deletions | additions       diff --git a/Experimental Results.tex b/Experimental Results.tex  index f945c4d..9d8b77e 100644  --- a/Experimental Results.tex  +++ b/Experimental Results.tex 
...
Kmeans gives the best clustering, with 5 clusters providing a good balance between size and distribution. One group, cluster 1, consistently stands out, alone. This site is the only on of the sample that contains a slip lane, which allows right-turning vehicles to avoid the roundabout merging zone entirely. This cluster is therefore rejected  \begin{table}  \begin{tabular}{@{}llllll@{}}  \hline  kmeans & Freq. (4) & Freq. (5) & Freq.(6) & Freq.(7) & Freq.(8) \\ \begin{table}[h]  \begin{tabular}{llllll}  \hline  kmeans & Freq. (4) & Freq. (5) & Freq.(6) & Freq.(7) & Freq.(8) \\ \hline  1 & 1 & 1 & 1 & 1 & 1 \\  2 & 3 & 3 & 3 & 3 & 2 \\  3 & 6 & 22 & 17 & 12 & 3 \\ 
...
8 & - & - & - & - & 10   \end{tabular}  \end{table}  \end{table}  \begin{verbatim}