static apop_data *colmeans(apop_data *in){
Get_vmsizes(in); //maxsize
apop_data *sums = apop_data_summarize(in);
Apop_col_tv(sums, "mean", means);
apop_data *out = apop_matrix_to_data(apop_vector_to_matrix(means, 'r'));
apop_name_stack(out->names, in->names, 'c', 'c');
apop_data *cov = apop_data_add_page(out, apop_data_covariance(in), "<Covariance>");
gsl_matrix_scale(cov->matrix, 1/sqrt(maxsize));
return out;
}
/* This sample produces a dummy times table, gets a summary, and prunes the summary table.
If you are not a test script, uncomment the last line to display the pruned table. */
void test_prune_cols(){
int i, j;
apop_data *d = apop_data_alloc(0, 10, 4);
for (i=0; i< 10; i++)
for (j=0; j< 4; j++)
apop_data_set(d, i, j, i*j);
apop_data *summary = apop_data_summarize(d);
apop_data_prune_columns(summary, "mean", "median");
assert(apop_name_find(summary->names, "mean", 'c')!=-2);
assert(apop_name_find(summary->names, "median", 'c')!=-2);
assert(apop_name_find(summary->names, "max", 'c')==-2); //not found
assert(apop_name_find(summary->names, "variance", 'c')==-2); //not found
assert(apop_data_get(summary, .row=0, .colname="mean")==0);
assert(apop_data_get(summary, .row=1, .colname="median")==4);
assert(apop_data_get(summary, .row=2, .colname="median")==8);
//apop_data_show(summary);
}
//We need to estimate the df via MLE.
//However, the right value of the wishart covariance grid is CM/df.
//So, for a value of df that we're trying, scale CM appropriately.
gsl_matrix_scale(m->parameters->matrix, 1./m->parameters->vector->data[0]);
double out = wishart_ll(in, m);
gsl_matrix_scale(m->parameters->matrix, m->parameters->vector->data[0]);
return out;
}
static void wishart_estimate(apop_data *d, apop_model *m){
Nullcheck_m(m, );
//apop_data_set(m->parameters, 0, -1, d->matrix->size1);
//Start with cov matrix via mean of inputs; df=NaN
apop_data_set(m->parameters, 0, -1, GSL_NAN);
apop_data *summ=apop_data_summarize(d);
Apop_col_t(summ, "mean", means);
gsl_vector *t = m->parameters->vector; //mask this while unpacking
m->parameters->vector=NULL;
apop_data_unpack(means, m->parameters);
m->parameters->vector=t;
//Estimate a model with fixed cov matrix and blank (NaN) df.
apop_model *modified_wish = apop_model_copy(m);
modified_wish->log_likelihood = fixed_wishart_ll;
apop_model *fixed_wish = apop_model_fix_params(modified_wish);
apop_model *est_via_fix = apop_estimate(d, fixed_wish);
//copy df from fixed version to the real thing; clean up.
t->data[0] = apop_data_get(est_via_fix->parameters, 0, -1);
gsl_matrix_scale(m->parameters->matrix, 1./t->data[0]);
