99 lines
4.2 KiB
Python
99 lines
4.2 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Tue Mar 15 11:09:50 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
#%% Data
|
|
X = all_df_wtgt[numerical_FN+categorical_FN]
|
|
y = all_df_wtgt[drug]
|
|
#y = all_df_wtgt['dst_mode']
|
|
#%% variables
|
|
|
|
#%% MultClassPipeSKFCV: function call()
|
|
mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
|
|
, target = y
|
|
, var_type = 'mixed'
|
|
, skf_cv = skf_cv)
|
|
|
|
mm_skf_scores_df_all = pd.DataFrame(mm_skf_scoresD)
|
|
mm_skf_scores_df_all
|
|
mm_skf_scores_df_test = mm_skf_scores_df_all.filter(like='test_', axis=0)
|
|
mm_skf_scores_df_train = mm_skf_scores_df_all.filter(like='train_', axis=0) # helps to see if you trust the results
|
|
baseline_BT = mm_skf_scores_df_all.filter(like='bts_', axis=0)
|
|
|
|
#%%
|
|
mm_skf_scoresD2 = MultClassPipeSKFCV(input_df = X_sm
|
|
, target = y_sm
|
|
, var_type = 'mixed'
|
|
, skf_cv = skf_cv)
|
|
sm_all = pd.DataFrame(mm_skf_scoresD2)
|
|
sm_df_CT = sm_all.filter(like='test_', axis=0)
|
|
sm_df_BT = sm_all.filter(like='bts_', axis=0)
|
|
|
|
#%%
|
|
mm_skf_scoresD3 = MultClassPipeSKFCV(input_df = X_ros
|
|
, target = y_ros
|
|
, var_type = 'mixed'
|
|
, skf_cv = rskf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
ros_all = pd.DataFrame(mm_skf_scoresD3)
|
|
ros_CT = ros_all.filter(like='test_', axis=0)
|
|
ros_BT = ros_all.filter(like='bts_', axis=0)
|
|
#--------- combined
|
|
mm_skf_scoresD3v2 = MultClassPipeSKFCV(input_df = X_rouC
|
|
, target = y_rouC
|
|
, var_type = 'mixed'
|
|
, skf_cv = rskf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
rouC_all = pd.DataFrame(mm_skf_scoresD3v2)
|
|
rouC_CT = ros_all.filter(like='test_', axis=0)
|
|
rouC_BT = ros_all.filter(like='bts_', axis=0)
|
|
|
|
|
|
#%%
|
|
mm_skf_scoresD4 = MultClassPipeSKFCV(input_df = X_rus
|
|
, target = y_rus
|
|
, var_type = 'numerical'
|
|
, skf_cv = rskf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
rus_all = pd.DataFrame(mm_skf_scoresD4)
|
|
rus_CT = rus_all.filter(like='test_', axis=0)
|
|
rus_BT = rus_all.filter(like='bts_' , axis=0)
|
|
|
|
#%%
|
|
mm_skf_scoresD5 = MultClassPipeSKFCV(input_df = X_enn
|
|
, target = y_enn
|
|
, var_type = 'numerical'
|
|
, skf_cv = rskf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
enn_all = pd.DataFrame(mm_skf_scoresD5)
|
|
enn_CT = enn_all.filter(like='test_', axis=0)
|
|
enn_BT = enn_all.filter(like='bts_', axis=0)
|
|
#%%
|
|
mm_skf_scoresD6 = MultClassPipeSKFCV(input_df = X_renn
|
|
, target = y_renn
|
|
, var_type = 'numerical'
|
|
, skf_cv = rskf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
renn_all = pd.DataFrame(mm_skf_scoresD6)
|
|
renn_CT = renn_all.filter(like='test_', axis=0)
|
|
renn_BT = renn_all.filter(like='bts_', axis=0)
|
|
|
|
#%%: with categorical values + oversampling
|
|
mm_skf_scoresD7 = MultClassPipeSKFCV(input_df = X_smnc
|
|
, target = y_smnc
|
|
, var_type = 'mixed'
|
|
, skf_cv = rskf_cv
|
|
, blind_test_input_df = X_bts
|
|
, blind_test_target = y_bts)
|
|
smnc_all = pd.DataFrame(mm_skf_scoresD7)
|
|
smnc_CT = smnc_all.filter(like='test_', axis=0)
|
|
smnc_BT = smnc_all.filter(like='bts_', axis=0)
|
|
|