#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Mar 15 11:09:50 2022

@author: tanu
"""
# stratified shuffle split
X_train, X_test, y_train, y_test = train_test_split(num_df_wtgt[numerical_FN]
                                                    , num_df_wtgt['mutation_class']
                                                    , test_size = 0.33
                                                    , **rs
                                                    , shuffle = True
                                                    , stratify = num_df_wtgt['mutation_class'])

y_train.to_frame().value_counts().plot(kind = 'bar')
y_test.to_frame().value_counts().plot(kind = 'bar')

MultClassPipelineCV(X_train, X_test, y_train, y_test
         , input_df = num_df_wtgt[numerical_FN]
         , var_type = 'numerical')


skf_cv_scores = MultClassPipelineCV(X_train, X_test, y_train, y_test
         , input_df = num_df_wtgt[numerical_FN]
         , var_type = 'numerical')

pp.pprint(skf_cv_scores)
# construct a df
skf_cv_scores_df = pd.DataFrame(skf_cv_scores)
skf_cv_scores_df
skf_cv_scores_df_test = skf_cv_scores_df.filter(like='test_', axis=0)
skf_cv_scores_df_train = skf_cv_scores_df.filter(like='train_', axis=0)