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

tidy script to run my versions of multiple modles with blind tests and also with oversampled data

Browse source
This commit is contained in:
Tanushree Tunstall 2022-05-28 09:41:30 +01:00
parent b6f0308e42
commit 2898686bf8
3 changed files with 433 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

130
MultModelsCl_CALL.py Normal file
View file

@ -0,0 +1,130 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Mar 15 11:09:50 2022
@author: tanu
"""
#%% 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)
#%% 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)
#%% 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)
#%% 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)
#%% 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)
#%% 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)
#%% 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 = ros_all.filter(like='test_', axis=1)
rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
rouC_BT = ros_all.filter(like='bts_', axis=1)
rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
#%%
# 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)