Lab6.R

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

#loading data
data <- mtcars
#structure of the dataset
str(data)

## '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 ...

#create kmeans object from the disp, wt, and qsec columns
datakmeans <- kmeans(mtcars[,1:3], centers=4, nstart=10)
#Size of clusters
datakmeans$size

## [1]  8 11  4  9

# Centers of each cluster 
datakmeans$centers

##        mpg      cyl      disp
## 1 20.50000 5.500000 164.08750
## 2 16.19091 7.818182 311.76364
## 3 13.67500 8.000000 443.00000
## 4 27.34444 4.000000  96.55556

#plotting data to see the patterns
plot(data$mpg~data$cyl)

plot(data$mpg~data$hp)

#Average cyl, hp and mpg for each cluster
mtcars %>% 
  mutate(clusters = datakmeans$cluster) %>% 
  group_by(clusters) %>% 
  summarise_each(funs(mean), c(cyl, hp, mpg))

## Warning: funs() is soft deprecated as of dplyr 0.8.0
## Please use a list of either functions or lambdas: 
## 
##   # Simple named list: 
##   list(mean = mean, median = median)
## 
##   # Auto named with `tibble::lst()`: 
##   tibble::lst(mean, median)
## 
##   # Using lambdas
##   list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## This warning is displayed once per session.

## # A tibble: 4 x 4
##   clusters   cyl    hp   mpg
##      <int> <dbl> <dbl> <dbl>
## 1        1  5.5  113.   20.5
## 2        2  7.82 201.   16.2
## 3        3  8    206.   13.7
## 4        4  4     83.6  27.3

#Description of clusters:
#Cluster 1: Cars with 7 cylinder engines, have horsepower of 174 that are designed for efficiency 
#and return an economica 16.8 mpg. These cars are also light in weight.

#Cluster 2: Cars with 4-5 cylinders which are less havier and less powerful than 7-8 cylinders cars, 
#Have less horsepower and weight is also less due to less cylinders, but has highest 24.5 mpg .

#Cluster 3 & 4: These cars have 8 cylinders, these cars have high horsepower, high in weight
#If you see the mpg is not great as less cylinders mpg. Mpg is 16.3 and 11.8 respectively, made for 
#selective customer needs highest horsepower then economical mass.