varepsilon / clickmodels Goto Github PK

        for iteration_count in xrange(self.config.get('MAX_ITERATIONS', MAX_ITERATIONS)):
            self.queryIntentsWeights = defaultdict(lambda: [])
            # not like in DBN! xxxFractions[0] is a numerator while xxxFraction[1] is a denominator
            alphaFractions = dict((i, [defaultdict(lambda: [1.0, 2.0]) for q in xrange(max_query_id)]) for i in possibleIntents)
            gammaFractions = [[[[1.0, 2.0] \
                for d in xrange(self.config.get('MAX_DOCS_PER_QUERY', MAX_DOCS_PER_QUERY))] \
                    for r in xrange(self.config.get('MAX_DOCS_PER_QUERY', MAX_DOCS_PER_QUERY))] \
                        for g in xrange(self.gammaTypesNum)]
            if self.explorationBias:
                eFractions = [[1.0, 2.0] \
                        for p in xrange(self.config.get('MAX_DOCS_PER_QUERY', MAX_DOCS_PER_QUERY))]
            # E-step
            for s in sessions:
                query = s.query
                layout = [False] * len(s.layout) if self.ignoreLayout else s.layout
                if self.explorationBias:
                    explorationBiasPossible = any((l and c for (l, c) in zip(s.layout, s.clicks)))
                    firstVerticalPos = -1 if not any(s.layout[:-1]) else [k for (k, l) in enumerate(s.layout) if l][0]
                if self.ignoreIntents:
                    p_I__C_G = {False: 1.0, True: 0}
                else:
                    a = self._getSessionProb(s) * (1 - s.intentWeight)
                    b = 1 * s.intentWeight
                    p_I__C_G = {False: a / (a + b), True: b / (a + b)}
                self.queryIntentsWeights[query].append(p_I__C_G[True])
                prevClick = -1
                for rank, c in enumerate(s.clicks):
                    url = s.results[rank]
                    for intent in possibleIntents:
                        a = self.alpha[intent][query][url]
                        if self.explorationBias and explorationBiasPossible:
                            e = self.e[firstVerticalPos]
                        if c == 0:
                            g = self.getGamma(self.gamma, rank, prevClick, layout, intent)
                            gCorrection = 1
                            if self.explorationBias and explorationBiasPossible and not s.layout[k]:
                                gCorrection = 1 - e
                                g *= gCorrection
                            alphaFractions[intent][query][url][0] += a * (1 - g) / (1 - a * g) * p_I__C_G[intent]
                            self.getGamma(gammaFractions, rank, prevClick, layout, intent)[0] += g / gCorrection * (1 - a) / (1 - a * g) * p_I__C_G[intent]
                            if self.explorationBias and explorationBiasPossible:
                                eFractions[firstVerticalPos][0] += (e if s.layout[k] else e / (1 - a * g)) * p_I__C_G[intent]
                        else:
                            alphaFractions[intent][query][url][0] += 1 * p_I__C_G[intent]
                            self.getGamma(gammaFractions, rank, prevClick, layout, intent)[0] += 1 * p_I__C_G[intent]
                            if self.explorationBias and explorationBiasPossible:
                                eFractions[firstVerticalPos][0] += (e if s.layout[k] else 0) * p_I__C_G[intent]
                        alphaFractions[intent][query][url][1] += 1 * p_I__C_G[intent]
                        self.getGamma(gammaFractions, rank, prevClick, layout, intent)[1] += 1 * p_I__C_G[intent]
                        if self.explorationBias and explorationBiasPossible:
                            eFractions[firstVerticalPos][1] += 1 * p_I__C_G[intent]
                    if c != 0:
                        prevClick = rank
            if not self.config.get('PRETTY_LOG', PRETTY_LOG):
                sys.stderr.write('E')
            # M-step
            sum_square_displacement = 0.0
            for i in possibleIntents:
                for q in xrange(max_query_id):
                    for url, aF in alphaFractions[i][q].iteritems():
                        new_alpha = aF[0] / aF[1]
                        sum_square_displacement += (self.alpha[i][q][url] - new_alpha) ** 2
                        self.alpha[i][q][url] = new_alpha
            for g in xrange(self.gammaTypesNum):
                for r in xrange(self.config.get('MAX_DOCS_PER_QUERY', MAX_DOCS_PER_QUERY)):
                    for d in xrange(self.config.get('MAX_DOCS_PER_QUERY', MAX_DOCS_PER_QUERY)):
                        gF = gammaFractions[g][r][d]
                        new_gamma = gF[0] / gF[1]
                        sum_square_displacement += (self.gamma[g][r][d] - new_gamma) ** 2
                        self.gamma[g][r][d] = new_gamma
            if self.explorationBias:
                for p in xrange(self.config.get('MAX_DOCS_PER_QUERY', MAX_DOCS_PER_QUERY)):
                    new_e = eFractions[p][0] / eFractions[p][1]
                    sum_square_displacement += (self.e[p] - new_e) ** 2
                    self.e[p] = new_e
            if not self.config.get('PRETTY_LOG', PRETTY_LOG):
                sys.stderr.write('M\n')
            rmsd = math.sqrt(sum_square_displacement)
            if self.config.get('PRETTY_LOG', PRETTY_LOG):
                sys.stderr.write('%d..' % (iteration_count + 1))
            else:
                print >>sys.stderr, 'Iteration: %d, ERROR: %f' % (iteration_count + 1, rmsd)