 So there we go. Let's do our descriptive statistics. The first thing I want to do is just to look down the infections column. Remember, I only have major mine infections, but I might not know that. I might not be the one who's done all the data gathering. I just want to see what data point values appear there. I just want to list of them, and I want to know how many of them they are. Remember, these were words. These were strings. They'll be categorical data. And to be more precise, they're going to be a normal type categorical data. There won't be any order to mine infection major infections. I suppose you could say one is worse than the other, but that depends on your point of view. We're going to create a computer variable called groups, because I want to save those numbers. And this is the by. By is our function, the data frame's function. It takes a few arguments. You see, it takes the name of the data frame. It takes the column you want to look at. Then it creates this computer variable inside of it. Then it becomes very difficult, because I'm going to assign to that. I'm going to use this data frame keyword. I'm going to create a new column called in, and it is going to tell me how many times whatever I find occurs. Very difficult to get used to this, but it's very powerful. Note it down, and you'll see it works. It works beautifully. Let me execute the code so that you can see. So it is going to create a data frame. It is going to have two columns, because it's going to take this in fiction column and see what it finds. And it only found two things. It's going to create in, which is a new column. And to it, it's going to pass how many times it finds whatever it finds there. So it found 60 instances of major infection and 60 instances of minor infection. Okay, difficult to get used to this line of code. Look at it. Let's do another one. We're going to go down gender and see how many of it we found. Now, we set up our data set that we would have these nice numbers, but it goes down. It's a sort by. You can see that it's going to sort by the gender column. How many it finds? It's going to add this new column called in and in it. It's going to find how many of the instances of whatever it finds, female male, it finds. And that's where the size, again, the size function comes in. So now I know I can make, I can almost make a little two-by-two contingency table of this, and I can do statistical analysis on this for proportions, can't I? And we certainly are going to do that. I can do simple descriptive statistics. I can say mean. What is the mean or average value? It's a function in Julia. Passed to the argument, the data frame, the age column, which is going to, in essence, be a data array. It's going to be an array of numbers and Julia's is going to work out for me the average value and there it is in a split second. The mean age of that whole age column of ours was 22.96786, et cetera, years. Simply, I can do the median. I can do standard deviation. That's STD function, STD. And then takes the argument of this data array that I want to pass to it, which is the age column of our data frame. I can do quite a few things at once. There's this nice describe function passed to it, the argument of the column that I'm interested in as well, and it gives me quite a few things. A little bit of a summary statistics. Mean, we thought was 22.9 or something odd. We get the minimum value was 10 years. The first quartile was at 12.967, the median, the third quartile, the maximum, so we can immediately do the interquartile range. We can start to calculate what statistical outliers would be, et cetera. We can do this describe function for everything. So immediately, I can start getting a feeling. My median, my mean, HPA1c was 5.9%, my median was 5.6%, and I can look at the CRP. So nice descriptive statistics. I don't have to do a thing. The only thing that it doesn't give you here, which is always helpful, is just the standard deviation. But you can simply ask STD. So we see the mean was 51, the median was 44, so a bit of a difference there. So we know that we might be dealing with a few outliers. Now, I want to stop there because I want to spend a little bit of time, and I don't want these sections to be too long. Very excitingly, we're going to do some get fly plotting.