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

disseted features to run all baseline YC models added

Browse source
This commit is contained in:
Tanushree Tunstall 2022-05-29 07:37:10 +01:00
parent 8305f7b6bd
commit dad7cbdd28
1 changed files with 11 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

31
uq_ml_models_FS/scriptfsycm.py
View file

@ -296,12 +296,22 @@ CVResultsDF_smnc.sort_values(by=['matthew'], ascending=False, inplace=True)
BTSResultsDF_smnc = YC_resD_smnc['BlindTestResultsDF']
BTSResultsDF_smnc.sort_values(by=['matthew'], ascending=False, inplace=True)
##############################################################################
#============================================
# BASELINE models with dissected featues
#============================================
# Genomics
yC_gf = run_all_ML(input_pd=X[X_genomicFN], target_label=y, blind_test_input_df=X_bts[X_genomicFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
yc_gfCT_baseline= yC_gf['CrossValResultsDF']
yc_gfCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_gfBT_baseline = yC_gf['BlindTestResultsDF']
yc_gfBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# Evolutionary
yC_ev = run_all_ML(input_pd=X[X_evolFN], target_label=y, blind_test_input_df=X_bts[X_evolFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
yc_evCT_baseline= yC_ev['CrossValResultsDF']
yc_evCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_evBT_baseline = yC_ev['BlindTestResultsDF']
yc_evBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# strucF:All
yC_sfall = run_all_ML(input_pd=X[X_strFN], target_label=y, blind_test_input_df=X_bts[X_strFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
@ -310,8 +320,7 @@ yc_sfallCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_sfallBT_baseline = yC_sfall['BlindTestResultsDF']
yc_sfallBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# strucF:Common
# strucF:Common ONLY
yC_sfco= run_all_ML(input_pd=X[common_cols_stabiltyN], target_label=y
, blind_test_input_df=X_bts[common_cols_stabiltyN]
, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
@ -320,7 +329,6 @@ yc_sfcoCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_sfcoBT_baseline = yC_sfco['BlindTestResultsDF']
yc_sfcoBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# strucF:common_stability + foldX_cols i.e interaction
yC_fxss= run_all_ML(input_pd=X[common_cols_stabiltyN+foldX_cols], target_label=y
, blind_test_input_df=X_bts[common_cols_stabiltyN+foldX_cols]
@ -330,17 +338,6 @@ yc_fxssCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_fxssBT_baseline = yC_fxss['BlindTestResultsDF']
yc_fxssBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# strucF:foldX_cols i.e interaction
yC_fx= run_all_ML(input_pd=X[common_cols_stabiltyN+foldX_cols], target_label=y
, blind_test_input_df=X_bts[common_cols_stabiltyN+foldX_cols]
, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
yc_fxCT_baseline= yC_fx['CrossValResultsDF']
yc_fxCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_fxBT_baseline = yC_fx['BlindTestResultsDF']
yc_fxBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# categorical
yC_cat= run_all_ML(input_pd=X[categorical_FN], target_label=y
, blind_test_input_df=X_bts[categorical_FN]
@ -351,9 +348,3 @@ yc_catBT_baseline = yC_cat['BlindTestResultsDF']
yc_catBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# Evolutionary
yC_ev = run_all_ML(input_pd=X[X_evolFN], target_label=y, blind_test_input_df=X_bts[X_evolFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
yc_evCT_baseline= yC_ev['CrossValResultsDF']
yc_evCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_evBT_baseline = yC_ev['BlindTestResultsDF']
yc_evBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)