Hi Felix. You should be fine the way you do it. You might want to rescale the continuous values though, possibly to lie within 0 to 1, using MinMaxScaler.
Cheers, Andy On 06/18/2015 05:05 AM, Felix Dreher wrote: > Dear all, > > I have a general question about running logistic regression with a > combination of numeric and binary predictors (independent variables). > I'm sorry if it was already asked before, but I couldn't find an answer > in the mail archives. > > The data set I'm working with looks as follows: > The numeric predictors are gene expression values (continuous values > ranging from 0 to 20,000) and the binary predictors are gene mutation > values (0: gene is not mutated, 1: gene is mutated). The dependent > variable is drug response (here: cell line is sensitive or resistant to > a drug). > > Currently I'm ignoring the heterogeneity of the predictors and run the > function as follows: > > lr = LogisticRegression(penalty='l1', C=1).fit(train_xs, train_ys) > > I was wondering if I need to adjust the model in order to reflect the > combination of numeric and binary predictors? > > Any hints are highly appreciated... > > Best regards, > Felix > > > > > ------------------------------------------------------------------------------ > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general ------------------------------------------------------------------------------ _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
