C++ graphchi_vertex::edge方法代码示例

  /**
   *  Vertex update function - computes the least square step
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
    vertex_data & vdata = latent_factors_inmem[vertex.id()];
    mat XtX = mat::Zero(D, D); 
    vec Xty = vec::Zero(D);

    bool compute_rmse = (vertex.num_outedges() > 0);
    // Compute XtX and Xty (NOTE: unweighted)
    for(int e=0; e < vertex.num_edges(); e++) {
      float observation = vertex.edge(e)->get_data();                
      vertex_data & nbr_latent = latent_factors_inmem[vertex.edge(e)->vertex_id()];
      Xty += nbr_latent.pvec * observation;
      XtX += nbr_latent.pvec * nbr_latent.pvec.transpose();
      if (compute_rmse) {
        double prediction;
        rmse_vec[omp_get_thread_num()] += sparse_als_predict(vdata, nbr_latent, observation, prediction);
      }
    }

    double regularization = lambda;
    if (regnormal)
      lambda *= vertex.num_edges();
    for(int i=0; i < D; i++) XtX(i,i) += regularization;


    bool isuser = vertex.id() < (uint)M;
    if (algorithm == SPARSE_BOTH_FACTORS || (algorithm == SPARSE_USR_FACTOR && isuser) || 
        (algorithm == SPARSE_ITM_FACTOR && !isuser)){ 
      double sparsity_level = 1.0;
      if (isuser)
        sparsity_level -= user_sparsity;
      else sparsity_level -= movie_sparsity;
      vdata.pvec = CoSaMP(XtX, Xty, (int)ceil(sparsity_level*(double)D), 10, 1e-4, D); 
    }
    else vdata.pvec = XtX.selfadjointView<Eigen::Upper>().ldlt().solve(Xty);
  }

  /**
   *  Vertex update function.
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
    //go over all user nodes
    if ( vertex.num_outedges() > 0){
      vertex_data & user = latent_factors_inmem[vertex.id()]; 
      //go over all ratings
      for(int e=0; e < vertex.num_edges(); e++) {
        float observation = vertex.edge(e)->get_data();                
        vertex_data & movie = latent_factors_inmem[vertex.edge(e)->vertex_id()];
        double estScore;
        rmse_vec[omp_get_thread_num()] += sgd_predict(user, movie, observation, estScore);
        double err = observation - estScore;
        if (std::isnan(err) || std::isinf(err))
          logstream(LOG_FATAL)<<"SGD got into numerical error. Please tune step size using --sgd_gamma and sgd_lambda" << std::endl;
        //NOTE: the following code is not thread safe, since potentially several
        //user nodes may updates this item gradient vector concurrently. However in practice it
        //did not matter in terms of accuracy on a multicore machine.
        //if you like to defend the code, you can define a global variable
        //mutex mymutex;
        //
        //and then do: mymutex.lock()
        movie.pvec += sgd_gamma*(err*user.pvec - sgd_lambda*movie.pvec);
        //and here add: mymutex.unlock();
        user.pvec += sgd_gamma*(err*movie.pvec - sgd_lambda*user.pvec);
      }
    }

  }

  /**
   *  Vertex update function.
   *  On first iteration ,each vertex chooses a label = the vertex id.
   *  On subsequent iterations, each vertex chooses the minimum of the neighbor's
   *  label (and itself).
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {

    /* On subsequent iterations, find the minimum label of my neighbors */
    if (!edge_count){
      vid_t curmin = vertex_values[vertex.id()];
      if (gcontext.iteration == 0 && vertex.num_edges() > 0){
        mymutex.lock(); actual_vertices++; mymutex.unlock();
      }
      for(int i=0; i < vertex.num_edges(); i++) {
        vid_t nblabel = neighbor_value(vertex.edge(i));
        curmin = std::min(nblabel, curmin);
      }

      if (vertex_values[vertex.id()] > curmin) {
        changes++;
        set_data(vertex, curmin);
      }
    }
    else {
      vid_t curmin = vertex_values[vertex.id()];
      for(int i=0; i < vertex.num_edges(); i++) {
        vid_t nblabel = neighbor_value(vertex.edge(i));
        curmin = std::min(nblabel, curmin);
        if (vertex.edge(i)->vertex_id() > vertex.id()){
        mymutex.lock();
        state[curmin]++;
        mymutex.unlock();
        }
      }
    }
  }

  /**
   *  Vertex update function - computes the least square step
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
    vertex_data & vdata = latent_factors_inmem[vertex.id()];
    bool isuser = vertex.id() < M;
    mat XtX = mat::Zero(D, D); 
    vec Xty = vec::Zero(D);

    bool compute_rmse = (vertex.num_outedges() > 0);
    // Compute XtX and Xty (NOTE: unweighted)
    for(int e=0; e < vertex.num_edges(); e++) {
      const edge_data & edge = vertex.edge(e)->get_data();
      float observation = edge.weight;                
      vertex_data & nbr_latent = latent_factors_inmem[vertex.edge(e)->vertex_id()];
      Xty += nbr_latent.pvec * observation;
      XtX.triangularView<Eigen::Upper>() += nbr_latent.pvec * nbr_latent.pvec.transpose();
      if (compute_rmse) {
        double prediction;
        rmse_vec[omp_get_thread_num()] += pmf_predict(vdata, nbr_latent, observation, prediction, (void*)&edge.avgprd);
        vertex.edge(e)->set_data(edge);
      }
    }

    double regularization = lambda;
    if (regnormal)
      lambda *= vertex.num_edges();
    for(int i=0; i < D; i++) XtX(i,i) += regularization;

    // Solve the least squares problem with eigen using Cholesky decomposition
    mat iAi_;
    bool ret =inv((isuser? A_U : A_V) + alpha *  XtX, iAi_);
    assert(ret);
    vec mui_ =  iAi_*((isuser? (A_U*mu_U) : (A_V*mu_V)) + alpha * Xty); 
    vdata.pvec = mvnrndex(mui_, iAi_, D, 0); 
    assert(vdata.pvec.size() == D);
 }

	/**
	 *  Vertex update function.
	 */
	void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
		//go over all samples (rows)
		if ( vertex.num_outedges() > 0){

			assert(vertex.id() < M);
			vertex_data & row = latent_factors_inmem[vertex.id()]; 
                        assert(row.y == -1 || row.y == 1);

			if (debug)
				std::cout<<"Entered item " << vertex.id() << " y: " << row.y << std::endl;
			row.sigma = beta*beta;
			row.xT_mu = 0;

			//go over all features
			for(int e=0; e < vertex.num_outedges(); e++) {
                                uint feature_id = vertex.edge(e)->vertex_id();
				edge_data edge = vertex.edge(e)->get_data();                

				assert(sigma_ij[feature_id] > 0);
                                assert(edge.x_ij  == 1);

                                /* compute equation (6) */
				row.sigma += edge.x_ij * sigma_ij[feature_id];
                                /* compute the sum xT*w as needed in equations (7) and (8) */
				row.xT_mu += edge.x_ij * mu_ij[feature_id];
                                
			}
			double prediction;
			double ret = ctr_predict(row, row, row.y, prediction);
                        double predicted_target = prediction < 0 ? -1: 1;
			if ((predicted_target == -1  && row.y == 1) || (predicted_target == 1 && row.y == -1))
				err_vec[omp_get_thread_num()] += 1.0;  
                        if (debug)
                                std::cout<<"Prediction was: " << prediction << " real value: " << row.y << std::endl;
			liklihood_vec[omp_get_thread_num()] += ret;

			assert(row.sigma > 0);

			//go over all features
			for(int e=0; e < vertex.num_outedges(); e++) {
				edge_data edge = vertex.edge(e)->get_data();                
                                uint feature_id = vertex.edge(e)->vertex_id();
				assert(row.sigma > 0);
				double product = row.y * row.xT_mu / sqrt(row.sigma);
				mu_ij[feature_id] +=  (row.y * edge.x_ij *  sigma_ij[feature_id]  / sqrt(row.sigma)) * v(product);
				//if (debug)
				//    std::cout<<"Added to edge: "<< vertex.edge(e)->vertex_id() << " product: " << product << " v(product): " << v(product) << " value: " <<(row.y * edge.x_ij *  edge.sigma_ij * edge.sigma_ij / sqrt(row.sigma)) * v(product) << std::endl; 
				double factor = 1.0 - (edge.x_ij * sigma_ij[feature_id] / row.sigma)*w(product); 
				//if (debug)
				//    std::cout<<"Added to edge: "<< vertex.edge(e)->vertex_id() << " product: " << product << " w(product): " << w(product) << " factor: " << (1.0 - (edge.x_ij * edge.sigma_ij / row.sigma)*w(product)) << " sigma_ij " << edge.sigma_ij << "  product: " << edge.sigma_ij * factor << std::endl; 

				assert(factor > 0);
				sigma_ij[feature_id] *= factor;
                                assert(sigma_ij[feature_id] > 0);
			}

		}
	}

 // Helper
 virtual void set_latent_factor(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, latentvec_t &fact) {
     vertex.set_data(fact);
     for(int i=0; i < vertex.num_edges(); i++) {
         als_factor_and_weight factwght = vertex.edge(i)->get_data();
         factwght.factor = fact;
         vertex.edge(i)->set_data(factwght);   // Note that neighbors override the values they have written to edges.
                                               // This is ok, because vertices are always executed in same order.
     }
 }

  /**
   *  Vertex update function.
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
      if ( vertex.num_outedges() > 0){
        vertex_data & user = latent_factors_inmem[vertex.id()]; 

        memset(&user.weight[0], 0, sizeof(double)*D);
        for(int e=0; e < vertex.num_outedges(); e++) {
          vertex_data & movie = latent_factors_inmem[vertex.edge(e)->vertex_id()]; 
          user.weight += movie.weight;

        }
        // sqrt(|N(u)|) 
        float usrNorm = double(1.0/sqrt(vertex.num_outedges()));
        //sqrt(|N(u)| * sum_j y_j
        user.weight *= usrNorm;

        vec step = zeros(D);

        // main algorithm, see Koren's paper, just below below equation (16)
        for(int e=0; e < vertex.num_outedges(); e++) {
          vertex_data & movie = latent_factors_inmem[vertex.edge(e)->vertex_id()]; 
          float observation = vertex.edge(e)->get_data();                
          double estScore;
          rmse_vec[omp_get_thread_num()] += svdpp_predict(user, movie,observation, estScore); 
          // e_ui = r_ui - \hat{r_ui}
          float err = observation - estScore;
          assert(!std::isnan(rmse_vec[omp_get_thread_num()]));
          vec itmFctr = movie.pvec;
          vec usrFctr = user.pvec;

          //q_i = q_i + gamma2     *(e_ui*(p_u      +  sqrt(N(U))\sum_j y_j) - gamma7    *q_i)
          for (int j=0; j< D; j++)
            movie.pvec[j] += svdpp.itmFctrStep*(err*(usrFctr[j] +  user.weight[j])             - svdpp.itmFctrReg*itmFctr[j]);
          //p_u = p_u + gamma2    *(e_ui*q_i   -gamma7     *p_u)
          for (int j=0; j< D; j++)
            user.pvec[j] += svdpp.usrFctrStep*(err *itmFctr[j] - svdpp.usrFctrReg*usrFctr[j]);
          step += err*itmFctr;

          //b_i = b_i + gamma1*(e_ui - gmma6 * b_i) 
          movie.bias += svdpp.itmBiasStep*(err-svdpp.itmBiasReg* movie.bias);
          //b_u = b_u + gamma1*(e_ui - gamma6 * b_u)
          user.bias += svdpp.usrBiasStep*(err-svdpp.usrBiasReg* user.bias);
        }

        step *= float(svdpp.itmFctr2Step*usrNorm);
        //gamma7 
        double mult = svdpp.itmFctr2Step*svdpp.itmFctr2Reg;
        for(int e=0; e < vertex.num_edges(); e++) {
          vertex_data&  movie = latent_factors_inmem[vertex.edge(e)->vertex_id()];
          //y_j = y_j  +   gamma2*sqrt|N(u)| * q_i - gamma7 * y_j
          movie.weight +=  step                    -  mult  * movie.weight;
        }
      }
  }

  /**
   *  Vertex update function.
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {

    if (vertex.id() < (uint)mi.start || vertex.id() >= (uint)mi.end)
      return;

    vertex_data& user = latent_factors_inmem[vertex.id()];
    bool rows = vertex.id() < (uint)info.get_start_node(false);
    if (info.is_square()) 
      rows = mi.A_transpose;
    (void) rows; // unused
    assert(mi.r_offset >=0);
    //store previous value for convergence detection
    if (mi.prev_offset >= 0)
      user.pvec[mi.prev_offset ] = user.pvec[mi.r_offset];

    double val = 0;
    assert(mi.x_offset >=0 || mi.y_offset>=0);

    /*** COMPUTE r = c*A*x  ********/
    if (mi.A_offset  && mi.x_offset >= 0){
      for(int e=0; e < vertex.num_edges(); e++) {
        const edge_data & edge = vertex.edge(e)->get_data();
        const vertex_data  & movie = latent_factors_inmem[vertex.edge(e)->vertex_id()];
        val += (edge.weight * movie.pvec[mi.x_offset]);
      }

      if  (info.is_square() && mi.use_diag)// add the diagonal term
        val += (/*mi.c**/ (user.A_ii+ regularization) * user.pvec[mi.x_offset]);

      val *= mi.c;
    }
    /***** COMPUTE r = c*I*x  *****/
    else if (!mi.A_offset && mi.x_offset >= 0){
      val = mi.c*user.pvec[mi.x_offset];
    }

    /**** COMPUTE r+= d*y (optional) ***/
    if (mi.y_offset>= 0){
      val += mi.d*user.pvec[mi.y_offset]; 
    }

    /***** compute r = (... ) / div */
    if (mi.div_offset >= 0){
      val /= user.pvec[mi.div_offset];
    }
    assert(mi.r_offset>=0 && mi.r_offset < user.pvec.size());
    user.pvec[mi.r_offset] = val;
  } //end update

  /** 
   * calc distance between two items.
   * Let a be all the users rated item 1
   * Let b be all the users rated item 2
   *
   * 3) Using Pearson correlation
   *      Dist_ab = (a - mean)*(b- mean)' / (std(a)*std(b))
   *
   * 4) Using cosine similarity:
   *      Dist_ab = (a*b) / sqrt(sum_sqr(a)) * sqrt(sum_sqr(b)))
   *
   *    5) Using chebychev:
   *          Dist_ab = max(abs(a-b))
   *
   * 6) Using manhatten distance:
   *      Dist_ab = sum(abs(a-b))
   *
   * 7) Using tanimoto:
   *      Dist_ab = 1.0 - [(a*b) / (sum_sqr(a) + sum_sqr(b) - a*b)]
   *
   * 8) Using log likelihood similarity
   *      Dist_ab = 1.0 - 1.0/(1.0 + loglikelihood)
   *
   * 9) Using Jaccard:
   *      Dist_ab = intersect(a,b) / (size(a) + size(b) - intersect(a,b)) 
   */
  double calc_distance(graphchi_vertex<VertexDataType, EdgeDataType> &v, vid_t pivot, int distance_metric) {
    //assert(is_pivot(pivot));
    //assert(is_item(pivot) && is_item(v.id()));
    dense_adj &pivot_edges = adjs[pivot - pivot_st];
    int num_edges = v.num_edges();

    dense_adj item_edges; 
    for(int i=0; i < num_edges; i++){ 
      set_new(item_edges.edges, v.edge(i)->vertexid, v.edge(i)->get_data());
    }

    if (distance_metric == JACCARD_WEIGHT){
      return calc_jaccard_weight_distance(pivot_edges.edges, item_edges.edges, get_val( pivot_edges.edges, v.id()), 0);
    }
    return NAN;  
  }

  /**
   *  compute validaton RMSE for a single user
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
    if (user_nodes && vertex.id() >= M)
      return;
    else if (!user_nodes && vertex.id() < M)
      return;
    vertex_data & vdata = latent_factors_inmem[vertex.id()];
    for(int e=0; e < vertex.num_outedges(); e++) {
      const EdgeDataType & observation = vertex.edge(e)->get_data();
      vertex_data & nbr_latent = latent_factors_inmem[vertex.edge(e)->vertex_id()];
      double prediction;
      double rmse = (*pprediction_func)(vdata, nbr_latent, observation, prediction, NULL);
//      assert(rmse <= pow(maxval - minval, 2));	<ice>
      assert(validation_rmse_vec.size() > omp_get_thread_num());
      validation_rmse_vec[omp_get_thread_num()] += rmse;
    }
  }

	void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
		if(gcontext.iteration == 0){
			if(vertex.num_edges() == 0)	 return;
			VertexDataType vertexdata = vertex.get_data();
			if(!vertexdata.confirmed || !vertexdata.reconfirmed)
				return ;	
			//assert(vertex.num_inedges() * vertex.num_outedges() <= product);
			int ct = 0;		
			for(int i=0; i<vertex.num_edges(); i++){
				graphchi_edge<EdgeDataType>* edge = vertex.edge(i);
				bidirectional_label edgedata = edge->get_data();
				if(edgedata.is_equal()){		
					/*
					if(edgedata.smaller_one != 0)
						std::cout<<edgedata.smaller_one<<" \t"<<edgedata.larger_one<<"\t root="<<root<<std::endl;
					*/
					if(root == edgedata.my_label(vertex.id(), edge->vertexid)){
						ct++;	
					}
				}
				/*
				   lock.lock();
				   fprintf(fpout1, "%u\t%u\n", vertex.id(), vertex.outedge(i)->vertexid);
				   lock.unlock();
				   */
			}
			assert(ct > 1);
		}
	}

    /**
     * Grab pivot's adjacency list into memory.
     */
    int load_edges_into_memory(graphchi_vertex<uint32_t, edge_data> &v) {
      assert(is_pivot(v.id()));
      assert(is_user(v.id()));

      int num_edges = v.num_edges();

      dense_adj dadj;
      for(int i=0; i<num_edges; i++) 
        set_new( dadj.edges, v.edge(i)->vertex_id(), v.edge(i)->get_data().up_weight);
      //dadj.ratings = zeros(N);
      dadj.vid = v.id();
      adjs[v.id() - pivot_st] = dadj;
      assert(v.id() - pivot_st < adjs.size());
      __sync_add_and_fetch(&grabbed_edges, num_edges /*edges_to_larger_id*/);
      return num_edges;
    }

  /**
   *  Vertex update function - computes the least square step
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
    vertex_data & vdata = latent_factors_inmem[vertex.id()];
    if (vertex.num_edges() == 0 || vdata.seed) //no edges, nothing to do here
      return;
    
    vec ret = zeros(D);
    double normalization = 0;
    for(int e=0; e < vertex.num_edges(); e++) {
      edge_data edge = vertex.edge(e)->get_data();                
      vertex_data & nbr_latent = latent_factors_inmem[vertex.edge(e)->vertex_id()];
      ret += edge.cooccurence_count * nbr_latent.pvec;
      normalization += edge.cooccurence_count;
    }

    ret /= normalization;
    vdata.pvec = alpha * vdata.pvec + (1-alpha)*ret;
  }

 /**
   * Grab pivot's adjacency list into memory.
   */
 int grab_adj(graphchi_vertex<uint32_t, uint32_t> &v) {
     if(is_pivot(v.id())) {            
         int ncount = v.num_edges();
         // Count how many neighbors have larger id than v
         v.sort_edges_indirect();
  
         
         int actcount = 0;
         vid_t lastvid = 0;
         for(int i=0; i<ncount; i++) {
             if (v.edge(i)->vertexid > v.id() && v.edge(i)->vertexid != lastvid)  
                 actcount++;  // Need to store only ids larger than me
             lastvid = v.edge(i)->vertex_id();
         }
         
         // Allocate the in-memory adjacency list, using the
         // knowledge of the number of edges.
         dense_adj dadj = dense_adj(actcount, (vid_t*) calloc(sizeof(vid_t), actcount));
         actcount = 0;
         lastvid = 0;
         for(int i=0; i<ncount; i++) {
             if (v.edge(i)->vertexid > v.id() && v.edge(i)->vertexid != lastvid) {  // Need to store only ids larger than me
                 dadj.adjlist[actcount++] = v.edge(i)->vertex_id();
             }
             lastvid = v.edge(i)->vertex_id();
         }
         assert(dadj.count == actcount);
         adjs[v.id() - pivot_st] = dadj;
         assert(v.id() - pivot_st < adjs.size());
         __sync_add_and_fetch(&grabbed_edges, actcount);
         return actcount;
     }
     return 0;
 }

  /**
   *  Vertex update function - computes the least square step
   */
  void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {

    if (gcontext.iteration == 0){
      if (vertex.num_outedges() == 0 && vertex.id() < M)
        logstream(LOG_FATAL)<<"NMF algorithm can not work when the row " << vertex.id() << " of the matrix contains all zeros" << std::endl;
      for(int e=0; e < vertex.num_edges(); e++) {
        float observation = vertex.edge(e)->get_data();                
        if (observation < 0 ){
          logstream(LOG_FATAL)<<"Found a negative entry in matirx row " << vertex.id() << " with value: " << observation << std::endl;
        }
      }
      return;   
    }

    bool isuser = (vertex.id() < M);
    if ((iter % 2 == 1 && !isuser) ||
        (iter % 2 == 0 && isuser))
      return;
    
    vec ret = zeros(D);

    vertex_data & vdata = latent_factors_inmem[vertex.id()];
    
    for(int e=0; e < vertex.num_edges(); e++) {
      float observation = vertex.edge(e)->get_data();                
      vertex_data & nbr_latent = latent_factors_inmem[vertex.edge(e)->vertex_id()];
      double prediction;
      rmse_vec[omp_get_thread_num()] += nmf_predict(vdata, nbr_latent, observation, prediction);
      if (prediction == 0)
        logstream(LOG_FATAL)<<"Got into numerical error! Please submit a bug report." << std::endl;
      ret += nbr_latent.pvec * (observation / prediction);
    }
    
    vec px;
    if (isuser)
      px = sum_of_item_latent_features;
    else 
      px = sum_of_user_latent_feautres;
    for (int i=0; i<D; i++){
      assert(px[i] != 0);
      vdata.pvec[i] *= ret[i] / px[i];
      if (vdata.pvec[i] < epsilon)
        vdata.pvec[i] = epsilon;
    }
  }