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

refactoring: added command line args to combine_dfs

Browse source
This commit is contained in:
Tanushree Tunstall 2020-04-08 11:44:53 +01:00
parent 49a38dd1ae
commit 30aa64fd2b
1 changed files with 30 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

48
meta_data_analysis/combine_dfs.py
View file

@ -6,35 +6,36 @@ Created on Tue Aug 6 12:56:03 2019
@author: tanu
'''
# FIXME: change filename 4 (mcsm normalised data)
# to be consistent like (pnca_mcsm_norm.csv)
# 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
# pnca_dssp.csv
# pnca_kd.csv
# pnca_rd.csv
# merge 1: of 3 dfs (filenames in lowercase)
# <gene.lower()>_dssp.csv
# <gene.lower()>_kd.csv
# <gene.lower()>_pnca_rd.csv
# merge 2: of 2 dfs
# mcsm_complex1_normalised.csv (!fix name)
# pnca_complex_mcsm_norm.csv (!fix name in mcsm script)
# output df from merge1
# Input: 3 dfs
# pnca_dssp.csv
# pnca_kd.csv
# pnca_rd.csv
# mcsm_complex1_normalised.csv (!fix name)
# <gene.lower()>_dssp.csv
# <gene.lower()>_kd.csv
# <gene.lower()>_pnca_rd.csv
# pnca_complex_mcsm_norm.csv (!fix name in mcsm script)
# Output: .csv of all 4 dfs combined
# useful link
#https://stackoverflow.com/questions/23668427/pandas-three-way-joining-multiple-dataframes-on-columns
# https://stackoverflow.com/questions/23668427/pandas-three-way-joining-multiple-dataframes-on-columns
#=============================================================================
#%% load packages
import sys, os
import pandas as pd
#import numpy as np
#=============================================================================
import argparse
#=======================================================================
#%% specify input and curr dir
homedir = os.path.expanduser('~')
@ -42,27 +43,36 @@ homedir = os.path.expanduser('~')
os.getcwd()
os.chdir(homedir + '/git/LSHTM_analysis/meta_data_analysis')
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
args = arg_parser.parse_args()
#=======================================================================
#%% variable assignment: input and output
drug = 'pyrazinamide'
gene = 'pncA'
gene_match = gene + '_p.'
#drug = 'pyrazinamide'
#gene = 'pncA'
#gene_match = gene + '_p.'
drug = args.drug
gene = args.gene
#==========
# data dir
#==========
#indir = 'git/Data/pyrazinamide/input/original'
datadir = homedir + '/' + 'git/Data'
#=======
# input
#=======
#indir = 'git/Data/pyrazinamide/input/original'
indir = datadir + '/' + drug + '/' + 'output'
in_filename1 = 'pnca_dssp.csv'
in_filename2 = 'pnca_kd.csv'
in_filename3 = 'pnca_rd.csv'
in_filename4 = 'mcsm_complex1_normalised.csv' # FIXNAME
#in_filename4 = 'mcsm_complex1_normalised.csv' # Fix name in mcsm script
in_filename4 = 'pnca_complex_mcsm_norm.csv' # manually changed temporarily
infile1 = indir + '/' + in_filename1
infile2 = indir + '/' + in_filename2