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

minor edits to format mcsm data like sorting df

Browse source
This commit is contained in:
Tanushree Tunstall 2020-07-09 11:15:56 +01:00
parent 8931441fa5
commit 6961a9cdb3
4 changed files with 127 additions and 85 deletions
Download patch file Download diff file Expand all files Collapse all files

56
mcsm/mcsm.py
View file

@ -376,23 +376,34 @@ def format_mcsm_output(mcsm_outputcsv):
# adding column: wild_position
# useful for plots and db
#############
print('Creating column: wild_position')
mcsm_data['wild_position'] = mcsm_data['wild_type'] + mcsm_data['position'].astype(str)
print(mcsm_data['wild_position'].head())
print('Creating column: wild_pos')
mcsm_data['wild_pos'] = mcsm_data['wild_type'] + mcsm_data['position'].astype(str)
print(mcsm_data['wild_pos'].head())
# Remove spaces b/w pasted columns
print('removing white space within column: wild_position')
mcsm_data['wild_position'] = mcsm_data['wild_position'].str.replace(' ', '')
print('Correctly formatted column: wild_position\n', mcsm_data['wild_position'].head()
print('removing white space within created column: wild_pos')
mcsm_data['wild_pos'] = mcsm_data['wild_pos'].str.replace(' ', '')
print('Correctly formatted column: wild_pos\n', mcsm_data['wild_pos'].head()
, '\n=========================================================')
#%%=====================================================================
#############
# adding column: wild_chain_pos
# useful for plots and db and its explicit
#############
print('Creating column: wild_chain_pos')
mcsm_data['wild_chain_pos'] = mcsm_data['wild_type'] + mcsm_data['chain'] + mcsm_data['position'].astype(str)
print(mcsm_data['wild_chain_pos'].head())
# Remove spaces b/w pasted columns
print('removing white space within created column: wild_chain_pos')
mcsm_data['wild_chain_pos'] = mcsm_data['wild_chain_pos'].str.replace(' ', '')
print('Correctly formatted column: wild_chain_pos\n', mcsm_data['wild_chain_pos'].head()
, '\n=========================================================')
#%%=====================================================================
#############
# ensuring corrrect dtype in non-numeric cols
#############
#############
#) char cols
char_cols = ['PredAffLog', 'mutationinformation', 'wild_type', 'mutant_type', 'chain', 'ligand_id', 'duet_outcome', 'ligand_outcome', 'wild_position']
char_cols = ['PredAffLog', 'mutationinformation', 'wild_type', 'mutant_type', 'chain', 'ligand_id', 'duet_outcome', 'ligand_outcome', 'wild_pos', 'wild_chain_pos']
#mcsm_data[char_cols] = mcsm_data[char_cols].astype(str)
cols_check_char = mcsm_data.select_dtypes(include = 'object').columns.isin(char_cols)
@ -408,36 +419,41 @@ def format_mcsm_output(mcsm_outputcsv):
#%%=====================================================================
# Removing PredAff log column as it is not needed?
print('Removing col: PredAffLog since relevant info has been extracted from it')
mcsm_dataf = mcsm_data.drop(columns = ['PredAffLog'])
mcsm_data_f = mcsm_data.drop(columns = ['PredAffLog'])
#%%=====================================================================
# sort df by position for convenience
print('Sorting df by position')
mcsm_data_fs = mcsm_data_f.sort_values(by = ['position'])
print('sorted df:\n', mcsm_data_fs.head())
#%%=====================================================================
#############
# sanity check before writing file
#############
expected_ncols_toadd = 5
expected_ncols_toadd = 6 # beware hardcoding!
dforig_len = dforig_shape[1]
expected_cols = dforig_len + expected_ncols_toadd
if len(mcsm_dataf.columns) == expected_cols:
if len(mcsm_data_fs.columns) == expected_cols:
print('PASS: formatting successful'
, '\nformatted df has expected no. of cols:', expected_cols
, '\n---------------------------------------------------'
, '\ncolnames:', mcsm_dataf.columns
, '\ncolnames:', mcsm_data_fs.columns
, '\n---------------------------------------------------'
, '\ndtypes in cols:', mcsm_dataf.dtypes
, '\ndtypes in cols:', mcsm_data_fs.dtypes
, '\n---------------------------------------------------'
, '\norig data shape:', dforig_shape
, '\nformatted df shape:', mcsm_dataf.shape
, '\nformatted df shape:', mcsm_data_fs.shape
, '\n===================================================')
else:
sys.exit('FAIL: something went wrong in formatting df'
print('FAIL: something went wrong in formatting df'
, '\nLen of orig df:', dforig_len
, '\nExpected number of cols to add:', expected_ncols_toadd
, '\nExpected no. of cols:', expected_cols, '(', dforig_len, '+', expected_ncols_toadd, ')'
, '\nGot no. of cols:', len(mcsm_dataf.columns)
, '\nGot no. of cols:', len(mcsm_data_fs.columns)
, '\nCheck formatting:'
, '\ncheck hardcoded value:', expected_ncols_toadd
, '\nis', expected_ncols_toadd, 'the no. of expected cols to add?'
, '\n===================================================')
sys.exit()
return mcsm_dataf
return mcsm_data_fs