Implemented frequencies visualization

radseq_analysis/modules/visualize.py

@@ -2,7 +2,7 @@ from radseq_analysis import visualization
 
 
 def detect_plot_type(input_file):
-    return 'clustering'
+    return 'frequencies'
 
 
 def analysis(input_file_path, popmap_file_path, output_file_path, parameters):
@@ -10,6 +10,13 @@ def analysis(input_file_path, popmap_file_path, output_file_path, parameters):
     plot_type = detect_plot_type(input_file_path)
 
     if plot_type == 'haplotypes':
-        visualization.haplotypes(input_file_path, output_file_path, parameters.species)
+        visualization.haplotypes(input_file_path,
+                                 output_file_path,
+                                 parameters.species)
     elif plot_type == 'clustering':
-        visualization.clustering(input_file_path, popmap_file_path, output_file_path)
+        visualization.clustering(input_file_path,
+                                 popmap_file_path,
+                                 output_file_path)
+    elif plot_type == 'frequencies':
+        visualization.frequencies(input_file_path,
+                                  output_file_path)

radseq_analysis/visualization/__init__.py

 from radseq_analysis.visualization.haplotypes import haplotypes
 from radseq_analysis.visualization.clustering import clustering
+from radseq_analysis.visualization.frequencies import frequencies

radseq_analysis/visualization/frequencies.py

+import os
+
+
+def frequencies(input_file_path, output_file_path):
+
+    scripts_d = ''.join(os.path.split(os.path.realpath(__file__))[:-1])
+    cmd = ('Rscript ' + os.path.join(scripts_d, 'r_scripts', 'frequencies.R') +
+           ' ' + input_file_path +
+           ' ' + output_file_path)
+    os.system(cmd)

radseq_analysis/visualization/r_scripts/frequencies.R

@@ -5,7 +5,7 @@ args = commandArgs(trailingOnly=TRUE)
 if (length(args)==0) {
     stop("At least one argument must be supplied (input file).", call.=FALSE)
 } else if (length(args) != 2){
-    stop("Usage: R frequencies.R input_file.tsv output_dir")
+    stop("Usage: R frequencies.R input_file.tsv output_file.png")
 }
 
 suppressMessages(library(readr))
@@ -13,20 +13,18 @@ suppressMessages(library(ggplot2))
 suppressMessages(library(svglite))
 suppressMessages(library(scales))
 
-file = args[1]
-output_dir = args[2]
+input_file_path = args[1]
+output_file_path = args[2]
 
-png_name = paste("tags_distribution.png", sep='')
-
-data = suppressMessages(read_delim(file, "\t", escape_double = FALSE, col_names = TRUE, trim_ws = TRUE))
+data = suppressMessages(read_delim(input_file_path, "\t", escape_double = FALSE, col_names = TRUE, trim_ws = TRUE))
 colnames(data) = c("Frequency", "Count")
 
 g = ggplot(data, aes(x=Frequency, y=Count/sum(Count))) +
     geom_bar(stat="identity", colour="black", fill="#CCCCCC") +
-    ggtitle(paste("Total tags: ", dim(data)[1], sep='')) + theme(plot.title = element_text(hjust = 0.5)) +
+    ggtitle(paste("Total tags: ", sum(data$Count), sep='')) + theme(plot.title = element_text(hjust = 0.5)) +
     xlab("Number of individuals in which a tag is present") + ylab("Frequency (%)") +
     scale_y_continuous(labels=percent)
 
-png(paste(output_dir, png_name, sep=''), width=1600, height=1000, res=130)
+png(output_file_path, width=1600, height=1000, res=130)
 print(g)
 x = dev.off()