UTS EDA
Rafael Fariid Nurwimaya (2504220022)
2026-04-08
Data titanic
data("Titanic")
# Menampilkan jumlah penumpang berdasarkan status selamat
survival_count <- margin.table(Titanic, 4)
survival_count## Survived
## No Yes
## 1490 711# Menampilkan total penumpang yang selamat
survival_count["Yes"]## Yes
## 711SUM Titanic
data("Titanic")
titanic_df <- as.data.frame(Titanic)
sum(titanic_df$Freq[titanic_df$Survived == "Yes"])## [1] 711Hubungan Durasi Erupsi vs Waktu Tunggu
# 1. Memanggil dataset
data(faithful)
# 2. Menghitung Korelasi (Pearson)
korelasi <- cor(faithful$eruptions, faithful$waiting)
print(paste("Nilai Korelasi:", korelasi))## [1] "Nilai Korelasi: 0.900811168321813"# 3. Membuat Visualisasi untuk melihat hubungan
library(ggplot2)
ggplot(faithful, aes(x = eruptions, y = waiting)) +
geom_point(color = "blue") +
geom_smooth(method = "lm", col = "red") +
labs(title = "Hubungan Durasi Erupsi vs Waktu Tunggu",
x = "Durasi Erupsi (menit)",
y = "Waktu Tunggu (menit)")## `geom_smooth()` using formula = 'y ~ x'
Distribusi Harga Berlian berdasarkan Kualitas Potongan
library(ggplot2)
# Memastikan data diamonds terload
data("diamonds")
# Membuat Box Plot untuk melihat distribusi harga berdasarkan cut
ggplot(diamonds, aes(x = cut, y = price, fill = cut)) +
geom_boxplot() +
labs(title = "Distribusi Harga Berlian berdasarkan Kualitas Potongan (Cut)",
x = "Kualitas Potongan (Cut)",
y = "Harga (Price)") +
theme_minimal()
Menangani Missing Value di kolom Ozone dalam dataset airquality
# Memanggil data
data(airquality)
# Menghitung median kolom Ozone (na.rm = TRUE agar NA tidak ikut dihitung)
median_ozone <- median(airquality$Ozone, na.rm = TRUE)
# Mengisi NA dengan median tersebut
airquality$Ozone[is.na(airquality$Ozone)] <- median_ozone
# Cek apakah masih ada NA
sum(is.na(airquality$Ozone))## [1] 0Membedakan distribusi Sepal. length antar Species dalam dataset Iris
# Load data
data("iris")
# Lihat struktur data
str(iris)## '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 ...# Ringkasan statistik per Species
aggregate(Sepal.Length ~ Species, data = iris, summary)## Species Sepal.Length.Min. Sepal.Length.1st Qu. Sepal.Length.Median
## 1 setosa 4.300 4.800 5.000
## 2 versicolor 4.900 5.600 5.900
## 3 virginica 4.900 6.225 6.500
## Sepal.Length.Mean Sepal.Length.3rd Qu. Sepal.Length.Max.
## 1 5.006 5.200 5.800
## 2 5.936 6.300 7.000
## 3 6.588 6.900 7.900# Visualisasi box plot
boxplot(Sepal.Length ~ Species, data = iris,
main = "Distribusi Sepal.Length antar Species",
xlab = "Species",
ylab = "Sepal.Length",
col = c("lightblue", "lightgreen", "lightpink"))
Korelasi antara mpg dan cyl dalam dataset mtcars
# Load data
data("mtcars")
# Lihat struktur data
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 ...# Hitung korelasi mpg dan cyl
korelasi <- cor(mtcars$mpg, mtcars$cyl)
# Tampilkan nilai korelasi
cat("Nilai korelasi antara mpg dan cyl:", korelasi, "\n")## Nilai korelasi antara mpg dan cyl: -0.852162# Visualisasi scatter plot
plot(mtcars$cyl, mtcars$mpg,
main = "Scatter Plot mpg vs cyl",
xlab = "Jumlah Silinder (cyl)",
ylab = "Miles per Gallon (mpg)",
pch = 19,
col = "blue")
# Hubungan antara mpg, hp, dan wt
# Load dataset bawaan
data("mtcars")
# Mengetahui struktur data
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 ...# Melihat 6 baris pertama
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# Ringkasan statistik
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# Ukuran dataset
dim(mtcars)## [1] 32 11# Nama kolom
names(mtcars)## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear"
## [11] "carb"pairs(mtcars[, c("mpg", "hp", "wt")],
main = "Hubungan antara mpg, hp, dan wt")
tipe data dari kolom cut pada dataset diamonds
# Load library
library(ggplot2)
# Lihat struktur kolom cut
str(diamonds$cut)## Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...# Lihat class kolom cut
class(diamonds$cut)## [1] "ordered" "factor"# Lihat level kategori
levels(diamonds$cut)## [1] "Fair" "Good" "Very Good" "Premium" "Ideal"Tren berat anak ayam dari waktu dalam dataset ChickWeight
avg_weight <- aggregate(weight ~ Time, data = ChickWeight, mean)
plot(avg_weight$Time, avg_weight$weight, type = "l",
main = "Tren Rata-rata Berat Anak Ayam terhadap Waktu",
xlab = "Time",
ylab = "Average Weight")
hubungan mpg vs wt
plot(mtcars$wt, mtcars$mpg,
main = "Hubungan mpg vs wt",
xlab = "wt",
ylab = "mpg")