From the course: Supervised Learning Essential Training
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Evaluating regression model predictions - Python Tutorial
From the course: Supervised Learning Essential Training
Evaluating regression model predictions
- [Instructor] Arguably the most important part of building machine learning models is properly evaluating our models. By running our logistic regression and printing the summary we can see how well our regression model performed. Starting here by importing our libraries, getting our data, there we go, and then running our regression model. Here, let's dig into some of these metrics. First, the R squared signifies the percentage variation that's explained by the independent variables. Here, our 81% variation in the G3 or RY is explained by G2. Our probability or F statistic, this basically tells us the overall significance of our regression. Under that, we see both AIC and BIC. So let's dig into it. AIC stands for Akaike Information Criterion and is used for model selection. It penalize the errors in case a new variable is added to the regression equation. Whereas BIC stands for Bayesian Information Criterion…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
Defining logistic and linear regression2m 51s
-
(Locked)
Steps to prepare data for modeling4m 31s
-
(Locked)
Checking your dataset for assumptions7m 18s
-
(Locked)
Creating a linear regression model2m 51s
-
(Locked)
Creating a logistic regression model4m 28s
-
(Locked)
Evaluating regression model predictions2m 40s
-
-
-
-
-