Clustering - Airlines

Normalize the Data

Load data

airlines <- read.csv("AirlinesCluster.csv")
colMeans(airlines)

##         Balance       QualMiles      BonusMiles      BonusTrans 
##    73601.327582      144.114529    17144.846212       11.601900 
##     FlightMiles     FlightTrans DaysSinceEnroll 
##      460.055764        1.373593     4118.559390

Normalize data. Get some column means, max, and min:

library(caret)

## Warning: package 'caret' was built under R version 3.1.3

## Loading required package: lattice
## Loading required package: ggplot2

preproc <- preProcess(airlines)
airlinesNorm <- predict(preproc, airlines)
(colMeans(airlinesNorm))

##         Balance       QualMiles      BonusMiles      BonusTrans 
##    2.748375e-17    2.663813e-17   -3.802077e-17   -7.652564e-17 
##     FlightMiles     FlightTrans DaysSinceEnroll 
##    1.440723e-17    1.217733e-17    6.999624e-17

(apply(airlinesNorm, 2, max))

##         Balance       QualMiles      BonusMiles      BonusTrans 
##       16.186811       14.223084       10.208293        7.746727 
##     FlightMiles     FlightTrans DaysSinceEnroll 
##       21.680292       13.610351        2.022842

(apply(airlinesNorm, 2, min))

##         Balance       QualMiles      BonusMiles      BonusTrans 
##      -0.7303482      -0.1862754      -0.7099031      -1.2080518 
##     FlightMiles     FlightTrans DaysSinceEnroll 
##      -0.3285622      -0.3621226      -1.9933614

Hierarchical Clustering

Generate Dendrogram

distances <- dist(airlinesNorm)
airlineClust <- hclust(distances, method="ward.D")
plot(airlineClust)

Divide into 5 clusters

tree <- cutree(airlineClust, k=5)
airlineClusters <- split(airlinesNorm, tree)
nrow(airlineClusters[[1]])

## [1] 776

Compute average of each variable in each cluster:

airlineUnnormClusters <- split(airlines, tree)
sapply(airlineUnnormClusters, colMeans)

##                            1            2            3            4
## Balance         5.786690e+04 1.106693e+05 1.981916e+05 52335.913594
## QualMiles       6.443299e-01 1.065983e+03 3.034615e+01     4.847926
## BonusMiles      1.036012e+04 2.288176e+04 5.579586e+04 20788.766129
## BonusTrans      1.082345e+01 1.822929e+01 1.966397e+01    17.087558
## FlightMiles     8.318428e+01 2.613418e+03 3.276761e+02   111.573733
## FlightTrans     3.028351e-01 7.402697e+00 1.068826e+00     0.344470
## DaysSinceEnroll 6.235365e+03 4.402414e+03 5.615709e+03  2840.822581
##                            5
## Balance         3.625591e+04
## QualMiles       2.511177e+00
## BonusMiles      2.264788e+03
## BonusTrans      2.973174e+00
## FlightMiles     1.193219e+02
## FlightTrans     4.388972e-01
## DaysSinceEnroll 3.060081e+03

K-means clustering

K-means clustering

set.seed(88)
kmClust <- kmeans(airlinesNorm, centers=5, iter.max=1000)
kmClusters <- split(airlinesNorm, kmClust$cluster)
sum(kmClust$size > 1000)

## [1] 2

Compare cluster centroids to each other:

kmClust$centers

##       Balance   QualMiles BonusMiles BonusTrans FlightMiles FlightTrans
## 1  1.44439706  0.51115730  1.8769284  1.0331951   0.1169945   0.1444636
## 2  1.00054098  0.68382234  0.6144780  1.7214887   3.8559798   4.1196141
## 3 -0.05580605 -0.14104391  0.3041358  0.7108744  -0.1218278  -0.1287569
## 4 -0.13331742 -0.11491607 -0.3492669 -0.3373455  -0.1833989  -0.1961819
## 5 -0.40579897 -0.02281076 -0.5816482 -0.7619054  -0.1989602  -0.2196582
##   DaysSinceEnroll
## 1       0.7198040
## 2       0.2742394
## 3      -0.3398209
## 4       0.9640923
## 5      -0.8897747