I was wondering what's the best way to preprocess new samples for my ML classifier.

I have a raw data with about 3000 samples. I'm preprocessing it with some LabelEncoders and TargetEncdoders for categorical variables and StandardScalers for numerical values.

What's the best way to preprocess a single sample for prediction, the same way as raw_data was. How to store parameters, calculated by my encoders.

EX. I have categorical variable, which is transformed with LabelEncoder and than TargetEncoder, and category "A" is transformed to value 0.5 . I want to make sure my single sample, with category "A" will be transofrmed to the same numerical value.

Is it possible to do with Sklearn's pipelines?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.