úÎÍ2     Perform one EM step FPerforms an infinite number of EM steps, iterating towards converging  parameters. 0Finds the fix-points of the EM step iterations. +Finds the best fix-point with all elements xs as starting points for the  means. It holds that mu_1 < mu_2. KPerform one EM step given the data. In General, emSteps should be iterated * until some convergence criterion is met. Produces an infinite list of !s that will (should) convergence  toward a local optimum. "Find an optimal set of parameters . The additional takeWhile (not . isnan . fst)* makes sure that in cases of overfitting,  does L terminate. Due to the way we check and take, in case of NaNs, the returned 4 values will be NaNs (checking fst, returning snd). ;Calculate the log-likelihood for a given set of parameters  and  some data  . Used by ( to estimate if convergence is reached. JTODO could be useful in a more general setting within StatisticalMethods. Given a set of  and a number k$ of Gaussian peaks, try to find the N optimal GMM. This is done by trying each data point as mu for each Gaussian. / Note that this will be rather slow for larger k (larger than, say 2 or 3). 9 In that case, a random-drawing method should be chosen. TODO xs' -> xs sorting makes me cry!  5Given a certain data-set, create a confusion matrix. The confusion matrix.     IThe ctor expects the total number of possibilities first, then a list of C true positive elements, followed by a list of predicted elements.  sensitivity  specificity positive predictive value  mathews correlation coefficient  F-measure        StatisticalMethods-0.0.0.1Statistics.EM.TwoGaussianStatistics.EM.GMMTestData.ElementsStatistics.ConfusionMatrix$Statistics.ConfusionMatrix.InstancesStatistics.PerformanceMetricsemFixemStarts table_8_1MkConfusionMatrixmkConfusionMatrix WrappedDoubleConfusionMatrixfnfptntp ListSimilar sensitivity specificityppvmccfmeasureNormalWeightemStepemIterThetaLThetaData logLikelihood