From b8653c6afe87f12cf26925658785a82d747205d7 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Sat, 2 Jul 2022 10:20:40 +0100
Subject: [PATCH] ML scripts: {'n_jobs': os.cpu_count() }

---
 scripts/ml/ml_functions/FS.py              |  3 +--
 scripts/ml/ml_functions/MultClfs.py        |  2 +-
 scripts/ml/ml_functions/SplitTTS.py        |  2 +-
 scripts/plotting/lineage_plots_multipage.R | 21 +++++++++++++--------
 4 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/scripts/ml/ml_functions/FS.py b/scripts/ml/ml_functions/FS.py
index b07b7ba..16d4ac2 100755
--- a/scripts/ml/ml_functions/FS.py
+++ b/scripts/ml/ml_functions/FS.py
@@ -76,8 +76,7 @@ import argparse
 import re
 #####################################
 rs = {'random_state': 42}
-njobs = {'n_jobs': 10}
-    
+njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
 
 scoring_fn =  ({ 'mcc'        : make_scorer(matthews_corrcoef)
                 , 'fscore'    : make_scorer(f1_score)
diff --git a/scripts/ml/ml_functions/MultClfs.py b/scripts/ml/ml_functions/MultClfs.py
index c687159..b16ce2e 100755
--- a/scripts/ml/ml_functions/MultClfs.py
+++ b/scripts/ml/ml_functions/MultClfs.py
@@ -76,7 +76,7 @@ import argparse
 import re
 #%% GLOBALS
 rs = {'random_state': 42}
-njobs = {'n_jobs': 10}
+njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
 
 scoring_fn =  ({ 'mcc'        : make_scorer(matthews_corrcoef)
                 , 'fscore'    : make_scorer(f1_score)
diff --git a/scripts/ml/ml_functions/SplitTTS.py b/scripts/ml/ml_functions/SplitTTS.py
index 99e6ef3..a2de72b 100644
--- a/scripts/ml/ml_functions/SplitTTS.py
+++ b/scripts/ml/ml_functions/SplitTTS.py
@@ -41,7 +41,7 @@ import re
 homedir = os.path.expanduser("~")
 #%% GLOBALS
 rs = {'random_state': 42}
-njobs = {'n_jobs': 10}
+njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
 
 #%% Define split_tts function #################################################
 def split_tts(ml_input_data
diff --git a/scripts/plotting/lineage_plots_multipage.R b/scripts/plotting/lineage_plots_multipage.R
index 799d809..f09d195 100644
--- a/scripts/plotting/lineage_plots_multipage.R
+++ b/scripts/plotting/lineage_plots_multipage.R
@@ -5,8 +5,8 @@ library(ggpubr)
 library(svglite)
 
 # for testing only
-gene="pncA"
-drug="pyrazinamide"
+#gene="pncA"
+#drug="pyrazinamide"
 
 lineage_plot=function(gene,drug){
   lineage_filename=paste0(tolower(gene),"_merged_df2.csv")
@@ -84,7 +84,7 @@ lineage_plot=function(gene,drug){
     #print (i)
     s_mut = plot_df[plot_df$mutationinformation == i,]
     s_tab = table(s_mut$lineage, s_mut$sensitivity)
-    ft_pvalue_i = fisher.test(s_tab)$p.value
+    ft_pvalue_i = fisher.test(s_tab, workspace=2000000)$p.value
     plot_df$pval[plot_df$mutationinformation == i] <- ft_pvalue_i
   }
   plot_df$pvalR = round(plot_df$pval, 3)
@@ -131,12 +131,14 @@ lineage_plot=function(gene,drug){
   
   # Do plots
   plot_pages = round(length(lin_muts)/25)
+  if (plot_pages<1){plot_pages=1}
   p_title = gene
   res = 144 # SVG dots-per-inch
+  print(paste0('About to plot ', plot_pages, ' page(s).'))
   
   sapply(1:plot_pages, function(page){
     print(paste0("Plotting page:", page))
-    svglite(paste0("/tmp/",drug,"-",page,".svg"), width=2048/res, height=1534/res) # old-school square 4:3 CRT shape 1.3:1
+    svglite(paste0("/tmp/",drug,"-",page,".svg"), width=2048/res, height=1534/res) # old-school square 4:3 CRT shape 1.33:1
     print(
       ggplot(plot_df2, aes(x = lineage
                            , fill = sensitivity)) + 
@@ -169,17 +171,19 @@ lineage_plot=function(gene,drug){
 
 # hardcoded list of drugs
 drugs = c(#"ethambutol",
-          #"isoniazid",
+          "isoniazid",
           "pyrazinamide",
           "rifampicin",
           "streptomycin",
-          "cycloserine")
+          #"cycloserine"
+          )
 genes = c(#"embB",
-          #"katG",
+          "katG",
           "pncA",
           "rpoB",
           "gid",
-          "alr")
+          #"alr"
+          )
 combo = data.frame(drugs, genes)
 
 #sapply(combo$drugs, function(x){print(c(x,combo[drugs==x,"genes"]))})
@@ -188,4 +192,5 @@ combo = data.frame(drugs, genes)
 sapply(combo$drugs, function(drug){
   gene=combo[drugs==drug,"genes"]
   lineage_plot(gene,drug)
+  print(c(gene,drug))
 })
\ No newline at end of file