[Scikit-learn-general] PDF User's Guide for 0.16.2

Hello, when can we expect a PDF version of the User’s Guide for 0.16.2? https://sourceforge.net/projects/scikit-learn/files/documentation/ Thanks very much. Dale Smith, Ph.D. Data Scientist ​ [http://host.msgapp.com/Extranet/96621/Signature%20Images/sig%20logo.png]http://nexidia.com/ d.

Re: [Scikit-learn-general] Decsion tree regression -- mean squared error or variance reduction

It is using the variance reduction algorithm to make the splits while the tree is being built. The final tree can be evaluated using the Mean Squared Error. On Thu, Jul 9, 2015 at 8:56 AM, Sebastian Raschka se.rasc...@gmail.com wrote: Hi, all, sorry, but I have another question regarding the

[Scikit-learn-general] Decsion tree regression -- mean squared error or variance reduction

Hi, all, sorry, but I have another question regarding the terminology in the documentation. In the DecisionTreeRegressor's documentation at http://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeRegressor.html#sklearn.tree.DecisionTreeRegressor is says criterion : string,

Re: [Scikit-learn-general] Decsion tree regression -- mean squared error or variance reduction

Thanks, so when I understand correctly, the criterion argument described as The function to measure the quality of a split. The only supported criterion is “mse” for the mean squared error. only reports the quality but does not influence the split ... Maybe the use of variance reduction, or

Re: [Scikit-learn-general] Number of subsamples in Random Forest

Hi Sebastian, Indeed, N samples are drawn with replacement, where N=len(original training set). I guess we could add an extra max_samples parameter, just like we have for the Bagging estimators. Gilles On 6 July 2015 at 23:00, Sebastian Raschka se.rasc...@gmail.com wrote: Thanks, Jeff, that

Re: [Scikit-learn-general] Number of subsamples in Random Forest

Thanks, Gilles, I think that's a good idea! It would make the implementation more flexible and would add clarity as well! Best, Sebastian On Jul 9, 2015, at 2:35 PM, Gilles Louppe g.lou...@gmail.com wrote: Hi Sebastian, Indeed, N samples are drawn with replacement, where N=len(original

Re: [Scikit-learn-general] Decsion tree regression -- mean squared error or variance reduction

Hi Sebastian, Both terminology are in fact strictly equivalent for regression. See e.g. page 46 of http://arxiv.org/abs/1407.7502 Best, Gilles On 9 July 2015 at 18:56, Sebastian Raschka se.rasc...@gmail.com wrote: Hi, all, sorry, but I have another question regarding the terminology in the

Re: [Scikit-learn-general] probability from a Model for the predicted class

Hi Herb Many classifiers have a `predict_proba` or a `predict_log_proba` method which returns the probability for each class for each point. Jacob On Thu, Jul 9, 2015 at 11:39 AM, Herbert Schulz hrbrt@gmail.com wrote: Hey, is there a way to get the probability for a predicted class?

Re: [Scikit-learn-general] probability from a Model for the predicted class

Thank you very much! -- Don't Limit Your Business. Reach for the Cloud. GigeNET's Cloud Solutions provide you with the tools and support that you need to offload your IT needs and focus on growing your business. Configured

[Scikit-learn-general] probability from a Model for the predicted class

Hey, is there a way to get the probability for a predicted class? For Example: my model is predicting the input1 to Class 3probability that it is class 3? . input2 to Class 1 probability that it is class 1? ( with 55% it is class 1). I think

Re: [Scikit-learn-general] Decsion tree regression -- mean squared error or variance reduction

Thanks, I think my confusion came from the fact that they use x_i as target variable, and I was thinking of feature/attribute when I saw the equation; makes sense now! Btw. That's a beautiful thesis and a useful reference, too! Best, Sebastian On Jul 9, 2015, at 2:23 PM, Gilles Louppe