Applies an R function to transform a data stream.
Arguments
- dsd
An object of class DSD.
- func
A function that takes a data frame as its first argument and returns the transformed data frame.
- ...
Further arguments passed to
func.- info
Logical; should the function also receive and modify the information columns?
Details
The function's first argument needs to be a data.frame representing points of the
data stream. The function will be called as ps %>% your_function(), where ps is the
data.frame with some points obtained using get_points() on the data stream source.
Examples
stream <- DSD_Gaussians(k = 3, d = 3)
get_points(stream, n = 5)
#> X1 X2 X3 .class
#> 1 0.45644198 0.3192106 0.7213576 2
#> 2 0.11084322 0.7060063 0.3254849 1
#> 3 0.15460289 0.6886859 0.3652530 1
#> 4 0.47480522 0.3168706 0.7498813 2
#> 5 0.08529232 0.7212409 0.3127524 1
## Example 1: rename the columns
rename <- function(x, names) {
colnames(x) <- names
x
}
# By default, the info columns starting with . are not affected.
stream2 <- stream %>% DSF_Func(rename, names = c("A", "B", "C"))
stream2
#> Gaussian Mixture (d = 3, k = 3)
#> + function: rename
#> Class: DSF_Func, DSF, DSD_R, DSD
get_points(stream2, n = 5)
#> A B C .class
#> 1 0.4342038 0.3322064 0.7157336 2
#> 2 0.3824367 0.1147064 0.1412927 3
#> 3 0.3733803 0.1483660 0.1584031 3
#> 4 0.1380883 0.7551047 0.4124708 1
#> 5 0.3474889 0.1122304 0.1654209 3
## Example 2: add a sum columns
stream3 <- stream2 %>% DSF_Func(function(x) {
x$sum = rowSums(x)
x
})
stream3
#> Gaussian Mixture (d = 3, k = 3)
#> + function: rename
#> + function: function(x) {; x$sum = rowSums(x); x; }
#> Class: DSF_Func, DSF, DSD_R, DSD
get_points(stream3, n = 5)
#> A B C sum .class
#> 1 0.07319499 0.7742238 0.3360901 1.1835089 1
#> 2 0.39464178 0.3911129 0.6904716 1.4762263 2
#> 3 0.09524489 0.7168854 0.3232897 1.1354199 1
#> 4 0.44223147 0.3676431 0.6463945 1.4562691 2
#> 5 0.45132830 0.1428343 0.1689007 0.7630633 3
## Example 3: Project the stream on its first 2 PCs (using a sample)
pr <- princomp(get_points(stream, n = 100, info = FALSE))
pca_trans <- function(x) predict(pr, x[, c("X1", "X2", "X3")])[, 1:2 , drop = FALSE]
pca_trans(get_points(stream, n = 3, info = FALSE))
#> Comp.1 Comp.2
#> [1,] 0.3402103 -0.1265072
#> [2,] -0.1041374 0.2394933
#> [3,] 0.3966679 -0.1333895
stream4 <- stream %>% DSF_Func(pca_trans)
stream4
#> Gaussian Mixture (d = 3, k = 3)
#> + function: pca_trans
#> Class: DSF_Func, DSF, DSD_R, DSD
get_points(stream4, n = 3)
#> Comp.1 Comp.2 .class
#> 1 -0.02680910 0.3166875 2
#> 2 -0.01125253 0.2773255 2
#> 3 -0.29376430 -0.1950964 1
plot(stream4)
## Example 4: Change a class labels using info = TRUE. We redefine class 3 as noise (NA)
stream5 <- stream %>% DSF_Func(
function(x) { x[['.class']][x[['.class']] == 3] <- NA; x },
info = TRUE)
stream5
#> Gaussian Mixture (d = 3, k = 3)
#> + function: function(x) {; x[[".class"]][x[[".class"]] == 3] <- NA; x;
#> }
#> Class: DSF_Func, DSF, DSD_R, DSD
get_points(stream5, n = 5)
#> X1 X2 X3 .class
#> 1 0.4590594 0.3239982 0.7254512 2
#> 2 0.4553169 0.3295803 0.7492146 2
#> 3 0.2780631 0.1934227 0.2678634 NA
#> 4 0.3986266 0.1221774 0.1386862 NA
#> 5 0.1461974 0.7123155 0.3797266 1
plot(stream5)
