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

trying to resolve copy warning in code

Browse source
This commit is contained in:
Tanushree Tunstall 2020-07-13 12:20:43 +01:00
parent 5655af42c0
commit da0c03c2e0
1 changed files with 10 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

19
scripts/or_kinship_link.py
View file

@ -34,8 +34,8 @@ arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb fi
arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + <drug> + output') arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + <drug> + output')
# FIXME: remove defaults # FIXME: remove defaults
arg_parser.add_argument('-s', '--start_coord', help = 'start of coding region (cds) of gene', default = 2288681) # pnca cds arg_parser.add_argument('-sc', '--start_coord', help = 'start of coding region (cds) of gene', default = None, type = int) # pnca cds
arg_parser.add_argument('-e', '--end_coord', help = 'end of coding region (cds) of gene', default = 2289241) # pnca cds arg_parser.add_argument('-ec', '--end_coord', help = 'end of coding region (cds) of gene', default = None, type = int) # pnca cds
arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode') arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode')
@ -314,18 +314,21 @@ print('No. of cols pre-formatting data:', df_ncols
#1) Add column: OR for kinship calculated from beta coef #1) Add column: OR for kinship calculated from beta coef
ncols_add = 0 ncols_add = 0
if not 'or_kin' in dfm2_mis.columns: if not 'or_kin' in dfm2_mis.columns:
dfm2_mis['or_kin'] = np.exp(dfm2_mis['beta']) #dfm2_mis['or_kin'] = np.exp(dfm2_mis['beta']) # gives copy warning
dfm2_mis.loc[:,'or_kin'] = np.exp(dfm2_mis.loc[:,'beta'])
print(dfm2_mis['or_kin'].head()) print(dfm2_mis['or_kin'].head())
ncols_add+=1 ncols_add+=1
print('Calculating OR from beta coeff by exponent function and adding column:' print('Calculating OR from beta coeff by exponent function and adding column:'
, '\nNo. of cols added:', ncols_add, '\n' , '\nNo. of cols added:', ncols_add
, dfm2_mis['beta'].head() , '\n', dfm2_mis['beta'].head()
, '\nNo. of cols after adding OR_kin:', len(dfm2_mis.columns)
, '\n===================================================================') , '\n===================================================================')
if dfm2_mis.shape[1] == df_ncols + ncols_add: if dfm2_mis.shape[1] == df_ncols + ncols_add:
print('PASS: Dimension of df match' print('PASS: Dimension of df match'
, '\nDim of df:', dfm2_mis.shape , '\nDim of df:', dfm2_mis.shape
, 'n================================================================') , '\n================================================================')
else: else:
print('FAIL: Dim mismatch' print('FAIL: Dim mismatch'
, '\nOriginal no. of cols:', df_ncols , '\nOriginal no. of cols:', df_ncols
@ -333,8 +336,6 @@ else:
, '\nGot:', dfm2_mis.shape[1]) , '\nGot:', dfm2_mis.shape[1])
sys.exit() sys.exit()
print('No. of cols after adding OR_kin:', len(dfm2_mis.columns))
#2) rename columns to reflect that it is coming from kinship matrix adjustment #2) rename columns to reflect that it is coming from kinship matrix adjustment
dfm2_mis.rename(columns = {'af': 'af_kin' dfm2_mis.rename(columns = {'af': 'af_kin'
, 'beta': 'beta_kin' , 'beta': 'beta_kin'
@ -399,7 +400,7 @@ else:
sys.exit() sys.exit()
del(df_ncols) del(df_ncols)
#%% #%%=====================================================================
#4) reorder columnn #4) reorder columnn
print('Reordering', dfm2_mis.shape[1], 'columns' print('Reordering', dfm2_mis.shape[1], 'columns'
, '\n===============================================') , '\n===============================================')