Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

1pmish -luke > On Aug 3, 2016, at 4:13 PM, Matthieu Brucher > wrote: > > True! > > 2016-08-03 20:38 GMT+01:00 Andreas Mueller : >> >> >>> On 08/03/2016 03:16 PM, Matthieu Brucher wrote: >>> More often than not, forward compatiblity is not possible. I don't think >>> there are lots of compa

Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

True! 2016-08-03 20:38 GMT+01:00 Andreas Mueller : > > > On 08/03/2016 03:16 PM, Matthieu Brucher wrote: > >> More often than not, forward compatiblity is not possible. I don't think >> there are lots of companies doing so, as even backward compatibility is >> tricky to achieve. >> Even with seri

Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

On 08/03/2016 03:16 PM, Matthieu Brucher wrote: More often than not, forward compatiblity is not possible. I don't think there are lots of companies doing so, as even backward compatibility is tricky to achieve. Even with serializing the version, if the previous version doesn't know about the

Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

e and paid a serious lesson for that. Best, Shi -- Forwarded message -- From: Andreas Mueller mailto:t3k...@gmail.com>> Date: Wed, Aug 3, 2016 at 1:29 PM Subject: Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15 To: Scikit-learn user an

Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

More often than not, forward compatiblity is not possible. I don't think there are lots of companies doing so, as even backward compatibility is tricky to achieve. Even with serializing the version, if the previous version doesn't know about the additional data structures that have an impact on the

Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

-- Forwarded message -- From: Andreas Mueller Date: Wed, Aug 3, 2016 at 1:29 PM Subject: Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15 To: Scikit-learn user and developer mailing list Hi Shi. In general, there is no guarantee that models built with one

Re: [scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

Hi Shi. In general, there is no guarantee that models built with one version will work in a different version. In particular, loading in an older version when built in a newer version seems something that's tricky to achieve. We might want to warn the user when doing this. The docs are not ver

[scikit-learn] Model trained in 0.17 gives entirely different results in 0.15

Hello, We trained SVM models in scikit-learn 0.17 and saved it as pickle files. When loading the models back in a lower version of scikit-learn 0.15, the outputs are entirely different. Basically for binary classification problem, for the same test data, it swapped the probabilities and gave an