library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
library(ggplot2)
mtcars <- datasets::mtcars
data("mtcars")
mtcars
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
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
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
dim(mtcars)
## [1] 32 11
colnames(mtcars)
## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear"
## [11] "carb"
sum(is.na(mtcars))
## [1] 0
hist(mtcars$mpg, main = "distribusi MPG", xlab="MPG", col="blue")
boxplot(mtcars$hp,main = "Distribusi Horse Power", ylab ="Horsepower", col="green")
plot(mtcars$mpg, mtcars$hp, main = "Scatterplot MPG vs HOrsepower", xlab="MPG", ylab = "horsepower", col="cyan")
cor(mtcars$mpg,mtcars$hp)
## [1] -0.7761684
heatmap(cor(mtcars), main = "Heatmap Korelasi",col=colorRampPalette(c("blue","white","red" ))(100))
pairs(mtcars[,1:4], main= "Pair Plot")
plot(mtcars$mpg, mtcars$hp,col =mtcars$cyl,pch =19,main = "MPG vs Horsepower by Cylinder", xlab="MPG",ylab= "Horsepower")
legend("topright", legend = unique(mtcars$cyl),col = unique(mtcars$cyl),pch = 19)
boxplot(mpg~am,data = mtcars,main="MPG by Transmission",xlab = "Transmission (0= Automatic,1=Manual",ylab = "MPG",col=c("blue","green"))
data("mtcars")
mtcars_selected <- mtcars[, c("mpg","cyl","disp","hp","hp","wt","qsec")]
mtcars_scaled <- scale(mtcars_selected)
wcss<- vector()
for (i in 1:10) {
kmeans_model <- kmeans(mtcars_scaled,centers = i,nstart = 25)
wcss[i] <- kmeans_model$tot.withinss
}
plot(1:10,wcss,type = "b",main = "Elbow Method", xlab = "Numbers of Clusters (K)",ylab = "WCSS", col = "blue")
set.seed(123)
kmeans_result <- kmeans(mtcars_scaled,centers = 3, nstart = 25)
mtcars$cluster <- as.factor(kmeans_result$cluster)
kmeans_result$cluster
## Mazda RX4 Mazda RX4 Wag Datsun 710 Hornet 4 Drive
## 3 3 2 3
## Hornet Sportabout Valiant Duster 360 Merc 240D
## 1 3 1 2
## Merc 230 Merc 280 Merc 280C Merc 450SE
## 2 3 3 1
## Merc 450SL Merc 450SLC Cadillac Fleetwood Lincoln Continental
## 1 1 1 1
## Chrysler Imperial Fiat 128 Honda Civic Toyota Corolla
## 1 2 2 2
## Toyota Corona Dodge Challenger AMC Javelin Camaro Z28
## 2 1 1 1
## Pontiac Firebird Fiat X1-9 Porsche 914-2 Lotus Europa
## 1 2 2 2
## Ford Pantera L Ferrari Dino Maserati Bora Volvo 142E
## 1 3 1 2
library(factoextra)
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
fviz_cluster(kmeans_result, data = mtcars_scaled,
palette = "jco",
geom = "point",
ellipse.type = "convex",
ggtheme = theme_minimal())
pca_result <- prcomp(mtcars_scaled, scale = TRUE)
pca_df <- as.data.frame(pca_result$x)
pca_df$cluster <- as.factor(kmeans_result$cluster)
ggplot(pca_df, aes(x = PC1, y = PC2, color = cluster)) +
geom_point(size = 3) +
ggtitle("Clustering of mtcars Data (K-Means)") +
theme_minimal()
mtcars$cluster <- as.factor(kmeans_result$cluster)
mtcars$cluster <- as.factor(kmeans_result$cluster)
mtcars%>%
group_by(cluster) %>%
summarise(across(everything(), list(mean = mean, sd = sd)))
## # A tibble: 3 × 23
## cluster mpg_mean mpg_sd cyl_mean cyl_sd disp_mean disp_sd hp_mean hp_sd
## <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 15.1 2.56 8 0 353. 67.8 209. 51.0
## 2 2 26.7 4.51 4 0 105. 26.9 82.6 20.9
## 3 3 19.7 1.45 6 0 183. 41.6 122. 24.3
## # ℹ 14 more variables: drat_mean <dbl>, drat_sd <dbl>, wt_mean <dbl>,
## # wt_sd <dbl>, qsec_mean <dbl>, qsec_sd <dbl>, vs_mean <dbl>, vs_sd <dbl>,
## # am_mean <dbl>, am_sd <dbl>, gear_mean <dbl>, gear_sd <dbl>,
## # carb_mean <dbl>, carb_sd <dbl>