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

added option to add confusion matrix and target numbers in the mult function

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-20 17:08:22 +01:00
parent 905327bf4e
commit 135efcee41
3 changed files with 144 additions and 140 deletions
Download patch file Download diff file Expand all files Collapse all files

40
scripts/ml/pnca_config_dissected.py
View file

@ -104,29 +104,29 @@ else:
print('\n#####################################################################\n')
###############################################################################
#==================
# Baseline models
#==================
mm_skf_scoresD = MultModelsCl(input_df = X
, target = y
, var_type = 'mixed'
, skf_cv = skf_cv
, blind_test_input_df = X_bts
, blind_test_target = y_bts)
# ###############################################################################
# #==================
# # Baseline models
# #==================
# mm_skf_scoresD = MultModelsCl(input_df = X
# , target = y
# , var_type = 'mixed'
# , skf_cv = skf_cv
# , blind_test_input_df = X_bts
# , blind_test_target = y_bts)
baseline_all = pd.DataFrame(mm_skf_scoresD)
baseline_all = baseline_all.T
#baseline_train = baseline_all.filter(like='train_', axis=1)
baseline_CT = baseline_all.filter(like='test_', axis=1)
baseline_CT.sort_values(by=['test_mcc'], ascending=False, inplace=True)
# baseline_all = pd.DataFrame(mm_skf_scoresD)
# baseline_all = baseline_all.T
# #baseline_train = baseline_all.filter(like='train_', axis=1)
# baseline_CT = baseline_all.filter(like='test_', axis=1)
# baseline_CT.sort_values(by=['test_mcc'], ascending=False, inplace=True)
baseline_BT = baseline_all.filter(like='bts_', axis=1)
baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
# baseline_BT = baseline_all.filter(like='bts_', axis=1)
# baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
# Write csv
baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
# # Write csv
# baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
# baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
# #%% SMOTE NC: Oversampling [Numerical + categorical]