So let's continue our simulation of a weather-related day or simulation of weather-related days to include that in our simulation estimate of revenue. So to do that, if you recall, what we did in the last segment was we created this probability or accumulative distribution probability of this four, which was the minimum span from a normal distribution whose mean was 5.125 and standard deviation of 1.31, which we gave estimated earlier in module 5. And that turns out to be this. So now how do we calculate number from this truncated distribution? How we draw a number from this truncated normal distribution? Well, it's simple what we do again, if B 14 part is just avoiding calculating it while I'm editing this sheet. So I have set B14 to 0, if I had it at one, what it will do is it will draw a number from norm inverse D8. Again, D8 is simply this number. So we have D8 plus 1 minus D8. Now we are going to get the probability between 0 and whatever the complement of this number is, multiplied by RAND, which is going to get us a random number between 0 and 1 and when we multiply by this fractional value, guess get us a number in that range of 0 to 1 minus D8. So we add these two because every probability is going to be greater than D8. And then rest is the standard mean, and standard deviation. So that's how we can get the value of the distribution here. Then we use this value to create another data table of customers spend if they were coming on, let's say a rainy day or a weather-related. I have created that data table in column C and D. Just to save time. I'm not going through the process again, but we have done this enough times. So you can see that this is just a data table where I set the first element equal to c 12, which is this number. And then go through our process of creating data table in columns. Once we do that, now I do the similar kind of a thing except that I'm doing just one thing here. What I'm doing is that either my customers spend is coming from the just the standard distribution or the truncated distribution. So now let's create a probability of the customer coming from our truncated distribution. Or in other words, simulating whether a weather event will take place or not. So what are we doing? Again, this part, if B 14 is just again. I'm trying to not generate a random number if we are not ready to. But the crux is here in the next segment. So what happens is what we are doing is we are saying if G 17 is less than 400, remember the maximum number of customers are going to be 400. And we are going to be generating these customers randomly here. So all I'm doing is I'm saying if this number is 400 or less, then there is a chance that it's weather event related issue. That's why- That's why customers haven't come. So what I'm going to do is I'm going to say if this is the case, then we draw a random number. We draw a random number. And if that random number is less than 0.4, now you'd ask why is it 0.4? Because it should be 0.2 because the probability of whether effective day is 20%. But remember, there's already a 50% chance that any value is less than, less than 400. So That's already 50 percent. So we have to take 50 percent off point to, which is going to be 0.4%. Or in other words, if it is 20 percent of the entire distribution, it is, it is going to be 40% of this part of the distribution, which is half of the total size. So that's why it's 0.4. And then if that is the case, if this random number I generate is less than this, then it's, then I'll declare it weather event, otherwise not. So again, It's trying to simulate weather when only 400 or fewer customers have come. Whether it's due to various naturally occurring or whether it's due to the weather. So that's what we are trying to similar case. So that's what we do here. Once we do that, then it's just a question of whether we get the number. So again, if it is not a weather-related event, then we draw the number from Basic, whatever. However, we created this array earlier as we saw. But if this was a weather event, if it were a weather event, what we are going to do is if, again, as it's saying, if this was a weather event, that means that this was one, then we will get the same thing from column D instead of column B. So remember column D has all the values that are from that truncated distribution which is related to the weather event. So that's how we would go ahead and simulate it. So now that we know how this was done, again, we fill all the things down. So now that we know how this was done, let's go ahead and simulate it by changing this to one. Once we do that, it will take a few minutes. Now as you can see, we have the new customers spend data in column B and D, respectively. B comes from the entire distribution and D comes from that truncated distribution representing spend on whether related days, the customer data is now no longer just all 400, but it has drawn differ from the entire distribution. And you can see that when it's 395, it could be a weather-related day. So it's saying one here at 341 also, it's saying there, but at 398 hair, it's not saying one. Similarly at 362, it's not saying one. So sometimes based on the probability designation that we have given it, it will have one and sometimes it will have 0. And depending upon whether it has one or 0, we either draw the numbers and add them up from column D, or we'll do them from column B. So it depends upon whether we are calling it or whether we're randomly drawing it as as a weather-related event or not. So that's how we can simulate weather-related or any type of event that you can break out and modulate so that you can draw different types of numbers when that something happens. And depending upon the events that you want to model, you will be able to generate that revenue. Now in the summary of this simulation, we'll look at and compare what happens to the revenue curve as compared to the revenue curve that we generated in Simulation Five.