added script to combine all files in one
This commit is contained in:
parent
01ef04613a
commit
0973717287
4 changed files with 435 additions and 748 deletions
|
|
@ -8,169 +8,280 @@ Created on Tue Aug 6 12:56:03 2019
|
|||
# FIXME: change filename 2(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 2 dfs on comm_valson cols by detecting them
|
||||
# includes sainity checks
|
||||
# Task: combine 2 dfs with aa position as linking column
|
||||
|
||||
# Input: 2 dfs
|
||||
# <gene.lower()>_complex_mcsm_norm.csv
|
||||
# <gene.lower()>_foldx.csv
|
||||
|
||||
# Output: .csv of all 2 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
|
||||
import numpy as np
|
||||
import re
|
||||
#from varname import nameof
|
||||
import argparse
|
||||
|
||||
#%% end of variable assignment for input and output files
|
||||
#=======================================================================
|
||||
#%% function/methd to combine dfs
|
||||
#%% specify input and curr dir
|
||||
homedir = os.path.expanduser('~')
|
||||
|
||||
def detect_common_cols (df1, df2):
|
||||
"""
|
||||
Detect comm_valson cols
|
||||
|
||||
@param df1: df
|
||||
@type df1: pandas df
|
||||
# set working dir
|
||||
os.getcwd()
|
||||
os.chdir(homedir + '/git/LSHTM_analysis/scripts')
|
||||
os.getcwd()
|
||||
|
||||
@param df2: df
|
||||
@type df2: pandas df
|
||||
|
||||
@return: comm_valson cols
|
||||
@type: list
|
||||
"""
|
||||
common_cols = np.intersect1d(df1.columns, df2.columns).tolist()
|
||||
print('Length of comm_cols:', len(common_cols)
|
||||
, '\nmerging column/s:', common_cols
|
||||
, '\ntype:', type(common_cols)
|
||||
, '\ndtypes in merging columns:\n', df1[common_cols].dtypes)
|
||||
|
||||
return common_cols
|
||||
|
||||
# FIXME: local imports
|
||||
#from combining import combine_dfs_with_checks
|
||||
from combining_FIXME import detect_common_cols
|
||||
#=======================================================================
|
||||
#%% 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
|
||||
#args = arg_parser.parse_args()
|
||||
#=======================================================================
|
||||
#%% variable assignment: input and output
|
||||
drug = 'pyrazinamide'
|
||||
gene = 'pncA'
|
||||
gene_match = gene + '_p.'
|
||||
|
||||
def combine_dfs_with_checks(df1, df2, my_join = 'outer'):
|
||||
"""
|
||||
Combine 2 dfs by finding merging columns automatically
|
||||
#drug = args.drug
|
||||
#gene = args.gene
|
||||
#======
|
||||
# dirs
|
||||
#======
|
||||
datadir = homedir + '/' + 'git/Data'
|
||||
indir = datadir + '/' + drug + '/' + 'input'
|
||||
outdir = datadir + '/' + drug + '/' + 'output'
|
||||
|
||||
@param df1: data frame
|
||||
@type df1: pandas df
|
||||
#=======
|
||||
# input
|
||||
#=======
|
||||
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv'
|
||||
in_filename_foldx = gene.lower() + '_foldx.csv'
|
||||
in_filename_dssp = gene.lower() + '_dssp.csv'
|
||||
in_filename_kd = gene.lower() + '_kd.csv'
|
||||
in_filename_rd = gene.lower() + '_rd.csv'
|
||||
in_filename_snpinfo = 'ns' + gene.lower() + '_snp_info.csv'
|
||||
in_filename_afor = gene.lower() + '_af_or.csv'
|
||||
in_filename_afor_kin = gene.lower() + '_af_or_kinship.csv'
|
||||
|
||||
@param df2: data frame
|
||||
@type df2: pandas df
|
||||
|
||||
@my_join: join type for merging
|
||||
@type my_join: string
|
||||
|
||||
@return: combined_df
|
||||
@type: pandas df
|
||||
"""
|
||||
|
||||
print('Finding comm_cols and merging cols:'
|
||||
,'\n=========================================================')
|
||||
|
||||
common_cols = np.intersect1d(df1.columns, df2.columns).tolist()
|
||||
print('Length of comm_cols:', len(common_cols)
|
||||
, '\nmerging column/s:', common_cols
|
||||
, '\ntype:', type(common_cols))
|
||||
|
||||
#print('\ndtypes in merging columns:\n', df1[common_cols].dtypes)
|
||||
|
||||
print('selecting consistent dtypes for merging (object i.e string)')
|
||||
#merging_cols = df1[comm_valson_cols].select_dtypes(include = [object]).columns.tolist()
|
||||
#merging_cols = df1[comm_valson_cols].select_dtypes(include = ['int64']).columns.tolist()
|
||||
merging_cols = common_cols.copy()
|
||||
infile_mcsm = outdir + '/' + in_filename_mcsm
|
||||
infile_foldx = outdir + '/' + in_filename_foldx
|
||||
infile_dssp = outdir + '/' + in_filename_dssp
|
||||
infile_kd = outdir + '/' + in_filename_kd
|
||||
infile_rd = outdir + '/' + in_filename_rd
|
||||
infile_snpinfo = indir + '/' + in_filename_snpinfo
|
||||
infile_afor = outdir + '/' + in_filename_afor
|
||||
infile_afor_kin = outdir + '/' + in_filename_afor_kin
|
||||
|
||||
nmerging_cols = len(merging_cols)
|
||||
print(' length of merging cols:', nmerging_cols
|
||||
, '\nmerging cols:', merging_cols, 'type:', type(merging_cols)
|
||||
, '\n=========================================================')
|
||||
|
||||
print('\nInput path:', outdir
|
||||
, '\nInput filename mcsm:', infile_mcsm
|
||||
, '\nInput filename foldx:', infile_foldx
|
||||
, '\nInput filename dssp:', infile_dssp
|
||||
, '\nInput filename kd:', infile_kd
|
||||
, '\nInput filename rd', infile_rd
|
||||
, '\nInput filename snp info:', infile_snpinfo
|
||||
, '\nInput filename af or:', infile_afor
|
||||
, '\nInput filename afor kinship:', infile_afor_kin
|
||||
, '\n============================================================')
|
||||
|
||||
#=======
|
||||
# output
|
||||
#=======
|
||||
out_filename_comb = gene.lower() + '_all_params.csv'
|
||||
outfile_comb = outdir + '/' + out_filename_comb
|
||||
print('Output filename:', outfile_comb
|
||||
, '\n============================================================')
|
||||
|
||||
o_join = 'outer'
|
||||
l_join = 'left'
|
||||
r_join = 'right'
|
||||
i_join = 'inner'
|
||||
|
||||
# end of variable assignment for input and output files
|
||||
#&%%====================================================================
|
||||
mcsm_df = pd.read_csv(infile_mcsm, sep = ',')
|
||||
mcsm_df.columns = mcsm_df.columns.str.lower()
|
||||
foldx_df = pd.read_csv(infile_foldx , sep = ',')
|
||||
|
||||
print('==================================='
|
||||
, '\nFirst merge: mcsm + foldx'
|
||||
, '\n===================================')
|
||||
#mcsm_foldx_dfs = combine_dfs_with_checks(mcsm_df, foldx_df, my_join = o_join)
|
||||
merging_cols_m1 = detect_common_cols(mcsm_df, foldx_df)
|
||||
|
||||
mcsm_foldx_dfs = pd.merge(mcsm_df, foldx_df, on = merging_cols_m1, how = 'outer')
|
||||
ncols_m1 = len(mcsm_foldx_dfs.columns)
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
print('==================================='
|
||||
, '\nSecond merge: dssp + kd'
|
||||
, '\n===================================')
|
||||
|
||||
dssp_df = pd.read_csv(infile_dssp, sep = ',')
|
||||
kd_df = pd.read_csv(infile_kd, sep = ',')
|
||||
rd_df = pd.read_csv(infile_rd, sep = ',')
|
||||
|
||||
#dssp_kd_dfs = combine_dfs_with_checks(dssp_df, kd_df, my_join = o_join)
|
||||
merging_cols_m2 = detect_common_cols(dssp_df, kd_df)
|
||||
|
||||
dssp_kd_dfs = pd.merge(dssp_df, kd_df, on = merging_cols_m2, how = 'outer')
|
||||
|
||||
print('==================================='
|
||||
, '\nThird merge: dssp_kd_dfs + rd_df'
|
||||
, '\n===================================')
|
||||
#dssp_kd_rd_dfs = combine_dfs_with_checks(dssp_kd_dfs, rd_df, my_join = o_join)
|
||||
merging_cols_m3 = detect_common_cols(dssp_df, kd_df)
|
||||
dssp_kd_rd_dfs = pd.merge(dssp_kd_dfs, rd_df, on = merging_cols_m3, how = 'outer')
|
||||
|
||||
ncols_m3 = len(dssp_kd_rd_dfs.columns)
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
print('==================================='
|
||||
, '\nFourth merge: First merge + Third merge'
|
||||
, '\n===================================')
|
||||
#combined_dfs = combine_dfs_with_checks(mcsm_foldx_dfs, dssp_kd_rd_dfs, my_join = i_join)# gives wrong!
|
||||
merging_cols_m4 = detect_common_cols(mcsm_foldx_dfs, dssp_kd_rd_dfs)
|
||||
combined_df_expected_cols = ncols_m1 + ncols_m3 - len(merging_cols_m4)
|
||||
|
||||
combined_df = pd.merge(mcsm_foldx_dfs, dssp_kd_rd_dfs, on = merging_cols_m4, how = 'inner')
|
||||
|
||||
|
||||
if len(combined_df) == len(mcsm_df) and len(combined_df.columns) == combined_df_expected_cols:
|
||||
print('PASS: successfully combined 5 dfs'
|
||||
, '\nnrows combined_df:', len(combined_df)
|
||||
, '\ncols combined_df:', len(combined_df.columns))
|
||||
else:
|
||||
sys.exit('FAIL: check individual df merges')
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
#%% OR combining
|
||||
afor_df = pd.read_csv(infile_afor, sep = ',')
|
||||
afor_df.columns = afor_df.columns.str.lower()
|
||||
|
||||
if afor_df['mutation'].shape[0] == afor_df['mutation'].nunique():
|
||||
print('No duplicate muts detected in afor_df')
|
||||
else:
|
||||
print('Dropping duplicate muts detected in afor_df')
|
||||
afor_df = afor_df.drop_duplicates(subset = 'mutation', keep = 'first')
|
||||
|
||||
|
||||
snpinfo_df_all = pd.read_csv(infile_snpinfo, sep = ',')
|
||||
snpinfo_df = snpinfo_df_all[['mutation', 'mutationinformation']]
|
||||
|
||||
|
||||
if snpinfo_df['mutation'].shape[0] == snpinfo_df['mutation'].nunique():
|
||||
print('No duplicate muts detected in snpinfo_df')
|
||||
else:
|
||||
dups = snpinfo_df['mutation'].duplicated().sum()
|
||||
print( dups, 'Duplicate muts detected in snpinfo_df'
|
||||
, '\nDim:', snpinfo_df.shape)
|
||||
print('Dropping duplicate muts')
|
||||
snpinfo_df = snpinfo_df.drop_duplicates(subset = 'mutation', keep = 'first')
|
||||
print('Dim:', snpinfo_df.shape)
|
||||
|
||||
print('==================================='
|
||||
, '\nFifth merge: afor_df + snpinfo_df'
|
||||
, '\n===================================')
|
||||
|
||||
merging_cols_m5 = detect_common_cols(afor_df, snpinfo_df)
|
||||
|
||||
afor_snpinfo_dfs = pd.merge(afor_df, snpinfo_df, on = merging_cols_m5, how = 'left')
|
||||
if len(afor_snpinfo_dfs) == afor_df.shape[0]:
|
||||
print('PASS: succesfully combined with left join'
|
||||
, '\nDim of df1:', afor_df.shape
|
||||
, '\nDim of df2:', snpinfo_df.shape)
|
||||
else:
|
||||
sys.exit('FAIL: unsuccessful merge')
|
||||
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
afor_kin_df = pd.read_csv(infile_afor_kin, sep = ',')
|
||||
afor_kin_df.columns = afor_kin_df.columns.str.lower()
|
||||
|
||||
print('==================================='
|
||||
, '\nSixth merge: afor_snpinfo_dfs + afor_kin_df'
|
||||
, '\n===================================')
|
||||
|
||||
merging_cols_m6 = detect_common_cols(afor_snpinfo_dfs, afor_kin_df)
|
||||
|
||||
print('Dim of df1:', afor_snpinfo_dfs.shape
|
||||
, '\nDim of df2:', afor_kin_df.shape
|
||||
, '\nno. of merging_cols:', len(merging_cols_m6))
|
||||
|
||||
ors_df = pd.merge(afor_snpinfo_dfs, afor_kin_df, on = merging_cols_m6, how = 'outer')
|
||||
|
||||
print('Dim of ors_df:', ors_df.shape)
|
||||
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
print('==================================='
|
||||
, '\nSeventh merge: combined_df + ors_df'
|
||||
, '\n===================================')
|
||||
|
||||
merging_cols_m7 = detect_common_cols(combined_df, ors_df)
|
||||
|
||||
print('Dim of df1:', combined_df.shape
|
||||
, '\nDim of df2:', ors_df.shape
|
||||
, '\nno. of merging_cols:', len(merging_cols_m7))
|
||||
|
||||
print('checking mutations in the two dfs:'
|
||||
, '\nmuts in df1 but NOT in df2:'
|
||||
, combined_df['mutationinformation'].isin(ors_df['mutationinformation']).sum()
|
||||
, '\nmuts in df2 but NOT in df1:'
|
||||
, ors_df['mutationinformation'].isin(combined_df['mutationinformation']).sum())
|
||||
|
||||
#print('\nNo. of common muts:', np.intersect1d(combined_df['mutationinformation'], ors_df['mutationinformation']) )
|
||||
|
||||
#combined_df_all = pd.merge(combined_df, ors_df, on = merging_cols_m7, how = 'outer') # FIXME
|
||||
combined_df_all = pd.merge(combined_df, ors_df, on = merging_cols_m7, how = 'left')
|
||||
|
||||
outdf_expected_rows = len(combined_df)
|
||||
outdf_expected_cols = len(combined_df.columns) + len(ors_df.columns) - len(merging_cols_m7)
|
||||
|
||||
print('\nDim of combined_df_all:', combined_df_all.shape
|
||||
, '\nwith join type: ????')
|
||||
|
||||
if combined_df_all.shape[1] == outdf_expected_cols:
|
||||
print('combined_df has expected no. of cols')
|
||||
if combined_df_all.shape[0] == outdf_expected_rows:
|
||||
print('combined_df has expected no. of rows')
|
||||
else:
|
||||
print('WARNING: nrows discrepancy noted'
|
||||
, '\nFIX IT')
|
||||
print ('thing finished')
|
||||
#%%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
# write csv
|
||||
|
||||
combined_df_all.to_csv(outfile_comb, index = False)
|
||||
|
||||
#=======================================================================
|
||||
#%% incase you FIX the the function: combine_dfs_with_checks
|
||||
#def main():
|
||||
|
||||
#========================
|
||||
# merge 1 (combined_df)
|
||||
# concatenating 2dfs:
|
||||
# df1, df2
|
||||
#========================
|
||||
# checking cross-over of mutations in the two dfs to merge
|
||||
ndiff_1 = df1[merging_cols].squeeze().isin(df2[merging_cols].squeeze()).sum()
|
||||
ndiff1 = df1.shape[0] - ndiff_1
|
||||
print('There are', ndiff1, 'unmatched mutations in left df')
|
||||
# print('Reading input files:')
|
||||
#mcsm_df = pd.read_csv(infile_mcsm, sep = ',')
|
||||
#mcsm_df.columns = mcsm_df.columns.str.lower()
|
||||
|
||||
#foldx_df = pd.read_csv(infile_foldx , sep = ',')
|
||||
|
||||
#dssp_df = pd.read_csv(infile_dssp, sep = ',')
|
||||
#dssp_df.columns = dssp_df.columns.str.lower()
|
||||
|
||||
#kd_df = pd.read_csv(infile_kd, sep = ',')
|
||||
#kd_df.columns = kd_df.columns.str.lower()
|
||||
|
||||
#missing_mutinfo = df1[~left_df['mutationinformation'].isin(df2['mutationinformation'])]
|
||||
#missing_mutinfo.to_csv('infoless_muts.csv')
|
||||
#rd_df = pd.read_csv(infile_kd, sep = ',')
|
||||
|
||||
|
||||
|
||||
ndiff_2 = df2[merging_cols].squeeze().isin(df1[merging_cols].squeeze()).sum()
|
||||
ndiff2 = df2.shape[0] - ndiff_2
|
||||
print('There are', ndiff2, 'unmatched mutations in right_df')
|
||||
|
||||
#comm_vals = np.intersect1d(df1[merging_cols], df2[merging_cols])
|
||||
#comm_vals_count = len(comm_vals)
|
||||
#print('length of comm_valson values:', comm_vals_count , '\ntype:', type(comm_vals_count))
|
||||
|
||||
#========================
|
||||
# merging dfs & sanity checks
|
||||
#========================
|
||||
fail = False
|
||||
print('combing with:', my_join)
|
||||
comb_df = pd.merge(df1, df2, on = merging_cols, how = my_join)
|
||||
|
||||
expected_cols = df1.shape[1] + df2.shape[1] - nmerging_cols
|
||||
|
||||
|
||||
if my_join == 'right':
|
||||
df2_nd = df2.drop_duplicates(merging_cols, keep = 'first')
|
||||
expected_rows = df2_nd.shape[0]
|
||||
|
||||
if my_join == 'left':
|
||||
expected_rows = df1.shape[0]
|
||||
|
||||
|
||||
#if my_join == 'inner':
|
||||
# expected_rows = comm_vals_count
|
||||
|
||||
#if my_join == 'outer':
|
||||
# df1_nd = df1.drop_duplicates(merging_cols, keep = 'first')
|
||||
# df2_nd = df2.drop_duplicates(merging_cols, keep = 'first')
|
||||
# expected_rows = df1_nd.shape[0] + df2_nd.shape[0] - comm_vals_count
|
||||
|
||||
|
||||
if my_join == ('inner' or 'outer') and len(merging_cols) > 1:
|
||||
#comm_vals = np.intersect1d(df1['mutationinformation'], df2['mutationinformation'])
|
||||
print('length of merging_cols > 1, therefore omitting row checks')
|
||||
combined_df = comb_df.copy()
|
||||
expected_rows = len(combined_df)
|
||||
|
||||
else:
|
||||
comm_vals = np.intersect1d(df1[merging_cols], df2[merging_cols])
|
||||
print('length of merging_cols == 1, calculating expected rows in merged_df')
|
||||
combined_df = comb_df.drop_duplicates(subset = merging_cols, keep ='first')
|
||||
if my_join == 'inner':
|
||||
expected_rows = len(comm_vals)
|
||||
if my_join == 'outer':
|
||||
df1_nd = df1.drop_duplicates(merging_cols, keep = 'first')
|
||||
df2_nd = df2.drop_duplicates(merging_cols, keep = 'first')
|
||||
expected_rows = df1_nd.shape[0] + df2_nd.shape[0] - len(comm_vals)
|
||||
|
||||
if len(combined_df) == expected_rows and len(combined_df.columns) == expected_cols:
|
||||
print('PASS: successfully combined dfs with:', my_join, 'join')
|
||||
else:
|
||||
print('FAIL: combined_df\'s expected rows and cols not matched')
|
||||
fail = True
|
||||
print('\nExpected no. of rows:', expected_rows
|
||||
, '\nGot:', len(combined_df)
|
||||
, '\nExpected no. of cols:', expected_cols
|
||||
, '\nGot:', len(combined_df.columns))
|
||||
if fail:
|
||||
sys.exit()
|
||||
|
||||
#if clean:
|
||||
#foo = combined_df2.filter(regex = r'.*_x|_y', axis = 1)
|
||||
#print(foo.columns)
|
||||
#print('Detected duplicate cols with suffix: _x _y'
|
||||
# , '\Dropping duplicate cols and cleaning')
|
||||
|
||||
# drop position col containing suffix '_y' and then rename col without suffix
|
||||
combined_df_clean = combined_df.drop(combined_df.filter(regex = r'.*_y').columns, axis = 1)
|
||||
combined_df_clean.rename(columns=lambda x: re.sub('_x$','', x), inplace = True)
|
||||
|
||||
return combined_df_clean
|
||||
|
||||
#%% end of function
|
||||
#=======================================================================
|
||||
|
||||
#if __name__ == '__main__':
|
||||
# main()
|
||||
#=======================================================================
|
||||
#%% end of script
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue