186 lines
7.9 KiB
Python
Executable file
186 lines
7.9 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Tue Mar 15 11:09:50 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
|
|
# from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
|
|
# from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
|
|
|
|
# from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
|
|
# from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
|
|
|
# from sklearn.pipeline import Pipeline, make_pipeline
|
|
# #%% GLOBALS
|
|
# rs = {'random_state': 42}
|
|
# njobs = {'n_jobs': 10}
|
|
|
|
# scoring_fn = ({'accuracy' : make_scorer(accuracy_score)
|
|
# , 'fscore' : make_scorer(f1_score)
|
|
# , 'mcc' : make_scorer(matthews_corrcoef)
|
|
# , 'precision' : make_scorer(precision_score)
|
|
# , 'recall' : make_scorer(recall_score)
|
|
# , 'roc_auc' : make_scorer(roc_auc_score)
|
|
# , 'jcc' : make_scorer(jaccard_score)
|
|
# })
|
|
|
|
# skf_cv = StratifiedKFold(n_splits = 10
|
|
# #, shuffle = False, random_state= None)
|
|
# , shuffle = True,**rs)
|
|
|
|
# rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
|
# , n_repeats = 3
|
|
# , **rs)
|
|
|
|
# mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
|
# jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
|
|
|
###############################################################################
|
|
#%% MultModelsCl: function call()
|
|
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_BT = baseline_all.filter(like='bts_', axis=1)
|
|
baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
baseline_BT.to_csv(outdir + 'ml/' + gene.lower() + '_baseline_BT_allF.csv')
|
|
|
|
#%% SMOTE NC: Oversampling [Numerical + categorical]
|
|
mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
|
|
, target = y_smnc
|
|
, var_type = 'mixed'
|
|
, skf_cv = skf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
smnc_all = pd.DataFrame(mm_skf_scoresD7)
|
|
smnc_all = smnc_all.T
|
|
|
|
smnc_CT = smnc_all.filter(like='test_', axis=1)
|
|
smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
smnc_BT = smnc_all.filter(like='bts_', axis=1)
|
|
smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
smnc_BT.to_csv(outdir + 'ml/' + gene.lower() + '_smnc_BT_allF.csv')
|
|
|
|
#%% ROS: Numerical + categorical
|
|
mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
|
|
, target = y_ros
|
|
, var_type = 'mixed'
|
|
, skf_cv = skf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
ros_all = pd.DataFrame(mm_skf_scoresD3)
|
|
ros_all = ros_all.T
|
|
|
|
ros_CT = ros_all.filter(like='test_', axis=1)
|
|
ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
ros_BT = ros_all.filter(like='bts_', axis=1)
|
|
ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
ros_BT.to_csv(outdir + 'ml/' + gene.lower() + '_ros_BT_allF.csv')
|
|
#%% RUS: Numerical + categorical
|
|
mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
|
|
, target = y_rus
|
|
, var_type = 'mixed'
|
|
, skf_cv = skf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
rus_all = pd.DataFrame(mm_skf_scoresD4)
|
|
rus_all = rus_all.T
|
|
|
|
rus_CT = rus_all.filter(like='test_', axis=1)
|
|
rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
rus_BT = rus_all.filter(like='bts_' , axis=1)
|
|
rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
rus_BT.to_csv(outdir + 'ml/' + gene.lower() + '_rus_BT_allF.csv')
|
|
#%% ROS + RUS Combined: Numerical + categorical
|
|
mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
|
|
, target = y_rouC
|
|
, var_type = 'mixed'
|
|
, skf_cv = skf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
rouC_all = pd.DataFrame(mm_skf_scoresD8)
|
|
rouC_all = rouC_all.T
|
|
|
|
rouC_CT = rouC_all.filter(like='test_', axis=1)
|
|
rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
rouC_BT = rouC_all.filter(like='bts_', axis=1)
|
|
rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
rouC_BT.to_csv(outdir + 'ml/' + gene.lower() + '_rouC_BT_allF.csv')
|
|
#%% SMOTE OS: Numerical only
|
|
# mm_skf_scoresD2 = MultModelsCl(input_df = X_sm
|
|
# , target = y_sm
|
|
# , var_type = 'numerical'
|
|
# , skf_cv = skf_cv)
|
|
# sm_all = pd.DataFrame(mm_skf_scoresD2)
|
|
# sm_all = sm_all.T
|
|
|
|
# sm_CT = sm_all.filter(like='test_', axis=1)
|
|
#sm_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
# sm_BT = sm_all.filter(like='bts_', axis=1)
|
|
#sm_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
#sm_BT.to_csv(outdir + 'ml/' + gene.lower() + '_sm_BT_allF.csv')
|
|
#%% SMOTE ENN: Over + Undersampling combined: Numerical ONLY
|
|
# mm_skf_scoresD5 = MultModelsCl(input_df = X_enn
|
|
# , target = y_enn
|
|
# , var_type = 'numerical'
|
|
# , skf_cv = skf_cv
|
|
# , blind_test_input_df = X_bts
|
|
# , blind_test_target = y_bts)
|
|
# enn_all = pd.DataFrame(mm_skf_scoresD5)
|
|
# enn_all = enn_all.T
|
|
|
|
# enn_CT = enn_all.filter(like='test_', axis=1)
|
|
#enn_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
# enn_BT = enn_all.filter(like='bts_', axis=1)
|
|
#enn_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
|
|
# Write csv
|
|
#enn_BT.to_csv(outdir + 'ml/' + gene.lower() + '_enn_BT_allF.csv')
|
|
|
|
#%% Repeated ENN
|
|
# mm_skf_scoresD6 = MultModelsCl(input_df = X_renn
|
|
# , target = y_renn
|
|
# , var_type = 'numerical'
|
|
# , skf_cv = skf_cv
|
|
# , blind_test_input_df = X_bts
|
|
# , blind_test_target = y_bts)
|
|
# renn_all = pd.DataFrame(mm_skf_scoresD6)
|
|
# renn_all = renn_all.T
|
|
|
|
# renn_CT = renn_all.filter(like='test_', axis=1)
|
|
#renn_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|
|
|
# renn_BT = renn_all.filter(like='bts_', axis=1)
|
|
# renn_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
|
###############################################################################
|
|
# end of script
|
|
##############################################################################
|