#include <output/table.h>
#include <data/value-labels.h>
#include <data/variable.h>
-#include "procedure.h"
+#include <procedure.h>
#define REG_LARGE_DATA 1000
all;
export=custom;
^dependent=varlist;
+ 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_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED)
+{
+ size_t i;
+ size_t n_vars;
+ size_t n_vals = 0;
+ union value *tmp = NULL;
+ struct reg_trns *t = t_;
+ pspp_linreg_cache *model;
+ union value *output;
+ const union value **vals = NULL;
+ struct variable **vars = NULL;
+ struct variable **model_vars = NULL;
+
+ assert (t != NULL);
+ model = t->c;
+ assert (model != NULL);
+ assert (model->depvar != NULL);
+ assert (model->pred != NULL);
+
+ dict_get_vars (default_dict, &vars, &n_vars, 1u << DC_SYSTEM);
+ vals = xnmalloc (n_vars, sizeof (*vals));
+ model_vars = xnmalloc (n_vars, sizeof (*model_vars));
+ assert (vals != NULL);
+ output = case_data_rw (c, model->pred->fv);
+ assert (output != NULL);
+
+ for (i = 0; i < n_vars; i++)
+ {
+ /* Use neither the predicted values nor the dependent variable. */
+ if (vars[i]->index != model->pred->index &&
+ vars[i]->index != model->depvar->index)
+ {
+ if (vars[i]->type == ALPHA && vars[i]->obs_vals != NULL)
+ {
+ tmp = vars[i]->obs_vals->vals;
+ }
+ else
+ {
+ tmp = NULL;
+ }
+ /*
+ Make sure the variable we use is in the linear model.
+ */
+ if (pspp_linreg_get_coeff (model, vars[i], tmp) != NULL)
+ {
+ vals[n_vals] = case_data (c, i);
+ model_vars[n_vals] = vars[i];
+ n_vals++;
+ }
+ }
+ }
+ output->f = (*model->predict) ((const struct variable **) vars,
+ vals, model, n_vals);
+ free (vals);
+ free (model_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_vars;
+ size_t n_vals = 0;
+ struct reg_trns *t = t_;
+ pspp_linreg_cache *model;
+ union value *output;
+ union value *tmp;
+ const union value **vals = NULL;
+ const union value *obs = NULL;
+ struct variable **vars = NULL;
+ struct variable **model_vars = NULL;
+
+ assert (t!= NULL);
+ model = t->c;
+ assert (model != NULL);
+ assert (model->depvar != NULL);
+ assert (model->resid != NULL);
+
+ dict_get_vars (default_dict, &vars, &n_vars, 1u << DC_SYSTEM);
+ vals = xnmalloc (n_vars, sizeof (*vals));
+ model_vars = xnmalloc (n_vars, sizeof (*model_vars));
+ assert (vals != NULL);
+ output = case_data_rw (c, model->resid->fv);
+ assert (output != NULL);
+
+ for (i = 0; i < n_vars; i++)
+ {
+ /* Use neither the predicted values nor the dependent variable. */
+ if (vars[i]->index != model->resid->index &&
+ vars[i]->index != model->depvar->index)
+ {
+ if (vars[i]->type == ALPHA && vars[i]->obs_vals != NULL)
+ {
+ tmp = vars[i]->obs_vals->vals;
+ }
+ else
+ {
+ tmp = NULL;
+ }
+ /*
+ Make sure the variable we use is in the linear model.
+ */
+ if (pspp_linreg_get_coeff (model, vars[i], tmp) != NULL)
+ {
+ vals[n_vals] = case_data (c, i);
+ model_vars[n_vals] = vars[i];
+ n_vals++;
+ }
+ }
+ if (vars[i]->index == model->depvar->index)
+ {
+ obs = case_data (c, i);
+ assert (obs != NULL);
+ }
+ }
+ output->f = (*model->residual) ((const struct variable **) vars,
+ vals, obs, model, n_vals);
+ free (vals);
+ free (model_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 + 1];
+ struct variable *new_var;
+ struct reg_trns *t = NULL;
+
+ t = xmalloc (sizeof (*t));
+ assert (t != NULL);
+ 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 **models)
+{
+ pspp_linreg_cache **lc;
+ int n_trns = 0;
+ int i;
+
+ assert (models != NULL);
+
+ if (save)
+ {
+ /* 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
+ {
+ for (lc = models; lc < models + cmd.n_dependent; lc++)
+ {
+ assert (*lc != NULL);
+ pspp_linreg_cache_free (*lc);
+ }
+ }
+}
static int
reg_inserted (const struct variable *v, struct variable **varlist, int n_vars)
{
"if (strncmp (v_name, model_depvars[i], PSPP_REG_MAXLEN) == 0)\n\t\t{\n\t\t\t");
fprintf (fp, "return i;\n\t\t}\n\t}\n}\n");
}
+static int
+reg_has_categorical (pspp_linreg_cache * c)
+{
+ int i;
+ const struct variable *v;
+
+ for (i = 1; i < c->n_coeffs; i++)
+ {
+ v = pspp_linreg_coeff_get_var (c->coeff + i, 0);
+ if (v->type == ALPHA)
+ {
+ return 1;
+ }
+ }
+ return 0;
+}
+
static void
subcommand_export (int export, pspp_linreg_cache * c)
{
{
assert (c != NULL);
assert (model_file != NULL);
- fp = fopen (fh_get_filename (model_file), "w");
+ fp = fopen (fh_get_file_name (model_file), "w");
assert (fp != NULL);
fprintf (fp, "%s", reg_preamble);
reg_print_getvar (fp, c);
- reg_print_categorical_encoding (fp, c);
+ if (reg_has_categorical (c))
+ {
+ reg_print_categorical_encoding (fp, c);
+ }
fprintf (fp, "%s", reg_export_t_quantiles_1);
increment = 0.5 / (double) increment;
for (i = 0; i < n_quantiles - 1; i++)
{
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);
+ 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);
- pspp_linreg_cache_free (lcache);
free (lopts.get_indep_mean_std);
casereader_destroy (r);
}