analyzer.h

Go to the documentation of this file.

/*
 * Author: Steven Ludtke, 04/10/2003 (sludtke@bcm.edu)
 * Copyright (c) 2000-2006 Baylor College of Medicine
 *
 * This software is issued under a joint BSD/GNU license. You may use the
 * source code in this file under either license. However, note that the
 * complete EMAN2 and SPARX software packages have some GPL dependencies,
 * so you are responsible for compliance with the licenses of these packages
 * if you opt to use BSD licensing. The warranty disclaimer below holds
 * in either instance.
 *
 * This complete copyright notice must be included in any revised version of the
 * source code. Additional authorship citations may be added, but existing
 * author citations must be preserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 *
 * */

#ifndef eman_analyzer_h__
#define eman_analyzer_h__

#include "emobject.h"
#include <gsl/gsl_linalg.h>
using std::vector;

namespace EMAN
{
        class EMData;

        class Analyzer
        {
          public:
                Analyzer() {}

                virtual ~Analyzer()
                {}

                virtual int insert_image(EMData * image) = 0;

                virtual int insert_images_list(vector<EMData *> image_list);

                virtual vector<EMData*> analyze() = 0;

                virtual string get_name() const = 0;

                virtual string get_desc() const = 0;

                virtual void set_params(const Dict & new_params)
                {
                        params = new_params;
                }

                virtual Dict get_params() const
                {
                        return params;
                }

                virtual TypeDict get_param_types() const = 0;

          protected:
                mutable Dict params;
                vector<EMData *> images;
        };

        class KMeansAnalyzer:public Analyzer
        {
          public:
                KMeansAnalyzer() : ncls(0),verbose(0),minchange(0),maxiter(100),mininclass(2),slowseed(0) {}

                virtual int insert_image(EMData * image) {
                        images.push_back(image);
                        return 0;
                }

                virtual vector<EMData*> analyze();

                string get_name() const
                {
                        return "kmeans";
                }

                string get_desc() const
                {
                        return "k-means classification";
                }

                static Analyzer * NEW()
                {
                        return new KMeansAnalyzer();
                }

                void set_params(const Dict & new_params);

                TypeDict get_param_types() const
                {
                        TypeDict d;
                        d.put("verbose", EMObject::INT, "Display progress if set, more detail with larger numbers (9 max)");
                        d.put("ncls", EMObject::INT, "number of desired classes");
                        d.put("maxiter", EMObject::INT, "maximum number of iterations");
                        d.put("minchange", EMObject::INT, "Terminate if fewer than minchange members move in an iteration");
                        d.put("mininclass", EMObject::INT, "Minumum number of particles to keep a class as good (not enforced at termination");
                        d.put("slowseed",EMObject::INT, "Instead of seeding all classes at once, it will gradually increase the number of classes by adding new seeds in groups with large standard deviations");
                        d.put("calcsigmamean",EMObject::INT, "Computes standard deviation of the mean image for each class-average (center), and returns them at the end of the list of centers");
                        return d;
                }

                protected:
                void update_centers(int sigmas=0);
                void reclassify();
                void reseed();

                vector<EMData *> centers;
                int ncls;       //number of desired classes
                int verbose;
                int minchange;
                int maxiter;
                int mininclass;
                int nchanged;
                int slowseed;
                int calcsigmamean;

        };

        class SVDAnalyzer : public Analyzer
        {
          public:
                SVDAnalyzer() : mask(0), nvec(0), nimg(0), A(NULL) {}

                virtual int insert_image(EMData * image);

                virtual int insert_images_list(vector<EMData *> image_list) {
                        vector<EMData*>::const_iterator iter;
                        for(iter=image_list.begin(); iter!=image_list.end(); ++iter) {
                                images.push_back(*iter);
                        }
                        return 0;
                }

                virtual vector<EMData*> analyze();

                string get_name() const
                {
                        return "svd_gsl";
                }

                string get_desc() const
                {
                        return "Singular Value Decomposition from GSL. Comparable to pca";
                }

                static Analyzer * NEW()
                {
                        return new SVDAnalyzer();
                }

                void set_params(const Dict & new_params);

                TypeDict get_param_types() const
                {
                        TypeDict d;
                        d.put("mask", EMObject::EMDATA, "mask image");
                        d.put("nvec", EMObject::INT, "number of desired basis vectors");
                        d.put("nimg", EMObject::INT, "total number of input images, required even with insert_image()");
                        return d;
                }

                protected:
                EMData * mask;
                int nvec;       //number of desired principal components
                int pixels;     // pixels under the mask
                int nimg; // number of input images

                private:
                int nsofar;
                gsl_matrix *A;
        };

        template <> Factory < Analyzer >::Factory();

        void dump_analyzers();
        map<string, vector<string> > dump_analyzers_list();
}

#endif  //eman_analyzer_h__