Example 2 of Running Collocation Topic Model (LDACOL)

How to save multiple samples from the same or different chains in the LDACOL model

Load a dataset

dataset = 1; % 1 = psych review; 2 = nips

if (dataset == 1)
    fprintf( 'Loading Psych Review Abstracts - Collocation Data\n' );
    load 'psychreviewcollocation'; % load in variables: WW WO DS WS SI
elseif (dataset == 2 )
    fprintf( 'Loading NIPS papers - Collocation Data\n' );
    load 'nipscollocation'; % load in variables: WW WO DS WS SI
end

Loading Psych Review Abstracts - Collocation Data

The number of topics

T = 50;

What output to show (0=no output; 1=iterations; 2=all output)

OUTPUT = 1;

Set the hyperparameters of the model

BETA   = 0.01;
ALPHA  = 50/T;
GAMMA0 = 0.1;
GAMMA1 = 0.1;
DELTA  = 0.1;

The number of iterations

BURNIN   = 100; % the number of iterations before taking samples
LAG      = 10; % the lag between samples
NSAMPLES = 2; % the number of samples for each chain
NCHAINS  = 2; % the number of chains to run

The starting seed number

SEED = 1;

for c=1:NCHAINS
    SEED = SEED + 1;
    N = BURNIN;
    fprintf( 'Running Gibbs sampler for burnin\n' );
    [ WP,DP,WC,C,Z ] = GibbsSamplerLDACOL( WS , DS , SI , WW , T , N , ALPHA , BETA , GAMMA0, GAMMA1 , DELTA , SEED , OUTPUT  );

    fprintf( 'Continue to run sampler to collect samples\n' );
    for s=1:NSAMPLES
        filename = sprintf( 'ldacol_chain%d_sample%d' , c , s );
        fprintf( 'Saving sample #%d from chain #%d: filename=%s\n' , s , c , filename );
        comm = sprintf( 'save ''%s'' WP DP WC C ALPHA BETA GAMMA0 GAMMA1 DELTA SEED N Z T s c' , filename );
        eval( comm );

        if (s < NSAMPLES)
           N = LAG;
           SEED = SEED + 1; % important -- change the seed between samples !!
           [ WP,DP,WC,C,Z ] = GibbsSamplerLDACOL( WS , DS , SI , WW , T , N , ALPHA , BETA , GAMMA0, GAMMA1 , DELTA , SEED , OUTPUT , C , Z );
        end
    end
end

Running Gibbs sampler for burnin
	Iteration 0 of 100;   Number of tokens in collocation = 0
	Iteration 10 of 100;   Number of tokens in collocation = 5476
	Iteration 20 of 100;   Number of tokens in collocation = 6720
	Iteration 30 of 100;   Number of tokens in collocation = 7204
	Iteration 40 of 100;   Number of tokens in collocation = 7502
	Iteration 50 of 100;   Number of tokens in collocation = 7457
	Iteration 60 of 100;   Number of tokens in collocation = 7508
	Iteration 70 of 100;   Number of tokens in collocation = 7511
	Iteration 80 of 100;   Number of tokens in collocation = 7453
	Iteration 90 of 100;   Number of tokens in collocation = 7474
Continue to run sampler to collect samples
Saving sample #1 from chain #1: filename=ldacol_chain1_sample1
	Iteration 0 of 10;   Number of tokens in collocation = 7602
Saving sample #2 from chain #1: filename=ldacol_chain1_sample2
Running Gibbs sampler for burnin
	Iteration 0 of 100;   Number of tokens in collocation = 0
	Iteration 10 of 100;   Number of tokens in collocation = 5155
	Iteration 20 of 100;   Number of tokens in collocation = 6561
	Iteration 30 of 100;   Number of tokens in collocation = 7082
	Iteration 40 of 100;   Number of tokens in collocation = 7400
	Iteration 50 of 100;   Number of tokens in collocation = 7595
	Iteration 60 of 100;   Number of tokens in collocation = 7491
	Iteration 70 of 100;   Number of tokens in collocation = 7492
	Iteration 80 of 100;   Number of tokens in collocation = 7516
	Iteration 90 of 100;   Number of tokens in collocation = 7543
Continue to run sampler to collect samples
Saving sample #1 from chain #2: filename=ldacol_chain2_sample1
	Iteration 0 of 10;   Number of tokens in collocation = 7641
Saving sample #2 from chain #2: filename=ldacol_chain2_sample2

Published with MATLAB® 7.0.4