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

added dummy classifier to models

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-27 17:10:04 +01:00
parent c32005c99c
commit 744bc8f4a1
4 changed files with 94 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

23
scripts/ml/ml_functions/test_func_singlegene.py
View file

@ -14,10 +14,11 @@ sys.path
# import
from GetMLData import *
from SplitTTS import *
#from MultClfs import *
from MultClfs_SIMPLE import *
from MultClfs import *
#from MultClfs_SIMPLE import *
#%%
rs = {'random_state': 42}
skf_cv = StratifiedKFold(n_splits = 10
, shuffle = True,**rs)
#sel_cv = logo
@ -28,12 +29,12 @@ skf_cv = StratifiedKFold(n_splits = 10
gene_model_paramD = {'data_combined_model' : False
, 'use_or' : False
, 'omit_all_genomic_features': False
, 'write_maskfile' : True
, 'write_maskfile' : False
, 'write_outfile' : False }
#df = getmldata(gene, drug, **gene_model_paramD)
df = getmldata('pncA', 'pyrazinamide', **gene_model_paramD)
#df = getmldata('embB', 'ethambutol' , **gene_model_paramD)
#df = getmldata('pncA', 'pyrazinamide', **gene_model_paramD)
df = getmldata('embB', 'ethambutol' , **gene_model_paramD)
#df = getmldata('katG', 'isoniazid' , **gene_model_paramD)
#df = getmldata('rpoB', 'rifampicin' , **gene_model_paramD)
#df = getmldata('gid' , 'streptomycin' , **gene_model_paramD)
@ -68,9 +69,8 @@ len(df)
Counter(df2['y'])
Counter(df2['y_bts'])
fooD = MultModelsCl(input_df = df2['X_ros']
, target = df2['y_ros']
fooD = MultModelsCl(input_df = df2['X']
, target = df2['y']
, sel_cv = skf_cv
, run_blind_test = True
, blind_test_df = df2['X_bts']
@ -87,7 +87,12 @@ for k, v in fooD.items():
, '\nTRAIN MCC:', fooD[k]['test_mcc']
, '\nBTS MCC:' , fooD[k]['bts_mcc']
, '\nDIFF:',fooD[k]['bts_mcc'] - fooD[k]['test_mcc'] )
for k, v in fooD.items():
print('\nModel:', k
, '\nTRAIN ACCURACY:', fooD[k]['test_accuracy']
, '\nBTS ACCURACY:' , fooD[k]['bts_accuracy']
, '\nDIFF:',fooD[k]['bts_accuracy'] - fooD[k]['test_accuracy'] )
#%% CHECK SCALING
embb_df = getmldata('embB', 'ethambutol' , **combined_model_paramD)
all(embb_df.columns.isin(['gene_name'])) # should be False