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

added notes to run yc models with dissected features

Browse source
This commit is contained in:
Tanushree Tunstall 2022-05-29 08:04:12 +01:00
parent a784f9cc4e
commit f761dd4479
2 changed files with 13 additions and 98 deletions
Download patch file Download diff file Expand all files Collapse all files

105
UQ_yc_RunAllClfs.py
View file

@ -1,3 +1,10 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sun May 29 07:43:21 2022
@author: tanu
"""
import pandas as pd
import numpy as np
import scipy as sp
@ -251,100 +258,4 @@ def run_all_ML(input_pd, target_label, blind_test_input_df, blind_test_target, p
#return(result_pd)
return(results_all)
#%% CALL function
#run_all_ML(input_pd=X, target_label=y, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
# Baseline_data
YC_resD2 = run_all_ML(input_pd=X, target_label=y, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
CVResultsDF_baseline = YC_resD2['CrossValResultsDF']
CVResultsDF_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
BTSResultsDF_baseline = YC_resD2['BlindTestResultsDF']
BTSResultsDF_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
# from sklearn.utils import all_estimators
# for name, algorithm in all_estimators(type_filter="classifier"):
# clf = algorithm()
# print('Name:', name, '\nAlgo:', clf)
# Random Oversampling
YC_resD_ros = run_all_ML(input_pd=X_ros, target_label=y_ros, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
CVResultsDF_ros = YC_resD_ros['CrossValResultsDF']
CVResultsDF_ros.sort_values(by=['matthew'], ascending=False, inplace=True)
BTSResultsDF_ros = YC_resD_ros['BlindTestResultsDF']
BTSResultsDF_ros.sort_values(by=['matthew'], ascending=False, inplace=True)
# Random Undersampling
YC_resD_rus = run_all_ML(input_pd=X_rus, target_label=y_rus, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
CVResultsDF_rus = YC_resD_rus['CrossValResultsDF']
CVResultsDF_rus.sort_values(by=['matthew'], ascending=False, inplace=True)
BTSResultsDF_rus = YC_resD_rus['BlindTestResultsDF']
BTSResultsDF_rus.sort_values(by=['matthew'], ascending=False, inplace=True)
# Random Oversampling+Undersampling
YC_resD_rouC = run_all_ML(input_pd=X_rouC, target_label=y_rouC, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
CVResultsDF_rouC = YC_resD_rouC['CrossValResultsDF']
CVResultsDF_rouC.sort_values(by=['matthew'], ascending=False, inplace=True)
BTSResultsDF_rouC = YC_resD_rouC['BlindTestResultsDF']
BTSResultsDF_rouC.sort_values(by=['matthew'], ascending=False, inplace=True)
# SMOTE NC
YC_resD_smnc = run_all_ML(input_pd=X_smnc, target_label=y_smnc, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
CVResultsDF_smnc = YC_resD_smnc['CrossValResultsDF']
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')
yc_sfallCT_baseline= yC_sfall['CrossValResultsDF']
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 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')
yc_sfcoCT_baseline= yC_sfco['CrossValResultsDF']
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]
, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
yc_fxssCT_baseline= yC_fxss['CrossValResultsDF']
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)
# categorical
yC_cat= run_all_ML(input_pd=X[categorical_FN], target_label=y
, blind_test_input_df=X_bts[categorical_FN]
, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
yc_catCT_baseline= yC_cat['CrossValResultsDF']
yc_catCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
yc_catBT_baseline = yC_cat['BlindTestResultsDF']
yc_catBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)