 So let's have a look at a density plot. It's another type of geometry. Now remember what a density plot is, it takes a continuous variable on the x-axis and it creates this density estimate. So plot again, it's data-aware, so I pass the data frame, data frame, df data frame to it and on the x-axis I want age and the geometry for all age variables is the density. I'm going to give it a guide.title, age distribution and again for theme what I usually do, color grid, color grid focus both white just to make everything disappear and then line width because density plots are lines and I'm going to give it quite a thick line at 4 pixels. Let's wait for that to render from Julia Box and there we see. So it takes this continuous variable called age and it gives us this kernel density estimate plot. So we can see the age distribution of our data set. Now I can add another dimension to this data by color. Now it uses the term color but remember it doesn't really have anything to do with color. It just states that I want to add another dimension. So I'm going to look at age again but I'm going to break it up by gender. So every gender male and female will have its own kernel density estimate. Again the geometry is density. I'm going to give it a new title and everything else we have seen before. This time I'm not passing a line width argument so it's going to be nice thin little lines which is the default. Let's have a look. There we go. So by color it found two different entities male and female and it gives us this little key. It found F and M and it added these default colors for us. Let's carry on. Let's just look at another one. This time I'm going to use category three just because remember there were some more categories. There were three different ones P, Q and R and you'll see it'll do for the age distribution. It'll do a kernel density estimate, the probability plot there of density plot I should say of all three of these categories. Let's have a look at one more and this time it's variable two by distribution in the categories. Let's have a look at that. So we can have a look and we can see this as far as variable two is concerned it has a more normal distribution. Perhaps then the age distribution that was not did not follow a normal distribution. So it helps us really to have a closer look at this data perhaps give us slightly more information than just the box plots themselves. So let's move on to histogram which is basically a density plot. Well I mean it's a bit more involved in that but we're just going to make little bins still out of continuous variable on the x-axis. So it's almost exactly the same so instead of age I'm using variable one year on the x-axis which is a continuous variable. And I'm passing the geometry to it as geom.histogram. I'm giving it a title and I'm using some theme arguments there as well. Let's have a look at that. Variable one let's have a look at what it's just distribution one seems to be quite random. Variable one's not really following a distribution pattern. But it is a continuous variable here at the bottom and it has decided on its own what the size of these little bins are. See these are how thin they are. That is a count of how many values occur between two sets of x-axis values. That's what a histogram is. But I can specify the bin count in the histogram geometry. Bin count equals and I've passed the value of 10 here which is going to take this variable instead of having these tiny little bins. We see the bins are quite a bit bigger. Quite a bit bigger once again we can see here that the data is really not normally distributed. So let's have a look at this. Let's have a look at variable two. We saw that it had a more normal distribution. Let's use 11 bin counts. Let's have a look at that and there we go. We see that normal distribution that we saw on the kernel density estimate before. Let's look at variable two but we add another dimension to it. I want two histograms and I'm going to split them up by color because I know it's two because I know there was male and female. So let's have a look at what GATFLY does there. Beautifully it will plot one on top of the other. Again I've specified a bin count this time 21 and it will plot one in front of the other so that you could see the both of them size have both histograms there together. Now a violin plot combines actually what we saw in the box in whisker plots with a density estimate. It actually just puts a density estimate on its side and duplicates it on both sides. So you get this nice little idea. Let's have a look at it. I'll show you. Remember category two, that's going to be my x-axis so this is like a box plot. And on the y we're going to take variable one and the geometry is violin. Let me show you what it looks like in case you are not familiar with a violin plot. There we are. So on the side here you can see the little kernel density estimate but it duplicates it on both sides. So you get this nice little idea of a box plot but indicating the density as well. So violin plots are quite a nice thing to do. Now let's add something else to it. I've got category three here as a color. Let's have a look at what happens now. Now this is density and that's what I wanted to show you. So if you were just to look at this P and you see the shape of that P and you can well see the shape of it as it lies there. And Q, you see this big dip in the Q and there's that big dip in the Q and then you see R, this more of a normal distribution to the R variable. Next up in the next section we're going to have a look at one of my favorite type of plots, a QQ plot.