ML_AI_training/UQ_pnca_ml_CALL.py

56 lines
1.2 KiB
Python

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon May 16 05:59:12 2022
@author: tanu
"""
#!/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]
X = all_df_wtgt[numerical_FN]
y = all_df_wtgt['dst_mode']
#%% variables
#%% MultClassPipeSKFCV: function call()
mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
, target = y
, var_type = 'numerical'
, 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
#%% CHECK with BLIND test
#%%
import plotly.express as px
corr = X.corr(method = 'spearman')
corr.head()
#p = corr.style.background_gradient(cmap='coolwarm')
p = corr.style.background_gradient(cmap='coolwarm').set_precision(2)
p
fig = px.imshow(corr)
fig.show()
#%%TODO:
# Add correlation plot
# Remove low variance features
# Add feature selection
# Then run your models on BLIND test WITHOUT CV