As far as I know, the default threshold considered by classifiers is 0.5,
but I want to change the threshold and check the results in Python . Can someone please help me with this.
I am using Random Forest, Decision Tree, Naive Bayes, SVM, KNN, Logistic regression classifiers.
The following link may be helpful
https://machinelearningmastery.com/threshold-moving-for-imbalanced-classification/
I suggest you follow this thread :
https://stackoverflow.com/questions/19984957/scikit-learn-predict-default-threshold
https://towardsdatascience.com/fine-tuning-a-classifier-in-scikit-learn-66e048c21e65
You can make a probability prediction (predict_proba, most of their models have this method) and vary it.
This allows you to observe the different scores for different values without having to call back to the prediction
https://towardsdatascience.com/fine-tuning-a-classifier-in-scikit-learn-66e048c21e65
Dear Himani Deshpande,
Please, I want the way the problem was solved.
Regards
Himani Deshpande
https://stackoverflow.com/questions/61034101/scikit-learn-change-threshold-in-confusion-matrix
- Badges
- Science topic
- Similar topics
- Mathematics