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

multiple changes

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-02 10:25:42 +01:00
parent 2fda32901b
commit dccd3c8eb2
7 changed files with 82 additions and 122 deletions
Download patch file Download diff file Expand all files Collapse all files

7
scripts/ml/ml_functions/MultClfs.py
View file

@ -344,12 +344,7 @@ def MultModelsCl(input_df, target, skf_cv
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
#ADD: target numbers for bts
yc2 = Counter(blind_test_target)
yc2_ratio = yc2[0]/yc2[1]
mm_skf_scoresD[model_name]['n_test_size'] = len(blind_test_df)
mm_skf_scoresD[model_name]['n_testY_ratio']= round(yc2_ratio,2)
#return(mm_skf_scoresD)
#============================

6
scripts/ml/ml_functions/MultClfs_logo.py
View file

@ -357,12 +357,6 @@ def MultModelsCl_logo(input_df
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
#ADD: target numbers for bts
yc2 = Counter(blind_test_target)
yc2_ratio = yc2[0]/yc2[1]
mm_skf_scoresD[model_name]['n_test_size'] = len(blind_test_df)
mm_skf_scoresD[model_name]['n_testY_ratio']= round(yc2_ratio,2)
#return(mm_skf_scoresD)
#============================

7
scripts/ml/ml_functions/MultClfs_logo_skf.py
View file

@ -369,12 +369,7 @@ def MultModelsCl_logo_skf(input_df
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
#ADD: target numbers for bts
yc2 = Counter(blind_test_target)
yc2_ratio = yc2[0]/yc2[1]
mm_skf_scoresD[model_name]['n_test_size'] = len(blind_test_df)
mm_skf_scoresD[model_name]['n_testY_ratio']= round(yc2_ratio,2)
#return(mm_skf_scoresD)
#============================

4
scripts/ml/ml_functions/ml_data_combined.py
View file

@ -67,4 +67,8 @@ if 'gene_name' in colnames_combined_df:
print("\nGene name included")
else:
('\nGene name NOT included')
omit_gene_alr = ['alr']
cm_input_df5 = combined_df[~combined_df['gene_name'].isin(omit_gene_alr)]
##############################################################################