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

minor tweaks

Browse source
This commit is contained in:
Tanushree Tunstall 2020-04-08 18:27:09 +01:00
parent fe3d431a3d
commit 7a8bbc6595
4 changed files with 30 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

28
scripts/combine_dfs.py
View file

@ -7,29 +7,29 @@ Created on Tue Aug 6 12:56:03 2019
'''
# FIXME: change filename 4 (mcsm normalised data)
# to be consistent like (pnca_complex_mcsm_norm.csv) : changed manually, but ensure this is done in the mcsm pipeline
#=============================================================================
#=======================================================================
# Task: combine 4 dfs with aa position as linking column
# This is done in 2 steps:
# merge 1: of 3 dfs (filenames in lowercase)
# <gene.lower()>_dssp.csv
# <gene.lower()>_kd.csv
# <gene.lower()>_pnca_rd.csv
# <gene.lower()>_rd.csv
# merge 2: of 2 dfs
# pnca_complex_mcsm_norm.csv (!fix name)
# gene.lower() + '_complex_mcsm_norm.csv' (!fix name)
# output df from merge1
# Input: 3 dfs
# <gene.lower()>_dssp.csv
# <gene.lower()>_kd.csv
# <gene.lower()>_pnca_rd.csv
# pnca_complex_mcsm_norm.csv (!fix name)
# <gene.lower()>_rd.csv
# gene.lower() + '_complex_mcsm_norm.csv' (!fix name)
# Output: .csv of all 4 dfs combined
# useful link
# https://stackoverflow.com/questions/23668427/pandas-three-way-joining-multiple-dataframes-on-columns
#=============================================================================
#=======================================================================
#%% load packages
import sys, os
import pandas as pd
@ -46,10 +46,10 @@ os.getcwd()
#=======================================================================
#%% command line args
arg_parser = argparse.ArgumentParser()
#arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazinamide')
#arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pncA') # case sensitive
arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazin')
arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pn') # case sensitive
arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazinamide')
arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pncA') # case sensitive
#arg_parser.add_argument('-d', '--drug', help='drug name', default = 'TESTDRUG')
#arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = 'testGene') # case sensitive
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output
@ -68,11 +68,11 @@ datadir = homedir + '/' + 'git/Data'
# input
#=======
indir = datadir + '/' + drug + '/' + 'output'
in_filename1 = 'pnca_dssp.csv'
in_filename2 = 'pnca_kd.csv'
in_filename3 = 'pnca_rd.csv'
in_filename1 = gene.lower() + '_dssp.csv'
in_filename2 = gene.lower() + '_kd.csv'
in_filename3 = gene.lower() + '_rd.csv'
#in_filename4 = 'mcsm_complex1_normalised.csv' # FIXNAME
in_filename4 = 'pnca_complex_mcsm_norm.csv'
in_filename4 = gene.lower() + '_complex_mcsm_norm.csv'
infile1 = indir + '/' + in_filename1
infile2 = indir + '/' + in_filename2