【独家发布】【kindle】R Data Analysis Cookbook - More Than 80 Recipes to Help You Delive

1. Linear Regression using R
   
2. 1. Load the caret package:
   
3. > library(caret)
   
4. 2. Read the data:
   
5. > auto <- read.csv("auto-mpg.csv")
   
6. 3. Convert the categorical variable cylinders into a factor with appropriate renaming of
   
7. the levels:
   
8. > auto$cylinders <- factor(auto$cylinders,
   
9. levels = c(3,4,5,6,8), labels = c("3cyl", "4cyl", "5cyl",
   
10. "6cyl", "8cyl"))
    
11. 4. Create partitions:
    
12. > set.seed(1000)
    
13. > t.idx <- createDataPartition(auto$mpg, p = 0.7,
    
14. list = FALSE)
    
15. 5. See the names of the variables in the data frame:
    
16. > names(auto)
    
17. 6. Build the linear regression model:
    
18. > mod <- lm(mpg ~ ., data = auto[t.idx, -c(1,8,9)])
    
19. 7. View the basic results (your results may differ because of random sampling
    
20. differences in creating the partitions):
    
21. > mod
    
22. 8. View more detailed results:
    
23. > summary(mod)
    
24. 9. Generate predictions for the test data:
    
25. > pred <- predict(mod, auto[-t.idx, -c(1,8,9)])
    
26. 10. Compute the RMS error on the test data (your results can differ):
    
27. > sqrt(mean((pred - auto[-t.idx, 2])^2))
    
28. [1] 4.333631
    
29. 11. View diagnostic plots of the model:
    
30. > par(mfrow = c(2,2))
    
31. > plot(mod)
    
32. > par(mfrow = c(1,1))

复制代码

thanks for sharing

下来看看

Thanks

tttttthx

thanks

收下  谢谢分享

thank you