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,] 0.01697650 1.27354051 0.47610966   . 0.1720769 1.2082188
## [2,] 0.81744722 2.51271829 2.04079252   . 1.9245318 2.4699751
## [3,] 0.84819879 0.99498045 0.44779360   . 0.9808279 0.4653678
## [4,] 0.71713771 1.02436650 0.08282317   . 0.4095251 0.4937126
## [5,] 0.72485684 1.57590795 0.95659526   . 1.2571164 0.8182053
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,] 0.01697650 1.27354051 0.47610966   . 0.1720769 1.2082188
## [2,] 0.81744722 2.51271829 2.04079252   . 1.9245318 2.4699751
## [3,] 0.84819879 0.99498045 0.44779360   . 0.9808279 0.4653678
## [4,] 0.71713771 1.02436650 0.08282317   . 0.4095251 0.4937126
## [5,] 0.72485684 1.57590795 0.95659526   . 1.2571164 0.8182053

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] 101586
# Compared to a dense array.
tmp2 <- tempfile(fileext=".h5")
out <- HDF5Array::writeHDF5Array(x, tmp2, "data")
file.info(tmp2)[["size"]]
## [1] 280228
# 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,]  0.01771287  0.01771287  0.01771287   .  0.01771287  0.01771287
##    [2,]  0.44563010  0.44563010  0.44563010   .  0.44563010  0.44563010
##    [3,]  0.79991925  0.79991925  0.79991925   .  0.79991925  0.79991925
##    [4,]  0.60239351  0.60239351  0.60239351   .  0.60239351  0.60239351
##    [5,]  0.01391598  0.01391598  0.01391598   .  0.01391598  0.01391598
##     ...           .           .           .   .           .           .
##  [996,] 0.902789496 0.902789496 0.902789496   . 0.902789496 0.902789496
##  [997,] 0.937786421 0.937786421 0.937786421   . 0.937786421 0.937786421
##  [998,] 0.153923149 0.759233275 0.759233275   . 0.759233275 0.759233275
##  [999,] 0.004593853 0.004593853 0.004593853   . 0.004593853 0.004593853
## [1000,] 0.249711755 0.249711755 0.249711755   . 0.249711755 0.249711755
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,]  0.01771287  0.01771287  0.01771287   .  0.01771287  0.01771287
##    [2,]  0.44563010  0.44563010  0.44563010   .  0.44563010  0.44563010
##    [3,]  0.79991925  0.79991925  0.79991925   .  0.79991925  0.79991925
##    [4,]  0.60239351  0.60239351  0.60239351   .  0.60239351  0.60239351
##    [5,]  0.01391598  0.01391598  0.01391598   .  0.01391598  0.01391598
##     ...           .           .           .   .           .           .
##  [996,] 0.902789496 0.902789496 0.902789496   . 0.902789496 0.902789496
##  [997,] 0.937786421 0.937786421 0.937786421   . 0.937786421 0.937786421
##  [998,] 0.153923149 0.759233275 0.759233275   . 0.759233275 0.759233275
##  [999,] 0.004593853 0.004593853 0.004593853   . 0.004593853 0.004593853
## [1000,] 0.249711755 0.249711755 0.249711755   . 0.249711755 0.249711755

Session information

sessionInfo()
## R version 4.4.1 (2024-06-14 ucrt)
## Platform: x86_64-w64-mingw32/x64
## Running under: Windows Server 2022 x64 (build 20348)
## 
## Matrix products: default
## 
## 
## locale:
## [1] LC_COLLATE=C                          
## [2] LC_CTYPE=English_United States.utf8   
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C                          
## [5] LC_TIME=English_United States.utf8    
## 
## 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_1.34.0      rhdf5_2.50.0          chihaya_1.6.0        
##  [4] DelayedArray_0.32.0   SparseArray_1.6.0     S4Arrays_1.6.0       
##  [7] abind_1.4-8           IRanges_2.40.0        S4Vectors_0.44.0     
## [10] MatrixGenerics_1.18.0 matrixStats_1.4.1     BiocGenerics_0.52.0  
## [13] Matrix_1.7-1          BiocStyle_2.34.0     
## 
## loaded via a namespace (and not attached):
##  [1] crayon_1.5.3        cli_3.6.3           knitr_1.48         
##  [4] rlang_1.1.4         xfun_0.48           jsonlite_1.8.9     
##  [7] htmltools_0.5.8.1   sass_0.4.9          rmarkdown_2.28     
## [10] grid_4.4.1          evaluate_1.0.1      jquerylib_0.1.4    
## [13] fastmap_1.2.0       Rhdf5lib_1.28.0     yaml_2.3.10        
## [16] lifecycle_1.0.4     bookdown_0.41       BiocManager_1.30.25
## [19] compiler_4.4.1      Rcpp_1.0.13         rhdf5filters_1.18.0
## [22] XVector_0.46.0      lattice_0.22-6      digest_0.6.37      
## [25] R6_2.5.1            bslib_0.8.0         tools_4.4.1        
## [28] zlibbioc_1.52.0     cachem_1.1.0