Geek Answers Handbook

Linear regression in R without copying data to memory?

The standard way to do linear regression is something like this:

l <- lm(Sepal.Width ~ Petal.Length + Petal.Width, data=iris)

then use predict(l, new_data)to create predictions where new_data is a data framework with columns matching the formula. But it lm()returns an object lm, which is a list containing many things that in most cases are irrelevant. This includes a copy of the source data and a bunch of named vectors and arrays of data length / size:

R> str(l)
List of 12
 $ coefficients : Named num [1:3] 3.587 -0.257 0.364
  ..- attr(*, "names")= chr [1:3] "(Intercept)" "Petal.Length" "Petal.Width"
 $ residuals    : Named num [1:150] 0.2 -0.3 -0.126 -0.174 0.3 ...
  ..- attr(*, "names")= chr [1:150] "1" "2" "3" "4" ...
 $ effects      : Named num [1:150] -37.445 -2.279 -0.914 -0.164 0.313 ...
  ..- attr(*, "names")= chr [1:150] "(Intercept)" "Petal.Length" "Petal.Width" "" ...
 $ rank         : int 3
 $ fitted.values: Named num [1:150] 3.3 3.3 3.33 3.27 3.3 ...
  ..- attr(*, "names")= chr [1:150] "1" "2" "3" "4" ...
 $ assign       : int [1:3] 0 1 2
 $ qr           :List of 5
  ..$ qr   : num [1:150, 1:3] -12.2474 0.0816 0.0816 0.0816 0.0816 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:150] "1" "2" "3" "4" ...
  .. .. ..$ : chr [1:3] "(Intercept)" "Petal.Length" "Petal.Width"
  .. ..- attr(*, "assign")= int [1:3] 0 1 2
  ..$ qraux: num [1:3] 1.08 1.1 1.01
  ..$ pivot: int [1:3] 1 2 3
  ..$ tol  : num 1e-07
  ..$ rank : int 3
  ..- attr(*, "class")= chr "qr"
 $ df.residual  : int 147
 $ xlevels      : Named list()
 $ call         : language lm(formula = Sepal.Width ~ Petal.Length + Petal.Width, data = iris)
 $ terms        :Classes 'terms', 'formula' length 3 Sepal.Width ~ Petal.Length + Petal.Width
  .. ..- attr(*, "variables")= language list(Sepal.Width, Petal.Length, Petal.Width)
  .. ..- attr(*, "factors")= int [1:3, 1:2] 0 1 0 0 0 1
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:3] "Sepal.Width" "Petal.Length" "Petal.Width"
  .. .. .. ..$ : chr [1:2] "Petal.Length" "Petal.Width"
  .. ..- attr(*, "term.labels")= chr [1:2] "Petal.Length" "Petal.Width"
  .. ..- attr(*, "order")= int [1:2] 1 1
  .. ..- attr(*, "intercept")= int 1
  .. ..- attr(*, "response")= int 1
  .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
  .. ..- attr(*, "predvars")= language list(Sepal.Width, Petal.Length, Petal.Width)
  .. ..- attr(*, "dataClasses")= Named chr [1:3] "numeric" "numeric" "numeric"
  .. .. ..- attr(*, "names")= chr [1:3] "Sepal.Width" "Petal.Length" "Petal.Width"
 $ model        :'data.frame':  150 obs. of  3 variables:
  ..$ Sepal.Width : num [1:150] 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
  ..$ Petal.Length: num [1:150] 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
  ..$ Petal.Width : num [1:150] 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
  ..- attr(*, "terms")=Classes 'terms', 'formula' length 3 Sepal.Width ~ Petal.Length + Petal.Width
  .. .. ..- attr(*, "variables")= language list(Sepal.Width, Petal.Length, Petal.Width)
  .. .. ..- attr(*, "factors")= int [1:3, 1:2] 0 1 0 0 0 1
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:3] "Sepal.Width" "Petal.Length" "Petal.Width"
  .. .. .. .. ..$ : chr [1:2] "Petal.Length" "Petal.Width"
  .. .. ..- attr(*, "term.labels")= chr [1:2] "Petal.Length" "Petal.Width"
  .. .. ..- attr(*, "order")= int [1:2] 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv> 
  .. .. ..- attr(*, "predvars")= language list(Sepal.Width, Petal.Length, Petal.Width)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:3] "numeric" "numeric" "numeric"
  .. .. .. ..- attr(*, "names")= chr [1:3] "Sepal.Width" "Petal.Length" "Petal.Width"
 - attr(*, "class")= chr "lm"

This material takes up a lot of space, and the object lmis almost an order of magnitude larger than the original data set:

R> object.size(iris)
7088 bytes
R> object.size(l)
52704 bytes

, 170 , 450mb lm. false, lm 5 :

R> ls <- lm(Sepal.Width ~ Petal.Length + Petal.Width, data=iris, model=FALSE, x=FALSE, y=FALSE, qr=FALSE)
R> object.size(ls)
30568 bytes

R, , ? , , ?

: , , lm, - ...

+4
3

biglm:

m <- biglm(Sepal.Length ~ Petal.Length + Petal.Width, iris)

biglm , :

p <- predict(m, newdata=iris)

biglm :

> object.size(m)
6720 bytes
> d <- rbind(iris, iris)
> m <- biglm(Sepal.Width ~ Petal.Length + Petal.Width, data=d)
> object.size(m)
6720 bytes

biglm update. , , .

+4

lm, , terms coefficients. , predict.lm , qr ( ). - .

m <- lm(Sepal.Length ~ Petal.Length + Petal.Width, iris)
m$effects <- m$fitted.values <- m$residuals <- m$model <- m$qr <-
     m$rank <- m$assign <- NULL

predict0 <- function(object, newdata)
{
    mm <- model.matrix(terms(object), newdata)
    mm %*% object$coefficients
}

predict0(m, iris[1:10,])
+2

, , :

  • lm . ., , . " ".
  • lm.

, , . , , , . fastLm RcppArmadillo - ( Eigen biglm)), . , . - . fastLm , .

, :

l <- lm(Sepal.Width ~ Petal.Length + Petal.Width, data=iris)
library(biglm)
m <- biglm(Sepal.Length ~ Petal.Length + Petal.Width, iris)
library(RcppArmadillo)
a <- fastLm(Sepal.Length ~ Petal.Length + Petal.Width, iris)

object.size(l)
# 52704 bytes
object.size(m)
# 6664 bytes
object.size(a)
# 6344 bytes
+2

More articles:


All Articles