static void __fscanf_and_set( matrix_type * matrix , int row , int col , FILE * stream) { double value; if (fscanf(stream , "%lg" , &value) == 1) matrix_iset( matrix , row , col , value ); else util_abort("%s: reading of matrix failed at row:%d col:%d \n",__func__ , row , col); }
void test_diag_std() { const int N = 25; double_vector_type * data = double_vector_alloc( 0,0); rng_type * rng = rng_alloc(MZRAN , INIT_DEV_URANDOM ); matrix_type * m = matrix_alloc( N , N ); double sum1 = 0; double sum2 = 0; int i; for (i=0; i < N; i++) { double R = rng_get_double( rng ); matrix_iset(m , i , i , R); double_vector_iset( data , i , R ); sum1 += R; sum2 += R*R; } { double mean = sum1 / N; double std = sqrt( sum2 / N - mean * mean ); test_assert_double_equal( std , matrix_diag_std( m , mean )); test_assert_double_equal( statistics_std( data ) , matrix_diag_std( m , mean )); test_assert_double_equal( statistics_mean( data ) , mean ); } matrix_free( m ); rng_free( rng ); }
void matrix_subtract_and_store_row_mean(matrix_type * matrix, matrix_type * row_mean) { int i; for ( i=0; i < matrix->rows; i++) { double mean = matrix_get_row_sum(matrix , i) / matrix->columns; matrix_shift_row( matrix , i , -mean); matrix_iset(row_mean , i , 0, mean ); } }
int main( int argc, char ** argv) { rng_type * rng = rng_alloc( MZRAN , INIT_DEV_RANDOM ); matrix_type * A = matrix_alloc( 12 , 12 ); matrix_type * B = matrix_alloc( 12 , 12 ); matrix_random_init( A , rng ); matrix_assign( B , A ); matrix_pretty_print( A , " A " , "%8.4f" ); #ifdef WITH_LAPACK matrix_inv( B ); printf("\n"); matrix_pretty_print( B , "inv(A)" , "%8.4f" ); matrix_inplace_matmul( B , A ); printf("\n"); matrix_pretty_print( B , " I " , "%8.4f" ); { matrix_type * A3 = matrix_alloc(3,3); matrix_random_init( A3 , rng ); matrix_iset( A3 , 0 , 0 , sin(0.98)); printf("matrix_det3:%g ",matrix_det3( A3 )); printf("matrix_det:%g \n",matrix_det( A3 )); } { matrix_type * A4 = matrix_alloc(4,4); matrix_random_init( A4 , rng ); matrix_iset( A4 , 0 , 0 , sin(0.98)); printf("matrix_det4:%g ",matrix_det4( A4 )); printf("matrix_det:%g \n",matrix_det( A4 )); } #endif matrix_free( A ); matrix_free( B ); rng_free( rng ); }
void matrix_set(matrix_type * matrix, double value) { int i,j; for (j=0; j < matrix->columns; j++) for (i=0; i < matrix->rows; i++) matrix_iset(matrix , i , j , value); }
void matrix_iset_safe(matrix_type * matrix , int i , int j, double value) { matrix_assert_ij( matrix , i , j ); matrix_iset( matrix , i , j , value ); }
void stepwise_isetY0( stepwise_type * stepwise , int i , double value ) { matrix_iset( stepwise->Y0, i , 0 , value ); }
static double stepwise_estimate__( stepwise_type * stepwise , bool_vector_type * active_rows) { matrix_type * X; matrix_type * E; matrix_type * Y; double y_mean = 0; int nvar = matrix_get_columns( stepwise->X0 ); int nsample = matrix_get_rows( stepwise->X0 ); nsample = bool_vector_count_equal( active_rows , true ); nvar = bool_vector_count_equal( stepwise->active_set , true ); matrix_set( stepwise->beta , 0 ); // It is essential to make sure that old finite values in the beta0 vector do not hang around. /* Extracting the data used for regression, and storing them in the temporary local matrices X and Y. Selecting data is based both on which varibles are active (stepwise->active_set) and which rows should be used for regression, versus which should be used for validation (@active_rows). */ if ((nsample < matrix_get_rows( stepwise->X0 )) || (nvar < matrix_get_columns( stepwise->X0 ))) { X = matrix_alloc( nsample , nvar ); E = matrix_alloc( nsample , nvar ); Y = matrix_alloc( nsample , 1); { int icol,irow; // Running over all values. int arow,acol; // Running over active values. arow = 0; for (irow = 0; irow < matrix_get_rows( stepwise->X0 ); irow++) { if (bool_vector_iget( active_rows , irow )) { acol = 0; for (icol = 0; icol < matrix_get_columns( stepwise->X0 ); icol++) { if (bool_vector_iget( stepwise->active_set , icol )) { matrix_iset( X , arow , acol , matrix_iget( stepwise->X0 , irow , icol )); matrix_iset( E , arow , acol , matrix_iget( stepwise->E0 , irow , icol )); acol++; } } matrix_iset( Y , arow , 0 , matrix_iget( stepwise->Y0 , irow , 0 )); arow++; } } } } else { X = matrix_alloc_copy( stepwise->X0 ); E = matrix_alloc_copy( stepwise->E0 ); Y = matrix_alloc_copy( stepwise->Y0 ); } { if (stepwise->X_mean != NULL) matrix_free( stepwise->X_mean); stepwise->X_mean = matrix_alloc( 1 , nvar ); if (stepwise->X_norm != NULL) matrix_free( stepwise->X_norm); stepwise->X_norm = matrix_alloc( 1 , nvar ); matrix_type * beta = matrix_alloc( nvar , 1); /* This is the beta vector as estimated from the OLS estimator. */ regression_augmented_OLS( X , Y , E, beta ); /* In this code block the beta/tmp_beta vector which is dense with fewer elements than the full model is scattered into the beta0 vector which has full size and @nvar elements. */ { int ivar,avar; avar = 0; for (ivar = 0; ivar < matrix_get_columns( stepwise->X0 ); ivar++) { if (bool_vector_iget( stepwise->active_set , ivar )) { matrix_iset( stepwise->beta , ivar , 0 , matrix_iget( beta , avar , 0)); avar++; } } } matrix_free( beta ); } matrix_free( X ); matrix_free( E ); matrix_free( Y ); return y_mean; }
void stepwise_estimate( stepwise_type * stepwise , double deltaR2_limit , int CV_blocks) { int nvar = matrix_get_columns( stepwise->X0 ); int nsample = matrix_get_rows( stepwise->X0 ); double currentR2 = -1; bool_vector_type * active_rows = bool_vector_alloc( nsample , true ); /*Reset beta*/ for (int i = 0; i < nvar; i++) { matrix_iset(stepwise->beta, i , 0 , 0.0); } bool_vector_set_all( stepwise->active_set , false ); double MSE_min = 10000000; double Prev_MSE_min = MSE_min; double minR2 = -1; while (true) { int best_var = 0; Prev_MSE_min = MSE_min; /* Go through all the inactive variables, and calculate the resulting prediction error IF this particular variable is added; keep track of the variable which gives the lowest prediction error. */ for (int ivar = 0; ivar < nvar; ivar++) { if (!bool_vector_iget( stepwise->active_set , ivar)) { double newR2 = stepwise_test_var(stepwise , ivar , CV_blocks); if ((minR2 < 0) || (newR2 < minR2)) { minR2 = newR2; best_var = ivar; } } } /* If the best relative improvement in prediction error is better than @deltaR2_limit, the corresponding variable is added to the active set, and we return to repeat the loop one more time. Otherwise we just exit. */ { MSE_min = minR2; double deltaR2 = MSE_min / Prev_MSE_min; if (( currentR2 < 0) || deltaR2 < deltaR2_limit) { bool_vector_iset( stepwise->active_set , best_var , true ); currentR2 = minR2; bool_vector_set_all(active_rows, true); stepwise_estimate__( stepwise , active_rows ); } else { /* The gain in prediction error is so small that we just leave the building. */ /* NB! Need one final compuation of beta (since the test_var function does not reset the last tested beta value !) */ bool_vector_set_all(active_rows, true); stepwise_estimate__( stepwise , active_rows ); break; } if (bool_vector_count_equal( stepwise->active_set , true) == matrix_get_columns( stepwise->X0 )) { stepwise_estimate__( stepwise , active_rows ); break; /* All variables are active. */ } } } stepwise_set_R2(stepwise, currentR2); bool_vector_free( active_rows ); }
void lars_isetX( lars_type * lars, int sample, int var , double value) { matrix_iset( lars->X , sample , var , value ); }
void lars_estimate(lars_type * lars , int max_vars , double max_beta , bool verbose) { int nvars = matrix_get_columns( lars->X ); int nsample = matrix_get_rows( lars->X ); matrix_type * X = matrix_alloc( nsample, nvars ); // Allocate local X and Y variables matrix_type * Y = matrix_alloc( nsample, 1 ); // which will hold the normalized data lars_estimate_init( lars , X , Y); // during the estimation process. { matrix_type * G = matrix_alloc_gram( X , true ); matrix_type * mu = matrix_alloc( nsample , 1 ); matrix_type * C = matrix_alloc( nvars , 1 ); matrix_type * Y_mu = matrix_alloc_copy( Y ); int_vector_type * active_set = int_vector_alloc(0,0); int_vector_type * inactive_set = int_vector_alloc(0,0); int active_size; if ((max_vars <= 0) || (max_vars > nvars)) max_vars = nvars; { int i; for (i=0; i < nvars; i++) int_vector_iset( inactive_set , i , i ); } matrix_set( mu , 0 ); while (true) { double maxC = 0; /* The first step is to calculate the correlations between the covariates, and the current residual. All the currently inactive covariates are searched; the covariate with the greatest correlation with (Y - mu) is selected and added to the active set. */ matrix_sub( Y_mu , Y , mu ); // Y_mu = Y - mu matrix_dgemm( C , X , Y_mu , true , false , 1.0 , 0); // C = X' * Y_mu { int i; int max_set_index = 0; for (i=0; i < int_vector_size( inactive_set ); i++) { int set_index = i; int var_index = int_vector_iget( inactive_set , set_index ); double value = fabs( matrix_iget(C , var_index , 0) ); if (value > maxC) { maxC = value; max_set_index = set_index; } } /* Remove element corresponding to max_set_index from the inactive set and add it to the active set: */ int_vector_append( active_set , int_vector_idel( inactive_set , max_set_index )); } active_size = int_vector_size( active_set ); /* Now we have calculated the correlations between all the covariates and the current residual @Y_mu. The correlations are stored in the matrix @C. The value of the maximum correlation is stored in @maxC. Based on the value of @maxC we have added one new covariate to the model, technically by moving the index from @inactive_set to @active_set. */ /*****************************************************************/ { matrix_type * weights = matrix_alloc( active_size , 1); double scale; /*****************************************************************/ /* This scope should compute and initialize the variables @weights and @scale. */ { matrix_type * subG = matrix_alloc( active_size , active_size ); matrix_type * STS = matrix_alloc( active_size , active_size ); matrix_type * sign_vector = matrix_alloc( active_size , 1); int i , j; /* STS = S' o S where 'o' is the Schur product and S is given by: [ s1 s2 s3 s4 ] S = [ s1 s2 s3 s4 ] [ s1 s2 s3 s4 ] [ s1 s2 s3 s4 ] Where si is the sign of the correlation between (active) variable 'i' and Y_mu. */ for (i=0; i < active_size ; i++) { int vari = int_vector_iget( active_set , i ); double signi = sgn( matrix_iget( C , vari , 0)); matrix_iset( sign_vector , i , 0 , signi ); for (j=0; j < active_size; j++) { int varj = int_vector_iget( active_set , j ); double signj = sgn( matrix_iget( C , varj , 0)); matrix_iset( STS , i , j , signi * signj ); } } // Extract the elements from G corresponding to active indices and // copy to the matrix subG: for (i=0; i < active_size ; i++) { int ii = int_vector_iget( active_set , i ); for (j=0; j < active_size; j++) { int jj = int_vector_iget( active_set , j ); matrix_iset( subG , i , j , matrix_iget(G , ii , jj)); } } // Weights matrix_inplace_mul( subG , STS ); matrix_inv( subG ); { matrix_type * ones = matrix_alloc( active_size , 1 ); matrix_type * GA1 = matrix_alloc( active_size , 1 ); matrix_set( ones , 1.0 ); matrix_matmul( GA1 , subG , ones ); scale = 1.0 / sqrt( matrix_get_column_sum( GA1 , 0 )); matrix_mul( weights , GA1 , sign_vector ); matrix_scale( weights , scale ); matrix_free( GA1 ); matrix_free( ones ); } matrix_free( sign_vector ); matrix_free( subG ); matrix_free( STS ); } /******************************************************************/ /* The variables weight and scale have been calculated, proceed to calculate the step length @gamma. */ { int i; double gamma; { matrix_type * u = matrix_alloc( nsample , 1 ); int j; for (i=0; i < nsample; i++) { double row_sum = 0; for (j =0; j < active_size; j++) row_sum += matrix_iget( X , i , int_vector_iget( active_set , j)) * matrix_iget(weights , j , 0 ); matrix_iset( u , i , 0 , row_sum ); } gamma = maxC / scale; if (active_size < matrix_get_columns( X )) { matrix_type * equi_corr = matrix_alloc( nvars , 1 ); matrix_dgemm( equi_corr , X , u , true , false , 1.0 , 0); // equi_corr = X'·u for (i=0; i < (nvars - active_size); i++) { int var_index = int_vector_iget( inactive_set , i ); double gamma1 = (maxC - matrix_iget(C , var_index , 0 )) / ( scale - matrix_iget( equi_corr , var_index , 0)); double gamma2 = (maxC + matrix_iget(C , var_index , 0 )) / ( scale + matrix_iget( equi_corr , var_index , 0)); if ((gamma1 > 0) && (gamma1 < gamma)) gamma = gamma1; if ((gamma2 > 0) && (gamma2 < gamma)) gamma = gamma2; } matrix_free( equi_corr ); } /* Update the current estimated 'location' mu. */ matrix_scale( u , gamma ); matrix_inplace_add( mu , u ); matrix_free( u ); } /* We have calculated the step length @gamma, and the @weights. Update the @beta matrix. */ for (i=0; i < active_size; i++) matrix_iset( lars->beta , int_vector_iget( active_set , i ) , active_size - 1 , gamma * matrix_iget( weights , i , 0)); if (active_size > 1) for (i=0; i < nvars; i++) matrix_iadd( lars->beta , i , active_size - 1 , matrix_iget( lars->beta , i , active_size - 2)); matrix_free( weights ); } } if (active_size == max_vars) break; if (max_beta > 0) { double beta_norm2 = matrix_get_column_abssum( lars->beta , active_size - 1 ); if (beta_norm2 > max_beta) { // We stop - we will use an interpolation between this beta estimate and // the previous, to ensure that the |beta| = max_beta criteria is satisfied. if (active_size >= 2) { double beta_norm1 = matrix_get_column_abssum( lars->beta , active_size - 2 ); double s = (max_beta - beta_norm1)/(beta_norm2 - beta_norm1); { int j; for (j=0; j < nvars; j++) { double beta1 = matrix_iget( lars->beta , j , active_size - 2 ); double beta2 = matrix_iget( lars->beta , j , active_size - 1 ); matrix_iset( lars->beta , j , active_size - 1 , beta1 + s*(beta2 - beta1)); } } } break; } } } matrix_free( G ); matrix_free( mu ); matrix_free( C ); matrix_free( Y_mu ); int_vector_free( active_set ); int_vector_free( inactive_set ); matrix_resize( lars->beta , nvars , active_size , true ); if (verbose) matrix_pretty_fprint( lars->beta , "beta" , "%12.5f" , stdout ); lars_select_beta( lars , active_size - 1); } matrix_free( X ); matrix_free( Y ); }
void lars_isetY( lars_type * lars, int sample, double value) { matrix_iset( lars->Y , sample , 0 , value ); }