apop_data * apop_bootstrap_cov_base(apop_data * data, apop_model *model, gsl_rng *rng, int iterations, char keep_boots, char ignore_nans, apop_data **boot_store){
#endif
Get_vmsizes(data); //vsize, msize1, msize2
apop_model *e = apop_model_copy(model);
apop_data *subset = apop_data_copy(data);
apop_data *array_of_boots = NULL,
*summary;
//prevent and infinite regression of covariance calculation.
Apop_model_add_group(e, apop_parts_wanted); //default wants for nothing.
size_t i, nan_draws=0;
apop_name *tmpnames = (data && data->names) ? data->names : NULL; //save on some copying below.
if (data && data->names) data->names = NULL;
int height = GSL_MAX(msize1, GSL_MAX(vsize, (data?(*data->textsize):0)));
for (i=0; i<iterations && nan_draws < iterations; i++){
for (size_t j=0; j< height; j++){ //create the data set
size_t randrow = gsl_rng_uniform_int(rng, height);
apop_data_memcpy(Apop_r(subset, j), Apop_r(data, randrow));
}
//get the parameter estimates.
apop_model *est = apop_estimate(subset, e);
gsl_vector *estp = apop_data_pack(est->parameters);
if (!gsl_isnan(apop_sum(estp))){
if (i==0){
array_of_boots = apop_data_alloc(iterations, estp->size);
apop_name_stack(array_of_boots->names, est->parameters->names, 'c', 'v');
apop_name_stack(array_of_boots->names, est->parameters->names, 'c', 'c');
apop_name_stack(array_of_boots->names, est->parameters->names, 'c', 'r');
}
gsl_matrix_set_row(array_of_boots->matrix, i, estp);
} else if (ignore_nans=='y'){
i--;
nan_draws++;
}
apop_model_free(est);
gsl_vector_free(estp);
}
if(data) data->names = tmpnames;
apop_data_free(subset);
apop_model_free(e);
int set_error=0;
Apop_stopif(i == 0 && nan_draws == iterations, apop_return_data_error(N),
1, "I ran into %i NaNs and no not-NaN estimations, and so stopped. "
, iterations);
Apop_stopif(nan_draws == iterations, set_error++;
apop_matrix_realloc(array_of_boots->matrix, i, array_of_boots->matrix->size2),
1, "I ran into %i NaNs, and so stopped. Returning results based "
"on %zu bootstrap iterations.", iterations, i);
summary = apop_data_covariance(array_of_boots);
if (boot_store) *boot_store = array_of_boots;
else apop_data_free(array_of_boots);
if (set_error) summary->error = 'N';
return summary;
}
static void rearrange(apop_data *data, size_t height, size_t *perm){
size_t i, start=0;
size_t sorted[height];
memset(sorted, 0, sizeof(size_t)*height);
while (1){
i =
start = find_min_unsorted(sorted, height, start);
if (i==-1) break;
apop_data *first_row_storage = apop_data_copy(Apop_r(data, start));
sorted[start]++;
while (perm[i]!=start){
//copy from perm[i] to i
apop_data_set_row(data, Apop_r(data, perm[i]), i);
sorted[perm[i]]++;
i = perm[i];
}
apop_data_set_row(data, first_row_storage, i);
apop_data_free(first_row_storage);
}
}
/** Give me a data set and a model, and I'll give you the jackknifed covariance matrix of the model parameters.
The basic algorithm for the jackknife (glossing over the details): create a sequence of data
sets, each with exactly one observation removed, and then produce a new set of parameter estimates
using that slightly shortened data set. Then, find the covariance matrix of the derived parameters.
\li Jackknife or bootstrap? As a broad rule of thumb, the jackknife works best on models
that are closer to linear. The worse a linear approximation does (at the given data),
the worse the jackknife approximates the variance.
\param in The data set. An \ref apop_data set where each row is a single data point.
\param model An \ref apop_model, that will be used internally by \ref apop_estimate.
\exception out->error=='n' \c NULL input data.
\return An \c apop_data set whose matrix element is the estimated covariance matrix of the parameters.
\see apop_bootstrap_cov
For example:
\include jack.c
*/
apop_data * apop_jackknife_cov(apop_data *in, apop_model *model){
Apop_stopif(!in, apop_return_data_error(n), 0, "The data input can't be NULL.");
Get_vmsizes(in); //msize1, msize2, vsize
apop_model *e = apop_model_copy(model);
int i, n = GSL_MAX(msize1, GSL_MAX(vsize, in->textsize[0]));
apop_model *overall_est = e->parameters ? e : apop_estimate(in, e);//if not estimated, do so
gsl_vector *overall_params = apop_data_pack(overall_est->parameters);
gsl_vector_scale(overall_params, n); //do it just once.
gsl_vector *pseudoval = gsl_vector_alloc(overall_params->size);
//Copy the original, minus the first row.
apop_data *subset = apop_data_copy(Apop_rs(in, 1, n-1));
apop_name *tmpnames = in->names;
in->names = NULL; //save on some copying below.
apop_data *array_of_boots = apop_data_alloc(n, overall_params->size);
for(i = -1; i< n-1; i++){
//Get a view of row i, and copy it to position i-1 in the short matrix.
if (i >= 0) apop_data_memcpy(Apop_r(subset, i), Apop_r(in, i));
apop_model *est = apop_estimate(subset, e);
gsl_vector *estp = apop_data_pack(est->parameters);
gsl_vector_memcpy(pseudoval, overall_params);// *n above.
gsl_vector_scale(estp, n-1);
gsl_vector_sub(pseudoval, estp);
gsl_matrix_set_row(array_of_boots->matrix, i+1, pseudoval);
apop_model_free(est);
gsl_vector_free(estp);
}
in->names = tmpnames;
apop_data *out = apop_data_covariance(array_of_boots);
gsl_matrix_scale(out->matrix, 1./(n-1.));
apop_data_free(subset);
gsl_vector_free(pseudoval);
apop_data_free(array_of_boots);
if (e!=overall_est)
apop_model_free(overall_est);
apop_model_free(e);
gsl_vector_free(overall_params);
return out;
}
