Kmeans Auto Data for Shinyapps.io

Demo of shiny app for auto MPG data from UC Irvine

This app utilizes auto mpg data from UC Irvine, available at https://archive.ics.uci.edu/ml/datasets/Auto+MPG

The original dataset has been clenaed for missing values, but in all other respects is unaltered

Using Shiny, we can observer trends and relationships between the variables. In this app, we can calculate the kmeans for clusters in the data, varying from 1-9.

Below is an example of the dataset in use.

  mpg cyl disp    hp   wt yr orig                      name
1  18   8  307 130.0 3504 70    1 chevrolet chevelle malibu
2  15   8  350 165.0 3693 70    1         buick skylark 320
3  18   8  318 150.0 3436 70    1        plymouth satellite
4  16   8  304 150.0 3433 70    1             amc rebel sst
5  17   8  302 140.0 3449 70    1               ford torino
6  15   8  429 198.0 4341 70    1          ford galaxie 500

k-means clustering aims to partition our observations into a defined number of clusters, in which each observation belongs to the cluster with the nearest mean.

The center-point of the cluster then represents the mean of that partition.

On the other hand, a kmeans plot of the data can allow us to visualize where breaks in the samples occur. Additionally, our shiny app can allow comparison of any two variables in the data set, and visualization of different partitions.