int main(){
gsl_rng *r = apop_rng_alloc(2468);
double binom_start = 0.6;
double beta_start_a = 0.3;
double beta_start_b = 0.5;
int i, draws = 1500;
double n = 4000;
//First, the easy estimation using the conjugate distribution table.
apop_model *bin = apop_model_set_parameters(apop_binomial, n, binom_start);
apop_model *beta = apop_model_set_parameters(apop_beta, beta_start_a, beta_start_b);
apop_model *updated = apop_update(.prior= beta, .likelihood=bin,.rng=r);
//Now estimate via Gibbs sampling.
//Requires a one-parameter binomial, with n fixed,
//and a data set of n data points with the right p.
apop_model *bcopy = apop_model_set_parameters(apop_binomial, n, GSL_NAN);
apop_data *bin_draws = apop_data_fill(apop_data_alloc(1,2), n*(1-binom_start), n*binom_start);
bin = apop_model_fix_params(bcopy);
apop_model_add_group(beta, apop_update, .burnin=.1, .periods=1e4);
apop_model *out_h = apop_update(bin_draws, beta, bin, NULL);
//We now have a histogram of values for p. What's the closest beta
//distribution?
apop_data *d = apop_data_alloc(0, draws, 1);
for(i=0; i < draws; i ++)
apop_draw(apop_data_ptr(d, i, 0), r, out_h);
apop_model *out_beta = apop_estimate(d, apop_beta);
//Finally, we can compare the conjugate and Gibbs results:
apop_vector_normalize(updated->parameters->vector);
apop_vector_normalize(out_beta->parameters->vector);
double error = apop_vector_distance(updated->parameters->vector, out_beta->parameters->vector, .metric='m');
double updated_size = apop_vector_sum(updated->parameters->vector);
Apop_assert(error/updated_size < 0.01, "The error is %g, which is too big.", error/updated_size);
}
int main(){
apop_data *d = apop_text_alloc(apop_data_alloc(6), 6, 1);
apop_data_fill(d, 1, 2, 3, 3, 1, 2);
apop_text_fill(d, "A", "A", "A", "A", "A", "B");
asprintf(&d->names->title, "Original data set");
printdata(d);
//binned, where bin ends are equidistant but not necessarily in the data
apop_data *binned = apop_data_to_bins(d, NULL);
asprintf(&binned->names->title, "Post binning");
printdata(binned);
assert(apop_sum(binned->weights)==6);
assert(fabs(//equal distance between bins
(apop_data_get(binned, 1, -1) - apop_data_get(binned, 0, -1))
- (apop_data_get(binned, 2, -1) - apop_data_get(binned, 1, -1))) < 1e-5);
//compressed, where the data is as in the original, but weights
//are redome to accommodate repeated observations.
apop_data_pmf_compress(d);
asprintf(&d->names->title, "Post compression");
printdata(d);
assert(apop_sum(d->weights)==6);
apop_model *d_as_pmf = apop_estimate(d, apop_pmf);
Apop_row(d, 0, firstrow); //1A
assert(fabs(apop_p(firstrow, d_as_pmf) - 2./6 < 1e-5));
}
int main(){
gsl_rng *r = apop_rng_alloc(10);
size_t i, ct = 5e4;
//set up the model & params
apop_data *d = apop_data_alloc(ct,2);
apop_data *params = apop_data_alloc(2,2,2);
apop_data_fill(params, 8, 1, 0.5,
2, 0.5, 1);
apop_model *pvm = apop_model_copy(apop_multivariate_normal);
pvm->parameters = apop_data_copy(params);
//make random draws from the multivar. normal
//this `pull a row view, fill its data element' form works for rows but not cols.
for(i=0; i< ct; i++){
Apop_row(d, i, onerow);
apop_draw(onerow->data, r, pvm);
}
//set up and estimate a model with fixed covariance matrix but free means
gsl_vector_set_all(pvm->parameters->vector, GSL_NAN);
apop_model *mep1 = apop_model_fix_params(pvm);
apop_model *e1 = apop_estimate(d, *mep1);
//compare results
printf("original params: ");
apop_vector_show(params->vector);
printf("estimated params: ");
apop_vector_show(e1->parameters->vector);
}