added my_data4 after outputting merged_df3 for pnca to test the ml models

This commit is contained in:
Tanushree Tunstall 2022-03-03 13:35:05 +00:00
parent 25a55ac914
commit 04e0267dd1
11 changed files with 5918 additions and 377 deletions

View file

@ -157,9 +157,9 @@ print('Class Ratio:',
sum(my_df2['resistance'])/len(my_df2['resistance'])
)
skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
target = my_df2.loc[:,'resistance']
skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
fold_no = 1
for train_index, test_index in skf.split(my_df2, target):
train = my_df2.loc[train_index,:]
@ -373,4 +373,4 @@ plot_confusion_matrix(cm, classes = ['0 - Susceptible', '1 - Resistant'],
title = 'R/S Confusion Matrix')
print(rf_classifier.feature_importances_)
print(f" There are {len(rf_classifier.feature_importances_)} features in total")
print(f" There are {len(rf_classifier.feature_importances_)} features in total")