C++ CDotFeatures类代码示例

CLatentLabels* CLatentSVM::apply()
{
	if (!m_model)
		SG_ERROR("LatentModel is not set!\n");

	if (!features)
		return NULL;

	index_t num_examples = m_model->get_num_vectors();
	CLatentLabels* hs = new CLatentLabels(num_examples);
	CBinaryLabels* ys = new CBinaryLabels(num_examples);
	hs->set_labels(ys);
	m_model->set_labels(hs);

	for (index_t i = 0; i < num_examples; ++i)
	{
		/* find h for the example */
		CData* h = m_model->infer_latent_variable(w, i);
		hs->add_latent_label(h);
	}

	/* compute the y labels */
	CDotFeatures* x = m_model->get_psi_feature_vectors();
	x->dense_dot_range(ys->get_labels().vector, 0, num_examples, NULL, w.vector, w.vlen, 0.0);

	return hs;
}

void CExactInferenceMethod::update_all()
{
	if (m_labels)
		m_label_vector =
				((CRegressionLabels*) m_labels)->get_labels().clone();

	if (m_features && m_features->has_property(FP_DOT) && m_features->get_num_vectors())
		m_feature_matrix =
				((CDotFeatures*)m_features)->get_computed_dot_feature_matrix();

	else if (m_features && m_features->get_feature_class() == C_COMBINED)
	{
		CDotFeatures* feat =
				(CDotFeatures*)((CCombinedFeatures*)m_features)->
				get_first_feature_obj();

		if (feat->get_num_vectors())
			m_feature_matrix = feat->get_computed_dot_feature_matrix();

		SG_UNREF(feat);
	}

	update_data_means();

	if (m_kernel)
		update_train_kernel();

	if (m_ktrtr.num_cols*m_ktrtr.num_rows)
	{
		update_chol();
		update_alpha();
	}
}

void CExactInferenceMethod::check_members()
{
	if (!m_labels)
		SG_ERROR("No labels set\n")

	if (m_labels->get_label_type() != LT_REGRESSION)
		SG_ERROR("Expected RegressionLabels\n")

	if (!m_features)
		SG_ERROR("No features set!\n")

	if (m_labels->get_num_labels() != m_features->get_num_vectors())
		SG_ERROR("Number of training vectors does not match number of labels\n")

	if(m_features->get_feature_class() == C_COMBINED)
	{
		CDotFeatures* feat =
				(CDotFeatures*)((CCombinedFeatures*)m_features)->
				get_first_feature_obj();

		if (!feat->has_property(FP_DOT))
			SG_ERROR("Specified features are not of type CFeatures\n")

		if (feat->get_feature_class() != C_DENSE)
			SG_ERROR("Expected Simple Features\n")

		if (feat->get_feature_type() != F_DREAL)
			SG_ERROR("Expected Real Features\n")

		SG_UNREF(feat);
	}

void CInferenceMethod::set_latent_features(CFeatures* feat)
{
	SG_REF(feat);
	SG_UNREF(m_latent_features);
	m_latent_features=feat;

	if (m_latent_features && m_latent_features->has_property(FP_DOT) && m_latent_features->get_num_vectors())
		m_latent_matrix =
				((CDotFeatures*)m_latent_features)->get_computed_dot_feature_matrix();

	else if (m_latent_features && m_latent_features->get_feature_class() == C_COMBINED)
	{
		CDotFeatures* subfeat =
				(CDotFeatures*)((CCombinedFeatures*)m_latent_features)->
				get_first_feature_obj();

		if (m_latent_features->get_num_vectors())
			m_latent_matrix = subfeat->get_computed_dot_feature_matrix();

		SG_UNREF(subfeat);
	}

	update_data_means();
	update_train_kernel();
	update_chol();
	update_alpha();
}

CRegressionLabels* CGaussianProcessRegression::apply_regression(CFeatures* data)
{

	if (data)
	{
		if(data->get_feature_class() == C_COMBINED)
		{
			CDotFeatures* feat =
					(CDotFeatures*)((CCombinedFeatures*)data)->
					get_first_feature_obj();

			if (!feat->has_property(FP_DOT))
				SG_ERROR("Specified features are not of type CFeatures\n")

			if (feat->get_feature_class() != C_DENSE)
				SG_ERROR("Expected Simple Features\n")

			if (feat->get_feature_type() != F_DREAL)
				SG_ERROR("Expected Real Features\n")

			SG_UNREF(feat);
		}

		else
		{
			if (!data->has_property(FP_DOT))

CResultSet* CMulticlassModel::argmax(
		SGVector< float64_t > w,
		int32_t feat_idx,
		bool const training)
{
	CDotFeatures* df = (CDotFeatures*) m_features;
	int32_t feats_dim   = df->get_dim_feature_space();

	if ( training )
	{
		CMulticlassSOLabels* ml = (CMulticlassSOLabels*) m_labels;
		m_num_classes = ml->get_num_classes();
	}
	else
	{
		REQUIRE(m_num_classes > 0, "The model needs to be trained before "
				"using it for prediction\n");
	}

	int32_t dim = get_dim();
	ASSERT(dim == w.vlen)

	// Find the class that gives the maximum score

	float64_t score = 0, ypred = 0;
	float64_t max_score = -CMath::INFTY;

	for ( int32_t c = 0 ; c < m_num_classes ; ++c )
	{
		score = df->dense_dot(feat_idx, w.vector+c*feats_dim, feats_dim);
		if ( training )
			score += delta_loss(feat_idx, c);

		if ( score > max_score )
		{
			max_score = score;
			ypred = c;
		}
	}

	// Build the CResultSet object to return
	CResultSet* ret = new CResultSet();
	SG_REF(ret);
	CRealNumber* y  = new CRealNumber(ypred);
	SG_REF(y);

	ret->psi_pred = get_joint_feature_vector(feat_idx, y);
	ret->score    = max_score;
	ret->argmax   = y;
	if ( training )
	{
		ret->delta     = CStructuredModel::delta_loss(feat_idx, y);
		ret->psi_truth = CStructuredModel::get_joint_feature_vector(
					feat_idx, feat_idx);
		ret->score    -= SGVector< float64_t >::dot(w.vector,
					ret->psi_truth.vector, dim);
	}

	return ret;
}

void CCombinedDotFeatures::set_subfeature_weights(
	float64_t* weights, int32_t num_weights)
{
	int32_t i=0 ;
	CListElement* current = NULL ;	
	CDotFeatures* f = get_first_feature_obj(current);

	ASSERT(num_weights==get_num_feature_obj());

	while(f)
	{
		f->set_combined_feature_weight(weights[i]);

		SG_UNREF(f);
		f = get_next_feature_obj(current);
		i++;
	}
}

void CCombinedDotFeatures::get_subfeature_weights(float64_t** weights, int32_t* num_weights)
{
	*num_weights = get_num_feature_obj();
	ASSERT(*num_weights > 0);

	*weights=SG_MALLOC(float64_t, *num_weights);
	float64_t* w = *weights;

	CListElement* current = NULL;
	CDotFeatures* f = get_first_feature_obj(current);

	while (f)
	{
		*w++=f->get_combined_feature_weight();

		SG_UNREF(f);
		f = get_next_feature_obj(current);
	}
}

bool CGaussian::train(CFeatures* data)
{
	// init features with data if necessary and assure type is correct
	if (data)
	{
		if (!data->has_property(FP_DOT))
				SG_ERROR("Specified features are not of type CDotFeatures\n");		
		set_features(data);
	}
	CDotFeatures* dotdata = (CDotFeatures *) data;

	delete[] m_mean;
	delete[] m_cov;

	dotdata->get_mean(&m_mean, &m_mean_length);
	dotdata->get_cov(&m_cov, &m_cov_rows, &m_cov_cols);

	init();

	return true;
}

bool CGMM::train(CFeatures* data)
{
	ASSERT(m_n != 0);
	if (m_components)
		cleanup();

	/** init features with data if necessary and assure type is correct */
	if (data)
	{
		if (!data->has_property(FP_DOT))
				SG_ERROR("Specified features are not of type CDotFeatures\n");		
		set_features(data);
	}

	CDotFeatures* dotdata = (CDotFeatures *) data;
	int32_t num_vectors = dotdata->get_num_vectors();
	int32_t num_dim = dotdata->get_dim_feature_space();

	CEuclidianDistance* dist = new CEuclidianDistance();
	CKMeans* init_k_means = new CKMeans(m_n, dist);
	init_k_means->train(dotdata);
	float64_t* init_means;
	int32_t init_mean_dim;
	int32_t init_mean_size;
	init_k_means->get_cluster_centers(&init_means, &init_mean_dim, &init_mean_size);

	float64_t* init_cov;
	int32_t init_cov_rows;
	int32_t init_cov_cols;
	dotdata->get_cov(&init_cov, &init_cov_rows, &init_cov_cols);

	m_coefficients = new float64_t[m_coef_size];
	m_components = new CGaussian*[m_n];

	for (int i=0; i<m_n; i++)
	{
		m_coefficients[i] = 1.0/m_coef_size;
		m_components[i] = new CGaussian(&(init_means[i*init_mean_dim]), init_mean_dim,
								init_cov, init_cov_rows, init_cov_cols);
	}

	/** question of faster vs. less memory using */
	float64_t* pdfs = new float64_t[num_vectors*m_n];
	float64_t* T = new float64_t[num_vectors*m_n];
	int32_t iter = 0;
	float64_t e_log_likelihood_change = m_minimal_change + 1;
	float64_t e_log_likelihood_old = 0;
	float64_t e_log_likelihood_new = -FLT_MAX;

	while (iter<m_max_iter && e_log_likelihood_change>m_minimal_change)
	{
		e_log_likelihood_old = e_log_likelihood_new;
		e_log_likelihood_new = 0;

		/** Precomputing likelihoods */
		float64_t* point;
		int32_t point_len;

		for (int i=0; i<num_vectors; i++)
		{
			dotdata->get_feature_vector(&point, &point_len, i);
			for (int j=0; j<m_n; j++)
				pdfs[i*m_n+j] = m_components[j]->compute_PDF(point, point_len);
			delete[] point;
		}

		for (int i=0; i<num_vectors; i++)
		{
			float64_t sum = 0;

			for (int j=0; j<m_n; j++)
				sum += m_coefficients[j]*pdfs[i*m_n+j];

			for (int j=0; j<m_n; j++)
			{
				T[i*m_n+j] = (m_coefficients[j]*pdfs[i*m_n+j])/sum;
				e_log_likelihood_new += T[i*m_n+j]*CMath::log(m_coefficients[j]*pdfs[i*m_n+j]);
			}
		}

		/** Not sure if getting the abs value is a good idea */
		e_log_likelihood_change = CMath::abs(e_log_likelihood_new - e_log_likelihood_old);

		/** Updates */
		float64_t T_sum;
		float64_t* mean_sum;
		float64_t* cov_sum;

		for (int i=0; i<m_n; i++)
		{
			T_sum = 0;
			mean_sum = new float64_t[num_dim];
			memset(mean_sum, 0, num_dim*sizeof(float64_t));

			for (int j=0; j<num_vectors; j++)
			{
				T_sum += T[j*m_n+i];
				dotdata->get_feature_vector(&point, &point_len, j);
				CMath::add<float64_t>(mean_sum, T[j*m_n+i], point, 1, mean_sum, point_len);
				delete[] point;
//.........这里部分代码省略.........

void CLibLinear::solve_l1r_lr(
    const problem *prob_col, double eps,
    double Cp, double Cn)
{
    int l = prob_col->l;
    int w_size = prob_col->n;
    int j, s, iter = 0;
    int active_size = w_size;
    int max_num_linesearch = 20;

    double x_min = 0;
    double sigma = 0.01;
    double d, G, H;
    double Gmax_old = CMath::INFTY;
    double Gmax_new;
    double Gmax_init=0;
    double sum1, appxcond1;
    double sum2, appxcond2;
    double cond;

    int *index = SG_MALLOC(int, w_size);
    int32_t *y = SG_MALLOC(int32_t, l);
    double *exp_wTx = SG_MALLOC(double, l);
    double *exp_wTx_new = SG_MALLOC(double, l);
    double *xj_max = SG_MALLOC(double, w_size);
    double *C_sum = SG_MALLOC(double, w_size);
    double *xjneg_sum = SG_MALLOC(double, w_size);
    double *xjpos_sum = SG_MALLOC(double, w_size);

    CDotFeatures* x = prob_col->x;
    void* iterator;
    int ind;
    double val;

    double C[3] = {Cn,0,Cp};

    int n = prob_col->n;
    if (prob_col->use_bias)
        n--;

    for(j=0; j<l; j++)
    {
        exp_wTx[j] = 1;
        if(prob_col->y[j] > 0)
            y[j] = 1;
        else
            y[j] = -1;
    }
    for(j=0; j<w_size; j++)
    {
        w.vector[j] = 0;
        index[j] = j;
        xj_max[j] = 0;
        C_sum[j] = 0;
        xjneg_sum[j] = 0;
        xjpos_sum[j] = 0;

        if (use_bias && j==n)
        {
            for (ind=0; ind<l; ind++)
            {
                x_min = CMath::min(x_min, 1.0);
                xj_max[j] = CMath::max(xj_max[j], 1.0);
                C_sum[j] += C[GETI(ind)];
                if(y[ind] == -1)
                    xjneg_sum[j] += C[GETI(ind)];
                else
                    xjpos_sum[j] += C[GETI(ind)];
            }
        }
        else
        {
            iterator=x->get_feature_iterator(j);
            while (x->get_next_feature(ind, val, iterator))
            {
                x_min = CMath::min(x_min, val);
                xj_max[j] = CMath::max(xj_max[j], val);
                C_sum[j] += C[GETI(ind)];
                if(y[ind] == -1)
                    xjneg_sum[j] += C[GETI(ind)]*val;
                else
                    xjpos_sum[j] += C[GETI(ind)]*val;
            }
            x->free_feature_iterator(iterator);
        }
    }

    CTime start_time;
    while (iter < max_iterations && !CSignal::cancel_computations())
    {
        if (m_max_train_time > 0 && start_time.cur_time_diff() > m_max_train_time)
            break;

        Gmax_new = 0;

        for(j=0; j<active_size; j++)
        {
            int i = j+rand()%(active_size-j);
            CMath::swap(index[i], index[j]);
        }
//.........这里部分代码省略.........

/*----------------------------------------------------------------------------------
  sparse_add_new_cut( new_col_H, new_cut, cut_length, nSel ) does the following:

    new_a = sum(data_X(:,find(new_cut ~=0 )),2);
    new_col_H = [sparse_A(:,1:nSel)'*new_a ; new_a'*new_a];
    sparse_A(:,nSel+1) = new_a;

  ---------------------------------------------------------------------------------*/
int CSVMOcas::add_new_cut(
	float64_t *new_col_H, uint32_t *new_cut, uint32_t cut_length,
	uint32_t nSel, void* ptr)
{
	CSVMOcas* o = (CSVMOcas*) ptr;
	CDotFeatures* f = o->features;
	uint32_t nDim=(uint32_t) o->w_dim;
	float64_t* y = o->lab.vector;

	float64_t** c_val = o->cp_value;
	uint32_t** c_idx = o->cp_index;
	uint32_t* c_nzd = o->cp_nz_dims;
	float64_t* c_bias = o->cp_bias;

	float64_t sq_norm_a;
	uint32_t i, j, nz_dims;

	/* temporary vector */
	float64_t* new_a = o->tmp_a_buf;
	memset(new_a, 0, sizeof(float64_t)*nDim);

	for(i=0; i < cut_length; i++)
	{
		f->add_to_dense_vec(y[new_cut[i]], new_cut[i], new_a, nDim);

		if (o->use_bias)
			c_bias[nSel]+=y[new_cut[i]];
	}

	/* compute new_a'*new_a and count number of non-zerou dimensions */
	nz_dims = 0;
	sq_norm_a = CMath::sq(c_bias[nSel]);
	for(j=0; j < nDim; j++ ) {
		if(new_a[j] != 0) {
			nz_dims++;
			sq_norm_a += new_a[j]*new_a[j];
		}
	}

	/* sparsify new_a and insert it to the last column of sparse_A */
	c_nzd[nSel] = nz_dims;
	c_idx[nSel]=NULL;
	c_val[nSel]=NULL;

	if(nz_dims > 0)
	{
		c_idx[nSel]=SG_MALLOC(uint32_t, nz_dims);
		c_val[nSel]=SG_MALLOC(float64_t, nz_dims);

		uint32_t idx=0;
		for(j=0; j < nDim; j++ )
		{
			if(new_a[j] != 0)
			{
				c_idx[nSel][idx] = j;
				c_val[nSel][idx++] = new_a[j];
			}
		}
	}

	new_col_H[nSel] = sq_norm_a;

	for(i=0; i < nSel; i++)
	{
		float64_t tmp = c_bias[nSel]*c_bias[i];
		for(j=0; j < c_nzd[i]; j++)
			tmp += new_a[c_idx[i][j]]*c_val[i][j];

		new_col_H[i] = tmp;
	}
	//CMath::display_vector(new_col_H, nSel+1, "new_col_H");
	//CMath::display_vector((int32_t*) c_idx[nSel], (int32_t) nz_dims, "c_idx");
	//CMath::display_vector((float64_t*) c_val[nSel], nz_dims, "c_val");
	return 0;
}