UTS EDA

library(ggplot2)

diamonds

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

titanic selamat

library(titanic)

Titanic <- titanic_train

total_selamat <- sum(Titanic$Survived)
print(paste("Total penumpang yang selamat adalah:", total_selamat))

## [1] "Total penumpang yang selamat adalah: 342"

ddata faithful

data(faithful)
head(faithful)

##   eruptions waiting
## 1     3.600      79
## 2     1.800      54
## 3     3.333      74
## 4     2.283      62
## 5     4.533      85
## 6     2.883      55

cor(faithful$eruptions, faithful$waiting)

## [1] 0.9008112

plot(faithful$eruptions, faithful$waiting,
     main = "Scatter Plot Eruptions vs Waiting",
     xlab = "Durasi Erupsi",
     ylab = "Waktu Tunggu",
     pch = 19)
abline(lm(waiting ~ eruptions, data = faithful), col = "red")

data chickweight

data("ChickWeight")

ggplot(data = ChickWeight, aes(x = Time, y = weight, group = Chick, color = Diet)) +
  geom_line(alpha = 0.5) + # Menampilkan garis tren setiap anak ayam
  geom_smooth(aes(group = 1), method = "loess", color = "black", se = FALSE) + # Garis tren rata-rata
  labs(title = "Tren Pertumbuhan Berat Anak Ayam",
       subtitle = "Berdasarkan Waktu dan Jenis Diet",
       x = "Waktu (Hari)",
       y = "Berat (gram)") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

eda dalam 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

dim(mtcars)

## [1] 32 11

plot(mtcars$hp, mtcars$mpg, main="Hubungan HP vs MPG", xlab="Horsepower", ylab="Miles per Gallon")

missing value

sum(is.na(airquality$Ozone))

## [1] 37

airquality$Ozone[is.na(airquality$Ozone)] <- median(airquality$Ozone, na.rm = TRUE)

sum(is.na(airquality$Ozone))

## [1] 0

head(airquality$Ozone)

## [1] 41.0 36.0 12.0 18.0 31.5 28.0

diamonds

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"

hubungan dalam mpg dan cyl

korelasi <- cor(mtcars$mpg, mtcars$cyl)
print(korelasi)

## [1] -0.852162

membedakan distribusi sepal.leght antar species dalam dataset iris

data(iris)
ggplot(iris, aes(x = Species, y = Sepal.Length, fill = Species)) +
  geom_boxplot() +
  theme_minimal() +
  labs(title = "Box Plot Sepal Length per Spesies")