SAMI/MissingNodes_SrcCode2014/MissingNodes_S8b.m

function [ rand_score, purity, p_triads, missing_nodes_mapping, removed_nodes] = MissingNodes_S8b(dataFilePath, dataFileName, attributes, attUpperRange, attWeightVec, addMissingAttVec, normFactorVec, affinityType, ...
									num_missing_nodes_arr, attAffinityThreshold, imagesData, numImagesProfiles, imgMissProb, imgSimType, imgSimProbDiff, percentKnownPlaceholdersVec, dumpSmallFlag, dumpSmallDataPath, iter, missingNodes )

    %%global g_threshold; % Sigal - 15.10.13 remove warning
    % addpath 'Spectral Clustering' % sigal 13.8.12
    % addpath 'mex'% sigal 13.8.12

    p_triads = [];
    k = 0
    %create a log file for this run
    %date_now = clock;
    %date_now = strcat(num2str(date_now(1)),'_',num2str(date_now(2)),'_', num2str(date_now(3)),'_', num2str(date_now(4)), num2str(date_now(5)),'_', num2str(date_now(6)));
    %dump dir for save reduce graphs for GED
    %dumpSmallDataPath = sprintf('%sdumpSmallData_%s/', resultsDir, date_now);
    %diary(strcat('C:\missingnodes\Code\Log\log', date_now,'.log'));

    %affinity calculation types
    global affinity_calculation_shortest_path;
    global affinity_calculation_euclid;
    global affinity_calculation_common_friends;
    global affinity_calculation_random_clustering;
    global affinity_calculation_adamic_adar;
    global affinity_calculation_katz_beta_0_5;
    global affinity_calculation_katz_beta_0_05;
    global affinity_calculation_katz_beta_0_005;
    global affinity_calculation_AA_RCN;
    global affinity_boost;
    global affinity_boost2;

    affinity_calculation_shortest_path = 0;
    affinity_calculation_euclid = 1;
    affinity_calculation_common_friends = 2;
    affinity_calculation_random_clustering = 3;
    affinity_calculation_adamic_adar = 4;
    affinity_calculation_katz_beta_0_5 = 5;
    affinity_calculation_katz_beta_0_05 = 6;
    affinity_calculation_katz_beta_0_005 = 7;
    affinity_calculation_AA_RCN = 8;
    % sigal 12.3.13 add BOOST option
    affinity_boost = 9;
    affinity_boost2 = 8;

    %%%%% for distance as function of num placeholders %%%%
    expectedParms = 19;
    if nargin < expectedParms
        LogMsg(sprintf('*** ERROR: MissingNodes_S8b - Inavlid # of parameters, expected %d got %d',expectedParms,nargin));
        return;
    end

    percent_known_placeholders_vec = percentKnownPlaceholdersVec;

    if nargin >= expectedParms+1
          select_random_missing_nodes = 0;
    else
          select_random_missing_nodes = 1;
    end

    affinity_types = affinityType;

    compensate_for_unknown_placeholers = 0;
    compensate_vec = [0 0.3 0.65 1 1.5];

    unite_common_friends = 0; %should UNK nodes be united in accordance with the "friend of my friend principle"

    cluster_only_missing_nodes = 1;
    % if affinity_calculation_type == affinity_calculation_shortest_path || affinity_calculation_type == affinity_calculation_euclid
    %     non_neighbors_distance = Inf;
    % elseif affinity_calculation_type == affinity_calculation_common_friends
    %     non_neighbors_distance = 0;
    % end

    non_neighbors_distance = 0;
    
    ExpNormFactorVecLen = 3;
    normFactorVecLen = size(normFactorVec,2);
    if  normFactorVecLen ~= ExpNormFactorVecLen
        LogMsg(sprintf('*** ERROR: MissingNodes_S8b - invalid normFactorVec expected len=%d got %d',ExpNormFactorVecLen, normFactorVecLen));
        return;
    end
    
    global netAffNormFactor1;
    global netAffNormFactor2;
    netAffNormFactor1 = normFactorVec(1);
    netAffNormFactor2 = normFactorVec(2);
    netAffNormFactor3 = normFactorVec(3);

    %compare SC to Kmean, 0=SC, 3=k-mean on PH (mxm), 2=k-mean on PH+Nodes (m*(m+n))
    %sigal 1=kmean on PH (with already cut affinitty)
    kmeanTypesVec = 1; %[0 1]; %1; %%2 3];

    %compare with/without attr, 0=MISC, 1=SAMI-A, 2=SAMI-N, 3=SAMI-AK (k-mean), 4=SAMI-NK
    % images => 5=PMI, 7=PMI+SAMI
    samiAttrVec = [0 3 5 7]; % [0 4]; % [0 1 3]; % 2];
    % Sigal - TODO - if no SAMI-N skip data_untouched_withAtt (~line 160)
    run_SAMI_N = 0;
    
    %read the full network, up to num_values links
    %disp('reading network information from file...');
    fprintf('reading network information from file %s%s ...\n', dataFilePath, dataFileName);
    data = load(strcat(dataFilePath, dataFileName), 'data');
    %use sparse data
    %a = struct2table(data);
    %LogMsg(sprintf('%s', a));
    data = cell2mat(struct2cell((data)));
    data = sparse(data); % THISS IS THE MMATRIX

    %sigal 25.11.12
    %combine the attributes with data as first #totalAttNum cols/rows
    %[dataWithAtt, totalAttNum] = CombineDataWithAttributes(data, attributes, attUpperRange, attWeight);
    sami_ind = find(samiAttrVec == 1);
    for sami = [1 2 3 4 7]
        sami_ind = sami_ind | find(samiAttrVec == sami);
    end
    if sum(sami_ind,2) > 0
        [attData, totalAttNum] = PreProcessDataAttributes(data, attributes, attUpperRange);
    else  % sigal 31.1.14 support runs without attributes, i.e. only images
        attData = 0;
        totalAttNum = 0;
    end

    clear('graph');

    %rand_score = zeros(2, 2, size(num_missing_nodes_arr,2), 6, 2); %(normalized or not, unite common friends, num missing nodes, affinity calculation, cluster only missing)
    %rand_score_sq = rand_score;
    %purity = zeros(2, size(num_missing_nodes_arr,2), 6, 2);%(unite common friends, num missing nodes, affinity calculation, cluster only missing)
    %purity_sq = purity;
    rand_score = [];
    purity = [];

    graph_size = size(data,1); % DATA == MATRIX!
    graph_edges = nnz(data)/2; % number of edges
    %graph_attr_edges = 0; %% sigal 3.1.13: nnz(dataWithAtt)/2 - graph_edges; % number of attributes edges
    %num_missing_nodes_arr = round(num_missing_nodes_arr .* graph_size);

    %initialize the data matrix (binary adjacency)
    disp('generating network graph...');

    original_graph_size = size(data,1);

    original_data = data;
    original_attData = attData;
    graph_attr_edges = nnz(attData); % number of attributes edges
    avg_attr_edges = graph_attr_edges/original_graph_size;
    %original_dataWithAtt = dataWithAtt;

    missing_nodes_mapping = [];

    for num_missing_nodes_idx = 1 : size(num_missing_nodes_arr,2)
      
      if select_random_missing_nodes
          num_missing_nodes = num_missing_nodes_arr(1, num_missing_nodes_idx);
      else
          num_missing_nodes = length(missingNodes);
      end
      
      if num_missing_nodes > numImagesProfiles
          LogMsg(sprintf('*** ERROR: MissingNodes_S8b - invalid numImagesProfiles %d vs. numMissingNodes %d.',numImagesProfiles, num_missing_nodes));
          return;
      end
      %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
      %remove random nodes                                                                  %
      %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
      
      %randomize the missing nodes indexes and sort in descending order
      %disp('selecting random missing nodes...');
      fprintf('selecting %d random missing nodes...\n',num_missing_nodes);

      %sigal - 25.11.12 - remove same nodes from data and dataWithAtt
      if select_random_missing_nodes
            %[data, missing_nodes_mapping] = RemoveRandomNodes( original_data, num_missing_nodes, missing_nodes_mapping, non_neighbors_distance );
            fprintf('testtesttes');
            fprintf('testsalam%i', num_missing_nodes);
            
			[data, attData, missing_nodes_mapping] = RemoveRandomNodesWithImages( original_data, original_attData, totalAttNum, num_missing_nodes, missing_nodes_mapping, numImagesProfiles );
            
      else
			%Sigal 13.10.13 - TODO - add option to pre selected missing node
            %Sigal - 23.1.14 - %%%%TODO - add option for images
            fprintf('*** ERROR:  pre selected missing node is not suported for images \n');
            [data, attData, missing_nodes_mapping] = RemoveRandomNodes3( original_data, original_attData, totalAttNum, num_missing_nodes, missing_nodes_mapping, non_neighbors_distance, missingNodes);
      end
      
      data_untouched = data;
      if run_SAMI_N
          tic %att_combine_calc_time in seconds
          data_untouched_withAtt = CombineDataWithAttributes4(data, attData);
          att_combine_calc_time = toc;%att_combine_calc_time
      else
          fprintf('Combining attribtes ...==> Skip\n');
          att_combine_calc_time = 0;
      end
      
      % loop over addMissingAtt options
      for addMissingAtt = addMissingAttVec
          LogMsg(sprintf('S8b:astddMissingAtt=%.3f',addMissingAtt));
      % loop over partial data options
      for percent_known_placeholders = percent_known_placeholders_vec
        data0 = data_untouched;

        %sigal - TODO all reference to data0 and S ???
        % S is uncertainty vector when we don't known the placeholders
        S = zeros(1, size(data0,2));
        num_placeholders_to_remove = 0;
        placeholders_to_remove = [];
        num_placeholders = size(data0,1) - original_graph_size + num_missing_nodes ;
        last_known_node = size(data0,1) - num_placeholders;

        if percent_known_placeholders < 1
            num_placeholders_to_remove = round(num_placeholders * (1 - percent_known_placeholders));

            while size(placeholders_to_remove, 2) < num_placeholders_to_remove
                %randomly selecting unique placeholder indexes
                placeholders_to_remove = unique([placeholders_to_remove, randi(num_placeholders, 1, num_placeholders_to_remove - size(placeholders_to_remove, 2))]);
            end

            %rand_vec = rand(1, num_placeholders);
            %placeholders_to_remove = find(rand_vec > percent_known_placeholders) + last_known_node;

            placeholders_to_remove = placeholders_to_remove + last_known_node;

            %S is the group of neighbors of the unknown placeholders
            S = data0(placeholders_to_remove(1), :);
            for i = placeholders_to_remove
                S = S | data0(i,:);
            end

            %switch from binary vector to list of indexes
            % S = find(S);

            %data_all_placeholders = data0;
            data0(placeholders_to_remove,:) = [];
            data0(:,placeholders_to_remove) = [];

            num_placeholders = num_placeholders - num_placeholders_to_remove;
        end

        %save the removed nodes in each iteration
        removed_nodes{num_missing_nodes_idx} = missing_nodes_mapping(1,:); 

        %save S
        orig_S = S;

        %sigal - adjust to withAttr flag TOCHECK
        %sigal - 12.6.13 - move after calcAffinity so we can calculate only the reduce entries
%             tic %att_affinity_calc_time in seconds
%             fprintf('calculating attribtes affinity matrix...\n');
%             attAffinity = CalcAttributesAffinity_S3(data0, attData, last_known_node, addMissingAtt, attAffinityThreshold);
%             att_affinity_calc_time = toc;%att_affinity_calc_time
        att_affinity_merge_time = 0;

        all_clustering = [];
        all_clustering_alg = [];
        all_att_clustering = [];
        all_att_clustering_alg = [];
        all_k1_clustering = [];
        all_k1_clustering_alg = [];
        all_k3_clustering = [];
        all_k3_clustering_alg = [];
        all_A2_clustering = [];
        all_A2_clustering_alg = [];
        all_A4_clustering = [];
        all_A4_clustering_alg = [];
        % sigal 12.6.13 - use as flag for first time calculation
        attAffinity = 0; 
        phsAttAffinity = 0;
        phsAttAffinity2 = 0;
        phsImgAffinity = 0;
        
        % loop over different affinity_types
        for affinity_calculation_type = affinity_types
            % sigal 12.11.13 - use as flag for first time calculation
            phsNetAffinity = 0; 
            
            if affinity_calculation_type == affinity_boost
                withAttrVec = affinity_boost; %[affinity_boost affinity_boost2];
            elseif affinity_calculation_type == affinity_calculation_random_clustering
                withAttrVec = 0;
            else
                % sigal 12.3.13 - run several times:
                % 0=original, 1=weighted affinity, 2=weighted dataWithAttr
                withAttrVec = samiAttrVec; %Sigal - 15.10.13
            end
            
            % sigal 25.11.12
            % run loop - once as original without attributes and next with attriutes
            for withAttr = withAttrVec
                netAffinity = 0; % sigal 24.10.13 - use as flag for first time calculation
                % sigal 5.3.13 - loop over weights
                if withAttr == 0
                    attWeightVector = 0;
                elseif withAttr == affinity_boost || withAttr == affinity_boost2
                    attWeightVector = [0.1 0.2 0.4]; % sigal - use OASCA per Affinity/kmean
                    if kmeanTypesVec==0 % find(kmeanTypesVec==0) % 
                        attWeightVector = [0 attWeightVector];
                    end
%                 elseif withAttr == 1 &&  addMissingAtt > 0 % sigal 23.10.13
%                     attWeightVector = 0.2:0.1:0.8; %0.8; %
                elseif affinity_calculation_type == affinity_calculation_common_friends
                    if withAttr == 3
                        attWeightVector = 0.3:0.1:0.5; %0.3:0.1:0.5;
                    else
                        attWeightVector = 0.2:0.1:0.4; %5; %%0.2:0.1:0.5; %0.3; %0.2:0.1:0.5; %0.3; %
                    end
                elseif affinity_calculation_type == affinity_calculation_adamic_adar
                    if withAttr == 4
                        attWeightVector = 0.2:0.1:0.4; %0.3:0.1:0.5;
                    else
                        attWeightVector = 0.6:0.1:0.8; %0.4:0.1:0.6; %0.5:0.1:0.7; %8; %0.4:0.1:0.7; %0.8; %0.5:0.1:0.8;
                    end
                elseif affinity_calculation_type == affinity_calculation_AA_RCN
                    attWeightVector = 0.1:0.1:0.9; %0.3; %0.2:0.1:0.8; %
                elseif affinity_calculation_type == affinity_calculation_katz_beta_0_05
                    attWeightVector = 0.1:0.1:0.4; %0.8; %0.2:0.1:0.8; %
                else
                    attWeightVector = attWeightVec;
                end
                if find(withAttr == [3 5 7])
                    attWeightVector = [0 attWeightVector 1];
                end
                
                % run loop for attWeight
                for attWeight = attWeightVector
                    affinity = 0;
                    phsAffinity = 0;
                    withAttrWeight = (withAttr+attWeight)*10;
                    
                    % sigal 3.1.13 - data is the same the change is in the attAffinity
                    if find(withAttr == [0 1 3 5 7 affinity_boost affinity_boost2])
                        actual_graph_size = original_graph_size;
                        num_attr_nodes = 0;
                        data = data_untouched;
                    elseif withAttr == 2 || withAttr == 4
                        actual_graph_size = original_graph_size+totalAttNum;
                        num_attr_nodes = totalAttNum;
                        data = data_untouched_withAtt;
                    else
                        exception = MException(fprintf('Invalid Attribute Type %d',withAttr));
                        throw(exception);
                    end
                    
                    last_known_node = actual_graph_size - num_missing_nodes;
                    first_unk_node = last_known_node + 1;
                    num_added_nodes = size(data,1) - last_known_node;
                    
                    if withAttr == affinity_boost || withAttr == affinity_boost2
                        fprintf('calculating best results for affinity matrix, type %d (withAttr=%d)...\n', affinity_calculation_type, withAttrWeight);
                        % Sigal 10.3.13 - TODO calc best results
                        if attWeight == 0.9
                            [test_clustering,  best_alg] =  ChooseBestResults(all_att_clustering,all_att_clustering_alg,withAttr);
                        elseif attWeight == 0.1
                            [test_clustering,  best_alg] =  ChooseBestResults(all_k1_clustering,all_k1_clustering_alg,withAttr);
                        elseif attWeight == 0.3
                            [test_clustering,  best_alg] =  ChooseBestResults(all_k3_clustering,all_k3_clustering_alg,withAttr);
                        elseif attWeight == 0.2
                            [test_clustering,  best_alg] =  ChooseBestResults(all_A2_clustering,all_A2_clustering_alg,withAttr);
                        elseif attWeight == 0.4
                            [test_clustering,  best_alg] =  ChooseBestResults(all_A4_clustering,all_A4_clustering_alg,withAttr);
                        else
                            [test_clustering,  best_alg] =  ChooseBestResults(all_clustering,all_clustering_alg,withAttr);
                        end
                        % Sigal 10.3.13 - TODO sum all times
                        affinity_calc_time = 0;
                        graph_predict_time= 0;
                        reduce_dim_time = 0;
                        att_affinity_calc_time = 0;
                        phs_att_affinity_calc_time = 0;
                        phs_img_affinity_calc_time = 0;
                       
                    else
                        
                        % calculate the affinity / similarity matrix
                        fprintf('calculating affinity matrix, type %d (withAttr=%d)...\n', affinity_calculation_type, withAttrWeight);
                        if withAttr == 2
                            tic %affinity_calc_time in seconds
                            affinity = CalcAffinity( data, affinity_calculation_type, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, 0);
                            affinity_calc_time = toc;%affinity_calc_time
                        %sigal - 12.11.13 - calculate once for each type
                        elseif nnz(netAffinity) == 0 && kmeanTypesVec==0 % find(kmeanTypesVec==0)% 
                            tic %affinity_calc_time
                            %sigal - adjust to withAttr flag TOCHECK
                            affinity = CalcAffinity( data, affinity_calculation_type, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
                            affinity_calc_time = toc;%affinity_calc_time
                            netAffinity = affinity;
%                             if affinity_calculation_type ~= affinity_calculation_AA_RCN
%                                 diffAff = affinity(first_unk_node:end,first_unk_node:end)-phsAffinity;
%                                 fprintf('nnz diffAff %d \n',full(nnz(diffAff)));
%                             end
                        else
                            affinity = netAffinity;
                            affinity_calc_time = 0;
                        end
                        if withAttr == 4
                            tic %affinity_calc_time in seconds
                            phsAffinity = CalcPHsAffinity( data, affinity_calculation_type, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
                            affinity_calc_time = toc;%affinity_calc_time
                        %sigal - 12.11.13 - calculate once for each type
                        elseif nnz(phsNetAffinity) == 0 && kmeanTypesVec==1 % find(kmeanTypesVec==1)% 
                            tic %affinity_calc_time in seconds
                            phsNetAffinity = CalcPHsAffinity( data, affinity_calculation_type, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
                            phsAffinity = phsNetAffinity;
                            affinity_calc_time = toc;%affinity_calc_time
                        else
                            %affinity_calc_time = 0;
                            phsAffinity = phsNetAffinity;
                        end
                        
                        %sigal - 12.6.13 - move after calcAffinity so we can calculate only the reduce entries
                        if withAttr == 1 && nnz(attAffinity) == 0
                            nodesToKeep = NodesToKeep(affinity, first_unk_node, 1);
                            fprintf('nodesToKeep %d \n',full(sum(nodesToKeep)));
                            % Sigal TODO - what if addMissingAtt > 0 ??
                            tic %att_affinity_calc_time in seconds
                            fprintf('calculating attribtes affinity matrix...\n');
                            debugCalcAttr = 0; %% Sigal 17.10.13 debugging nodesToKeep & maxAttStat
                            debugAddMissingAtt = 0; %% sigal 16.12.13 backward - use 0 instead of addMissingAtt;
                            if debugCalcAttr == 1
                                attAffinity = CalcAttributesAffinity_S5(data0, attData, last_known_node, debugAddMissingAtt, attAffinityThreshold);
                            else
                                attAffinity = CalcAttributesAffinity_S5(data0, attData, last_known_node, debugAddMissingAtt, attAffinityThreshold, nodesToKeep);
                            end
                            att_affinity_calc_time = toc;%att_affinity_calc_time
                        end
                        %sigal - 12.11.13 - calculate once for each type
                        if (withAttr == 3 || withAttr == 7) && nnz(phsAttAffinity) == 0
                            tic %att_affinity_calc_time in seconds
                            phsAttAffinity = netAffNormFactor3*CalcPHsAffinityByAttributes(data0, attData, last_known_node, addMissingAtt, attAffinityThreshold);
                            phs_att_affinity_calc_time = toc;%att_affinity_calc_time
                        end
                        %sigal - 22.2.14 - calculate once for each type %%%%% TODO
                        if (withAttr == 5 || withAttr == 7) && nnz(phsImgAffinity) == 0
                            tic %img_affinity_calc_time in seconds
                            phsImgAffinity = netAffNormFactor3*CalcPHsAffinityByImages(data0, imagesData, last_known_node, missing_nodes_mapping, imgMissProb, imgSimType, imgSimProbDiff);
                            phs_img_affinity_calc_time = toc;%att_affinity_calc_time
                        end
                        if withAttr == 3 %sigal - 22.2.14 - SAMI_AK
                            if attWeight == 0
                                if nnz(phsAttAffinity2) == 0
                                    tic %att_affinity_calc_time in seconds
                                    phsAttAffinity2 = netAffNormFactor3*CalcPHsAffinityByAttributes(data0, attData, last_known_node, addMissingAtt, attAffinityThreshold, 1);
                                    phs_att_affinity_calc_time = toc;%att_affinity_calc_time
                                end
                                phsAffinity = [netAffNormFactor2*phsAffinity phsAttAffinity2]; % sigal 5.11.13 original order with factor 10
                            else
                                phsAffinity = (1-attWeight)*phsAffinity+attWeight*phsAttAffinity;
                            end
                        elseif withAttr == 5 %sigal - 22.2.14 - PMI %%%%% TODO
                            if attWeight == 0
                                phsAffinity = [netAffNormFactor2*phsAffinity phsImgAffinity]; % sigal 5.11.13 original order with factor 10
                            else
                                phsAffinity = (1-attWeight)*phsAffinity+attWeight*phsImgAffinity;
                            end
                        elseif withAttr == 7 %sigal - 22.2.14 - PMI+SAMI %%%%% TODO
                            if attWeight == 0
                                if nnz(phsAttAffinity2) == 0
                                    tic %att_affinity_calc_time in seconds
                                    phsAttAffinity2 = netAffNormFactor3*CalcPHsAffinityByAttributes(data0, attData, last_known_node, addMissingAtt, attAffinityThreshold, 1);
                                    phs_att_affinity_calc_time = toc;%att_affinity_calc_time
                                end
                                phsAffinity = [netAffNormFactor2*phsAffinity phsAttAffinity2 phsImgAffinity];
                            else
                                phsAffinity = (1-attWeight)*phsAffinity+attWeight*(phsAttAffinity+phsImgAffinity)/2;
                            end
                        end
                        
                    end
                    
                    %  sigal 3.1.13 - weighted affinity
                    if withAttr == 1
                        fprintf('merge affinity matrix with attributes affinity\n');
                        if debugAddMissingAtt > 0
                            e = size(affinity,1);
                        else
                            e=last_known_node;
                        end
                        tic %att_affinity_calc_time
                        %Sigal - 16.6.13 - use full C implementation
                        affinity = WeightedSum(affinity, attAffinity, attWeight, e);
                        %Sigal - 17.6.13 free memory
                        if original_graph_size > 20000
                            fprintf('free attAffinity memory\n');
                            clear('attAffinity');
                            attAffinity = 0;
                            fprintf('free netAffinity memory\n');
                            clear('netAffinity');
                            netAffinity = 0;
                        end
                        %                       affinity(1:e, 1:e)= affinity(1:e,1:e)*(1-attWeight)+attAffinity(1:e,1:e)*attWeight;
                        %                       nnz1 = nnz(affinity);
                        %                       nnz2 = nnz(affinity2);
                        %                       aaa = affinity2-affinity;
                        %                       nnz3 = nnz(aaa);
                        %                       fprintf('nnz affinity: nnz1=%d, nnz2=%d, nnz3=%d\n',nnz1,nnz2,nnz3);
                        att_affinity_merge_time = toc;%att_affinity_merge_time
                    end
                    
                    %TODO: extend the dimension reduction to adding missing links / reclustering
                    %Sigal/ron - ToRECEK ron TODO (done?)
                    
                    %Sigal - run always with 1 (ron)
                    for reduce_dimensions = [1] %0 must be first because it does not change the affinity matrix
                        
                        reduce_dim_time = 0;
                        skip_reduce_dimensions = find(withAttr == [3 4 5 7 affinity_boost affinity_boost2]); %Sigal 22.1.14 %%% TOCHECK
                        if reduce_dimensions == 1 && nnz(affinity) > 0 && ~skip_reduce_dimensions 
                            fprintf('reduce dimensions\n');
                            tic %ReduceDimensions
                            [affinity, num_placeholders, first_unk_node] = ReduceDimensions(affinity, first_unk_node);
                            reduce_dim_time = toc; %ReduceDimensions
                            fprintf('new dimensions %d\n',size(affinity,1));
                        end
                        
                        %sigal - why each iteration? simple calculation - can be done once
                        %sigal - adjust to withAttr flag TODO
                        fprintf('calculating true clustering\n');
                        true_clustering = BuildTrueClustering(missing_nodes_mapping, original_graph_size, num_missing_nodes, percent_known_placeholders, placeholders_to_remove, last_known_node);
                        
                        %figure,imshow(affinity,[]), title('Affinity Matrix')
                        %sigal - use 0:1 if we want to compare with unknown #missNodes
                        % (type=2 wasn't tested by ron)
                        for num_clusters_known = [1] %[0, 1]
                            
                            % sigal 29.7.13
                            % Test other clustering kmean types
                            if affinity_calculation_type == affinity_calculation_random_clustering || affinity_calculation_type == affinity_boost || affinity_calculation_type == affinity_boost2
                                kmeanTypes = 1;
                            elseif withAttr == 0
                                kmeanTypes = kmeanTypesVec;
                            elseif withAttr == 1 || withAttr == 2
                                kmeanTypes = 0;
                             elseif find(withAttr == [3 4 5 7])
                                kmeanTypes = 1;
                            else
                                kmeanTypes = kmeanTypesVec;
                            end
                            % loop over added kmeanTypes (clustering types)
                            for kmeanType = kmeanTypes
                                
                                %sigal - adjust to withAttr flag TODO - which params? data_untouched, original_graph_size
                                k = DetermineNumberOfClusters(num_clusters_known, data_untouched, original_graph_size, num_missing_nodes, num_added_nodes);
                                
                                debugEstimateK = 0;
                                if debugEstimateK == 1 && affinity_calculation_type == affinity_calculation_common_friends
                                    for type=[0,3,4,8]
                                        estK = DetermineNumberOfClusters(type, data_untouched, actual_graph_size, num_missing_nodes, num_added_nodes);
                                        fprintf('debugEstimateK: type=%d, estK=%d\n',type,estK);
                                    end
                                end
                                
                                if num_clusters_known == 1
                                    withAttrC = 0;
                                elseif num_clusters_known == 0
                                    withAttrC = 10;
                                else
                                    withAttrC = num_clusters_known*10;
                                end
                                
                                % sigal 15.10.13 - add kmeanType & num_clusters to alg type
                                withAttrC = withAttrC+kmeanType;
                                withAttrWeight = withAttrC*100+(withAttr+attWeight)*10;
                                
                                %sigal - first_unk_node might change after ReduceDimensions
                                last_known_node =  first_unk_node - 1;
                                
                                
                                if withAttr ~= affinity_boost && withAttr ~= affinity_boost2
                                    %sigal - adjust to withAttr flag TOCHECK
                                    fprintf('predicting the graph\n');
                                    tic %graph_predict_time
                                    if kmeanType == 1
                                        [newData, test_clustering] = PredictGraph(phsAffinity, k, data, num_placeholders, affinity_calculation_type, cluster_only_missing_nodes, kmeanType);
                                    else
                                        [newData, test_clustering] = PredictGraph(affinity, k, data, num_placeholders, affinity_calculation_type, cluster_only_missing_nodes, kmeanType);
                                    end
                                    graph_predict_time = toc; %graph_predict_time
                                end
                                out_data = newData;
                                out_clusterrr = test_clustering;
                                
                                

                                %sigal - when to use - only if there are unknown placeholders
                                if compensate_for_unknown_placeholers == 1
                                    fprintf('*** running with compensate_for_unknown_placeholers mode ...\n');
                                    S = orig_S;
                                    
                                    if size(newData,1) > size(S,2)
                                        %for breakpoint
                                        tttt = 98;
                                    end
                                    sigma = 1/4;
                                    S = S(1:size(newData,1));
                                    S = S + randn(size(S)) * sigma;
                                    sorted_S = sort(S, 'descend');
                                    
                                    %sum over the columns and find the columns which
                                    %indicate at least one neighbor
                                    %neighbors_of_new_nodes = find(sum(newData(first_unk_node:size(newData,1), :)));
                                    
                                    first_united_node = size(newData,1) - k +1;
                                    if affinity_calculation_type == affinity_calculation_katz_beta_0_05
                                        newAffinity = CalcAffinityByKatzBeta_Sparse( newData, 0.05, 4  );
                                    elseif affinity_calculation_type == affinity_calculation_adamic_adar
                                        newAffinity = CalculateAffinityByAdamicAdar_Sparse(newData, size(newData,1), 0, 0);
                                    elseif affinity_calculation_type == affinity_calculation_common_friends
                                        newAffinity = CalcAffinityByCommonNeighbors_Sparse(newData, size(newData,1), 0);
                                    end
                                    
                                    newNodesAffinity = newAffinity(first_united_node:size(newAffinity,1), :);
                                    newNodesAffinity(newNodesAffinity>=1) = 0;
                                    newNodesAffinity = newNodesAffinity / max(max(newNodesAffinity));
                                    %newNodesAffinity = newNodesAffinity / 2;
                                    
                                    newNodesAffinity(newData(first_united_node:size(newAffinity,1), :) >= 1) = 0;
                                    
                                    newNodesAffinity = (newNodesAffinity / max(max(newNodesAffinity)));
                                    %%%%trying to take only the
                                    %%%%k highest affinities
                                    sortedNewNodesAffinity = sort(newNodesAffinity(:), 'descend');
                                    %affinityThreshold = sortedNewNodesAffinity(k + size(neighbors_of_new_nodes, 2));
                                    newNodesAffinity_orig = newNodesAffinity;
                                end % compensate_for_unknown_placeholers == 1
                                
                                if percent_known_placeholders < 1 && compensate_for_unknown_placeholers == 1
                                    %calculating as a function of number of links added
                                    
                                    meanNumLinks = mean(sum(data(1:last_known_node, 1:last_known_node)));
                                    maxNumLinksToAdd = meanNumLinks * num_placeholders;
                                    maxNumLinksToAdd = min(maxNumLinksToAdd, 25);
                                    
                                    %sigal 27.6.13
                                    linksToAdd = round(compensate_vec*num_missing_nodes);
                                else
                                    maxNumLinksToAdd = 0;
                                    %sigal 27.6.13
                                    linksToAdd = 0;
                                end
                                %%%%% for distance as
                                %%%%% function of num
                                %%%%% placeholders %%%%
                                
                                %max_neighbors = S >= sorted_S(maxNumLinksToAdd);
                                %sigal  27.6.13
                                %for numLinksToAdd = 0 : maxNumLinksToAdd
								origWithAttrWeight = withAttrWeight;
                                for linksInx = 1:size(linksToAdd,2)
                                    numLinksToAdd = linksToAdd(linksInx);
                                    %Sigal - 13.10.13 - TODO - fix withAttr flag calculation
                                    withAttrXX = compensate_vec(linksInx)*100; % numLinksToAdd
                                    withAttrWeight = origWithAttrWeight+1000*withAttrXX;
                                    if compensate_for_unknown_placeholers == 1
                                        
                                        newNodesAffinity = newNodesAffinity_orig;
                                        
                                        neighbors = [];
                                        if numLinksToAdd > 0
                                            neighbors = find(S >= sorted_S(numLinksToAdd), numLinksToAdd);
                                        end
                                        
                                        newDataWithMissingLinks = newData; % partial graph with the clustered nodes
                                        newDataForClustering = data0; % partial graph with partial PHs
                                        for neighbor = neighbors
                                            [value, closest_new_node] = max(newNodesAffinity(:,neighbor));
                                            closest_new_node = closest_new_node(1);
                                            newDataWithMissingLinks(first_united_node +  closest_new_node - 1, neighbor) = 1;
                                            newDataWithMissingLinks(neighbor, first_united_node +  closest_new_node - 1) = 1;
                                            
                                            newPlaceholder = zeros(1, size(newDataForClustering,2));
                                            newPlaceholder(neighbor) = 1;
                                            newDataForClustering = [newDataForClustering, newPlaceholder'; newPlaceholder, 0];
                                            
                                        end
                                        
                                        affinityWithS = CalcAffinity( newDataForClustering, affinity_calculation_type, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
                                        
                                        if reduce_dimensions == 1
                                            [affinityWithS, num_placeholdersWithS, first_unk_node_with_s] = ReduceDimensions(affinityWithS, first_united_node);
                                        else
                                            num_placeholdersWithS  =  num_placeholders + length(neighbors);
                                            first_unk_node_with_s = first_united_node;
                                        end
                                        
                                        % Sigal 15.10.13 - we are not using the new clusteing result as in this
                                        % cases we are using the GED as the main measure
                                        fprintf('^%s', newPredictedGraph)
                                       
                                        
                                        %remap the original data so that the known nodes match the
                                        %predicted data and the missing nodes match the predicted
                                        % nodes created from each cluster
                                        
                                        %sigal - adjust to withAttr flag TODO original_data
                                        perm_vector = 1:size(original_data,1);
                                        perm_vector(missing_nodes_mapping(1,:)) = [];
                                        perm_vector = [perm_vector, missing_nodes_mapping(1,:)];
                                        remapped_data = original_data(perm_vector,perm_vector);
                                        
                                        [small_data, indices_to_remove] = DecreaseGraphSize(remapped_data, first_united_node : size(remapped_data,1), neighbors); %changed from neighbors to perm(max_neighbors) - to be fair when there are more nieghbors
                                        %small_data2 = DecreaseGraphSize(newData, last_known_node+1 : size(newData,1));
                                        %new_nodes_affinity_sum = sum(sum(newNodesAffinity));
                                        
                                        %in case there is an empty cluster, the unrelated nodes may contain node index that does not exist
                                        %in the predicted graph (which may contain less nodes)
                                        indices_to_remove(indices_to_remove > size(newPredictedGraph,2)) = [];
                                        
                                        
                                        small_data2 = newData;
                                        small_data2(indices_to_remove,:) = [];
                                        small_data2(:,indices_to_remove) = [];
                                        %small_data3 = DecreaseGraphSize(newDataWithMissingLinks, last_known_node+1 : size(newDataWithMissingLinks,1));
                                        small_data3 = newDataWithMissingLinks;
                                        small_data3(indices_to_remove,:) = [];
                                        small_data3(:,indices_to_remove) = [];
                                        
                                        small_data4 = newPredictedGraph;
                                        small_data4(indices_to_remove,:) = [];
                                        small_data4(:,indices_to_remove) = [];
Sigal 27.1.13 - save reduce graphs for GED
                                        if dumpSmallFlag == 1
                                            saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, small_data, 1);
                                            saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, small_data2, 2);
                                        end
                                        
                                        %only calculate on the first iteration to save time
                                        if numLinksToAdd == 0
                                            edit_distance = 99; %GraphEditDistance( small_data, small_data2, num_missing_nodes );
                                            edit_distance2 = edit_distance;
                                            edit_distance3 = edit_distance;
                                        else
                                            edit_distance2 = 99; %GraphEditDistance( small_data, small_data3, num_missing_nodes );
                                            edit_distance3 = 99; %GraphEditDistance( small_data, small_data4, num_missing_nodes );
                                            if dumpSmallFlag == 1
                                                saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, small_data3, 3);
                                                saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, small_data4, 4);
                                            end
                                        end
                                    elseif withAttr == affinity_boost || withAttr == affinity_boost2 % NOT compensate_for_unknown_placeholers == 1
                                        if dumpSmallFlag == 1
                                            saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, best_alg, 1);
                                            saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, best_alg, 2);
                                        end
                                    else % NOT compensate_for_unknown_placeholers == 1
                                        
                                        %sigal - adjust to withAttr flag TODO original_data
                                        perm_vector = 1:size(original_data,1);          % set values 1:n
                                        perm_vector(missing_nodes_mapping(1,:)) = [];   % according to 1st line of missing nodes remove indexes from perm
                                        perm_vector = [perm_vector, missing_nodes_mapping(1,:)]; % add missing node as last indexes
                                        remapped_data = original_data(perm_vector,perm_vector); % return original graph according to perm
                                        out_data_p = out_data%(perm_vector,perm_vector);
                                        graphs_out = sprintf('../output/graphed_%d.mat', iter);
                                        save(graphs_out, 'out_data_p', 'out_data', 'remapped_data', 'original_data');
                                        %sigal - return data only with missing nodes and their friends
                                        % reduce size to improve GED calulation
                                        [small_data, indices_to_remove] = DecreaseGraphSize(remapped_data, (size(remapped_data,1) - num_missing_nodes + 1) : size(remapped_data,1), []); %changed from neighbors to perm(max_neighbors) - to be fair when there are more nieghbors
                                        
                                        %Sigal - now according to original data remove indexes,
                                        %adjust/reduce the predict grpah return at newData
                                        small_data2 = newData;
                                        %sigal - adjust to withAttr flag - remove att nodes TOCHECK
                                        if num_attr_nodes > 0
                                            small_data2(1:num_attr_nodes,:) = [];
                                            small_data2(:,1:num_attr_nodes) = [];
                                        end
                                        
                                        %sigal 26.11.12 - change newData to small_data2 after resizing
                                        indices_to_remove(indices_to_remove > size(small_data2,2)) = [];
                                        
                                        small_data2(indices_to_remove,:) = [];
                                        small_data2(:,indices_to_remove) = [];
                                        %fprintf('&%s', small_data2)
                                        %fprintf('&&%s', small_data)
Sigal 27.1.13 - save reduce graphs for GED
                                        withAttrWeight = origWithAttrWeight+1000*(1-percent_known_placeholders)*10;
                                        if dumpSmallFlag == 1
                                            saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, small_data, 1);
                                            saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_calculation_type, withAttrWeight, num_missing_nodes, small_data2, 2);
                                        end
                                        %sigal 6.12.12 - *** TODO *** temporary for test only TODO
                                        %edit_distance = GraphEditDistance( small_data, small_data2, num_missing_nodes );
                                        edit_distance = 99;
                                        
                                        % Sigal 10.3.13 - save results (without random)
                                        if attWeight ~= 1 && affinity_calculation_type ~= affinity_calculation_random_clustering
                                            currAlg =  affinity_calculation_type*1000+withAttrWeight;
                                            % sigal 21.10.13 (only on SC)
                                            if kmeanType == 0
                                                res_index = size(all_clustering,2) + 1;
                                                all_clustering(:, res_index) = test_clustering;
                                                all_clustering_alg(res_index) = currAlg;
                                                if withAttr ~= 0
                                                    att_index = size(all_att_clustering,2) + 1;
                                                    all_att_clustering(:, att_index) = test_clustering;
                                                    all_att_clustering_alg(att_index) = currAlg;
                                                end
                                            end
                                            % sigal 17.10.13 - find best based on kmeanType == 2
                                            if kmeanType == 1 
                                                k_index = size(all_k1_clustering,2) + 1;
                                                all_k1_clustering(:, k_index) = test_clustering;
                                                all_k1_clustering_alg(k_index) = currAlg;
                                                if affinity_calculation_type == affinity_calculation_common_friends
                                                    k_index = size(all_A2_clustering,2) + 1;
                                                    all_A2_clustering(:, k_index) = test_clustering;
                                                    all_A2_clustering_alg(k_index) = currAlg;
                                                elseif affinity_calculation_type == affinity_calculation_adamic_adar
                                                    k_index = size(all_A4_clustering,2) + 1;
                                                    all_A4_clustering(:, k_index) = test_clustering;
                                                    all_A4_clustering_alg(k_index) = currAlg;
                                                end
                                            end
                                            if kmeanType == 2 || kmeanType == 3
                                                k_index = size(all_k3_clustering,2) + 1;
                                                all_k3_clustering(:, k_index) = test_clustering;
                                                all_k3_clustering_alg(k_index) = currAlg;
                                            end
                                        end
                                    end % compensate_for_unknown_placeholers == 1
                                    
                                    % calculate the purity for actual clustering
                                    fprintf('calculating purity\n');
                                    try
                                        %sigal - calulation done accoring to definition
                                        temp_purity = ClusteringPurity(true_clustering, test_clustering);
                                    catch ME1
                                        temp_purity = 99; %Sigal 12.8.12 - add invalid value incase of exception
                                        ddddd = 1;
                                    end
                                    clusters_out = sprintf('../output/OUTp_%d.mat', iter);
                                    save(clusters_out, 'true_clustering', 'test_clustering');
                                    
                                    % save results
                                    fprintf('saving results (withAttr %d, purity %.5f) \n',withAttrWeight,temp_purity);
                                    %oooo = sprintf('/Users/armin/Desktop/output/OUT_%d.mat', k);
                                    %save(oooo, 'withAttrWeight', 'temp_purity');
                                    curr_index = size(purity,2) + 1;
                                    purity(curr_index).score = temp_purity;
                                    purity(curr_index).score_sq = temp_purity^2;
                                    purity(curr_index).edit_distance = edit_distance;
                                    if compensate_for_unknown_placeholers == 1
                                        purity(curr_index).numLinksToAdd = numLinksToAdd;
                                        purity(curr_index).edit_distance_missing_links = edit_distance2;
                                        purity(curr_index).edit_distance_new_clustering = edit_distance3;
                                        fprintf('numLinksToAdd - %d\nedit_distance - %d\nedit_distance_missing_links - %d\nedit_distance_new_clustering - %d\n', numLinksToAdd, full(edit_distance), full(edit_distance2), full(edit_distance3));
                                    end
                                    purity(curr_index).withAttr = withAttrWeight; % sigal 15.10.13
                                    purity(curr_index).num_missing_nodes_idx = num_missing_nodes_idx;
                                    purity(curr_index).num_missing_nodes = num_missing_nodes_arr(num_missing_nodes_idx);
                                    purity(curr_index).affinity_calculation_type = affinity_calculation_type;
                                    purity(curr_index).addMissingAtt = addMissingAtt; %sigal 8.11.13
                                    purity(curr_index).cluster_only_missing_nodes = cluster_only_missing_nodes;
                                    purity(curr_index).num_clusters_known = num_clusters_known;
                                    purity(curr_index).num_clusters_estimated = k; % sigal 26.11.12
                                    purity(curr_index).num_placeholders = num_placeholders;
                                    purity(curr_index).num_placeholders_to_remove = num_placeholders_to_remove;
                                    purity(curr_index).num_attr_nodes = totalAttNum; % sigal 3.1.13
                                    purity(curr_index).unite_common_friends = unite_common_friends;
                                    purity(curr_index).iteration = 1;
                                    purity(curr_index).test_clustering = test_clustering;
                                    purity(curr_index).true_clustering = true_clustering;
                                    purity(curr_index).graph_size = graph_size;
                                    purity(curr_index).graph_edges = graph_edges; % sigal - number of edges
                                    purity(curr_index).graph_attr_edges = graph_attr_edges; % sigal - number of attributes edges
                                    purity(curr_index).inverse_purity = 99; % Sigal 12.8.12 - tmp ??? % CalculateInversePurity(true_clustering, test_clustering);
                                    purity(curr_index).NMI = 99; %CalcNormalizedMutualInformation(true_clustering, test_clustering);
                                    purity(curr_index).removed_nodes = removed_nodes;
                                    purity(curr_index).percent_known_placeholders = percent_known_placeholders;
                                    purity(curr_index).reduce_dimensions = reduce_dimensions;
                                    purity(curr_index).missing_nodes_mapping = missing_nodes_mapping;
                                    purity(curr_index).compensate_for_unknown_placeholers = compensate_for_unknown_placeholers;
                                    purity(curr_index).affinity_calc_time = affinity_calc_time;
                                    purity(curr_index).reduce_dim_time = reduce_dim_time;
                                    purity(curr_index).graph_predict_time = graph_predict_time;
                                    if withAttr == 1 %% save this time only for this variation
                                        purity(curr_index).att_affinity_calc_time = att_affinity_calc_time; %sigal 14.3.13
                                        purity(curr_index).affinity_calc_time = affinity_calc_time+att_affinity_merge_time; %sigal 14.3.13
                                    elseif withAttr == 2 || withAttr == 4 %% save this time only for this variation
                                        purity(curr_index).att_affinity_calc_time = att_combine_calc_time; %sigal 13.3.13
                                    elseif withAttr == 3 %% sigal 22.1.14
                                        purity(curr_index).att_affinity_calc_time = phs_att_affinity_calc_time; 
                                    elseif withAttr == 5 %% sigal 22.1.14
                                        purity(curr_index).att_affinity_calc_time = phs_img_affinity_calc_time; 
                                    elseif withAttr == 7 %% sigal 22.1.14
                                        purity(curr_index).att_affinity_calc_time = phs_att_affinity_calc_time+phs_img_affinity_calc_time; 
                                    else
                                        purity(curr_index).att_affinity_calc_time = 0; %sigal 12.3.13
                                    end
                                    
                                    if compensate_for_unknown_placeholers == 0
                                        break
                                    end
                                end %linksToAdd
                                %
                                %                     purity(unite_common_friends+1, num_missing_nodes_idx,  affinity_calculation_type+1, cluster_only_missing_nodes+1)  = ...
                                %                         purity(unite_common_friends+1, num_missing_nodes_idx,  affinity_calculation_type+1, cluster_only_missing_nodes+1) + temp_purity;
                                %
                                %                     purity_sq(unite_common_friends+1, num_missing_nodes_idx,  affinity_calculation_type+1, cluster_only_missing_nodes+1)  = ...
                                %                         purity_sq(unite_common_friends+1, num_missing_nodes_idx,  affinity_calculation_type+1, cluster_only_missing_nodes+1) + temp_purity^2;
                                %
                                
                                
                                LogMsg(sprintf('S8b: Size=%d,Miss=%d,PHs=%d,Affinity=%d,Att=%d,Purity=%.3f', ...
                                    graph_size,purity(curr_index).num_missing_nodes,num_placeholders,affinity_calculation_type,withAttrWeight,temp_purity));
                                
                                %fprintf('affinity_calculation_type = %d, unite_common_friends = %d\n', affinity_calculation_type, unite_common_friends);
                                fprintf('Graph size: %d, Number of missing nodes: %d, Purity: %f \n' ,graph_size, num_missing_nodes, temp_purity);
                                %fprintf('============================================\n\n\n');
                                
                                %clear U;
                                
                                clear eigValues;
                                clear eigVectors;
                            end %kmeanTypes (clustering types)
                        end %num_clusters_known
                    end %reduce_dimensions
                    clear('affinity');
                    clear('phsAffinity');
                end % run loop for attWeight
            end % run over - once as original without attributes and next with attriutes/images
            clear('netAffinity');
            clear('phsNetAffinity');
        end % loop over different affinity_types
        clear('attAffinity');
        clear('phsAttAffinity');
        clear('phsAttAffinity2');
      end %loop over percent_known_placeholders_vec
      end %loop over addMissingAtt
    end %loop over num_missing_nodes...
    
end %main function


% sigal - 29.10.13
% calc only PHs affinity

function [affinity] = CalcPHsAffinity( data, affType, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt)
    global affinity_calculation_shortest_path;
    global affinity_calculation_euclid;
    global affinity_calculation_common_friends;
    global affinity_calculation_random_clustering;
    global affinity_calculation_adamic_adar;
    global affinity_calculation_katz_beta_0_5;
    global affinity_calculation_katz_beta_0_05;
    global affinity_calculation_katz_beta_0_005;
    global affinity_calculation_AA_RCN;
    
    global netAffNormFactor1;
    global netAffNormFactor2;

    firstPH = actual_graph_size-num_missing_nodes+1;
    normAttWeight = attWeight / netAffNormFactor2; % only for SAMI-N
    
    if affType == affinity_calculation_euclid
        LogMsg(sprintf('*** ERROR: MissingNodes_S8b:CalcPHsAffinity - affType %d not supported !!!',affType));
        return;
    elseif affType == affinity_calculation_shortest_path
        LogMsg(sprintf('*** ERROR: MissingNodes_S8b:CalcPHsAffinity - affType %d not supported !!!',affType));
        return;
    elseif affType == affinity_calculation_common_friends
          affinity = CalcPHsAffinityByRCN(data, actual_graph_size, num_missing_nodes, num_attr_nodes, normAttWeight, addMissingAtt);
    elseif affType == affinity_calculation_random_clustering
        affinity = data(firstPH:end, firstPH:end); %just a placeholder...
    elseif affType == affinity_calculation_adamic_adar
          affinity =  CalcPHsAffinityByAA( data, actual_graph_size, num_missing_nodes, 1, num_attr_nodes, normAttWeight, addMissingAtt);
    elseif affType == affinity_calculation_katz_beta_0_5
          affinity = CalcPHsAffinityByKatzBeta( data, 0.5, 3, firstPH );
    elseif affType == affinity_calculation_katz_beta_0_05
          affinity = CalcPHsAffinityByKatzBeta( data, 0.05, 4, firstPH );
    elseif affType == affinity_calculation_katz_beta_0_005
          affinity = CalcPHsAffinityByKatzBeta( data, 0.005, 4, firstPH );
    elseif affType == affinity_calculation_AA_RCN
          affinity = CalcPHsAffinity( data, affinity_calculation_adamic_adar, actual_graph_size, num_missing_nodes, num_attr_nodes, normAttWeight, addMissingAtt);
          affinity2 = CalcPHsAffinity( data, affinity_calculation_common_friends, actual_graph_size, num_missing_nodes, num_attr_nodes, normAttWeight, addMissingAtt);
          affinity = [affinity2 affinity];
    end

    %sigal 14.11.13
    affinity = affinity * netAffNormFactor1;
    
end %main function


%sigal - adjust to withAttr flag TODO
function [affinity] = CalcAffinity( data, affinity_calculation_type, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt)
    global affinity_calculation_shortest_path;
    global affinity_calculation_euclid;
    global affinity_calculation_common_friends;
    global affinity_calculation_random_clustering;
    global affinity_calculation_adamic_adar;
    global affinity_calculation_katz_beta_0_5;
    global affinity_calculation_katz_beta_0_05;
    global affinity_calculation_katz_beta_0_005;
    global affinity_calculation_AA_RCN;
    
    global netAffNormFactor1;
    
    % sigal 11.2.14 - backward compitbility with ASONAM 13
    addMissingAtt = 0;
    
    if affinity_calculation_type == affinity_calculation_euclid
          sp_mat = graphallshortestpaths(data);
          %remove INF values
          max_value = max(sp_mat(sp_mat ~= Inf)) + 1;
          sp_mat_euclid = sp_mat;
          sp_mat_euclid(sp_mat == Inf) = max_value;
          affinity = CalculateAffinity(sp_mat_euclid);
          %affinity = exp(-(sp_mat.^2))/(2 * 0.3^2);
    elseif affinity_calculation_type == affinity_calculation_shortest_path
          %                 max_value = max(sp_mat(sp_mat ~= Inf)) + 1;
          %                 sp_mat_euclid = sp_mat;
          %                 sp_mat_euclid(sp_mat == Inf) = max_value;
          %                 affinity = (sp_mat_euclid + 1).^(-affinity_exp_factor);


          %affinity = spfun(affinityFunc, data);
          affinity = graphallshortestpaths(data);
          affinity = affinity .^ -2;

          affinity(affinity == Inf) = 1; %added on 05/11/11

    elseif affinity_calculation_type == affinity_calculation_common_friends
          affinity = CalcAffinityByCommonNeighbors_Sparse(data, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
          %affinity = CalcAffinityByCommonNeighbors(data, actual_graph_size, num_missing_nodes);
    elseif affinity_calculation_type == affinity_calculation_random_clustering
          affinity = data; %just a placeholder...
    elseif affinity_calculation_type == affinity_calculation_adamic_adar
          affinity =  CalculateAffinityByAdamicAdar_S3o( data, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, 1  , addMissingAtt);
          %%affinity2 =  CalculateAffinityByAdamicAdar_S2( data, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, 1  , addMissingAtt);
          if nnz(affinity) < 5
                x = 8;
          end
    %       diff = affinity2-affinity;
    %       if nnz(diff) > 0
    %           LogMsg(sprintf('*** WARNING: affinityAA - mismatch (nnz=%d)',nnz(diff)));
    %           zz = 999;
    %       end
    elseif affinity_calculation_type == affinity_calculation_katz_beta_0_5
          affinity = CalcAffinityByKatzBeta_Sparse( data, 0.5, 3, num_attr_nodes );
    elseif affinity_calculation_type == affinity_calculation_katz_beta_0_05
          affinity = CalcAffinityByKatzBeta_Sparse( data, 0.05, 4, num_attr_nodes );
    elseif affinity_calculation_type == affinity_calculation_katz_beta_0_005
          affinity = CalcAffinityByKatzBeta_Sparse( data, 0.005, 4, num_attr_nodes );
    elseif affinity_calculation_type == affinity_calculation_AA_RCN
          w2 = 0.5;
          affinity = CalcAffinity( data, affinity_calculation_adamic_adar, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
          affinity2 = CalcAffinity( data, affinity_calculation_common_friends, actual_graph_size, num_missing_nodes, num_attr_nodes, attWeight, addMissingAtt);
          affinity = WeightedSum(affinity, affinity2, w2, size(affinity,1));
    end
    
    %sigal 22.11.13
    %affinity = affinity * 10; %%netAffNormFactor1;

end % function CalcAffinity

%sigal - review code and messages TODO
function [test_clustering] = SpectralClustering(affinity, k, num_placeholders, affinityType, cluster_only_missing_nodes)

    fprintf('kmeans clustering type=0 (SP)\n');
    
    first_unk_node = size(affinity,1) - num_placeholders + 1;

    diagonal = sum(affinity, 2); %sum the rows
    D = sparse(diag(diagonal)); %D is the matrix whose diagonal is the sum of the rows of A
    clear('diagonal');

    fprintf('calculating NL\n');

    D = sqrt(D);
    NL1 = D * affinity * D;
    clear('D');

    fprintf('calculating U - eigs\n');

    fail = 0;
    try
        [nEigVec,eigValues] = eigs(NL1,k);
    catch ME1 % variable that get the exception
        opts.tol = 1e-1;
        try
            fprintf('calculating U - 2nd try\n');
            [nEigVec,eigValues] = eigs(NL1,k, 'LM', opts);
        catch ME2
            fail = 1;
        end
    end

    % select k largest eigen vectors
    if fail == 0
        U = [];
        % construct the normalized matrix U from the obtained eigen vectors
        fprintf('calculating U - construct\n');
        for i=1:size(nEigVec,1)
            n = sqrt(sum(nEigVec(i,:).^2));
            U(i,:) = nEigVec(i,:) ./ n;
        end

        num_samples = size(affinity,1) - first_unk_node + 1;

        if cluster_only_missing_nodes == 1
            U(1:first_unk_node - 1 ,:) = []; %cluster only the missing nodes
        end

        fprintf('SC: run kmeans clustering\n');
        % perform kmeans clustering on the matrix U
        test_clustering = calcKMean(U, k, num_samples, affinityType);
    else %fail == 0
        disp('Failed in finding eigenvectors - using random!');
        if cluster_only_missing_nodes == 0
            num_samples = size(affinity,1);
        else
            num_samples = num_placeholders;
        end
        test_clustering = randi(k, num_samples, 1);
    end
    
end % function SpectralClustering

% Sigal 29.7.13
% add option for clustering with Kmean intead of SP
% options: kmean_type 0=SP, 3=kmean on PH (mxm), 2=Kmean on PH+Nodes (m*(m+n))
% 1=kmean on already cut affinity
function [test_clustering] = KMeanClustering(affinity, k, num_placeholders, affinityType, kmean_type)

    first_unk_node = size(affinity,1) - num_placeholders + 1;
    num_samples = num_placeholders;

    if kmean_type == 1
        U = affinity; 
    elseif kmean_type == 3 % previous kmean_type == 1
        U(1:num_placeholders,1:num_placeholders) = affinity(first_unk_node:end,first_unk_node:end); 
    else
        U(1:num_placeholders,:) = affinity(first_unk_node:end,:); 
    end

    fprintf('kmeans clustering type=%d\n',kmean_type);

    % perform kmeans clustering on the matrix U
    test_clustering = calcKMean(U, k, num_samples, affinityType);
      
end % function SpectralClustering

% Sigal 29.10.13
% perform kmeans clustering on the matrix U
% use same method for both KMeanClustering and SpectralClustering
function [test_clustering] = calcKMean(U, num_clusters, num_samples, affinityType)

    global affinity_calculation_random_clustering;

    if num_clusters > 99
        numReplicates = 1;
    else
        numReplicates = 3;
    end
        
    fprintf('calcKMean\n');

    % perform kmeans clustering on the matrix U
    fail = 1;
    while fail > 0
        try
              currK = num_clusters;
              % OPT: 'EmptyAction','singleton' - in case of an empty cluster just drop it
              % OPT: 'Replicates',3 - repeat run/start points
              [IDX,C, SUMD, D] = kmeans(U,currK,'EmptyAction','singleton','Replicates',numReplicates); 
              fail = 0;
        catch ME1
              fail = fail + 1;
              if fail < 100
                    %disp('error in kmeans clustering. trying again...');
              else
                    %give up on clustering and select random clusters...
                    IDX = randi(currK, size(U));
                    fail = 0;
              end
        end
    end

    test_clustering = IDX(size(IDX,1) - num_samples + 1  : size(IDX,1));
    
    %if it's random just replace everything...
    if affinityType == affinity_calculation_random_clustering
        test_clustering = randi(num_clusters, size(test_clustering,1), size(test_clustering,2));
    end
end %function KMeanClustering



% sigal - adjust to withAttr flag TOCHECK - which data to use?
% Sigal 29.7.13
% add option for clustering with Kmean intead of SP
% original implementation with SP, i.e use kmean_type = 0
% k is the number of return clusters
function [newData, test_clustering] = PredictGraph(affinity, k, data, num_placeholders, affinity_calculation_type, cluster_only_missing_nodes, kmean_type)

    % sigal - backwards compatibility
    if nargin < 7
        kmean_type = 0;
    end

    last_known_node =  size(data,1) - num_placeholders;
    %%first_unk_node =  last_known_node + 1; % Sigal 15.10.13 remove unuse warning


    if kmean_type == 0
        [test_clustering] = SpectralClustering(affinity, k, num_placeholders, affinity_calculation_type, cluster_only_missing_nodes);
    else
        [test_clustering] = KMeanClustering(affinity, k, num_placeholders, affinity_calculation_type, kmean_type);
    end
    %sigal - what if #clusters diffrent than #missing ???
    newNodes = CreateNewNodesFromClusters(data, test_clustering);

    %sigal - ... means continue command at next line
    newData = [data(1:last_known_node,1:last_known_node),       newNodes(:, 1:last_known_node)';...
                                  newNodes(:,1:last_known_node),                                       zeros(size(newNodes,1))];

end % function PredictGraph

%sigal - estimation can be wrong ???
%sigal - adjust to withAttr flag TODO 
function [k] = DetermineNumberOfClusters(num_clusters_known, data_untouched, actual_graph_size, num_missing_nodes, num_added_nodes)

    %determine k - the number of clusters
    if num_clusters_known == 1
          k = num_missing_nodes;
    else
        numKnownNodes = actual_graph_size - num_missing_nodes;
        sumKnownEdges = sum(sum(data_untouched(1 : numKnownNodes, 1 : numKnownNodes)));
        meanKnownEdges = sumKnownEdges/numKnownNodes;
        addedEdges = num_added_nodes*2; % undirect graph
        fprintf('EstimatedK: numKnownN=%d, meanKnownE=%.3f, addedE=%d, missN=%d, meanMissE=%.3f\n', ...
            numKnownNodes,full(meanKnownEdges),num_added_nodes,num_missing_nodes,addedEdges/num_missing_nodes);
        if num_clusters_known == 0
            %k = round(num_added_nodes / meanKnownEdges);
            k = round(num_added_nodes / floor(meanKnownEdges));
            %fprintf('EstimatedK: type=%d, actual=%d, rounding k to %d\n',num_clusters_known, num_missing_nodes, k);
        elseif num_clusters_known == 2 %guessing upper limit
            k = 2*round(num_added_nodes / meanKnownEdges);
            %fprintf('EstimatedK: type=%d, actual=%d, guessing upper limit %d\n',num_clusters_known, num_missing_nodes, k);
        elseif  num_clusters_known == 3 % e=a*n
            a = meanKnownEdges;
            e = sumKnownEdges+num_added_nodes;
            k = round(e/a-numKnownNodes);
            %fprintf('EstimatedK: type=%d, actual=%d, rounding k to %d\n',num_clusters_known, num_missing_nodes, k);
        elseif  num_clusters_known == 4 % e=a*n^2
            a =  meanKnownEdges/numKnownNodes;
            e = sumKnownEdges+addedEdges;
            k = round(sqrt(e/a)-numKnownNodes);
            %fprintf('EstimatedK: type=%d, actual=%d, rounding k to %d\n',num_clusters_known, num_missing_nodes, k);
        elseif  num_clusters_known == 5 % e=a*n^2
            a =  meanKnownEdges/numKnownNodes;
            e = sumKnownEdges+addedEdges;
            k = ceil(sqrt(e/a)-numKnownNodes);
            %fprintf('EstimatedK: type=%d, actual=%d, rounding k to %d\n',num_clusters_known, num_missing_nodes, k);
        elseif  num_clusters_known == 6 % e=a*n
            a = meanKnownEdges;
            e = sumKnownEdges+num_added_nodes;
            k = ceil(e/a-numKnownNodes);
        elseif num_clusters_known == 7
            k = ceil(num_added_nodes / meanKnownEdges);
        elseif num_clusters_known == 8
            k = round(num_added_nodes / meanKnownEdges);
        end
        LogMsg(sprintf('EstimatedK(size,PHs,type,actual,k):\t%d\t%d\t%d\t%d\t%d', ...
            actual_graph_size,num_added_nodes,num_clusters_known, num_missing_nodes, k),'EstimateK_Log2.txt');

    end 
end % function DetermineNumberOfClusters

%find nodes with some affinity to one or more missing node
function [nodes_to_keep] = NodesToKeep(affinity, first_unk_node, includePHs)

    affinity_sum = sum(affinity(first_unk_node:size(affinity,1),:)); %the sum of the affinity of placeholders to all other nodes
    nodes_to_keep = (affinity_sum > 0); %keep only nodes which have some affinity to the placeholders

    if includePHs == 1
        nodes_to_keep(first_unk_node:size(affinity,1)) = 1; %keep all the placeholders even if for some reason they have a sum of zero...
    end

end % function NodesToKeep


%keep only missing node rows and their friends
function [affinity, num_placeholders, first_unk_node] = ReduceDimensions(affinity, first_unk_node)

    num_placeholders = size(affinity,1) - first_unk_node + 1;
    %keep only nodes which have some affinity to the placeholders and all of the placeholders
    nodes_to_keep = NodesToKeep(affinity, first_unk_node, 1); 

    affinity = affinity(nodes_to_keep, nodes_to_keep);

    first_unk_node = size(affinity,1) - num_placeholders + 1;

end % function ReduceDimensions

%return the true clustering accoring to the savd missing_nodes_mapping
function [true_clustering] = BuildTrueClustering(missing_nodes_mapping, actual_graph_size, num_missing_nodes, percent_known_placeholders, placeholders_to_remove, last_known_node)

    %sigal 25.11.12 - count nonzero cell (beside first raw) - i.e. number of placeholder
    numMapping = 0;
    %sigal 23.1.14 - start form thrid row (first row original id, second row images profile)
    for i = 3 : size(missing_nodes_mapping, 1)
        nz=find(missing_nodes_mapping(i,:));  
        numMapping = numMapping + size(nz,2);
    end
    true_clustering = zeros(numMapping,1);
    %sigal 25.11.12
    %true_clustering = []; %zeros(size(test_clustering, 1), 1);

    for i = 3 : size(missing_nodes_mapping, 1)
          for j = 1 : size(missing_nodes_mapping,2)
                if missing_nodes_mapping(i,j) ~= 0
                      true_clustering(missing_nodes_mapping(i,j) - actual_graph_size + num_missing_nodes, 1) = j; % missing_nodes_mapping(1, j);
                end
          end
    end

    %sigal - adjust to withAttr flag TODO 
    if percent_known_placeholders < 1
          true_clustering(placeholders_to_remove - last_known_node) = [];
    end

end % function BuildTrueClustering


function saveSmallData(dumpSmallDataPath, dataFileName, iter, affinity_type, withAttr, missNodes, small_data, i)
Sigal 24.1.13 - TODO
    outFile = sprintf('%s_%d_%d_%d_%d_small_data_%d', dataFileName, iter, missNodes, affinity_type, withAttr, i);
    if affinity_type == 9 % save instead a dummy size (1) and the best_alg
        SaveIntMatrixToFile(strcat(dumpSmallDataPath, outFile,'_edges.txt'), small_data, 1);
    else
        SaveAsciiGraph(dumpSmallDataPath, outFile, small_data, 1); %% also save graph size
    end

end % function saveSmallData

function [best_clustering, best_alg] = ChooseBestResults(clusteringResults, clusteringAlg, type)
    global affinity_boost;
    global affinity_boost2;
    
    if type == affinity_boost
        best_clustering_inx = ChooseBestResults1(clusteringResults);
    elseif type == affinity_boost2
        best_clustering_inx = ChooseBestResults2(clusteringResults, clusteringAlg);
    else
        fprintf('*** ERROR: ChooseBestResults: invalid tye %d\n', type);
    end
    best_clustering =  clusteringResults(:,best_clustering_inx);
    best_alg = clusteringAlg(best_clustering_inx);
end % function ChooseBestResults

function [best_clustering_inx] = ChooseBestResults1(clusteringResults, indices)
    numResults = size(clusteringResults,2);
    if nargin < 2
        indices = ones(1,numResults); % i.e. all
    end
    sumPurity = CalcSumPurity(clusteringResults, indices);
    % return max entry
    [val, inx] = max(sumPurity);
    fprintf('ChooseBestResults: val %d, inx %d\n', val, inx);
    best_clustering_inx =  inx;
end % function ChooseBestResults

function [best_clustering_inx] = ChooseBestResults2(clusteringResults, clusteringAlg)
    max_num_level_2 = 10;
    last_level_2 = 1;

    numResults = size(clusteringResults,2);
    indices_level_1 = zeros(1,numResults);
    indices_level_2 = zeros(max_num_level_2,numResults);
    alg_level_2 = zeros(1,max_num_level_2);
    
    for i=1:numResults
        base_alg = floor(clusteringAlg(i)/10);
        %base_att = base_alg-10*floor(base_alg/10);
        var_alg = clusteringAlg(i)-base_alg*10;
        if var_alg == 0 || var_alg == 0
            indices_level_1(i) = 1;
        else
            found = 0;
            for j=1:last_level_2-1
                if alg_level_2(j)==base_alg
                    l2 = j;
                    found = 1;
                    break;
                end
            end
            if found == 0
                l2 = last_level_2;
                alg_level_2(l2)=base_alg;
                last_level_2 = l2+1;
            end
            indices_level_2(l2,i) = 1;
        end
    end
    
    for j=1:last_level_2-1
        best = ChooseBestResults1(clusteringResults, indices_level_2(j,:));
        indices_level_1(best) = 1;
    end
    
    best_clustering_inx = ChooseBestResults1(clusteringResults, indices_level_1);
    
end % function ChooseBestResults

function [sumPurity] = CalcSumPurity(clusteringResults, indices)
    numResults = size(clusteringResults,2);
    crossPurity = zeros(numResults,numResults);
    for i=1:numResults
        for j=1:numResults
            if i~=j && indices(i)==1 && indices(j)==1
                crossPurity(i,j) = ClusteringPurity(clusteringResults(:,j), clusteringResults(:,i));
            end
        end
    end
    sumPurity = sum(crossPurity,2);
end % function CalcSumPurity