAHAN/Semester 2/Linier Algebra/data/datainflowbalitahunan.xlsx")
## New names:
## * `` -> ...1
inflowbali
## # A tibble: 5 x 13
##    ...1 Provinsi  `2011` `2012` `2013` `2014` `2015` `2016` `2017` `2018` `2019`
##   <dbl> <chr>      <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1    NA <NA>         NA     NA     NA     NA     NA     NA     NA     NA     NA 
## 2     1 Bali Nus~ 10322. 14613. 17512. 20807. 23008. 30965. 30797. 33866. 38116.
## 3     2 Bali       6394.  8202.  5066. 11590. 13072. 17914. 16962. 18610. 21422.
## 4     3 Nusa Ten~  1803.  3676.  7024.  5704.  6285.  8842.  8383.  9140.  9614.
## 5     4 Nusa Ten~  2125.  2735.  5422.  3512.  3651.  4210.  5452.  6116.  7080.
## # ... with 2 more variables: `2020` <dbl>, `2021` <dbl>
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.1.3
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.8
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   2.1.2     v forcats 0.5.1
## Warning: package 'ggplot2' was built under R version 4.1.3
## Warning: package 'tibble' was built under R version 4.1.2
## Warning: package 'tidyr' was built under R version 4.1.3
## Warning: package 'readr' was built under R version 4.1.3
## Warning: package 'purrr' was built under R version 4.1.3
## Warning: package 'dplyr' was built under R version 4.1.3
## Warning: package 'forcats' was built under R version 4.1.3
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

Manipulasi Data: Menampilkan Data Inflow Pada tahun 2015

bali2015 <- select(inflowbali, '2015')
bali2015
## # A tibble: 5 x 1
##   `2015`
##    <dbl>
## 1    NA 
## 2 23008.
## 3 13072.
## 4  6285.
## 5  3651.

Manipulasi Data: Menampilkan Data Inflow Tahun 2011-2020 (Tanpa 2015)

library(tidyverse)
balinon2015 <- select(inflowbali, -'2015')
balinon2015
## # A tibble: 5 x 12
##    ...1 Provinsi  `2011` `2012` `2013` `2014` `2016` `2017` `2018` `2019` `2020`
##   <dbl> <chr>      <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1    NA <NA>         NA     NA     NA     NA     NA     NA     NA     NA     NA 
## 2     1 Bali Nus~ 10322. 14613. 17512. 20807. 30965. 30797. 33866. 38116. 29400.
## 3     2 Bali       6394.  8202.  5066. 11590. 17914. 16962. 18610. 21422. 14735.
## 4     3 Nusa Ten~  1803.  3676.  7024.  5704.  8842.  8383.  9140.  9614.  8007.
## 5     4 Nusa Ten~  2125.  2735.  5422.  3512.  4210.  5452.  6116.  7080.  6657.
## # ... with 1 more variable: `2021` <dbl>

Manipulasi Data: Merubah “2011” menjadi “Tahun 2011”

library(dplyr)
rename2011 <- inflowbali %>% rename('Tahun 2011' = '2011')
head(rename2011)
## # A tibble: 5 x 13
##    ...1 Provinsi   `Tahun 2011` `2012` `2013` `2014` `2015` `2016` `2017` `2018`
##   <dbl> <chr>             <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1    NA <NA>                NA     NA     NA     NA     NA     NA     NA     NA 
## 2     1 Bali Nusra       10322. 14613. 17512. 20807. 23008. 30965. 30797. 33866.
## 3     2 Bali              6394.  8202.  5066. 11590. 13072. 17914. 16962. 18610.
## 4     3 Nusa Teng~        1803.  3676.  7024.  5704.  6285.  8842.  8383.  9140.
## 5     4 Nusa Teng~        2125.  2735.  5422.  3512.  3651.  4210.  5452.  6116.
## # ... with 3 more variables: `2019` <dbl>, `2020` <dbl>, `2021` <dbl>

Manipulasi Data: Menampilkan Data Inflow Provinsi Bali tahun 2011-2015

library(dplyr)
nusrabali <- inflowbali %>%
    filter(Provinsi == 'Bali') %>%
    select('2011','2012','2013','2014','2015')
nusrabali
## # A tibble: 1 x 5
##   `2011` `2012` `2013` `2014` `2015`
##    <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1  6394.  8202.  5066. 11590. 13072.

Manipulasi Data: Menampilkan Data Inflow Provinsi NTB tahun 2012,2014,2016,2018

library(dplyr)
nusrantb <- inflowbali %>%
    filter(Provinsi == 'Nusa Tenggara Barat') %>%
    select('2012','2014','2016','2018')
nusrantb
## # A tibble: 1 x 4
##   `2012` `2014` `2016` `2018`
##    <dbl>  <dbl>  <dbl>  <dbl>
## 1  3676.  5704.  8842.  9140.

Manipulasi Data: Menampilkan Struktur Data Inflow Uang Kuartal Pulau Bali-Nusra

str(inflowbali)
## tibble [5 x 13] (S3: tbl_df/tbl/data.frame)
##  $ ...1    : num [1:5] NA 1 2 3 4
##  $ Provinsi: chr [1:5] NA "Bali Nusra" "Bali" "Nusa Tenggara Barat" ...
##  $ 2011    : num [1:5] NA 10322 6394 1803 2125
##  $ 2012    : num [1:5] NA 14613 8202 3676 2735
##  $ 2013    : num [1:5] NA 17512 5066 7024 5422
##  $ 2014    : num [1:5] NA 20807 11590 5704 3512
##  $ 2015    : num [1:5] NA 23008 13072 6285 3651
##  $ 2016    : num [1:5] NA 30965 17914 8842 4210
##  $ 2017    : num [1:5] NA 30797 16962 8383 5452
##  $ 2018    : num [1:5] NA 33866 18610 9140 6116
##  $ 2019    : num [1:5] NA 38116 21422 9614 7080
##  $ 2020    : num [1:5] NA 29400 14735 8007 6657
##  $ 2021    : num [1:5] NA 18892 7505 5888 5498
str(inflowbali %>% group_by(Provinsi))
## grouped_df [5 x 13] (S3: grouped_df/tbl_df/tbl/data.frame)
##  $ ...1    : num [1:5] NA 1 2 3 4
##  $ Provinsi: chr [1:5] NA "Bali Nusra" "Bali" "Nusa Tenggara Barat" ...
##  $ 2011    : num [1:5] NA 10322 6394 1803 2125
##  $ 2012    : num [1:5] NA 14613 8202 3676 2735
##  $ 2013    : num [1:5] NA 17512 5066 7024 5422
##  $ 2014    : num [1:5] NA 20807 11590 5704 3512
##  $ 2015    : num [1:5] NA 23008 13072 6285 3651
##  $ 2016    : num [1:5] NA 30965 17914 8842 4210
##  $ 2017    : num [1:5] NA 30797 16962 8383 5452
##  $ 2018    : num [1:5] NA 33866 18610 9140 6116
##  $ 2019    : num [1:5] NA 38116 21422 9614 7080
##  $ 2020    : num [1:5] NA 29400 14735 8007 6657
##  $ 2021    : num [1:5] NA 18892 7505 5888 5498
##  - attr(*, "groups")= tibble [5 x 2] (S3: tbl_df/tbl/data.frame)
##   ..$ Provinsi: chr [1:5] "Bali" "Bali Nusra" "Nusa Tenggara Barat" "Nusa Tenggara Timur" ...
##   ..$ .rows   : list<int> [1:5] 
##   .. ..$ : int 3
##   .. ..$ : int 2
##   .. ..$ : int 4
##   .. ..$ : int 5
##   .. ..$ : int 1
##   .. ..@ ptype: int(0) 
##   ..- attr(*, ".drop")= logi TRUE

Manipulasi Data: Menampilkan Visualisasi Data Inflow Uang Kuartal Pulau Bali-Nusra 2015

ggplot(data = inflowbali, mapping = aes(x = Provinsi, y = `2015`)) +
  geom_point()
## Warning: Removed 1 rows containing missing values (geom_point).