2+3[1] 57-5[1] 23*5[1] 153/4[1] 0.752:4[1] 2 3 42**3[1] 8Modul 1 Praktikum PSD 2023/2024 Semester Ganjil
Kembali ke Pengantar Sains Data
Versi file .R dari modul ini bisa diunduh: Modul 1.R
Dataset “Iris” yang digunakan di modul ini bisa langsung diakses melalui R, atau bisa juga diunduh:
PART 1: Operasi Dasar
Operasi Dasar. Layaknya matematika pada umumnya, R dapat malakukan operasi dasar.
Cara me-run sebuah program adalah dengan ctrl + Enter
Untuk me-run beberapa program sekaligus, Anda select programnya, lalu ctrl + Enter
Pendefinisian variable pada R dapat menggunakan <- atau =
Cara pendefinisian variable adalah sebagai berikut
apel<- 4
jeruk <- 7Kiri merupakan nama variable dan kanan merupakan nilai variable
Untuk memanggil variable, cukup Anda ketik namanya
apel[1] 4lalu run.
Layaknya sebuah angka, variable tersebut dapat melakukan opreasi dasar
apel+jeruk[1] 11apel-jeruk[1] -3apel*jeruk[1] 28apel/jeruk[1] 0.5714286Variable juga dapat didefinisikan oleh variable variable lainnya
banyakbuah <- jeruk+apel
banyakbuah[1] 11Variable yang telah terdefinisi dapat dilihat pada enviorment (sebelah kanan script)
atau menggunakan
ls() #lihat list variabel[1] "apel" "banyakbuah" "jeruk" untuk menghapus variable, gunakan fungsi rm
rm(banyakbuah) #hapus variabel banyakbuahuntuk menghapus semua variabel gunakan
rm(list=ls())DATA VIZ
Import data
import data iris (dataset built-in nya R)
data("iris")
iris #liat datanya di console Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
3 4.7 3.2 1.3 0.2 setosa
4 4.6 3.1 1.5 0.2 setosa
5 5.0 3.6 1.4 0.2 setosa
6 5.4 3.9 1.7 0.4 setosa
7 4.6 3.4 1.4 0.3 setosa
8 5.0 3.4 1.5 0.2 setosa
9 4.4 2.9 1.4 0.2 setosa
10 4.9 3.1 1.5 0.1 setosa
11 5.4 3.7 1.5 0.2 setosa
12 4.8 3.4 1.6 0.2 setosa
13 4.8 3.0 1.4 0.1 setosa
14 4.3 3.0 1.1 0.1 setosa
15 5.8 4.0 1.2 0.2 setosa
16 5.7 4.4 1.5 0.4 setosa
17 5.4 3.9 1.3 0.4 setosa
18 5.1 3.5 1.4 0.3 setosa
19 5.7 3.8 1.7 0.3 setosa
20 5.1 3.8 1.5 0.3 setosa
21 5.4 3.4 1.7 0.2 setosa
22 5.1 3.7 1.5 0.4 setosa
23 4.6 3.6 1.0 0.2 setosa
24 5.1 3.3 1.7 0.5 setosa
25 4.8 3.4 1.9 0.2 setosa
26 5.0 3.0 1.6 0.2 setosa
27 5.0 3.4 1.6 0.4 setosa
28 5.2 3.5 1.5 0.2 setosa
29 5.2 3.4 1.4 0.2 setosa
30 4.7 3.2 1.6 0.2 setosa
31 4.8 3.1 1.6 0.2 setosa
32 5.4 3.4 1.5 0.4 setosa
33 5.2 4.1 1.5 0.1 setosa
34 5.5 4.2 1.4 0.2 setosa
35 4.9 3.1 1.5 0.2 setosa
36 5.0 3.2 1.2 0.2 setosa
37 5.5 3.5 1.3 0.2 setosa
38 4.9 3.6 1.4 0.1 setosa
39 4.4 3.0 1.3 0.2 setosa
40 5.1 3.4 1.5 0.2 setosa
41 5.0 3.5 1.3 0.3 setosa
42 4.5 2.3 1.3 0.3 setosa
43 4.4 3.2 1.3 0.2 setosa
44 5.0 3.5 1.6 0.6 setosa
45 5.1 3.8 1.9 0.4 setosa
46 4.8 3.0 1.4 0.3 setosa
47 5.1 3.8 1.6 0.2 setosa
48 4.6 3.2 1.4 0.2 setosa
49 5.3 3.7 1.5 0.2 setosa
50 5.0 3.3 1.4 0.2 setosa
51 7.0 3.2 4.7 1.4 versicolor
52 6.4 3.2 4.5 1.5 versicolor
53 6.9 3.1 4.9 1.5 versicolor
54 5.5 2.3 4.0 1.3 versicolor
55 6.5 2.8 4.6 1.5 versicolor
56 5.7 2.8 4.5 1.3 versicolor
57 6.3 3.3 4.7 1.6 versicolor
58 4.9 2.4 3.3 1.0 versicolor
59 6.6 2.9 4.6 1.3 versicolor
60 5.2 2.7 3.9 1.4 versicolor
61 5.0 2.0 3.5 1.0 versicolor
62 5.9 3.0 4.2 1.5 versicolor
63 6.0 2.2 4.0 1.0 versicolor
64 6.1 2.9 4.7 1.4 versicolor
65 5.6 2.9 3.6 1.3 versicolor
66 6.7 3.1 4.4 1.4 versicolor
67 5.6 3.0 4.5 1.5 versicolor
68 5.8 2.7 4.1 1.0 versicolor
69 6.2 2.2 4.5 1.5 versicolor
70 5.6 2.5 3.9 1.1 versicolor
71 5.9 3.2 4.8 1.8 versicolor
72 6.1 2.8 4.0 1.3 versicolor
73 6.3 2.5 4.9 1.5 versicolor
74 6.1 2.8 4.7 1.2 versicolor
75 6.4 2.9 4.3 1.3 versicolor
76 6.6 3.0 4.4 1.4 versicolor
77 6.8 2.8 4.8 1.4 versicolor
78 6.7 3.0 5.0 1.7 versicolor
79 6.0 2.9 4.5 1.5 versicolor
80 5.7 2.6 3.5 1.0 versicolor
81 5.5 2.4 3.8 1.1 versicolor
82 5.5 2.4 3.7 1.0 versicolor
83 5.8 2.7 3.9 1.2 versicolor
84 6.0 2.7 5.1 1.6 versicolor
85 5.4 3.0 4.5 1.5 versicolor
86 6.0 3.4 4.5 1.6 versicolor
87 6.7 3.1 4.7 1.5 versicolor
88 6.3 2.3 4.4 1.3 versicolor
89 5.6 3.0 4.1 1.3 versicolor
90 5.5 2.5 4.0 1.3 versicolor
91 5.5 2.6 4.4 1.2 versicolor
92 6.1 3.0 4.6 1.4 versicolor
93 5.8 2.6 4.0 1.2 versicolor
94 5.0 2.3 3.3 1.0 versicolor
95 5.6 2.7 4.2 1.3 versicolor
96 5.7 3.0 4.2 1.2 versicolor
97 5.7 2.9 4.2 1.3 versicolor
98 6.2 2.9 4.3 1.3 versicolor
99 5.1 2.5 3.0 1.1 versicolor
100 5.7 2.8 4.1 1.3 versicolor
101 6.3 3.3 6.0 2.5 virginica
102 5.8 2.7 5.1 1.9 virginica
103 7.1 3.0 5.9 2.1 virginica
104 6.3 2.9 5.6 1.8 virginica
105 6.5 3.0 5.8 2.2 virginica
106 7.6 3.0 6.6 2.1 virginica
107 4.9 2.5 4.5 1.7 virginica
108 7.3 2.9 6.3 1.8 virginica
109 6.7 2.5 5.8 1.8 virginica
110 7.2 3.6 6.1 2.5 virginica
111 6.5 3.2 5.1 2.0 virginica
112 6.4 2.7 5.3 1.9 virginica
113 6.8 3.0 5.5 2.1 virginica
114 5.7 2.5 5.0 2.0 virginica
115 5.8 2.8 5.1 2.4 virginica
116 6.4 3.2 5.3 2.3 virginica
117 6.5 3.0 5.5 1.8 virginica
118 7.7 3.8 6.7 2.2 virginica
119 7.7 2.6 6.9 2.3 virginica
120 6.0 2.2 5.0 1.5 virginica
121 6.9 3.2 5.7 2.3 virginica
122 5.6 2.8 4.9 2.0 virginica
123 7.7 2.8 6.7 2.0 virginica
124 6.3 2.7 4.9 1.8 virginica
125 6.7 3.3 5.7 2.1 virginica
126 7.2 3.2 6.0 1.8 virginica
127 6.2 2.8 4.8 1.8 virginica
128 6.1 3.0 4.9 1.8 virginica
129 6.4 2.8 5.6 2.1 virginica
130 7.2 3.0 5.8 1.6 virginica
131 7.4 2.8 6.1 1.9 virginica
132 7.9 3.8 6.4 2.0 virginica
133 6.4 2.8 5.6 2.2 virginica
134 6.3 2.8 5.1 1.5 virginica
135 6.1 2.6 5.6 1.4 virginica
136 7.7 3.0 6.1 2.3 virginica
137 6.3 3.4 5.6 2.4 virginica
138 6.4 3.1 5.5 1.8 virginica
139 6.0 3.0 4.8 1.8 virginica
140 6.9 3.1 5.4 2.1 virginica
141 6.7 3.1 5.6 2.4 virginica
142 6.9 3.1 5.1 2.3 virginica
143 5.8 2.7 5.1 1.9 virginica
144 6.8 3.2 5.9 2.3 virginica
145 6.7 3.3 5.7 2.5 virginica
146 6.7 3.0 5.2 2.3 virginica
147 6.3 2.5 5.0 1.9 virginica
148 6.5 3.0 5.2 2.0 virginica
149 6.2 3.4 5.4 2.3 virginica
150 5.9 3.0 5.1 1.8 virginicaView(iris) #liat datanya di window baru
str(iris) #informasi dan tipe data'data.frame': 150 obs. of 5 variables:
$ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
$ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
$ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
$ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
$ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...atau kalo mau import data dari file Iris.csv atau Iris.xlsx
df <- read.csv("./Iris.csv") #janlup dikasih tau parameternya path ya jadi bebasatau pake package readr dan readxl pada R
library(readr)
df <- read_csv("./Iris.csv")Rows: 150 Columns: 5
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (1): Species
dbl (4): Sepal.Length, Sepal.Width, Petal.Length, Petal.Width
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.library(readxl)
df_excel <- read_excel("./Iris.xlsx")
#cara manual agak ribet sehingga direkomendasikan pake fitur import dataset di Rstudio sajaStatistik deskriptif sederhana
deskriptif yg simple dulu
View(df)
dim(df) #cek dimensi[1] 150 5ls(df) #cek nama kolom[1] "Petal.Length" "Petal.Width" "Sepal.Length" "Sepal.Width" "Species" deskriptif setiap kolom
mean(df$Sepal.Length)[1] 5.843333median(df$Sepal.Length)[1] 5.8sum(df$Sepal.Length)[1] 876.5sd(df$Sepal.Length)[1] 0.8280661var(df$Sepal.Length)[1] 0.6856935length(df$Sepal.Length)[1] 150standarerror <- sd(df$Sepal.Length)/sqrt(length(df$Sepal.Length))
sort(df$Sepal.Length) [1] 4.3 4.4 4.4 4.4 4.5 4.6 4.6 4.6 4.6 4.7 4.7 4.8 4.8 4.8 4.8 4.8 4.9 4.9
[19] 4.9 4.9 4.9 4.9 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.1 5.1 5.1 5.1
[37] 5.1 5.1 5.1 5.1 5.1 5.2 5.2 5.2 5.2 5.3 5.4 5.4 5.4 5.4 5.4 5.4 5.5 5.5
[55] 5.5 5.5 5.5 5.5 5.5 5.6 5.6 5.6 5.6 5.6 5.6 5.7 5.7 5.7 5.7 5.7 5.7 5.7
[73] 5.7 5.8 5.8 5.8 5.8 5.8 5.8 5.8 5.9 5.9 5.9 6.0 6.0 6.0 6.0 6.0 6.0 6.1
[91] 6.1 6.1 6.1 6.1 6.1 6.2 6.2 6.2 6.2 6.3 6.3 6.3 6.3 6.3 6.3 6.3 6.3 6.3
[109] 6.4 6.4 6.4 6.4 6.4 6.4 6.4 6.5 6.5 6.5 6.5 6.5 6.6 6.6 6.7 6.7 6.7 6.7
[127] 6.7 6.7 6.7 6.7 6.8 6.8 6.8 6.9 6.9 6.9 6.9 7.0 7.1 7.2 7.2 7.2 7.3 7.4
[145] 7.6 7.7 7.7 7.7 7.7 7.9min(df$Sepal.Length)[1] 4.3max(df$Sepal.Length)[1] 7.9range(df$Sepal.Length)[1] 4.3 7.9library(DescTools)
Mode(df$Sepal.Length) #package DescTools[1] 5
attr(,"freq")
[1] 10plot(density(df$Sepal.Length))
summary(df$Sepal.Length) Min. 1st Qu. Median Mean 3rd Qu. Max.
4.300 5.100 5.800 5.843 6.400 7.900 #alternatif
library(psych)
Attaching package: 'psych'The following objects are masked from 'package:DescTools':
AUC, ICC, SDdescribe(df$Sepal.Length) vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 150 5.84 0.83 5.8 5.81 1.04 4.3 7.9 3.6 0.31 -0.61 0.07#kalo dari 1 kolom doang, skrg langsung keseluruhan variabel dalam data
summary(df) #khusus numerik Sepal.Length Sepal.Width Petal.Length Petal.Width
Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
Median :5.800 Median :3.000 Median :4.350 Median :1.300
Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
Species
Length:150
Class :character
Mode :character
describe(df) vars n mean sd median trimmed mad min max range skew
Sepal.Length 1 150 5.84 0.83 5.80 5.81 1.04 4.3 7.9 3.6 0.31
Sepal.Width 2 150 3.06 0.44 3.00 3.04 0.44 2.0 4.4 2.4 0.31
Petal.Length 3 150 3.76 1.77 4.35 3.76 1.85 1.0 6.9 5.9 -0.27
Petal.Width 4 150 1.20 0.76 1.30 1.18 1.04 0.1 2.5 2.4 -0.10
Species* 5 150 2.00 0.82 2.00 2.00 1.48 1.0 3.0 2.0 0.00
kurtosis se
Sepal.Length -0.61 0.07
Sepal.Width 0.14 0.04
Petal.Length -1.42 0.14
Petal.Width -1.36 0.06
Species* -1.52 0.07Scatter
plot paling dasar: semua variabel numerik menjadi scatter
plot(df)
plot(df$Sepal.Length, df$Sepal.Width)
tambahkan judul pake main
plot(df$Sepal.Length, df$Sepal.Width,
main = "Ini Judul grafiknya")
tambahkan label sumbu
plot(df$Sepal.Length, df$Sepal.Width,
main = "Ini Judul grafiknya",
xlab = "Sumbu X",
ylab = "Sumbu Y")
Histogram
hist(df$Sepal.Length) #standar
hist(df$Sepal.Length, main = "Judul", xlab = "Nilai Sepal Length")
hist(df$Sepal.Length, main = "Judul", xlab = "Nilai Sepal Length", freq = FALSE)
hist(df$Sepal.Length,
main = "Judul",
xlab = "Nilai Sepal Length",
freq = FALSE,
breaks = 20)
hist(df$Sepal.Length,
main = "Judul",
xlab = "Nilai Sepal Length",
freq = FALSE,
breaks = 20,
xlim = c(min(df$Sepal.Length),max(df$Sepal.Length)),
col = "yellow")
hist(df$Sepal.Length, prob = TRUE)
grid(lty = 2, col = "gray", lwd = 1)
grid(nx = NA, ny = NULL, lty = 2, col = "gray", lwd = 1)
lines(density(df$Sepal.Length), lwd = 2, col = 'red')
Boxplot
boxplot(df$Sepal.Length) #1 variabel
boxplot(df$Sepal.Length, df$Sepal.Width) #2 variabel atau lebih
boxplot(df$Sepal.Length, df$Sepal.Width,
main = "Boxplot Perbandingan Sepal Length dan Sepal Width",
names = c("Sepal Length", "Sepal Width")) #tambahkan judul dan xlabel
boxplot(df$Sepal.Length, df$Sepal.Width,
main = "Boxplot Perbandingan Sepal Length dan Sepal Width",
names = c("Sepal Length", "Sepal Width"),
col = c("red", "blue")) #ganti warna
boxplot(df$Sepal.Length, df$Sepal.Width,
main = "Boxplot Perbandingan Sepal Length dan Sepal Width",
names = c("Sepal Length", "Sepal Width"),
col = c("red", "blue"),
horizontal = TRUE) #rotate jadi horizontal
boxplot(df$Sepal.Length ~ df$Species)
boxplot(Sepal.Length ~ Species, data = df)
boxplot(df$Sepal.Length ~ df$Species,
main = "Perbandingan Sepal Length berdasarkan Species",
xlab = "Species",
ylab = "Sepal Length",
col = c("blue","yellow","red"),
notch = TRUE)
Barchart
dummy <- data.frame(name=letters[1:5],
value=sample(seq(4,15),5))barplot(height = dummy$value,
names.arg = dummy$name,
horiz = F,
col = "violet",
width = 1, space = 2, density = 10,
font.axis = 2,
col.axis = "red",
cex.axis = 1)
counts <- table(df$Species)
barplot(counts,
main = "Persebaran Spesies",
xlab = "Spesies", ylab = "Counts")
Piechart
pie(counts,
labels = counts,
col = rainbow(6),
main = "Persebaran Spesies")
pielabels <- round(counts/sum(counts)*100, 2)
pie(counts,
labels = paste0(pielabels, "%"),
col = rainbow(6),
main = "Persebaran Spesies")
legend("topleft", legend = c("setosa","versicolor", "virginica"),
fill = rainbow(6), cex = 0.8)
Line chart
plot(df$Sepal.Length, type = 'l')
plot(df$Sepal.Length, type = 'l', main = "Pergerakan Sepal Length per Waktu",
xlab = "Unit Waktu",
ylab = "Sepal Length",
col = "darkgreen",
lty = 1,
lwd = 2)
lines(df$Sepal.Width, type = "l")
plot(df$Sepal.Length, type = 'l', main = "Perbandingan Pertumbuhan Panjang dan Lebar Kelopak",
xlab = "Unit Waktu",
ylab = "Pengukuran",
col = "darkgreen",
lty = 1,
lwd = 2,
ylim = c(min(df$Sepal.Length, df$Sepal.Width),
max(df$Sepal.Length, df$Sepal.Width)))
lines(df$Sepal.Width,
type = "l",
col = "blue", lwd = 2)
legend("topleft",
legend = c("Panjang", "Lebar"),
col = c("darkgreen", "blue"),
lty = 1, lwd = 2,
bty = "n")
legend(-10,8,
legend = c("Panjang", "Lebar"),
col = c("darkgreen", "blue"),
lty = 1, lwd = 2,
bty = "n")