Fix analysis cluster

R/solGS/kclustering.r

@@ -20,20 +20,20 @@
 library(phenoAnalysis)
 library(factoextra)
 
 allArgs <- commandArgs()
 
 outputFiles <- grep("output_files", allArgs, value = TRUE)
 outputFiles <- scan(outputFiles, what = "character")
 
 inputFiles <- grep("input_files", allArgs, value = TRUE)
 inputFiles <- scan(inputFiles, what = "character")
 
 optionsFile <- grep("options", inputFiles, value = TRUE)
 clusterOptions <- read.table(optionsFile, header = TRUE, sep = "\t", stringsAsFactors = FALSE,
     na.strings = "")
 print(clusterOptions)
 
 kmeansPlotFile <- grep("k-means_plot", outputFiles, value = TRUE)
 kResultFile <- grep("result", outputFiles, value = TRUE)
 elbowPlotFile <- grep("elbow_plot", outputFiles, value = TRUE)
 clusterMeansFile <- grep("k-means_means", outputFiles, value = TRUE)
@@ -77,7 +77,7 @@
 
     } else {
         genoFile <- genoFiles
-        genoData <- fread(genoFile, header = TRUE, na.strings = c("NA", " ", "--",
+        genoData <- fread(genoFile, header = TRUE, na.strings = c("NA", "", "--",
             "-", "."))
 
         if (is.null(genoData)) {
@@ -129,7 +129,7 @@
         metaFile <- grep("meta", inputFiles, value = TRUE)
 
         clusterData <- cleanAveragePhenotypes(inputFiles, metaDataFile = metaFile)
-        
+
         if (length(predictedTraits) > 1) {
             clusterData <- rownames_to_column(clusterData, var = "germplasmName")
             clusterData <- clusterData %>%
@@ -216,7 +216,7 @@
 
 clusterMeans <- c()
 if (!grepl('genotype', kResultFile)) {
-    message('adding cluster means to clusters...')
+    message("adding cluster means to clusters...")
     clusterMeans <- aggregate(clusterDataNotScaled, by = list(cluster = kMeansOut$cluster),
     mean)
 
@@ -227,7 +227,9 @@
 }
 
 pca <- c()
-if (is.null(selectedIndexGenotypes)) {
+if (grepl("genotype", dataType, ignore.case = TRUE)) {
+    pca    <- prcomp(clusterData, retx=TRUE)
+} else if (is.null(selectedIndexGenotypes)) {
     pca    <- prcomp(clusterData, scale=TRUE, retx=TRUE)
 } else {
     pca    <- prcomp(clusterData, retx=TRUE)
@@ -240,7 +242,7 @@
 
 clusterPcScoresGroups <- c()
 if (length(clusterPcScoresFile)) {
-    message('adding cluster groups to pc scores...')
+    message("adding cluster groups to pc scores...")
     scores <- rownames_to_column(scores)
     names(scores)[1] <- c("germplasmName")
 

lib/solGS/JobSubmission.pm

@@ -72,15 +72,16 @@ sub run_prerequisite_jobs {
             $remaining_jobs = $self->wait_till_jobs_end($submitted_priority_jobs);
         }
         else {
-            if ( reftype $pre_jobs eq 'SCALAR' ) {
+            if ( reftype($pre_jobs) eq 'SCALAR' ) {
                 $pre_jobs = [$pre_jobs];
             }
 
             my $submitted_jobs = $self->submit_jobs($pre_jobs);
 
             $remaining_jobs = $self->wait_till_jobs_end($submitted_jobs);
-            print STDERR "\nremaining jobs: $remaining_jobs\n";
-
+	    if (defined $remaining_jobs) {
+                print STDERR "\nremaining jobs: $remaining_jobs\n";
+	    }
         }
     }
 
@@ -126,14 +127,16 @@ sub run_dependent_jobs {
     my $jobs_file = $self->dependent_jobs;
     my $dep_jobs  = retrieve($jobs_file);
 
-    if ( reftype $dep_jobs ne 'ARRAY' ) {
+    if ( reftype($dep_jobs) ne 'ARRAY' ) {
         $dep_jobs = [$dep_jobs];
     }
 
     my $submitted_jobs = $self->submit_jobs($dep_jobs);
 
     my $remaining_jobs = $self->wait_till_jobs_end($submitted_jobs);
-    print STDERR "\nremaining jobs: $remaining_jobs\n";
+    if (defined $remaining_jobs) {
+        print STDERR "\nremaining jobs: $remaining_jobs\n";
+    }
     return $remaining_jobs;
 
 }