comparison w4mkmeans_wrapper.R @ 1:02cafb660b72 draft

planemo upload for repository https://github.com/HegemanLab/w4mkmeans_galaxy_wrapper/tree/master commit f600ce8a783df16e49272341dce0fc6bbc299b0a

0:6ccbe18131a6

#   - [stats::p.adjust](https://stat.ethz.ch/R-manual/R-devel/library/stats/html/p.adjust.html)
#   how this does what it does:
#   - [parallel::clusterApply](https://stat.ethz.ch/R-manual/R-devel/library/parallel/html/clusterApply.html)

# invocation:
#   Rscript $__tool_directory__/w4mkmeans_wrapper.R \
#     tool_directory $__tool_directory__
#     data_matrix_path '$dataMatrix_in' \
#     variable_metadata_path '$variableMetadata_in' \
#     sample_metadata_path '$sampleMetadata_in' \
#     kfeatures '$kfeatures' \
#     ksamples '$ksamples' \
#     iter_max '$iter_max' \
#     nstart '$nstart' \
#     algorithm '$algorithm' \
#     scores '$scores' \
#     sampleMetadata_out '$sampleMetadata_out' \
#     variableMetadata_out '$variableMetadata_out' \
#     slots "\${GALAXY_SLOTS:-1}" \
# 
# <inputs>
#   <param name="dataMatrix_in" label="Data matrix file" type="data" format="tabular" help="variable x sample, decimal: '.', missing: NA, mode: numerical, separator: tab" />
#   <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata columns, separator: tab" />
#   <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata columns, separator: tab" />
#   <param name="kfeatures" label="K value(s) for features" type="text" value="0" help="Single or min,max value(s) for K for features (variables), or 0 for none." />
#   <param name="ksamples" label="K value(s) for samples" type="text" value="0" help="Single or min,max value(s) for K for samples, or 0 for none." />
#   <param name="iter_max" label="Max number of iterations" type="text" value="10" help="The maximum number of iterations allowed; default 10." />
#   <param name="nstart" label="Number of random sets" type="text" value="1" help="How many random sets should be chosen; default 1." />
# 	<param name="algorithm" label="Algorithm for clustering" type="select" value = "Hartigan-Wong" help="K-means clustering algorithm, default 'Hartigan-Wong'; alternatives 'Lloyd', 'MacQueen'; 'Forgy' is a synonym for 'Lloyd', see stats::kmeans reference for further info and references.">

args_env$iter_max  <- as.numeric(               argVc['iter_max'  ])
args_env$nstart    <- as.numeric(               argVc['nstart'   ])
args_env$slots     <- as.numeric(               argVc['slots'    ])
# string args
args_env$algorithm <- as.character(             argVc['algorithm'])
args_env$log_print <- log_print

log_print("PARAMETERS (parsed):")
for (member in ls(args_env)) {
  value <- get(member, args_env)

1:02cafb660b72

#   - [stats::p.adjust](https://stat.ethz.ch/R-manual/R-devel/library/stats/html/p.adjust.html)
#   how this does what it does:
#   - [parallel::clusterApply](https://stat.ethz.ch/R-manual/R-devel/library/parallel/html/clusterApply.html)

# invocation:
#   Rscript w4mkmeans_wrapper.R \
#     algorithm "$algorithm" \
#     categorical_prefix "$categorical_prefix" \
#     data_matrix_path "$dataMatrix_in" \
#     iter_max "$iter_max" \
#     kfeatures "$kfeatures" \
#     ksamples "$ksamples" \
#     nstart "$nstart" \
#     sampleMetadata_out "$sampleMetadata_out" \
#     sample_metadata_path "$sampleMetadata_in" \
#     scores_out "$scores_out" \
#     slots "${GALAXY_SLOTS:-1}" \
#     variableMetadata_out "$variableMetadata_out" \
#     variable_metadata_path "$variableMetadata_in"
# 
# <inputs>
#   <param name="dataMatrix_in" label="Data matrix file" type="data" format="tabular" help="variable x sample, decimal: '.', missing: NA, mode: numerical, separator: tab" />
#   <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata columns, separator: tab" />
#   <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata columns, separator: tab" />
#   <param name="categoricalPrefix" label="prefix for cluster names " type="text" value="k" help="Some tools require non-numeric values to discern categorical; e.g., enter 'k' here to prepend 'k' to cluster numbers in the output; default 'k'." />
#   <param name="kfeatures" label="K value(s) for features" type="text" value="0" help="Single or min,max value(s) for K for features (variables), or 0 for none." />
#   <param name="ksamples" label="K value(s) for samples" type="text" value="0" help="Single or min,max value(s) for K for samples, or 0 for none." />
#   <param name="iter_max" label="Max number of iterations" type="text" value="10" help="The maximum number of iterations allowed; default 10." />
#   <param name="nstart" label="Number of random sets" type="text" value="1" help="How many random sets should be chosen; default 1." />
# 	<param name="algorithm" label="Algorithm for clustering" type="select" value = "Hartigan-Wong" help="K-means clustering algorithm, default 'Hartigan-Wong'; alternatives 'Lloyd', 'MacQueen'; 'Forgy' is a synonym for 'Lloyd', see stats::kmeans reference for further info and references.">

args_env$iter_max  <- as.numeric(               argVc['iter_max'  ])
args_env$nstart    <- as.numeric(               argVc['nstart'   ])
args_env$slots     <- as.numeric(               argVc['slots'    ])
# string args
args_env$algorithm <- as.character(             argVc['algorithm'])
args_env$categorical_prefix <- as.character(    argVc['categorical_prefix'])


# make local 'log_print' function available through 'env'
args_env$log_print <- log_print

log_print("PARAMETERS (parsed):")
for (member in ls(args_env)) {
  value <- get(member, args_env)