def cluster()

in clustering.py [0:0]

• 29 lines of code
• 14 McCabe index (conditional complexity)

    def cluster(self, data, verbose=False):
        end = time.time()

        # preprocess the data
        xb = preprocess_features(data)

        # construct nnn graph
        I, D = make_graph(xb, self.nnn)

        # run PIC
        clust = run_pic(I, D, self.sigma, self.alpha)
        images_lists = {}
        for h in set(clust):
            images_lists[h] = []
        for data, c in enumerate(clust):
            images_lists[c].append(data)

        # allocate singletons to clusters of their closest NN not singleton
        if self.distribute_singletons:
            clust_NN = {}
            for i in images_lists:
                # if singleton
                if len(images_lists[i]) == 1:
                    s = images_lists[i][0]
                    # for NN
                    for n in I[s, 1:]:
                        # if NN is not a singleton
                        if not len(images_lists[clust[n]]) == 1:
                            clust_NN[s] = n
                            break
            for s in clust_NN:
                del images_lists[clust[s]]
                clust[s] = clust[clust_NN[s]]
                images_lists[clust[s]].append(s)

        self.images_lists = []
        for c in images_lists:
            self.images_lists.append(images_lists[c])

        if verbose:
            print('pic time: {0:.0f} s'.format(time.time() - end))
        return 0