ó ö.$Ic@s„dZy eZWn!ek r3ddlmZnXddlZddlZdd d„ƒYZddd„Z d„Z d„Z dS( sF This module provides code for doing logistic regressions. Classes: LogisticRegression Holds information for a LogisticRegression classifier. Functions: train Train a new classifier. calculate Calculate the probabilities of each class, given an observation. classify Classify an observation into a class. iÿÿÿÿ(tSetNtLogisticRegressioncBseZdZd„ZRS(s‘Holds information necessary to do logistic regression classification. Members: beta List of the weights for each dimension. cCs g|_dS(sLogisticRegression()N(tbeta(tself((s‰/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/LogisticRegression.pyt__init__$s(t__name__t __module__t__doc__R(((s‰/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/LogisticRegression.pyRscCsæt|ƒt|ƒkr'tdƒ‚nt|ƒ}|tddgƒkrZtdƒ‚n|dkrod}nt|ƒt|dƒd}}|dks¨|dkr·tdƒ‚ntj||f|ƒ}||dd…dd…f LogisticRegression Train a logistic regression classifier on a training set. xs is a list of observations and ys is a list of the class assignments, which should be 0 or 1. xs and ys should contain the same number of elements. update_fn is an optional callback function that takes as parameters that iteration number and log likelihood. s$xs and ys should be the same length.iisClasses should be 0's and 1'stds.No observations or observation of 0 dimension.Niôg{®Gáz„?gð?g@gü©ñÒMbP?sDidn't converge.(tlent ValueErrortsettNonetnumpytonest transposetasarraytzerostexptdottlogtsumtfabstidentitytlinalgtsolvet RuntimeErrorRtmaptfloatR(txstyst update_fnttypecodetclassestNtndimstXtXttyRtMAX_ITERATIONStCONVERGE_THRESHOLDtstepsizetitertold_betatold_lliktebetaXtptlogptlliktWtXtyptXtWXtdeltatlr((s‰/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/LogisticRegression.pyttrain(sZ    ! ,     %     cCsPtjdg|ƒ}tjtj|j|ƒƒ}|d|}d||gS(sßcalculate(lr, x) -> list of probabilities Calculate the probability for each class. lr is a LogisticRegression object. x is the observed data. Returns a list of the probability that it fits each class. gð?i(R RRRR(R5txR-R.((s‰/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/LogisticRegression.pyt calculatevs cCs+t||ƒ}|d|dkr'dSdS(sJclassify(lr, x) -> 1 or 0 Classify an observation into a class. ii(R8(R5R7tprobs((s‰/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/LogisticRegression.pytclassify…s(( RR t NameErrortsetsRR t numpy.linalgRR R6R8R:(((s‰/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/LogisticRegression.pyts     N