The code for supporting market segment business case calculations in Chapter 5, Data Mining with Cluster Analysis, is as follows:

# create dataframe with columns for distances 
 
compare <- cbind(clus, dist2 = rep(0, dim(clus)[1]), 
                 dist3 = rep(0, dim(clus)[1])) 
 
# ------- 
# functions to find distance based on Spherical Law of Cosines 
 
distance2 <- function(lat, long, clus_id) { 
    acos(sin(lat * pi / 180) * sin(two$centers[clus_id, 1]  
         * pi / 180) + cos(lat * pi / 180) *  
         cos(two$centers[clus_id, 1] * pi / 180) * 
         cos(two$centers[clus_id, 2] * pi / 180 - long *  
         pi / 180)) * 6371  #in km 
} 
 
distance3 <- function(lat, long, clus_id) { 
    acos(sin(lat * pi / 180)*sin(three$centers[clus_id, 1]  
         * pi / 180) + cos(lat * pi / 180) * 
         cos(three$centers[clus_id, 1] * pi / 180) * 
         cos(three$centers[clus_id, 2] * pi / 180 - long *  
         pi / 180)) * 6371  #in km 
} 
 
# ------- 
 
for (e in 1:dim(compare[1])[1]) { 
     compare[e, 5] <- distance2(compare[e, 1], compare[e, 2],  
                                compare[e,3]) 
     compare[e, 6] <- distance3(compare[e, 1], compare[e, 2],  
                                compare[e, 4]) 
} 
 
if(!require("dplyr")) install.packages("dplyr")
suppressMessages(suppressWarnings(library(dplyr))) 
compare <- cbind(compare, hybrid = rep(0, dim(compare)[1])) 
 
for (e in 1:dim(compare[1])[1]) { 
     compare[e, 7] <- distance3(compare[e, 1], compare[e, 2],  
                                compare[e, 3]) 
} 
 
compare <- mutate(compare, temp_increase = (hybrid - dist3)) 
 
# ------- 
 
par(mfrow = c(1, 3)) 
hist(compare[ ,5], ylim = c(0, 80), xlim = c(0, 8), 
     col = "lightgray", xlab = "Dist (km)", main = "Two Kiosks") 
abline(v = mean(compare[ ,5]), lty = "dashed") 
 
hist(compare[ ,6], ylim = c(0, 80), xlim = c(0, 8),  
     col = "lightgray", xlab = "Dist (km)", 
     main = "Three Kiosks") 
abline(v = mean(compare[ ,6]), lty = "dashed") 
 
hist(compare[ ,7], ylim = c(0, 80), xlim = c(0, 8), 
     col = "lightgray", xlab = "Dist (km)",  
     main = "Two (Hybrid Solution)") 
abline(v = mean(compare[ ,7]), lty = "dashed") 
par(mfrow = c(1, 1)) 
 
summary(compare)  #to indicate max 
 
hist(compare$temp_increase, breaks = 4, xlab = "Distance (km)", 
     main = "Distance Increase: Building Two Kiosks at Future Locations",  
     col = "gray") 
bins <- as.data.frame(table(cut(compare$temp_increase, 
                      breaks = c(-1:5)))) 
text(seq(-.5, 4.5, 1), 50, cex = 1.1, col = 'black', bins[ ,2]) 
 
increase <- filter(compare, temp_increase > 0) 
increase <- increase[ ,-c(1:7)] 
 
summary(increase) 
 
text(2, 80, paste("Average increase:", round(mean(increase) *  
     0.62137119, 2),"miles")) # .62 mi/km