Impute via missForest

impute_missForest() imputes missing values in a dataset using the missForest method. It can also display the percentage of missing values in each column before imputation.

Usage

hd_impute_missForest(
  dat,
  maxiter = 10,
  ntree = 100,
  parallelize = "no",
  verbose = TRUE
)

Arguments

dat

An HDAnalyzeR object or a dataset in wide format and sample ID as its first column.

maxiter

The maximum number of iterations.

ntree

The number of trees to grow.

parallelize

If "no", the imputation is done in a single core. If "variables", the imputation is done in parallel for each variable. If "forest", the imputation is done in parallel for each tree. For more information, check the missForest documentation.

verbose

If TRUE, the percentage of missing values in each column is displayed.

Value

The imputed dataset.

Details

This is the slowest and more complex imputation method. If KNN works fine, it is recommended to use it instead of missForest. In case of large datasets, it is recommended to parallelize the imputation. However, the user must have the doParallel package installed and register a cluster before running the function. An example of how to parallelize the imputation is provided in the examples section.

Examples

# Create the HDAnalyzeR object providing the data and metadata
hd_object <- hd_initialize(example_data, example_metadata)
hd_object$data
#> # A tibble: 586 × 101
#>    DAid    AARSD1   ABL1  ACAA1    ACAN    ACE2  ACOX1   ACP5    ACP6  ACTA2
#>    <chr>    <dbl>  <dbl>  <dbl>   <dbl>   <dbl>  <dbl>  <dbl>   <dbl>  <dbl>
#>  1 DA00001   3.39  2.76   1.71   0.0333  1.76   -0.919 1.54    2.15    2.81 
#>  2 DA00002   1.42  1.25  -0.816 -0.459   0.826  -0.902 0.647   1.30    0.798
#>  3 DA00003  NA    NA     NA      0.989  NA       0.330 1.37   NA      NA    
#>  4 DA00004   3.41  3.38   1.69  NA       1.52   NA     0.841   0.582   1.70 
#>  5 DA00005   5.01  5.05   0.128  0.401  -0.933  -0.584 0.0265  1.16    2.73 
#>  6 DA00006   6.83  1.18  -1.74  -0.156   1.53   -0.721 0.620   0.527   0.772
#>  7 DA00007  NA    NA      3.96   0.682   3.14    2.62  1.47    2.25    2.01 
#>  8 DA00008   2.78  0.812 -0.552  0.982  -0.101  -0.304 0.376  -0.826   1.52 
#>  9 DA00009   4.39  3.34  -0.452 -0.868   0.395   1.71  1.49   -0.0285  0.200
#> 10 DA00010   1.83  1.21  -0.912 -1.04   -0.0918 -0.304 1.69    0.0920  2.04 
#> # ℹ 576 more rows
#> # ℹ 91 more variables: ACTN4 <dbl>, ACY1 <dbl>, ADA <dbl>, ADA2 <dbl>,
#> #   ADAM15 <dbl>, ADAM23 <dbl>, ADAM8 <dbl>, ADAMTS13 <dbl>, ADAMTS15 <dbl>,
#> #   ADAMTS16 <dbl>, ADAMTS8 <dbl>, ADCYAP1R1 <dbl>, ADGRE2 <dbl>, ADGRE5 <dbl>,
#> #   ADGRG1 <dbl>, ADGRG2 <dbl>, ADH4 <dbl>, ADM <dbl>, AGER <dbl>, AGR2 <dbl>,
#> #   AGR3 <dbl>, AGRN <dbl>, AGRP <dbl>, AGXT <dbl>, AHCY <dbl>, AHSP <dbl>,
#> #   AIF1 <dbl>, AIFM1 <dbl>, AK1 <dbl>, AKR1B1 <dbl>, AKR1C4 <dbl>, …

# Data after imputation
res <- hd_impute_missForest(hd_object, maxiter = 1, ntree = 50)
#> # A tibble: 91 × 2
#>    Variable NA_percentage
#>    <chr>            <dbl>
#>  1 AARSD1            5.80
#>  2 ABL1              5.80
#>  3 ACAA1             5.29
#>  4 ACAN              3.92
#>  5 ACE2              6.14
#>  6 ACOX1             3.92
#>  7 ACP6              2.22
#>  8 ACTA2             6.14
#>  9 ACTN4             6.14
#> 10 ACY1              3.92
#> # ℹ 81 more rows
#>   missForest iteration 1 in progress...done!
#>     estimated error(s): 0.6198153 
#>     difference(s): 0.003816952 
#>     time: 20.668 seconds
#> 
res$data
#> # A tibble: 586 × 101
#>    DAid  AARSD1  ABL1  ACAA1    ACAN    ACE2  ACOX1   ACP5    ACP6 ACTA2   ACTN4
#>    <chr>  <dbl> <dbl>  <dbl>   <dbl>   <dbl>  <dbl>  <dbl>   <dbl> <dbl>   <dbl>
#>  1 DA00…   3.39 2.76   1.71   0.0333  1.76   -0.919 1.54    2.15   2.81   0.742 
#>  2 DA00…   1.42 1.25  -0.816 -0.459   0.826  -0.902 0.647   1.30   0.798 -0.0659
#>  3 DA00…   3.48 2.37   1.41   0.989   0.427   0.330 1.37    1.36   1.45   0.308 
#>  4 DA00…   3.41 3.38   1.69   0.410   1.52    1.06  0.841   0.582  1.70   0.108 
#>  5 DA00…   5.01 5.05   0.128  0.401  -0.933  -0.584 0.0265  1.16   2.73   0.350 
#>  6 DA00…   6.83 1.18  -1.74  -0.156   1.53   -0.721 0.620   0.527  0.772  0.317 
#>  7 DA00…   4.22 3.86   3.96   0.682   3.14    2.62  1.47    2.25   2.01   0.170 
#>  8 DA00…   2.78 0.812 -0.552  0.982  -0.101  -0.304 0.376  -0.826  1.52  -0.597 
#>  9 DA00…   4.39 3.34  -0.452 -0.868   0.395   1.71  1.49   -0.0285 0.200 -0.532 
#> 10 DA00…   1.83 1.21  -0.912 -1.04   -0.0918 -0.304 1.69    0.0920 2.04   0.501 
#> # ℹ 576 more rows
#> # ℹ 90 more variables: ACY1 <dbl>, ADA <dbl>, ADA2 <dbl>, ADAM15 <dbl>,
#> #   ADAM23 <dbl>, ADAM8 <dbl>, ADAMTS13 <dbl>, ADAMTS15 <dbl>, ADAMTS16 <dbl>,
#> #   ADAMTS8 <dbl>, ADCYAP1R1 <dbl>, ADGRE2 <dbl>, ADGRE5 <dbl>, ADGRG1 <dbl>,
#> #   ADGRG2 <dbl>, ADH4 <dbl>, ADM <dbl>, AGER <dbl>, AGR2 <dbl>, AGR3 <dbl>,
#> #   AGRN <dbl>, AGRP <dbl>, AGXT <dbl>, AHCY <dbl>, AHSP <dbl>, AIF1 <dbl>,
#> #   AIFM1 <dbl>, AK1 <dbl>, AKR1B1 <dbl>, AKR1C4 <dbl>, AKT1S1 <dbl>, …

if (FALSE) { # \dontrun{
# Parallelize the imputation
library(doParallel)  # Load the doParallel package
cl <- makeCluster(4)  # Create a cluster with 4 cores
registerDoParallel(cl)  # Register the cluster
res <- hd_impute_missForest(hd_object, maxiter = 1, ntree = 50, parallelize = "forests")
} # }