Wrong calculation for E-step

[matsuren]

Thank you for your useful material! Correct me if I'm wrong, but there is wrong calculation for E-step?

    def Estep(self):
        "Perform an E(stimation)-step, freshening up self.loglike in the process"
        # compute weights
        self.loglike = 0. # = log(p = 1)
        for datum in self.data:
            # unnormalized weights
            wp1 = self.one.pdf(datum) * self.mix
            wp2 = self.two.pdf(datum) * (1. - self.mix)
            # compute denominator
            den = wp1 + wp2
            # normalize
            wp1 /= den
            wp2 /= den
            # add into loglike
            self.loglike += log(wp1 + wp2)
            # yield weight tuple
            yield (wp1, wp2)

wp1 and wp2 are normalized so self.loglike += log(wp1 + wp2) doesn't make sense since wp1 + wp2=1. Also I think self.loglike += (log(wp1) + log(wp2)) is correct.

Thanks,