SOAL NOMOR 2
library(ggplot2)
data("diamonds")
head(diamonds)
## # A tibble: 6 × 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.29 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 6 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48
ggplot(data = diamonds, aes(x = cut, y = price)) +
geom_boxplot(fill = "cornflowerblue", color = "black") +
labs(title = "Distribusi Harga Berlian Berdasarkan Kualitas Potongan (Cut)",
x = "Kualitas Potongan (Cut)",
y = "Harga (USD)") +
theme_minimal()
SOAL NOMOR 4
data("Titanic")
survival_count <- margin.table(Titanic, 4)
survival_count
## Survived
## No Yes
## 1490 711
survival_count["Yes"]
## Yes
## 711
data("Titanic")
titanic_df <- as.data.frame(Titanic)
sum(titanic_df$Freq[titanic_df$Survived == "Yes"])
## [1] 711
SOAL NOMOR 7
library(ggplot2)
str(diamonds$cut)
## Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
class(diamonds$cut)
## [1] "ordered" "factor"
levels(diamonds$cut)
## [1] "Fair" "Good" "Very Good" "Premium" "Ideal"
SOAL NOMOR 12
data("mtcars")
str(mtcars)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
summary(mtcars)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
head(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
library(ggplot2)
ggplot(mtcars, aes(x = wt, y = mpg)) +
geom_point() +
theme_minimal()
cor(mtcars)
## mpg cyl disp hp drat wt
## mpg 1.0000000 -0.8521620 -0.8475514 -0.7761684 0.68117191 -0.8676594
## cyl -0.8521620 1.0000000 0.9020329 0.8324475 -0.69993811 0.7824958
## disp -0.8475514 0.9020329 1.0000000 0.7909486 -0.71021393 0.8879799
## hp -0.7761684 0.8324475 0.7909486 1.0000000 -0.44875912 0.6587479
## drat 0.6811719 -0.6999381 -0.7102139 -0.4487591 1.00000000 -0.7124406
## wt -0.8676594 0.7824958 0.8879799 0.6587479 -0.71244065 1.0000000
## qsec 0.4186840 -0.5912421 -0.4336979 -0.7082234 0.09120476 -0.1747159
## vs 0.6640389 -0.8108118 -0.7104159 -0.7230967 0.44027846 -0.5549157
## am 0.5998324 -0.5226070 -0.5912270 -0.2432043 0.71271113 -0.6924953
## gear 0.4802848 -0.4926866 -0.5555692 -0.1257043 0.69961013 -0.5832870
## carb -0.5509251 0.5269883 0.3949769 0.7498125 -0.09078980 0.4276059
## qsec vs am gear carb
## mpg 0.41868403 0.6640389 0.59983243 0.4802848 -0.55092507
## cyl -0.59124207 -0.8108118 -0.52260705 -0.4926866 0.52698829
## disp -0.43369788 -0.7104159 -0.59122704 -0.5555692 0.39497686
## hp -0.70822339 -0.7230967 -0.24320426 -0.1257043 0.74981247
## drat 0.09120476 0.4402785 0.71271113 0.6996101 -0.09078980
## wt -0.17471588 -0.5549157 -0.69249526 -0.5832870 0.42760594
## qsec 1.00000000 0.7445354 -0.22986086 -0.2126822 -0.65624923
## vs 0.74453544 1.0000000 0.16834512 0.2060233 -0.56960714
## am -0.22986086 0.1683451 1.00000000 0.7940588 0.05753435
## gear -0.21268223 0.2060233 0.79405876 1.0000000 0.27407284
## carb -0.65624923 -0.5696071 0.05753435 0.2740728 1.00000000
SOAL NOMOR 14
library(ggplot2)
data("ChickWeight")
ggplot(ChickWeight, aes(x = Time, y = weight, group = Chick)) +
geom_line(alpha = 0.3) +
labs(title = "Tren Berat Anak Ayam dari Waktu ke Waktu",
x = "Waktu (Hari)",
y = "Berat (Gram)") +
theme_minimal()
SOAL NOMOR 16
library(ggplot2)
data(faithful)
ggplot(faithful, aes(x = eruptions, y = waiting)) +
geom_point(color = "blue") +
geom_smooth(method = "lm", col = "red") +
labs(title = "Hubungan antara Eruptions dan Waiting",
x = "Durasi Erupsi (menit)",
y = "Waktu Tunggu (menit)")
## `geom_smooth()` using formula = 'y ~ x'
cor(faithful$eruptions, faithful$waiting)
## [1] 0.9008112
SOAL NOMOR 17
library(ggplot2)
ggplot(iris, aes(x = Species, y = Sepal.Length, fill = Species)) +
geom_boxplot() +
labs(title = "Perbandingan Distribusi Panjang Sepal Berdasarkan Spesies",
y = "Sepal Length (cm)") +
theme_minimal()
SOAL NOMOR 19
data("mtcars")
head(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
korelasi <- cor(mtcars$mpg, mtcars$cyl)
print(korelasi)
## [1] -0.852162
plot(mtcars$cyl, mtcars$mpg,
main = "Hubungan antara Silinder dan Efisiensi BBM",
xlab = "Jumlah Silinder (cyl)",
ylab = "Miles per Gallon (mpg)",
pch = 19, col = "blue")
abline(lm(mpg ~ cyl, data = mtcars), col = "darkred")
SOAL NOMOR 28
data("airquality")
head(airquality)
## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6
sum(is.na(airquality$Ozone))
## [1] 37
median_ozone <- median(airquality$Ozone, na.rm = TRUE)
airquality$Ozone[is.na(airquality$Ozone)] <- median_ozone
sum(is.na(airquality$Ozone))
## [1] 0
SOAL NOMOR 30
library(ggplot2)
ggplot(mtcars, aes(x = wt, y = mpg)) +
geom_point(size = 3, color = "red") +
geom_smooth(method = "lm", se = FALSE, color = "black") +
labs(title = "Analisis EDA: mpg vs wt",
subtitle = "Dataset mtcars",
x = "Weight (1000 lbs)",
y = "Miles/(US) gallon") +
theme_minimal()
## `geom_smooth()` using formula = 'y ~ x'
