tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

replaced single quotes with double in R scripts

Browse source
This commit is contained in:
Tanushree Tunstall 2020-07-16 14:18:18 +01:00
parent eed3450236
commit 8a8790a7d1
5 changed files with 113 additions and 113 deletions
Download patch file Download diff file Expand all files Collapse all files

44
scripts/plotting/mcsm_mean_stability.R
View file

@ -1,5 +1,5 @@
getwd()
setwd('~/git/LSHTM_analysis/scripts/plotting')
setwd("~/git/LSHTM_analysis/scripts/plotting")
getwd()
#########################################################
@ -17,25 +17,25 @@ require(dplyr)
#========================================================
#%% variable assignment: input and output paths & filenames
drug = 'pyrazinamide'
gene = 'pncA'
gene_match = paste0(gene,'_p.')
drug = "pyrazinamide"
gene = "pncA"
gene_match = paste0(gene,"_p.")
cat(gene_match)
#=============
# directories
#=============
datadir = paste0('~/git/Data')
indir = paste0(datadir, '/', drug, '/input')
outdir = paste0('~/git/Data', '/', drug, '/output')
datadir = paste0("~/git/Data")
indir = paste0(datadir, "/", drug, "/input")
outdir = paste0("~/git/Data", "/", drug, "/output")
#======
# input
#======
#in_filename = 'mcsm_complex1_normalised.csv'
in_filename_params = paste0(tolower(gene), '_all_params.csv')
infile_params = paste0(outdir, '/', in_filename_params)
cat(paste0('Input file 1:', infile_params) )
#in_filename = "mcsm_complex1_normalised.csv"
in_filename_params = paste0(tolower(gene), "_all_params.csv")
infile_params = paste0(outdir, "/", in_filename_params)
cat(paste0("Input file 1:", infile_params) )
#=======
# output
@ -48,13 +48,13 @@ print(paste0("Output file:", outfile_mean_stability))
###########################
# Read file: struct params
###########################
cat('Reading struct params including mcsm:', in_filename_params)
cat("Reading struct params including mcsm:", in_filename_params)
my_df = read.csv(infile_params
#, stringsAsFactors = F
, header = T)
cat('Input dimensions:', dim(my_df))
cat("Input dimensions:", dim(my_df))
# clear variables
rm(in_filename_params, infile_params)
@ -65,23 +65,23 @@ str(my_df)
# check for duplicate mutations
if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformation)){
cat(paste0('CAUTION:', ' Duplicate mutations identified'
, '\nExtracting these...'))
cat(paste0("CAUTION:", " Duplicate mutations identified"
, "\nExtracting these..."))
dup_muts = my_df[duplicated(my_df$mutationinformation),]
dup_muts_nu = length(unique(dup_muts$mutationinformation))
cat(paste0('\nDim of duplicate mutation df:', nrow(dup_muts)
, '\nNo. of unique duplicate mutations:', dup_muts_nu
, '\n\nExtracting df with unique mutations only'))
cat(paste0("\nDim of duplicate mutation df:", nrow(dup_muts)
, "\nNo. of unique duplicate mutations:", dup_muts_nu
, "\n\nExtracting df with unique mutations only"))
my_df_u = my_df[!duplicated(my_df$mutationinformation),]
}else{
cat(paste0('No duplicate mutations detected'))
cat(paste0("No duplicate mutations detected"))
my_df_u = my_df
}
upos = unique(my_df_u$position)
cat('Dim of clean df:')
cat("Dim of clean df:")
cat(dim(my_df_u))
cat('\nNo. of unique mutational positions:'); cat(length(upos))
cat("\nNo. of unique mutational positions:"); cat(length(upos))
########################################################################
# end of data extraction and cleaning for plots #
@ -160,4 +160,4 @@ cat("Finished writing file:\n"
, "\nNo. of cols:", ncol(combined_df))
# end of script
#===============================================================
#===============================================================