Contents

1 Motivation

The chihaya package saves DelayedArray objects for efficient, portable and stable reproduction of delayed operations in a new R session or other programming frameworks.

Check out the specification for more details.

2 Quick start

Make a DelayedArray object with some operations:

library(DelayedArray)
x <- DelayedArray(matrix(runif(1000), ncol=10))
x <- x[11:15,] / runif(5) 
x <- log2(x + 1)
x
## <5 x 10> DelayedMatrix object of type "double":
##           [,1]      [,2]      [,3] ...      [,9]     [,10]
## [1,] 0.2712298 1.3445004 0.2033835   . 1.4399352 0.8858851
## [2,] 0.9912982 0.4130893 1.4479727   . 1.2925699 0.6405589
## [3,] 1.3442491 0.1816329 1.2858321   . 0.2008262 0.9568943
## [4,] 0.5485856 0.5260304 0.3941459   . 1.2224496 1.4611243
## [5,] 0.7662436 0.9351326 2.0990324   . 2.1479931 2.2941956
showtree(x)
## 5x10 double: DelayedMatrix object
## └─ 5x10 double: Stack of 2 unary iso op(s)
##    └─ 5x10 double: Unary iso op with args
##       └─ 5x10 double: Subset
##          └─ 100x10 double: [seed] matrix object

Save it into a HDF5 file with saveDelayed():

library(chihaya)
tmp <- tempfile(fileext=".h5")
saveDelayed(x, tmp)
rhdf5::h5ls(tmp)
##                            group    name       otype  dclass      dim
## 0                              / delayed   H5I_GROUP                 
## 1                       /delayed    base H5I_DATASET   FLOAT    ( 0 )
## 2                       /delayed  method H5I_DATASET  STRING    ( 0 )
## 3                       /delayed    seed   H5I_GROUP                 
## 4                  /delayed/seed  method H5I_DATASET  STRING    ( 0 )
## 5                  /delayed/seed    seed   H5I_GROUP                 
## 6             /delayed/seed/seed   along H5I_DATASET INTEGER    ( 0 )
## 7             /delayed/seed/seed  method H5I_DATASET  STRING    ( 0 )
## 8             /delayed/seed/seed    seed   H5I_GROUP                 
## 9        /delayed/seed/seed/seed   index   H5I_GROUP                 
## 10 /delayed/seed/seed/seed/index       0 H5I_DATASET INTEGER        5
## 11       /delayed/seed/seed/seed    seed   H5I_GROUP                 
## 12  /delayed/seed/seed/seed/seed    data H5I_DATASET   FLOAT 100 x 10
## 13  /delayed/seed/seed/seed/seed  native H5I_DATASET INTEGER    ( 0 )
## 14            /delayed/seed/seed    side H5I_DATASET  STRING    ( 0 )
## 15            /delayed/seed/seed   value H5I_DATASET   FLOAT        5
## 16                 /delayed/seed    side H5I_DATASET  STRING    ( 0 )
## 17                 /delayed/seed   value H5I_DATASET   FLOAT    ( 0 )

And then load it back in later:

y <- loadDelayed(tmp)
y
## <5 x 10> DelayedMatrix object of type "double":
##           [,1]      [,2]      [,3] ...      [,9]     [,10]
## [1,] 0.2712298 1.3445004 0.2033835   . 1.4399352 0.8858851
## [2,] 0.9912982 0.4130893 1.4479727   . 1.2925699 0.6405589
## [3,] 1.3442491 0.1816329 1.2858321   . 0.2008262 0.9568943
## [4,] 0.5485856 0.5260304 0.3941459   . 1.2224496 1.4611243
## [5,] 0.7662436 0.9351326 2.0990324   . 2.1479931 2.2941956

Of course, this is not a particularly interesting case as we end up saving the original array inside our HDF5 file anyway. The real fun begins when you have some more interesting seeds.

3 More interesting seeds

We can use the delayed nature of the operations to avoid breaking sparsity. For example:

library(Matrix)
x <- rsparsematrix(1000, 1000, density=0.01)
x <- DelayedArray(x) + runif(1000)

tmp <- tempfile(fileext=".h5")
saveDelayed(x, tmp)
rhdf5::h5ls(tmp)
##            group     name       otype  dclass   dim
## 0              /  delayed   H5I_GROUP              
## 1       /delayed    along H5I_DATASET INTEGER ( 0 )
## 2       /delayed   method H5I_DATASET  STRING ( 0 )
## 3       /delayed     seed   H5I_GROUP              
## 4  /delayed/seed     data H5I_DATASET   FLOAT 10000
## 5  /delayed/seed dimnames   H5I_GROUP              
## 6  /delayed/seed  indices H5I_DATASET INTEGER 10000
## 7  /delayed/seed   indptr H5I_DATASET INTEGER  1001
## 8  /delayed/seed    shape H5I_DATASET INTEGER     2
## 9       /delayed     side H5I_DATASET  STRING ( 0 )
## 10      /delayed    value H5I_DATASET   FLOAT  1000
file.info(tmp)[["size"]]
## [1] 101998
# Compared to a dense array.
tmp2 <- tempfile(fileext=".h5")
out <- HDF5Array::writeHDF5Array(x, tmp2, "data")
file.info(tmp2)[["size"]]
## [1] 280269
# Loading it back in.
y <- loadDelayed(tmp)
showtree(y)
## 1000x1000 double: DelayedMatrix object
## └─ 1000x1000 double: Unary iso op with args
##    └─ 1000x1000 double, sparse: [seed] dgCMatrix object

We can also store references to external files, thus avoiding data duplication:

library(HDF5Array)
test <- HDF5Array(tmp2, "data")
stuff <- log2(test + 1)
stuff
## <1000 x 1000> DelayedMatrix object of type "double":
##               [,1]       [,2]       [,3] ...     [,999]    [,1000]
##    [1,] 0.76255014 0.76255014 0.76255014   . 0.76255014 0.76255014
##    [2,] 0.04758857 0.04758857 0.04758857   . 0.04758857 0.04758857
##    [3,] 0.45619508 0.45619508 0.45619508   . 0.45619508 0.45619508
##    [4,] 0.60570309 0.60570309 0.60570309   . 0.60570309 0.60570309
##    [5,] 0.36736943 0.36736943 0.36736943   . 0.36736943 0.36736943
##     ...          .          .          .   .          .          .
##  [996,]  0.8108745  0.8108745  0.8108745   .  0.8108745  0.8108745
##  [997,]  0.3458396  0.3458396  0.3458396   .  0.3458396  0.3458396
##  [998,]  0.9527872  0.9527872  0.9527872   .  0.9527872  0.9527872
##  [999,]  0.7059206  0.7059206  0.7059206   .  0.7059206  0.7059206
## [1000,]  0.7817127  0.7817127  0.7817127   .  0.7817127  0.7817127
tmp <- tempfile(fileext=".h5")
saveDelayed(stuff, tmp)
rhdf5::h5ls(tmp)
##                 group       name       otype  dclass   dim
## 0                   /    delayed   H5I_GROUP              
## 1            /delayed       base H5I_DATASET   FLOAT ( 0 )
## 2            /delayed     method H5I_DATASET  STRING ( 0 )
## 3            /delayed       seed   H5I_GROUP              
## 4       /delayed/seed     method H5I_DATASET  STRING ( 0 )
## 5       /delayed/seed       seed   H5I_GROUP              
## 6  /delayed/seed/seed dimensions H5I_DATASET INTEGER     2
## 7  /delayed/seed/seed       file H5I_DATASET  STRING ( 0 )
## 8  /delayed/seed/seed       name H5I_DATASET  STRING ( 0 )
## 9  /delayed/seed/seed     sparse H5I_DATASET INTEGER ( 0 )
## 10 /delayed/seed/seed       type H5I_DATASET  STRING ( 0 )
## 11      /delayed/seed       side H5I_DATASET  STRING ( 0 )
## 12      /delayed/seed      value H5I_DATASET   FLOAT ( 0 )
file.info(tmp)[["size"]] # size of the delayed operations + pointer to the actual file
## [1] 49642
y <- loadDelayed(tmp)
y
## <1000 x 1000> DelayedMatrix object of type "double":
##               [,1]       [,2]       [,3] ...     [,999]    [,1000]
##    [1,] 0.76255014 0.76255014 0.76255014   . 0.76255014 0.76255014
##    [2,] 0.04758857 0.04758857 0.04758857   . 0.04758857 0.04758857
##    [3,] 0.45619508 0.45619508 0.45619508   . 0.45619508 0.45619508
##    [4,] 0.60570309 0.60570309 0.60570309   . 0.60570309 0.60570309
##    [5,] 0.36736943 0.36736943 0.36736943   . 0.36736943 0.36736943
##     ...          .          .          .   .          .          .
##  [996,]  0.8108745  0.8108745  0.8108745   .  0.8108745  0.8108745
##  [997,]  0.3458396  0.3458396  0.3458396   .  0.3458396  0.3458396
##  [998,]  0.9527872  0.9527872  0.9527872   .  0.9527872  0.9527872
##  [999,]  0.7059206  0.7059206  0.7059206   .  0.7059206  0.7059206
## [1000,]  0.7817127  0.7817127  0.7817127   .  0.7817127  0.7817127

Session information

sessionInfo()
## R Under development (unstable) (2024-11-20 r87352)
## Platform: aarch64-apple-darwin20
## Running under: macOS Ventura 13.7.1
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRblas.0.dylib 
## LAPACK: /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.0
## 
## locale:
## [1] C/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## time zone: America/New_York
## tzcode source: internal
## 
## attached base packages:
## [1] stats4    stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
##  [1] HDF5Array_1.35.1      rhdf5_2.51.0          chihaya_1.7.0        
##  [4] DelayedArray_0.33.2   SparseArray_1.7.2     S4Arrays_1.7.1       
##  [7] abind_1.4-8           IRanges_2.41.1        S4Vectors_0.45.2     
## [10] MatrixGenerics_1.19.0 matrixStats_1.4.1     BiocGenerics_0.53.3  
## [13] generics_0.1.3        Matrix_1.7-1          BiocStyle_2.35.0     
## 
## loaded via a namespace (and not attached):
##  [1] jsonlite_1.8.9      compiler_4.5.0      BiocManager_1.30.25
##  [4] crayon_1.5.3        Rcpp_1.0.13-1       rhdf5filters_1.19.0
##  [7] jquerylib_0.1.4     yaml_2.3.10         fastmap_1.2.0      
## [10] lattice_0.22-6      R6_2.5.1            XVector_0.47.0     
## [13] knitr_1.49          bookdown_0.41       bslib_0.8.0        
## [16] rlang_1.1.4         cachem_1.1.0        xfun_0.49          
## [19] sass_0.4.9          cli_3.6.3           Rhdf5lib_1.29.0    
## [22] zlibbioc_1.53.0     digest_0.6.37       grid_4.5.0         
## [25] lifecycle_1.0.4     evaluate_1.0.1      rmarkdown_2.29     
## [28] tools_4.5.0         htmltools_0.5.8.1