I want to use the sample_weights parameter in sklearn Naive Bayes classification.
I have seen online that it can be used to balance data but I have also seen that it can be used to weight data with different importance.
I have data for which I have greater confidence in and thus would like the algorithm to consider this.
- Is weighting data using sample_weights the correct way to do this?
- What does sample_weights actually do in the sklearn Naive Bayes classification algorithm?