02110-1301, USA. */
#include <config.h>
-#include <stdlib.h>
+
#include <gsl/gsl_cdf.h>
-#include <gsl/gsl_vector.h>
#include <gsl/gsl_matrix.h>
+#include <gsl/gsl_vector.h>
#include <math.h>
-#include <libpspp/alloc.h>
+#include <stdlib.h>
+
+#include "regression-export.h"
#include <data/case.h>
#include <data/casefile.h>
-#include <data/category.h>
#include <data/cat-routines.h>
-#include <language/command.h>
-#include <libpspp/compiler.h>
-#include <math/design-matrix.h>
+#include <data/category.h>
#include <data/dictionary.h>
-#include <libpspp/message.h>
+#include <data/missing-values.h>
+#include <data/transformations.h>
+#include <data/value-labels.h>
+#include <data/variable.h>
+#include <language/command.h>
#include <language/data-io/file-handle.h>
-#include "gettext.h"
#include <language/lexer/lexer.h>
-#include <math/linreg/linreg.h>
+#include <libpspp/alloc.h>
+#include <libpspp/compiler.h>
+#include <libpspp/message.h>
+#include <math/design-matrix.h>
#include <math/linreg/coefficient.h>
-#include <data/missing-values.h>
-#include "regression-export.h"
+#include <math/linreg/linreg.h>
#include <output/table.h>
-#include <data/value-labels.h>
-#include <data/variable.h>
-#include "procedure.h"
+#include <procedure.h>
+
+#include "gettext.h"
#define REG_LARGE_DATA 1000
all;
export=custom;
^dependent=varlist;
- save=residuals;
+ save[sv_]=resid,pred;
method=enter.
*/
/* (declarations) */
/* (functions) */
static struct cmd_regression cmd;
+/* Linear regression models. */
+pspp_linreg_cache **models = NULL;
+
+/*
+ Transformations for saving predicted values
+ and residuals, etc.
+ */
+struct reg_trns
+{
+ int n_trns; /* Number of transformations. */
+ int trns_id; /* Which trns is this one? */
+ pspp_linreg_cache *c; /* Linear model for this trns. */
+};
/*
Variables used (both explanatory and response).
*/
statistics_keyword_output (reg_stats_tol, keywords[tol], c);
statistics_keyword_output (reg_stats_selection, keywords[selection], c);
}
+/*
+ Free the transformation. Free its linear model if this
+ transformation is the last one.
+ */
+static
+bool regression_trns_free (void *t_)
+{
+ bool result = true;
+ struct reg_trns *t = t_;
+
+ if (t->trns_id == t->n_trns)
+ {
+ result = pspp_linreg_cache_free (t->c);
+ }
+ free (t);
+
+ return result;
+}
+/*
+ Gets the predicted values.
+ */
static int
-regression_trns_proc (void *m, struct ccase *c, int case_idx UNUSED)
+regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED)
{
size_t i;
- size_t n_vars;
- pspp_linreg_cache *model = m;
- union value *output;
+ size_t n_vals;
+ struct reg_trns *trns = t_;
+ pspp_linreg_cache *model;
+ union value *output = NULL;
+ const union value **vals = NULL;
+ struct variable **vars = NULL;
+
+ assert (trns!= NULL);
+ model = trns->c;
+ assert (model != NULL);
+ assert (model->depvar != NULL);
+ assert (model->pred != NULL);
+
+ vars = xnmalloc (model->n_coeffs, sizeof (*vars));
+ n_vals = (*model->get_vars) (model, vars);
+
+ vals = xnmalloc (n_vals, sizeof (*vals));
+ output = case_data_rw (c, model->pred->fv);
+ assert (output != NULL);
+
+ for (i = 0; i < n_vals; i++)
+ {
+ vals[i] = case_data (c, vars[i]->fv);
+ }
+ output->f = (*model->predict) ((const struct variable **) vars,
+ vals, model, n_vals);
+ free (vals);
+ free (vars);
+ return TRNS_CONTINUE;
+}
+/*
+ Gets the residuals.
+ */
+static int
+regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED)
+{
+ size_t i;
+ size_t n_vals;
+ struct reg_trns *trns = t_;
+ pspp_linreg_cache *model;
+ union value *output = NULL;
const union value **vals = NULL;
const union value *obs = NULL;
struct variable **vars = NULL;
+ assert (trns!= NULL);
+ model = trns->c;
assert (model != NULL);
assert (model->depvar != NULL);
assert (model->resid != NULL);
-
- dict_get_vars (default_dict, &vars, &n_vars, 1u << DC_ORDINARY);
- vals = xnmalloc (n_vars, sizeof (*vals));
- assert (vals != NULL);
+
+ vars = xnmalloc (model->n_coeffs, sizeof (*vars));
+ n_vals = (*model->get_vars) (model, vars);
+
+ vals = xnmalloc (n_vals, sizeof (*vals));
output = case_data_rw (c, model->resid->fv);
assert (output != NULL);
- for (i = 0; i < n_vars; i++)
+ for (i = 0; i < n_vals; i++)
{
- /* Do not use the residual variable. */
- if (vars[i]->index != model->resid->index)
- {
- /* Do not use the dependent variable as a predictor. */
- if (vars[i]->index == model->depvar->index)
- {
- obs = case_data (c, i);
- assert (obs != NULL);
- }
- else
- {
- vals[i] = case_data (c, i);
- }
- }
+ vals[i] = case_data (c, vars[i]->fv);
}
+ obs = case_data (c, model->depvar->fv);
output->f = (*model->residual) ((const struct variable **) vars,
- vals, obs, model, i);
+ vals, obs, model, n_vals);
free (vals);
+ free (vars);
return TRNS_CONTINUE;
}
+/*
+ Returns 0 if NAME is a duplicate of any existing variable name.
+*/
+static int
+try_name (char *name)
+{
+ if (dict_lookup_var (default_dict, name) != NULL)
+ return 0;
+
+ return 1;
+}
+static
+void reg_get_name (char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN])
+{
+ int i = 1;
+
+ snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i);
+ while (!try_name(name))
+ {
+ i++;
+ snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i);
+ }
+}
+static void
+reg_save_var (const char *prefix, trns_proc_func *f,
+ pspp_linreg_cache *c, struct variable **v,
+ int n_trns)
+{
+ static int trns_index = 1;
+ char name[LONG_NAME_LEN];
+ struct variable *new_var;
+ struct reg_trns *t = NULL;
+
+ t = xmalloc (sizeof (*t));
+ t->trns_id = trns_index;
+ t->n_trns = n_trns;
+ t->c = c;
+ reg_get_name (name, prefix);
+ new_var = dict_create_var (default_dict, name, 0);
+ assert (new_var != NULL);
+ *v = new_var;
+ add_transformation (f, regression_trns_free, t);
+ trns_index++;
+}
static void
-subcommand_save (int save, pspp_linreg_cache *lc)
+subcommand_save (int save, pspp_linreg_cache **models)
{
- struct variable *residuals = NULL;
+ pspp_linreg_cache **lc;
+ int n_trns = 0;
+ int i;
- assert (lc != NULL);
- assert (lc->depvar != NULL);
+ assert (models != NULL);
if (save)
{
- residuals = dict_create_var (default_dict, "residuals", 0);
- assert (residuals != NULL);
- lc->resid = residuals;
- add_transformation (regression_trns_proc, pspp_linreg_cache_free, lc);
+ /* Count the number of transformations we will need. */
+ for (i = 0; i < REGRESSION_SV_count; i++)
+ {
+ if (cmd.a_save[i])
+ {
+ n_trns++;
+ }
+ }
+ n_trns *= cmd.n_dependent;
+
+ for (lc = models; lc < models + cmd.n_dependent; lc++)
+ {
+ assert (*lc != NULL);
+ assert ((*lc)->depvar != NULL);
+ if (cmd.a_save[REGRESSION_SV_RESID])
+ {
+ reg_save_var ("RES", regression_trns_resid_proc, *lc, &(*lc)->resid, n_trns);
+ }
+ if (cmd.a_save[REGRESSION_SV_PRED])
+ {
+ reg_save_var ("PRED", regression_trns_pred_proc, *lc, &(*lc)->pred, n_trns);
+ }
+ }
}
else
{
- pspp_linreg_cache_free (lc);
+ for (lc = models; lc < models + cmd.n_dependent; lc++)
+ {
+ assert (*lc != NULL);
+ pspp_linreg_cache_free (*lc);
+ }
}
}
static int
{
if (!parse_regression (&cmd))
return CMD_FAILURE;
+
+ models = xnmalloc (cmd.n_dependent, sizeof *models);
if (!multipass_procedure_with_splits (run_regression, &cmd))
return CMD_CASCADING_FAILURE;
-
+ subcommand_save (cmd.sbc_save, models);
free (v_variables);
-
+ free (models);
return pspp_reg_rc;
}
struct variable **indep_vars;
struct design_matrix *X;
gsl_vector *Y;
- pspp_linreg_cache *lcache;
+
pspp_linreg_opts lopts;
+ assert (models != NULL);
if (!v_variables)
{
dict_get_vars (default_dict, &v_variables, &n_variables,
lopts.get_depvar_mean_std = 1;
-
for (k = 0; k < cmd.n_dependent; k++)
{
n_indep = get_n_indep ((const struct variable *) cmd.v_dependent[k]);
{
lopts.get_indep_mean_std[i] = 1;
}
- lcache = pspp_linreg_cache_alloc (X->m->size1, X->m->size2);
- lcache->indep_means = gsl_vector_alloc (X->m->size2);
- lcache->indep_std = gsl_vector_alloc (X->m->size2);
- lcache->depvar = (const struct variable *) cmd.v_dependent[k];
+ models[k] = pspp_linreg_cache_alloc (X->m->size1, X->m->size2);
+ models[k]->indep_means = gsl_vector_alloc (X->m->size2);
+ models[k]->indep_std = gsl_vector_alloc (X->m->size2);
+ models[k]->depvar = (const struct variable *) cmd.v_dependent[k];
/*
For large data sets, use QR decomposition.
*/
if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
{
- lcache->method = PSPP_LINREG_SVD;
+ models[k]->method = PSPP_LINREG_SVD;
}
/*
- The second pass creates the design matrix.
+ The second pass fills the design matrix.
*/
row = 0;
for (r = casefile_get_reader (cf); casereader_read (r, &c);
and store pointers to the variables that correspond to the
coefficients.
*/
- pspp_linreg_coeff_init (lcache, X);
+ pspp_linreg_coeff_init (models[k], X);
/*
Find the least-squares estimates and other statistics.
*/
- pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, lcache);
- subcommand_statistics (cmd.a_statistics, lcache);
- subcommand_export (cmd.sbc_export, lcache);
- subcommand_save (cmd.sbc_save, lcache);
+ pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]);
+ subcommand_statistics (cmd.a_statistics, models[k]);
+ subcommand_export (cmd.sbc_export, models[k]);
+
gsl_vector_free (Y);
design_matrix_destroy (X);
free (indep_vars);
projects / pspp-builds.git / blobdiff