R Notebook

Shortcuts Summary

• Control/Ctrl + 1: Source editor (your script)

• Control/Ctrl + 2: Console

• Control/Ctrl + 3: Help

• Control/Ctrl + 4: History

• Control/Ctrl + 5: Files

• Control/Ctrl + 6: Plots

• Control/Ctrl + 7: Packages

• Control/Ctrl + 8: Environment

• Control/Ctrl + 9: Viewer

• Tools > Keyboard Shortcuts Help (Alt + Shift + K)

• <- (Alt + - )

• %<% (Ctrl + Shift + M)

• Comment or uncomment lines → Ctrl + Shift + C

• Move Lines Up/Down → Alt+Up/Down

• Delete Line → Ctrl+D

• Select → Shift+[Arrow]

• Select Word → Ctrl+Shift+Left/Right

• Select to Line Start → Alt+Shift+Left

• Select to Line End → Alt+Shift+Right

• Run current line → Ctrl + Enter

• Run current line (retain cursor position) → Alt+Enter

• Run all lines of code → Ctrl + A + Enter

• Clear Console → Ctrl+L

• Restart the current R session → Ctrl + Shift + F10

• Search the command history from the Console → Ctrl + [up arrow])

• Quickly Find Files and Functions → Ctrl + .

• Open Files → Ctrl+O

• New File R Script → Ctrl+Shift+N

R Markdown

• Insert R chunk → Ctrl+Alt+I

Additional

• Find and Add Next → Ctrl + D

General Introduction to R

R & RStudio

Apa itu R ?

Bahasa pemrograman sekaligus software yang memungkinkan pengolahan data secara statistik (statistical computing) → But it’s more than that: supporting the whole data science flow + other purposes

source: https://www.storybench.org/getting-started-with-tidyverse-in-r

Why Learn R?

• free & open source
• cross platform → Windows, Linux, MacOS
• multi purposes → not only for computational statistics.
• outstanding visualization → ggplot & Shiny.
• intuitive language.
• vast community and package ecosystem
  • you can almost find what you need in The Comprehensive R Archive Network (CRAN)
• used both in academic and industrial field.

R & RStudio: How Do They Relate?

• R : Engine, RStudio : Dashboard
• RStudio is essentially a user-friendly interface for R

Instalasi R & RStudio

• Install R
  • download R from https://cran.r-project.org/
  • install
• Install RStudio:
  • download RStudio Desktop from https://www.rstudio.com/products/rstudio/
  • Install
• For non Windows OS (Linux or MacOS), install R & RStudio using package manager or terminal.

RStudio cheatsheet collections: https://www.rstudio.com/resources/cheatsheets/

R Studio

• IDE (Integrated Development Environment)
• editor dengan fitur yang lengkap untuk mendukung pembangunan suatu script atau package R dengan lebih produktif.
• 4 quadrants → can be arranged using menu ‘View’

Working Directory

• check your current working directory
  • ketik getwd()
• set your working directory
  • setwd(directory_path)
  • e.g: setwd(‘/run/media/DATA/myR/’)
• Check your R version → R.version

Tambahan :

R Project An R project enables your work to be bundled in a portable, self-contained folder. Within the project, all the relevant scripts, data files, figures/outputs, and history are stored in sub-folders and importantly - the working directory is the project’s root folder.

Writing Your First R Code

Start Writing The Code + Help

• Create a new R file: File > New File > R Script
• Let’s start with playing with various R operators

# Print greeting
print("Welcome to R!")

[1] "Welcome to R!"

# Help
# ?thingstosearch

?print()
?print()
?cbind()

print("R is the coolest subject I've ever learned")

[1] "R is the coolest subject I've ever learned"

"R is the coolest subject I've ever learned"

[1] "R is the coolest subject I've ever learned"

# 'R is the coolest subject I've ever learned' #ERROR

R Packages

Collections of functions written by R’s talented community of developers.

Memperkaya fungsionalitas R dalam mengolah data.

contoh: tidyverse, ggplot, and RMySQL. → anything else??

• INSTALL → get the packages available in your R environment

  • From https://cran.r-project.org .

    • install.packages(package_name)

    • or using GUI

  • From GitHub

    • install.packages(“devtools”)
    • devtools::install_github(“hadley/babynames”)

• LOAD → get the package ready for our needs.

  • library(package_name)
  • or using GUI

• See what packages we have in our R environment:

  • installed.packages()
  • library()

• UNINSTALL PACKAGE → remove.packages(package_name)

• UNLOAD PACKAGE → detach(NAMA_PACKAGE, unload=true) or using GUI

try to install & load a package:

1. readxl
2. RMySQL
3. mongolite
4. jsonlite
5. googlesheets4
6. haven
7. foreign

# Install Package

## Install package from CRAN
# install.packages('dplyr')

## Install package from github
# install.packages('devtools')
# devtools::install_github('hadley/babynames')

## List installed package
# installed.packages()

Operators

Arithmetic Operators

• + : addition
• - : substraction
• * : multiply
• / : division
• ^ : power
• %%: modulo

example

a <- 81
b <- 9
x1 <- a + b
x2 <- a - b
x3 <- b * b
x4 <- a / b
x5 <- b ^ 2

x <- 1:4
y <- 6:9
z <- x+y

Relational operators

• == : equals to (note the double equals sign)
• != : not equals to
• > : greater than
• >= : greater than or equal to
• < : less than
• <= : less than or equal to

example

a <- 81
b <- 9

a == b

[1] FALSE

a <= b 

[1] FALSE

a > b   

[1] TRUE

a - 72 == b

[1] TRUE

a - 72 > b

[1] FALSE

a - 72 >= b

[1] TRUE

x <- 1:4
x > 2

[1] FALSE FALSE  TRUE  TRUE

Logical operators

• ! NOT
• & AND
• | OR

example

a <- 81
b <- 9

a != b

[1] TRUE

!(a == b)

[1] TRUE

(a - 72 == b) | (a - 72 > b)

[1] TRUE

(a - 72 == b) & (a - 72 > b)

[1] FALSE

Mathematical + String functions

Mathematical

• cos() : cosine
• exp() : exponential
• log10() : logarithm (base 10)
• log() : logarithm (base e)
• sqrt() : square-root of 2
• round() : round to decimal places
• signif() : round to certain significant figures
• floor() : round down
• abs() : absolute value

String

• paste()

example:

sqrt(16)

[1] 4

str1 = 'Hello'
str2 = 'World!'

# concatenate two strings using paste function
paste(str1,str2)

[1] "Hello World!"

Variables

• nama variable bersifat case-sensitive
• tidak boleh diawali dengan angka/simbol.
• jika nama > 1 kata, sambung dengan -, _, atau .
• Assignment atau pemberian nilai pada variable menggunakan operator <- atau =
• yang bisa di-variablekan:
  • angka
  • text
  • object
  • formula, etc.
• Tidak boleh menggunakan simbol seperti ^, !, $, @, +, -, /, %, or *:

## Assign variable
a <- 10
b <- 8

c <- a + b
d <- a ^ b
i <- sqrt(25)
j <- round(0.34567)
k <- factorial(5)

e <- 'Hello'
f <- 'World'
g <- paste(e, f)
g2 <- paste(e, f, sep=",")

Data Types

• Tunggal (atomic)
  • character
  • numeric
  • categorical
  • logical (boolean)
  • Integer
  • date
  • Complex
  • Raw
• Untuk melihat tipe data, gunakan fungsi class( ) atau typeof( ).
• Untuk menguji tipe atomic di atas dari suatu data, maka gunakan
  • is.integer is.numeric is.character is.complex is.logical
• Non Tunggal
  • 1D
    • Vector → semua element harus bertipe sama → v <- c(1, 2, 3, 4, 5)
    • List → element tidak harus bertipe sama.
      • l1 <- list(1, 2, “a”, “b”)
      • l2 <- list(1, “a”, 3, TRUE, c(5, 6, 7))
    • Factor → kategorik → f <- factor(c("single", "married", "married", "single"));
  • 2D
    • table-like → Matrix, Dataframe, Tibble,

• vector

  is what is called an array in all other programming languages except R — a collection of cells with a fixed size where all cells hold the same type (integers or characters or reals or whatever).

• list

  can hold items of different types and the list size can be increased on the fly. List contents can be accessed either by index (like mylist[[1]]) or by name (like mylist$age).

• matrix

  is a two-dimensional vector (fixed size, all cell types the same).

• array

  is a vector with one or more dimensions. So, an array with one dimension is (almost) the same as a vector. An array with two dimensions is (almost) the same as a matrix. An array with three or more dimensions is an n-dimensional array.

• data frame

  is called a table in most languages. Each column holds the same type, and the columns can have header names.

Example vector code:

v = c(1:3)  # a vector with [1.0 2.0 3.0]
cat(v, "\n\n")

1 2 3 

v = vector(mode="integer", 4)  # [0 0 0 0]
cat(v, "\n\n")

0 0 0 0 

v = c("a", "b", "x")
cat(v, "\n\n")

a b x 

Example list code:

ls = list("a", 2.2)
ls[3] = as.integer(3)
print(ls)

[[1]]
[1] "a"

[[2]]
[1] 2.2

[[3]]
[1] 3

cat(ls[[2]], "\n\n")

2.2 

ls = list(name="Smith", age=22)
cat(ls$name, ":", ls$age)

Smith : 22

Example matrix code:

m = matrix(0.0, nrow=2, ncol=3) # 2x3
print(m)

     [,1] [,2] [,3]
[1,]    0    0    0
[2,]    0    0    0

Example array code:

arr = array(0.0, 3)  # [0.0 0.0 0.0]
print(arr)

[1] 0 0 0

arr = array(0.0, c(2,3))  # 2x3 matrix
print(arr)

     [,1] [,2] [,3]
[1,]    0    0    0
[2,]    0    0    0

arr = array(0.0, c(2,5,4)) # 2x5x4 n-array
# print(arr)  # 40 values displayed

Example data frame code:

people = c("Alex", "Barb", "Carl") # col 1
ages = c(19, 29, 39)  # col 2
df = data.frame(people, ages)  # create
names(df) = c("NAME", "AGE")  # headers
print(df)

Vector

h <- 1:10
h_mult <- h*5

# get n-th element
h_mult[1]

[1] 5

# subset vector
h_mult[2:4]

[1] 10 15 20

# subsetting with subset()
subset(h_mult, h_mult > 20)

[1] 25 30 35 40 45 50

h <- c(1, 2, 3, 4, 5)
h2 <- c(1:5)

h_mult <- h*5

# get n-th element
h_mult[1]

[1] 5

# subset vector
h_mult[2:4]

[1] 10 15 20

# subsetting with subset()
subset(h_mult, h_mult > 20)

[1] 25

# menggunakan c( )
x <- c(1:10)
x <- c(1,2,3,4,5,6,7,8,9,10)

# menggunakan seq()
x <- seq(1,10,by=1)

# menggabungkan vector dengan rbind() dan cbind()
h <- c(1, 2, 3, 4, 5)
i <- c(2, 5)
rbind(h, i) # by row

Warning: number of columns of result is not a multiple of vector length (arg 2)

  [,1] [,2] [,3] [,4] [,5]
h    1    2    3    4    5
i    2    5    2    5    2

cbind(h, i) # by column

Warning: number of rows of result is not a multiple of vector length (arg 2)

     h i
[1,] 1 2
[2,] 2 5
[3,] 3 2
[4,] 4 5
[5,] 5 2

x <- c(1:5)
y <- c(6:10)
cbind(x, y)

     x  y
[1,] 1  6
[2,] 2  7
[3,] 3  8
[4,] 4  9
[5,] 5 10

rbind(x, y)

  [,1] [,2] [,3] [,4] [,5]
x    1    2    3    4    5
y    6    7    8    9   10

Mathematical Function

c <- c(1:10)
m <- mean(c)
m

[1] 5.5

List

• Element di dalam-nya bisa berbeda tipe dan ukuran berbeda.

• Element bisa tunggal, bisa juga berupa another list.

• Dibuat dengan menggunakan fungsi list().

• contoh:

```r
varlist <- list(nama="Pandora", jumlahbulan=4, bobotkelas=c(4,3,5,4))
varlist
```

```
$nama
[1] "Pandora"

$jumlahbulan
[1] 4

$bobotkelas
[1] 4 3 5 4
```

• Akses isi list:

  • Menggunakan posisi indeks

    • kurung siku tunggal [ ] untuk mendapatkan list
    • kurung siku ganda [[ ]] untuk mendapatkan elemen dari list

  • Menggunakan operator $ berindex nama untuk mendapatkan element

• unlist() → mengubah list menjadi vector

varlist <- list(nama="Pandora", jumlahbulan=4, bobotkelas=c(4,3,5,4))
varlist

$nama
[1] "Pandora"

$jumlahbulan
[1] 4

$bobotkelas
[1] 4 3 5 4

varlist[3]

$bobotkelas
[1] 4 3 5 4

varlist[[3]]

[1] 4 3 5 4

varlist$bobotkelas

[1] 4 3 5 4

# does not have to be the same type
list_a <- list("a", "b", "c")
list_a

[[1]]
[1] "a"

[[2]]
[1] "b"

[[3]]
[1] "c"

list_b <- list(1, 2, 3)
list_b

[[1]]
[1] 1

[[2]]
[1] 2

[[3]]
[1] 3

# ----------------------

list_c <- list(1, "a", TRUE)
list_c

[[1]]
[1] 1

[[2]]
[1] "a"

[[3]]
[1] TRUE

list_c[1]

[[1]]
[1] 1

list_c[[1]]

[1] 1

# ----------------------

list_d <- list(a = "x", b = "y", c = "z")
list_d

$a
[1] "x"

$b
[1] "y"

$c
[1] "z"

list_d["a"]

$a
[1] "x"

list_d[["a"]]

[1] "x"

list_d$a

[1] "x"

Factor

# categoric

# levelnya dari urutan alphabet
fact_a <- factor(c("zebra", "beruang", "macan"))
# levelnya ditentukan
fact_b <- factor(c("zebra", "beruang", "macan"), levels = c("macan", "beruang", "zebra"))

fact_a

[1] zebra   beruang macan  
Levels: beruang macan zebra

fact_b

[1] zebra   beruang macan  
Levels: macan beruang zebra

# levelnya urutan angka
fact_c <- factor(c(5, 10, 2))
fact_c

[1] 5  10 2 
Levels: 2 5 10

factor(c(50, 10, "macan"))

[1] 50    10    macan
Levels: 10 50 macan

Matrix

matrix_a = matrix(
  c(1, 2, 3, 4, 5, 6, 7, 8, 9),
  nrow = 3,  
  ncol = 3,
)
matrix_a

     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9

matrix_b = matrix(
  c(1, 2, 3, 4, 5, 6, 7, 8, 9),
  nrow = 3,  
  ncol = 3, 
  # By default matrices are in column-wise order
  byrow = T         
)
matrix_b

     [,1] [,2] [,3]
[1,]    1    2    3
[2,]    4    5    6
[3,]    7    8    9

# Naming rows
rownames(matrix_a) = c("a", "b", "c")
# Naming columns
colnames(matrix_a) = c("d", "e", "f")

matrix_a

  d e f
a 1 4 7
b 2 5 8
c 3 6 9

# Naming rows
rownames(matrix_b) = c("a", "b", "c")
# Naming columns
colnames(matrix_b) = c("c", "d", "e")

matrix_b

  c d e
a 1 2 3
b 4 5 6
c 7 8 9

# Naming rows
rownames(matrix_b) = c("umur", "jumlah anak", "c")
# Naming columns
colnames(matrix_b) = c("bla", "bli", "blu")

matrix_b

            bla bli blu
umur          1   2   3
jumlah anak   4   5   6
c             7   8   9

Data Frame

Struktur dua dimensi seperti table dimana bisa terdiri dari beberapa kolom dan tiap kolom memiliki tipe data yang sama, dan total baris tiap kolom haruslah sama.

• terdiri dari beberapa kolom

• tipe data yang sama

• total baris tiap kolom harus sama

• Membuat data frame menggunakan fungsi data.frame

```r
data.transaksi <- data.frame( 
  kode_transaksi = c(1:5), 
  nama = c("Ari","Budi","Celine","Darmin","Erik") 
)

data.transaksi
```

<div data-pagedtable="false">
  <script data-pagedtable-source type="application/json">
{"columns":[{"label":["kode_transaksi"],"name":[1],"type":["int"],"align":["right"]},{"label":["nama"],"name":[2],"type":["chr"],"align":["left"]}],"data":[{"1":"1","2":"Ari"},{"1":"2","2":"Budi"},{"1":"3","2":"Celine"},{"1":"4","2":"Darmin"},{"1":"5","2":"Erik"}],"options":{"columns":{"min":{},"max":[10],"total":[2]},"rows":{"min":[10],"max":[10],"total":[5]},"pages":{}}}
  </script>
</div>

• Akses isi data frame:

  • $ operator: Mengambil data pada kolom setelah operator $.
  • [m]: Mengambil kolom m.
  • [m, ]: Mengambil baris m, all columns.
  • [c(m,n),]: Mengambil baris m dan n, all columns.
  • [c(m:n),]: Mengambil baris m sampai n, all columns.

employee <- c('John Doe','Peter Gynn','Jolie Hope')
salary <- c(21000, 23400, 26800)
startdate <- as.Date(c('2010-11-1','2008-3-25','2007-3-14'))

employ.data <- data.frame(employee, salary, startdate)
employ.data

# View(employ.data) # must Capital

data(mtcars)
dim(mtcars)
mtcars[c(3:5), ]

Tibble

# tidyverse's dataframe
library("tidyverse")

── Attaching core tidyverse packages ───────────────────────────────────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.0     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.1     ✔ tibble    3.2.0
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.1     ── Conflicts ─────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

employ.data <- as_tibble(employ.data)
employ.data

Check Data Types + Data Type Conversion

a <- 10
b <- c(1, 2, 3, 4, 5)

# data types
class(a)

[1] "numeric"

class(b)

[1] "numeric"

# structure
str(a)

 num 10

str(b)

 num [1:5] 1 2 3 4 5

# data types
x <- c(1, "a", 3, TRUE)
typeof(x)

[1] "character"

# check if data types -> is.*
is.numeric(10)

[1] TRUE

x <- c(1, 2, 3, 5)
class(x)

[1] "numeric"

typeof(x)

[1] "double"

# Data Type Conversion -> as.*
a = 100
str_a <- as.character(a)
num_a <- as.numeric(str_a)

as.numeric(c("-.1", " 2.7 ", "B"))

Warning: NAs introduced by coercion

[1] -0.1  2.7   NA

Acquiring & Inspecting Data in R

How to Acquire Data in R

1. Internal

   • Embedded datasets in RStudio:

     • data() → from RStudio

     • data(package = .packages(all.available = TRUE)) → from packages installed in RStudio.

   • Create your own:

     • vector → c( )

       • tiga_angka <- c(1, 2, 3)

       • index start from 1 (not 0)

     • teks → diapit quote ” ”

       • teks <- "halo DQLab"

     • dataframe()

2. External (import)

External Data

• Jenis:
  • text-based
    • csv
    • other delimiter → read_delim()
  • excel → perlu install package readxl
  • json → perlu install package jsonlite
  • mysql → perlu install package RMySQL atau RMariaDB
  • mongoDB → perlu install package mongolite
  • googlesheets → perlu install package googlesheets4
  • SPSS, SAS, STATA → perlu install package haven atau foreign
  • etc.
• Input:
  • local file → defined by local path
  • from www → defined by URL

Embedded datasets

# data()
# data(mtcars)
force(mtcars)

Data Frame

## Creating Data Frame
employee <- c('John Doe','Peter Gynn','Jolie Hope')
salary <- c(21000, 23400, 26800)
startdate <- as.Date(c('2010-11-1','2008-3-25','2007-3-14'))

employ.data <- data.frame(employee, salary, startdate)
str(employ.data)

'data.frame':   3 obs. of  3 variables:
 $ employee : chr  "John Doe" "Peter Gynn" "Jolie Hope"
 $ salary   : num  21000 23400 26800
 $ startdate: Date, format: "2010-11-01" "2008-03-25" "2007-03-14"

Import From CSV

library(readr)

# tidyverse -> read_csv
flavors_of_cacao <- read_csv('data/flavors_of_cacao.csv')

Rows: 1795 Columns: 9── Column specification ─────────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (6): Company 
(Maker-if known), Specific Bean Origin
or Bar Name, Cocoa
Percent, Company
Location, Be...
dbl (3): REF, Review
Date, Rating
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.

# base (bawaan R) -> read.csv
flavors_of_cacao <- read.csv('data/flavors_of_cacao.csv')

flavors_of_cacao

Import From Excel

library(readxl)
flavors_of_cacao <- read_xlsx('data/flavors_of_cacao.xlsx')

New names:

flavors_of_cacao

Import From JSON

library(jsonlite)

Warning: package ‘jsonlite’ was built under R version 4.2.3
Attaching package: ‘jsonlite’

The following object is masked from ‘package:purrr’:

    flatten

flavors_of_cacao <- fromJSON('data/flavors_of_cacao.json')
flavors_of_cacao

Import From Google Sheets

library(gsheet)

Warning: package ‘gsheet’ was built under R version 4.2.3

mtcars <- gsheet2tbl('docs.google.com/spreadsheets/d/1I9mJsS5QnXF2TNNntTy-HrcdHmIF9wJ8ONYvEJTXSNo')
mtcars

Import From Mongodb

# mongodb+srv://<username>:<password>@cluster0.uqpkp.mongodb.net/myFirstDatabase?retryWrites=true&w=majority

# library(mongolite)
# url <- "mongodb+srv://dqlab:wguifGPUKQZDYX6@cluster0.uqpkp.mongodb.net/dqlab?retryWrites=true&w=majority"
# flavors_of_cacao_4 <- mongo("flavors_of_cacao", url = url)$find()

Import From MySql/MariaDb

# library(RMariaDB)
# con <- dbConnect(
#   RMariaDB::MariaDB(), host = "0.0.0.0", port = 3307, username = "user", 
#   password = "password", dbname = "database")
# res <- dbSendQuery(con, "SELECT * FROM v2021_statement")
# mysql_data <- dbFetch(res)
# dbClearResult(res)

# library(RMySQL)
# con <- dbConnect(
#   RMySQL::MySQL(), host = "localhost", port = 3306, username = "root", 
#   password = "nurimammasri", dbname = "training")
# rs <- dbSendQuery(con, "SELECT * FROM ms_cabang")
# mysql_data <- dbFetch(rs)
# str(mysql_data)

Exercise

# 1. Read dataset from https://github.com/owid/covid-19-data/raw/master/public/data/vaccinations/vaccinations.csv into dataframe
vaccinations <- read_csv('https://github.com/owid/covid-19-data/raw/master/public/data/vaccinations/vaccinations.csv', show_col_types = FALSE)

# 2. read dataset from https://raw.githubusercontent.com/erikaris/dataset/main/indonesia_prov_iso.json
indonesia_prov_iso <- fromJSON('https://raw.githubusercontent.com/erikaris/dataset/main/indonesia_prov_iso.json')

# 3. read iris dataset from https://docs.google.com/spreadsheets/d/1fI9kwibZTpOGPGcTk30TJG740AMyB1KGRsRNrHFUPEw
iris <- gsheet2tbl('https://docs.google.com/spreadsheets/d/1fI9kwibZTpOGPGcTk30TJG740AMyB1KGRsRNrHFUPEw')

# 4. read mysql db from your previous sessions using RMariaDB. 
library(RMySQL)

Warning: package ‘RMySQL’ was built under R version 4.2.3Loading required package: DBI

con <- dbConnect(
  RMySQL::MySQL(), host = "localhost", port = 3306, username = "root", 
  password = "nurimammasri", dbname = "training")
rs <- dbSendQuery(con, "SELECT * FROM ms_cabang")
mysql_data <- dbFetch(rs)
str(mysql_data)

'data.frame':   500 obs. of  3 variables:
 $ kode_cabang: chr  "CABANG-001" "CABANG-002" "CABANG-003" "CABANG-004" ...
 $ nama_cabang: chr  "PHI Mini Market - Lhokseumawe 01" "PHI Mini Market - Bau-Bau 01" "PHI Mini Market - Bogor 01" "PHI Mini Market - Medan 01" ...
 $ kode_kota  : chr  "KOTA-003" "KOTA-083" "KOTA-039" "KOTA-007" ...

# con <- dbConnect(
#   RMariaDB::MariaDB(), host = "127.0.0.1", port = 3306, username = "root", dbname = "minimart")
# res <- dbSendQuery(con, "SELECT * FROM ms_people")
# mysql_data <- dbFetch(res)

Inspecting Your DataFrame

• look the whole data: type the data name or View()

• Look part of the data:

  • head() -> menampilkan 5 data pertama
  • tail() -> menampilkan 5 data terakhir
  • glimpse() -> menampilkan 5 data pertama
  • str() -> menampilkan struktur

• Look at the dimension

  • dim()
  • nrow()
  • ncol()
  • length()

• Look at the structure:

  • str()
  • class()
  • typeof()
  • names()
  • nchar()

• Tambahan

  • table()

iris <- read.csv('data/iris_dataset.csv')
iris

# Look the whole data: type the data name or View()
# View(iris)

# . Look part of the data:
head(mtcars)

tail(mtcars)

# . Look at the structure:
library(dplyr)
glimpse(mtcars)

Rows: 32
Columns: 11
$ mpg  <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4…
$ cyl  <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8, 8, 8, 8, 4, 4, 4, 8, 6, 8, 4
$ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 167.6, 167.6, 275.8, 275.8, 275…
$ hp   <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180, 205, 215, 230, 66, 52, 65, …
$ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92, 3.07, 3.07, 3.07, 2.93, 3.00…
$ wt   <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.440, 3.440, 4.070, 3.730, 3.7…
$ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18.30, 18.90, 17.40, 17.60, 18.…
$ vs   <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1
$ am   <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1
$ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 5, 4
$ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2, 2, 4, 2, 1, 2, 2, 4, 6, 8, 2

str(mtcars)

spc_tbl_ [32 × 11] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ mpg : num [1:32] 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
 $ cyl : num [1:32] 6 6 4 6 8 6 8 4 4 6 ...
 $ disp: num [1:32] 160 160 108 258 360 ...
 $ hp  : num [1:32] 110 110 93 110 175 105 245 62 95 123 ...
 $ drat: num [1:32] 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
 $ wt  : num [1:32] 2.62 2.88 2.32 3.21 3.44 ...
 $ qsec: num [1:32] 16.5 17 18.6 19.4 17 ...
 $ vs  : num [1:32] 0 0 1 1 0 1 0 1 1 1 ...
 $ am  : num [1:32] 1 1 1 0 0 0 0 0 0 0 ...
 $ gear: num [1:32] 4 4 4 3 3 3 3 4 4 4 ...
 $ carb: num [1:32] 4 4 1 1 2 1 4 2 2 4 ...
 - attr(*, "spec")=
  .. cols(
  ..   mpg = col_double(),
  ..   cyl = col_double(),
  ..   disp = col_double(),
  ..   hp = col_double(),
  ..   drat = col_double(),
  ..   wt = col_double(),
  ..   qsec = col_double(),
  ..   vs = col_double(),
  ..   am = col_double(),
  ..   gear = col_double(),
  ..   carb = col_double()
  .. )
 - attr(*, "problems")=<externalptr> 

# . Look at the dimension
dim(iris)

[1] 150   5

nrow(iris)

[1] 150

ncol(iris)

[1] 5

length(iris)

[1] 5

class(iris)

[1] "data.frame"

typeof(iris)

[1] "list"

names(iris)

[1] "sepal.length..cm." "sepal.width..cm."  "petal.length..cm." "petal.width..cm." 
[5] "target"           

employee <- c('John Doe','Peter Gynn','Jolie Hope')
salary <- c(21000, 23400, 26800)
startdate <- as.Date(c('2010-11-1','2008-3-25','2007-3-14'))

employ.data <- data.frame(employee, salary, startdate)
table(employ.data)

, , startdate = 2007-03-14

            salary
employee     21000 23400 26800
  John Doe       0     0     0
  Jolie Hope     0     0     1
  Peter Gynn     0     0     0

, , startdate = 2008-03-25

            salary
employee     21000 23400 26800
  John Doe       0     0     0
  Jolie Hope     0     0     0
  Peter Gynn     0     1     0

, , startdate = 2010-11-01

            salary
employee     21000 23400 26800
  John Doe       1     0     0
  Jolie Hope     0     0     0
  Peter Gynn     0     0     0