Pengenalan data sains

~ TUGAS 1 ~


*Kontak *: \(\downarrow\)**
Email
Instagram https://www.instagram.com/jeremyheryand/
RPubs https://rpubs.com/jeremyheriyandi23/

Import data

can_lang = read.csv("C:\\Users\\Public\\can_lang.csv")
can_lang

Create and organize subsets of tabular data using filter, select, arrange, and slice.

Filter

library(dplyr)

Filter <-  filter(can_lang, category == "Aboriginal languages")
Filter

select

Select <- select(Filter, language, mother_tongue)
Select

arrange

library(dplyr)
arranged_lang <- arrange(Select, by = desc(mother_tongue))
arranged_lang

slice

ten_lang <- slice(arranged_lang, 1:10)
ten_lang

Visualize data with a ggplot bar plot.

library(tidyverse)

# load the data set
can_lang <- read_csv("C:\\Users\\Public\\can_lang.csv")

# obtain the 10 most common Aboriginal languages
aboriginal_lang <- filter(can_lang, category == "Aboriginal languages")
arranged_lang <- arrange(aboriginal_lang, by = desc(mother_tongue))
ten_lang <- slice(arranged_lang, 1:10)

# create the visualization
ggplot(ten_lang, aes(x = mother_tongue,
                     y = reorder(language, mother_tongue))) +
  geom_bar(stat = "identity",fill="blue") + 
  xlab("Mother Tongue (Number of Canadian Residents)") +
  ylab("Language")