R语言rhdf5读写hdf5并展示文件组织结构和索引数据

install.packages("BiocManager");BiocManager::install("rhdf5");library(rhdf5)

h5_file= H5Fopen("new.h5")
####如下所示，new.h5文件内创建了一个组（group1_mat）
#组内又创建了df和matrix两个层级用以保存矩阵和数据框
> h5dump(h5_file,load=FALSE)
$group1_mat
$group1_mat$df
  group name       otype   dclass dim
1     /   df H5I_DATASET COMPOUND   5

$group1_mat$matrix
  group   name       otype dclass   dim
1     / matrix H5I_DATASET  FLOAT 3 x 2

> h5_file$group1_mat$df
  C_1 C_2 C_3 name
1   3   5  69   xx
2   2   8  60   yy
3   8   4  92   gg
4   1   6  16   ll
5   7   4  25   mm

H5Fclose(h5_file)#关闭当前打开的hdf5文件
h5closeAll()#关闭所有打开的hdf5文件

###准备数据
mdat <- matrix(c(0,2,3, 11,12,13), nrow = 2, ncol = 3, byrow = TRUE,dimnames = list(c("row1", "row2"),c("C.1", "C.2", "C.3")))
df <- data.frame(C_1 = c(3,2,8,1,7),C_2 = c(5,8,4,6,4),C_3 = round(runif(n = 5), 2) * 100,name = c("xx","yy","gg",'ll','mm'))
mdat.spar <- Matrix::Matrix(mdat, sparse = TRUE)
my_array <- array(seq(0.1,2.0,by=0.1),dim=c(5,2,2))
my_list <- list(my_array[,,1],my_array[,,2])
my_string <- "This is one hdf structure file"
###构建.h5文件
h5createFile("new.h5")
# Saving matrix information.
h5createGroup("new.h5","group1_mat")
h5write(mdat, "new.h5", "group1_mat/matrix")
h5write(df, "new.h5", "group1_mat/df")
# Saving sparse_matrix information.
mdat.spar <- as(mdat, "dGCMatrix")
h5createGroup("new.h5","group2_sparseMTX")
h5write(mdat.spar@x, "new.h5", "group2_sparseMTX/data")
h5write(dim(mdat.spar), "new.h5", "group2_sparseMTX/shape")
h5write(mdat.spar@i, "new.h5", "group2_sparseMTX/indices") # already zero-indexed.
h5write(mdat.spar@p, "new.h5", "group2_sparseMTX/indptr")
# Saving array and list data
h5createGroup("new.h5","group3_aL")
h5write(my_list, "new.h5", "group3_aL/list")
h5write(my_array, "new.h5", "group3_aL/array")
# Saving string data
h5createGroup("new.h5","group4_string")
h5write(my_string, "new.h5", "group4_string/string")
h5closeAll()