'Updating a NaiveBayes Classifier (in scikit-learn) over time
I'm building a NaiveBayes classifier using scikit-learn, and so far things are going well if I have a set body of data to train. However, for the particular project I'm working on, there will be new data coming in every day that ideally would be part of the training set.
I'm aware that you can pickle the classifier to store it for later use, but is there any way to "update" the classifier with new data?
Re-training the classifier from scratch every day is obviously an option, but that would require drawing a lot of historical data each time, for a growing time period.
Solution 1:[1]
Use the partial_fit method on the naive Bayes estimator.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | Fred Foo |