geopoints.py 文件源码

def group_by_proximity(self, k=10):
        if len(self.points) == 0:
            return {}

        X = numpy.array([[p.lat, p.lon] for p in self.points])

        distance_matrix = distance.squareform(distance.pdist(X))
        db = KMeans(n_clusters=k).fit(distance_matrix)

        # re-attach ids
        grouped_points = {}
        for i, k in enumerate(db.labels_):
            logger.debug('idx, label [%s, %s]', i, k)
            if k not in grouped_points:
                grouped_points[k] = []
            point = self.points[i]
            grouped_points[k].append({'id': point.uid, 'lat': point.lat, 'lon': point.lon})

        logger.info('Finished grouping into %d groups.', len(grouped_points))
        return grouped_points