Pengenalan Tidyverse

summarise()

creates a new data frame. It will have one (or more) rows for each combination of grouping variables; if there are no grouping variables, the output will have a single row summarising all observations in the input. It will contain one column for each grouping variable and one column for each of the summary statistics that you have specified.

Pada contoh ini data akan diringkas untuk menghitung rata-rata jumlah cylinder (cyl) dan total jumlah carburator (carb) untuk automobile dengan tranmisi automatic dan manua; (am)

summarised_dataset = dataset %>%  group_by(am) %>%  summarise(mean_cyl = mean(cyl), total_carb = sum(carb))
summarised_dataset %>% kbl(caption = "Summarised Dataset") %>%  kable_styling()

arrange()

orders the rows of a data frame by the values of selected columns.

Pada contoh berikut ini akan diurutkan mobil dengan penggunaan bahan bakar dari yang paling kecil ke yang paling besar

arranged_dataset = dataset %>%  arrange(mpg)
arranged_dataset%>%  kbl(caption = "Arranged Dataset") %>%  kable_styling() %>%  column_spec(2, bold = T, background = "#FA5754") %>%  scroll_box(height = "400px")

filter()

used to subset a data frame, retaining all rows that satisfy your conditions.

Untuk fungsi filter(), akan dilakukan pemilihan mobil dengan berat (wt) diatas 4000 lbs,

filtered_dataset = dataset %>%  filter(wt >4)
filtered_dataset %>% kbl(caption = "Filtered Dataset") %>% kable_styling()  %>%  column_spec(7, bold = T, background = "#FA5754")

mutate()

adds new variables and preserves existing ones;

Untuk fungsi mutate(), akan dilakukan pembentukan dua variable yaitu : - wt_to_cyl = berat dibagi dengan jumlah cylinders - vs_str = yaitu string version dari variable vs.

mutated_dataset = dataset %>% mutate(wt_to_cyl = wt/cyl, vs_str = ifelse(vs == 0 , "V-shaped","straight"))
mutated_dataset %>% kbl(caption = "Mutated Dataset") %>% kable_styling()  %>%  column_spec(12, bold = T, background = "#FA5754") %>%  column_spec(13, bold = T, background = "#009CD9") %>% scroll_box(height = "400px")

select()

Select (and optionally rename) variables in a data frame, using a concise mini-language that makes it easy to refer to variables based on their name (e.g. a:f selects all columns from a on the left to f on the right).

Untuk fungsi select akan dipilih 4 variabel = hp, wt, am ,carb

selected_dataset = dataset %>% select(hp,wt,am, carb)
selected_dataset %>% kbl(caption = "Mutated Dataset") %>% kable_styling() %>%  scroll_box(height = "200px") 

cook it all !

Seluruh fungsi diatas dapat digunakan secara bersamaan, potongan kode di bawah akan menerapkan :

• memilih colom cyl,disp,hp,wt
• filter Displacement (disp) lebih dari 1000
• mengelompokkan data berdasarkan jumlah silinder
• menghitung total untuk variable disp,hp, dan wt
• mengurutkan data berdasarkan variable wt
• terakhir, mengembalikan variabel wt ke skala awal (1000 lbs)

wrangled_dataset = dataset %>% select(cyl,disp,hp,wt) %>% filter(disp >100) %>% group_by(cyl) %>%  summarise(total_disp = sum(disp),total_hp = sum(hp),total_wt = sum(wt)) %>% arrange(total_wt) %>% mutate( wt_1000 = total_wt*1000)
wrangled_dataset %>% kbl(caption = "Wrangled Dataset") %>% kable_styling()