elbow plot

elbow-plot.R

#Calculate lm's for emphasis
lm(cost_df$cost[1:10] ~ cost_df$cluster[1:10])
lm(cost_df$cost[10:19] ~ cost_df$cluster[10:19])
lm(cost_df$cost[20:100] ~ cost_df$cluster[20:100])

cost_df$fitted <- ifelse(cost_df$cluster <10, (19019.9 - 550.9*cost_df$cluster), 
                         ifelse(cost_df$cluster <20, (15251.5 - 116.5*cost_df$cluster),
                         (13246.1 - 35.9*cost_df$cluster)))

#Cost plot
ggplot(data=cost_df, aes(x=cluster, y=cost, group=1)) + 
theme_bw(base_family="Garamond") + 
geom_line(colour = "darkgreen") +
theme(text = element_text(size=20)) +
ggtitle("Reduction In Cost For Values of 'k'\n") +
xlab("\nClusters") + 
ylab("Within-Cluster Sum of Squares\n") +
scale_x_continuous(breaks=seq(from=0, to=100, by= 10)) +
geom_line(aes(y= fitted), linetype=2)

Thanks