Another kind of plot that we use a lot is the scatter plot. r_break r_break We allow our attribute values to determine the position. We pick two attribute values and we plot the two values against each other for every data object. We can also use the size, shape, and color of our markers to display supplementary attributes. This allows us to construct three- or four-dimensional graphs on a two-dimensional plane very easily. And, in particular, we will see arrays of scatter plots used quite often as a way to compactly summarize our factor relationships. r_break r_break Here’s an example of that same iris data set and a scatter plot of the attributes. We’ve got every attribute plotted against the others. So, we’ve got sepal width and sepal length, and then sepal width and petal length, and then sepal width and petal width here. And the color and shape of our markers tell us what the species of the plant is. We can see, for instance, that sepal length and petal width - petal width in particular, if we look at the petal width row and column - seems to be a very good predictor for at least the setosa species. r_break r_break Other plots that we use a lot are contour plots, which we’ve seen before. Essentially, you can think of geographical maps here. We use contour plots for topographical maps all the time. So, in this case, we partition the plane into regions of similar values and color in those values, separating them with little contour lines to show the differences. r_break r_break All right. So that was a very, very fast blast through a number of different kinds of graphs. And that concludes our webinar on the fundamentals of data mining. Thank you for taking the time to watch this presentation. Please check out the next video in our introductory series, introduction to R. r_break r_break Have a nice day.