So far Python we can also use this on multiple linear regression. So, pretty common sense ah called regression This is why we call it a simple linear regressions. So, far multiple linear regression we have more variables here. So, for simple linear regression we have only one variable here right. So, we can create multiple linear regression by changing this r s value here Okay, so we can add in more columns or more variables here packed the land that we have SEPA we have a pet. We've okay then we can just Randy's Korea okay.

So we are going Ah, we call this our coefficient. So constant is our 1.8451. Pet, land is 0.711 separate is 0.6549. petal width is minus 0.56 to six. So the p value is zero. Here we have the confidence interval. So constant is a, we can say constant is from the, from this value to this value we've lost 95% correct.

Okay then pacta land, you can see a pattern we have 0.599 to 0.8 to three with 95% correct. So you can see SEPA we've extended the coefficient or the values between 0.5 to three to 0.7 a salad with 95% correct. And then Petra we can see, we have a minus 0.814 to minus 0.311. With 95% corral 95% completed, then we can look into the R square. Then we can look into the R square, so r square is 0.8590 point if ISIS okay then we can look into r square is 0.8 by nine adjusted R square is 0.8 Pisces, the higher the R squared betta as SS e smaller SS e sum of squared error. So the higher the R square the sum of squared error is smaller.

So it means the higher the R squared or smaller somehow