dplyr adalah suatu package yang digunakan untuk data wrangling seperti transformasi dataframe, melakukan aggregate, menampilkan statistika deskriptif, menggabungkan dataframe, mengubah kolom dan baris, mengurutkan data, dan lain sebagainya
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.5.3## Warning: package 'ggplot2' was built under R version 4.5.3## Warning: package 'tidyr' was built under R version 4.5.3## Warning: package 'readr' was built under R version 4.5.3## Warning: package 'purrr' was built under R version 4.5.3## Warning: package 'dplyr' was built under R version 4.5.3## Warning: package 'stringr' was built under R version 4.5.3## Warning: package 'forcats' was built under R version 4.5.3## Warning: package 'lubridate' was built under R version 4.5.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.2 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── 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# Menyimpan URL raw data GitHub ke dalam variabel
url <- "https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-09-01/key_crop_yields.csv"
# Membaca data read_csv
df_crop <- read_csv(url)## Rows: 13075 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Entity, Code
## dbl (12): Year, Wheat (tonnes per hectare), Rice (tonnes per hectare), Maize...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.# Melihat data
glimpse(df_crop)## Rows: 13,075
## Columns: 14
## $ Entity <chr> "Afghanistan", "Afghanistan", "Afgh…
## $ Code <chr> "AFG", "AFG", "AFG", "AFG", "AFG", …
## $ Year <dbl> 1961, 1962, 1963, 1964, 1965, 1966,…
## $ `Wheat (tonnes per hectare)` <dbl> 1.0220, 0.9735, 0.8317, 0.9510, 0.9…
## $ `Rice (tonnes per hectare)` <dbl> 1.5190, 1.5190, 1.5190, 1.7273, 1.7…
## $ `Maize (tonnes per hectare)` <dbl> 1.4000, 1.4000, 1.4260, 1.4257, 1.4…
## $ `Soybeans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Potatoes (tonnes per hectare)` <dbl> 8.6667, 7.6667, 8.1333, 8.6000, 8.8…
## $ `Beans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Peas (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Cassava (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Barley (tonnes per hectare)` <dbl> 1.0800, 1.0800, 1.0800, 1.0857, 1.0…
## $ `Cocoa beans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Bananas (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…Mengubah semua kolom berkarakter (character) menjadi factor
df_crop$Entity <- as.factor(df_crop$Entity)
df_crop$Code <- as.factor(df_crop$Code)
#Periksa apakah ada perubahan
glimpse(df_crop)## Rows: 13,075
## Columns: 14
## $ Entity <fct> "Afghanistan", "Afghanistan", "Afgh…
## $ Code <fct> AFG, AFG, AFG, AFG, AFG, AFG, AFG, …
## $ Year <dbl> 1961, 1962, 1963, 1964, 1965, 1966,…
## $ `Wheat (tonnes per hectare)` <dbl> 1.0220, 0.9735, 0.8317, 0.9510, 0.9…
## $ `Rice (tonnes per hectare)` <dbl> 1.5190, 1.5190, 1.5190, 1.7273, 1.7…
## $ `Maize (tonnes per hectare)` <dbl> 1.4000, 1.4000, 1.4260, 1.4257, 1.4…
## $ `Soybeans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Potatoes (tonnes per hectare)` <dbl> 8.6667, 7.6667, 8.1333, 8.6000, 8.8…
## $ `Beans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Peas (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Cassava (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Barley (tonnes per hectare)` <dbl> 1.0800, 1.0800, 1.0800, 1.0857, 1.0…
## $ `Cocoa beans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Bananas (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…Select adalah fungsi yang digunakan untuk memilih kolom dari suatu dataframe.
data_select <- select(df_crop, Entity, Year, `Wheat (tonnes per hectare)`)
data_select## # A tibble: 13,075 × 3
## Entity Year `Wheat (tonnes per hectare)`
## <fct> <dbl> <dbl>
## 1 Afghanistan 1961 1.02
## 2 Afghanistan 1962 0.974
## 3 Afghanistan 1963 0.832
## 4 Afghanistan 1964 0.951
## 5 Afghanistan 1965 0.972
## 6 Afghanistan 1966 0.867
## 7 Afghanistan 1967 1.12
## 8 Afghanistan 1968 1.16
## 9 Afghanistan 1969 1.19
## 10 Afghanistan 1970 0.956
## # ℹ 13,065 more rowsMemilih beberapa kolom pertama
select(df_crop, 1:4)## # A tibble: 13,075 × 4
## Entity Code Year `Wheat (tonnes per hectare)`
## <fct> <fct> <dbl> <dbl>
## 1 Afghanistan AFG 1961 1.02
## 2 Afghanistan AFG 1962 0.974
## 3 Afghanistan AFG 1963 0.832
## 4 Afghanistan AFG 1964 0.951
## 5 Afghanistan AFG 1965 0.972
## 6 Afghanistan AFG 1966 0.867
## 7 Afghanistan AFG 1967 1.12
## 8 Afghanistan AFG 1968 1.16
## 9 Afghanistan AFG 1969 1.19
## 10 Afghanistan AFG 1970 0.956
## # ℹ 13,065 more rowsMengecualikan kolom
select(df_crop, -c(`Entity`, `Year`))## # A tibble: 13,075 × 12
## Code Wheat (tonnes per hecta…¹ Rice (tonnes per hec…² Maize (tonnes per he…³
## <fct> <dbl> <dbl> <dbl>
## 1 AFG 1.02 1.52 1.4
## 2 AFG 0.974 1.52 1.4
## 3 AFG 0.832 1.52 1.43
## 4 AFG 0.951 1.73 1.43
## 5 AFG 0.972 1.73 1.44
## 6 AFG 0.867 1.52 1.44
## 7 AFG 1.12 1.92 1.41
## 8 AFG 1.16 1.95 1.71
## 9 AFG 1.19 1.98 1.72
## 10 AFG 0.956 1.81 1.48
## # ℹ 13,065 more rows
## # ℹ abbreviated names: ¹`Wheat (tonnes per hectare)`,
## # ²`Rice (tonnes per hectare)`, ³`Maize (tonnes per hectare)`
## # ℹ 8 more variables: `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>, …Memilih kolom yang mengandung teks
select(df_crop, contains("(tonnes per hectare)"))## # A tibble: 13,075 × 11
## `Wheat (tonnes per hectare)` Rice (tonnes per hectar…¹ Maize (tonnes per he…²
## <dbl> <dbl> <dbl>
## 1 1.02 1.52 1.4
## 2 0.974 1.52 1.4
## 3 0.832 1.52 1.43
## 4 0.951 1.73 1.43
## 5 0.972 1.73 1.44
## 6 0.867 1.52 1.44
## 7 1.12 1.92 1.41
## 8 1.16 1.95 1.71
## 9 1.19 1.98 1.72
## 10 0.956 1.81 1.48
## # ℹ 13,065 more rows
## # ℹ abbreviated names: ¹`Rice (tonnes per hectare)`,
## # ²`Maize (tonnes per hectare)`
## # ℹ 8 more variables: `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>, …##Operator Pipe %>% Operator Pipe adalah fitur yang memungkinkan mengalirkan data atau hasil dari satu fungsi secara langsung ke fungsi berikutnya. Pipe secara bahasa sebagai padanan kata “dan kemudian” dalam alur logika kode.
#tidak perlu lagi menyebut nama data di dalam select
#data df_crop dan kemudian dipilih 1-3 kolom pertama dan kemudian dipilih yang bertipe numerik
df_crop %>% select(1:3) %>% select(where(is.numeric)) ## # A tibble: 13,075 × 1
## Year
## <dbl>
## 1 1961
## 2 1962
## 3 1963
## 4 1964
## 5 1965
## 6 1966
## 7 1967
## 8 1968
## 9 1969
## 10 1970
## # ℹ 13,065 more rows##Filter filter adalah fungsi yang digunakan untuk memilih baris sesuai dengan kriteria tertentu.
#data_filter berisi data yang telah disaring untuk Entity dari Indonesia
data_filter<-filter(df_crop, Entity=="Indonesia")
data_filter## # A tibble: 58 × 14
## Entity Code Year `Wheat (tonnes per hectare)` Rice (tonnes per hectare…¹
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 Indonesia IDN 1961 NA 1.76
## 2 Indonesia IDN 1962 NA 1.79
## 3 Indonesia IDN 1963 NA 1.72
## 4 Indonesia IDN 1964 NA 1.76
## 5 Indonesia IDN 1965 NA 1.77
## 6 Indonesia IDN 1966 NA 1.77
## 7 Indonesia IDN 1967 NA 1.76
## 8 Indonesia IDN 1968 NA 2.14
## 9 Indonesia IDN 1969 NA 2.25
## 10 Indonesia IDN 1970 NA 2.38
## # ℹ 48 more rows
## # ℹ abbreviated name: ¹`Rice (tonnes per hectare)`
## # ℹ 9 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>, …Menyaring suatu kolom tanpa nilai NA
filter(df_crop, !is.na(`Wheat (tonnes per hectare)`))## # A tibble: 8,101 × 14
## Entity Code Year `Wheat (tonnes per hectare)` Rice (tonnes per hecta…¹
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 Afghanistan AFG 1961 1.02 1.52
## 2 Afghanistan AFG 1962 0.974 1.52
## 3 Afghanistan AFG 1963 0.832 1.52
## 4 Afghanistan AFG 1964 0.951 1.73
## 5 Afghanistan AFG 1965 0.972 1.73
## 6 Afghanistan AFG 1966 0.867 1.52
## 7 Afghanistan AFG 1967 1.12 1.92
## 8 Afghanistan AFG 1968 1.16 1.95
## 9 Afghanistan AFG 1969 1.19 1.98
## 10 Afghanistan AFG 1970 0.956 1.81
## # ℹ 8,091 more rows
## # ℹ abbreviated name: ¹`Rice (tonnes per hectare)`
## # ℹ 9 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>, …Menyaring lebih dari satu kondisi
filter(df_crop,Code=="IDN" , Year > 2000, `Bananas (tonnes per hectare)` <50 )## # A tibble: 1 × 14
## Entity Code Year `Wheat (tonnes per hectare)` `Rice (tonnes per hectare)`
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 Indonesia IDN 2003 NA 4.54
## # ℹ 9 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>,
## # `Cocoa beans (tonnes per hectare)` <dbl>,
## # `Bananas (tonnes per hectare)` <dbl>##Arrange arrange adalah fungsi yang digunakan untuk mengurutkan data. Gunakan desc untuk mengurutkan secara menurun.
#mengurutkan data berdasarkan Year secara menaik dan annual salary menurun
arrange(df_crop, Year, desc(`Rice (tonnes per hectare)`))## # A tibble: 13,075 × 14
## Entity Code Year Wheat (tonnes per he…¹ Rice (tonnes per hec…²
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 Puerto Rico PRI 1961 NA 6.44
## 2 Spain ESP 1961 0.884 6.36
## 3 Australia AUS 1961 1.13 5.9
## 4 Australia & New Ze… <NA> 1961 1.16 5.9
## 5 Italy ITA 1961 1.91 5.68
## 6 Southern Europe <NA> 1961 1.40 5.42
## 7 Egypt EGY 1961 2.47 5.05
## 8 Northern Africa <NA> 1961 0.696 4.98
## 9 European Union <NA> 1961 1.86 4.95
## 10 Japan JPN 1961 2.75 4.88
## # ℹ 13,065 more rows
## # ℹ abbreviated names: ¹`Wheat (tonnes per hectare)`,
## # ²`Rice (tonnes per hectare)`
## # ℹ 9 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>, …##Mutate mutate adalah fungsi yang digunakan untuk membuat kolom atau variabel baru.
#Menghasilkan kolom baru bernama Wheat (kg per hectare)
mutate(df_crop, `Wheat (kg per hectare)` = `Wheat (tonnes per hectare)` * 1000)## # A tibble: 13,075 × 15
## Entity Code Year `Wheat (tonnes per hectare)` Rice (tonnes per hecta…¹
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 Afghanistan AFG 1961 1.02 1.52
## 2 Afghanistan AFG 1962 0.974 1.52
## 3 Afghanistan AFG 1963 0.832 1.52
## 4 Afghanistan AFG 1964 0.951 1.73
## 5 Afghanistan AFG 1965 0.972 1.73
## 6 Afghanistan AFG 1966 0.867 1.52
## 7 Afghanistan AFG 1967 1.12 1.92
## 8 Afghanistan AFG 1968 1.16 1.95
## 9 Afghanistan AFG 1969 1.19 1.98
## 10 Afghanistan AFG 1970 0.956 1.81
## # ℹ 13,065 more rows
## # ℹ abbreviated name: ¹`Rice (tonnes per hectare)`
## # ℹ 10 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>, …Kolom baru dengan kondisi
df_crop %>%
mutate(Wheat_Status = ifelse(`Wheat (tonnes per hectare)` > 1, "Lebih dari 1", "Kurang dari 1")) %>% select(Code,Year,Wheat_Status)## # A tibble: 13,075 × 3
## Code Year Wheat_Status
## <fct> <dbl> <chr>
## 1 AFG 1961 Lebih dari 1
## 2 AFG 1962 Kurang dari 1
## 3 AFG 1963 Kurang dari 1
## 4 AFG 1964 Kurang dari 1
## 5 AFG 1965 Kurang dari 1
## 6 AFG 1966 Kurang dari 1
## 7 AFG 1967 Lebih dari 1
## 8 AFG 1968 Lebih dari 1
## 9 AFG 1969 Lebih dari 1
## 10 AFG 1970 Kurang dari 1
## # ℹ 13,065 more rows##Summarise summarise adalah fungsi yang digunakan untuk melakukan statistika deskriptif.
#ada dua summarise yang ingin dihasilkan
#gunakan na.rm = TRUE untuk meremove atau membuang nilai yang hilang
df_sum <- summarise(df_crop,
`maksimum Wheat` = max(`Wheat (tonnes per hectare)`, na.rm = TRUE),
`maksimum Rice` = max(`Rice (tonnes per hectare)`, na.rm = TRUE))
df_sum## # A tibble: 1 × 2
## `maksimum Wheat` `maksimum Rice`
## <dbl> <dbl>
## 1 10.7 10.7##Group by Group by mengelompokan data dan menyimpulkannya. Untuk mengeksplorasi lebih lanjut, dapat ditambahkan fungsi fungsi lain.
#Memilih beberapa kolom awal, Mengelompokkan, kemudian menghitung rata rata, menyaring yang tidak kosong, menambahkan kolom baru, mengurutkan
df_crop %>%
select(1:4) %>%
group_by(Code) %>%
summarise(`Mean Wheat (tonnes per hectare)` = mean(`Wheat (tonnes per hectare)`)) %>%
filter(!is.na(`Mean Wheat (tonnes per hectare)`)) %>%
mutate(`Mean Wheat (kg per hectare)` = `Mean Wheat (tonnes per hectare)` * 1000) %>%
arrange(desc(`Mean Wheat (kg per hectare)`))## # A tibble: 118 × 3
## Code `Mean Wheat (tonnes per hectare)` `Mean Wheat (kg per hectare)`
## <fct> <dbl> <dbl>
## 1 BEL 8.54 8544.
## 2 NLD 7.03 7030.
## 3 IRL 6.83 6830.
## 4 GBR 6.37 6366.
## 5 DNK 6.18 6175.
## 6 LUX 5.98 5977.
## 7 DEU 5.89 5894.
## 8 FRA 5.65 5645.
## 9 NZL 5.36 5358.
## 10 SWE 5.18 5179.
## # ℹ 108 more rows