X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=947f82854663e96d3adf1132cfe79fb87fcd02cf;hb=e40c90b1b6dbd03ce58046ada7f4ddb5a6b4b354;hp=3f41e16aad3e5e9d489f850100b193ec649219e0;hpb=8266aff290c15d0bfc89f054582451070562c5f3;p=pspp-builds.git

diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q
index 3f41e16a..947f8285 100644
--- a/src/language/stats/regression.q
+++ b/src/language/stats/regression.q
@@ -57,34 +57,34 @@
 /* (specification)
    "REGRESSION" (regression_):
    *variables=custom;
-   statistics[st_]=r,
-   coeff,
-   anova,
-   outs,
-   zpp,
-   label,
-   sha,
-   ci,
-   bcov,
-   ses,
-   xtx,
-   collin,
-   tol,
-   selection,
-   f,
-   defaults,
-   all;
+   +statistics[st_]=r,
+                    coeff,
+                    anova,
+                    outs,
+                    zpp,
+                    label,
+                    sha,
+                    ci,
+                    bcov,
+                    ses,
+                    xtx,
+                    collin,
+                    tol,
+                    selection,
+                    f,
+                    defaults,
+                    all;
    export=custom;
    ^dependent=varlist;
-   save[sv_]=resid,pred;
-   method=enter.
+   +save[sv_]=resid,pred;
+   +method=enter.
 */
 /* (declarations) */
 /* (functions) */
 static struct cmd_regression cmd;
 
 /* Linear regression models. */
-pspp_linreg_cache **models = NULL;
+static pspp_linreg_cache **models = NULL;
 
 /*
   Transformations for saving predicted values
@@ -110,15 +110,15 @@ static size_t n_variables;
   File where the model will be saved if the EXPORT subcommand
   is given. 
  */
-struct file_handle *model_file;
+static struct file_handle *model_file;
 
 /*
   Return value for the procedure.
  */
-int pspp_reg_rc = CMD_SUCCESS;
+static int pspp_reg_rc = CMD_SUCCESS;
 
 static bool run_regression (const struct ccase *,
-                            const struct casefile *, void *);
+			    const struct casefile *, void *);
 
 /* 
    STATISTICS subcommand output functions.
@@ -225,7 +225,7 @@ reg_stats_coeff (pspp_linreg_cache * c)
   tab_float (t, 6, 1, 0, pval, 10, 2);
   for (j = 1; j <= c->n_indeps; j++)
     {
-      v = pspp_linreg_coeff_get_var (c->coeff[j], 0);
+      v = pspp_coeff_get_var (c->coeff[j], 0);
       label = var_to_string (v);
       /* Do not overwrite the variable's name. */
       strncpy (tmp, label, MAX_STRING);
@@ -237,7 +237,7 @@ reg_stats_coeff (pspp_linreg_cache * c)
 	     for that value.
 	   */
 
-	  val = pspp_linreg_coeff_get_value (c->coeff[j], v);
+	  val = pspp_coeff_get_value (c->coeff[j], v);
 	  val_s = value_to_string (val, v);
 	  strncat (tmp, val_s, MAX_STRING);
 	}
@@ -392,7 +392,7 @@ reg_stats_bcov (pspp_linreg_cache * c)
   tab_text (t, 1, 1, TAB_CENTER | TAT_TITLE, _("Covariances"));
   for (i = 1; i < c->n_coeffs; i++)
     {
-      const struct variable *v = pspp_linreg_coeff_get_var (c->coeff[i], 0);
+      const struct variable *v = pspp_coeff_get_var (c->coeff[i], 0);
       label = var_to_string (v);
       tab_text (t, 2, i, TAB_CENTER, label);
       tab_text (t, i + 2, 0, TAB_CENTER, label);
@@ -544,7 +544,8 @@ regression_trns_free (void *t_)
   Gets the predicted values.
  */
 static int
-regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED)
+regression_trns_pred_proc (void *t_, struct ccase *c,
+			   casenum_t case_idx UNUSED)
 {
   size_t i;
   size_t n_vals;
@@ -582,7 +583,8 @@ regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED)
   Gets the residuals.
  */
 static int
-regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED)
+regression_trns_resid_proc (void *t_, struct ccase *c,
+			    casenum_t case_idx UNUSED)
 {
   size_t i;
   size_t n_vals;
@@ -624,7 +626,7 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED)
 static int
 try_name (char *name)
 {
-  if (dict_lookup_var (default_dict, name) != NULL)
+  if (dict_lookup_var (dataset_dict (current_dataset), name) != NULL)
     return 0;
 
   return 1;
@@ -655,10 +657,10 @@ reg_save_var (const char *prefix, trns_proc_func * f,
   t->n_trns = n_trns;
   t->c = c;
   reg_get_name (name, prefix);
-  new_var = dict_create_var (default_dict, name, 0);
+  new_var = dict_create_var (dataset_dict (current_dataset), name, 0);
   assert (new_var != NULL);
   *v = new_var;
-  add_transformation (f, regression_trns_free, t);
+  add_transformation (current_dataset, f, regression_trns_free, t);
   trns_index++;
 }
 static void
@@ -728,7 +730,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c)
   size_t j;
   int n_vars = 0;
   struct variable **varlist;
-  struct pspp_linreg_coeff *coeff;
+  struct pspp_coeff *coeff;
   const struct variable *v;
   union value *val;
 
@@ -738,7 +740,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c)
   for (i = 1; i < c->n_indeps; i++)	/* c->coeff[0] is the intercept. */
     {
       coeff = c->coeff[i];
-      v = pspp_linreg_coeff_get_var (coeff, 0);
+      v = pspp_coeff_get_var (coeff, 0);
       if (v->type == ALPHA)
 	{
 	  if (!reg_inserted (v, varlist, n_vars))
@@ -781,18 +783,18 @@ static void
 reg_print_depvars (FILE * fp, pspp_linreg_cache * c)
 {
   int i;
-  struct pspp_linreg_coeff *coeff;
+  struct pspp_coeff *coeff;
   const struct variable *v;
 
   fprintf (fp, "char *model_depvars[%d] = {", c->n_indeps);
   for (i = 1; i < c->n_indeps; i++)
     {
       coeff = c->coeff[i];
-      v = pspp_linreg_coeff_get_var (coeff, 0);
+      v = pspp_coeff_get_var (coeff, 0);
       fprintf (fp, "\"%s\",\n\t\t", v->name);
     }
   coeff = c->coeff[i];
-  v = pspp_linreg_coeff_get_var (coeff, 0);
+  v = pspp_coeff_get_var (coeff, 0);
   fprintf (fp, "\"%s\"};\n\t", v->name);
 }
 static void
@@ -814,7 +816,7 @@ reg_has_categorical (pspp_linreg_cache * c)
 
   for (i = 1; i < c->n_coeffs; i++)
     {
-      v = pspp_linreg_coeff_get_var (c->coeff[i], 0);
+      v = pspp_coeff_get_var (c->coeff[i], 0);
       if (v->type == ALPHA)
 	{
 	  return 1;
@@ -830,9 +832,8 @@ subcommand_export (int export, pspp_linreg_cache * c)
   size_t i;
   size_t j;
   int n_quantiles = 100;
-  double increment;
   double tmp;
-  struct pspp_linreg_coeff *coeff;
+  struct pspp_coeff *coeff;
 
   if (export)
     {
@@ -847,7 +848,6 @@ subcommand_export (int export, pspp_linreg_cache * 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++)
 	{
 	  tmp = 0.5 + 0.005 * (double) i;
@@ -908,7 +908,7 @@ subcommand_export (int export, pspp_linreg_cache * c)
     }
 }
 static int
-regression_custom_export (struct cmd_regression *cmd UNUSED)
+regression_custom_export (struct cmd_regression *cmd UNUSED, void *aux UNUSED)
 {
   /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */
   if (!lex_force_match ('('))
@@ -932,11 +932,11 @@ regression_custom_export (struct cmd_regression *cmd UNUSED)
 int
 cmd_regression (void)
 {
-  if (!parse_regression (&cmd))
+  if (!parse_regression (&cmd, NULL))
     return CMD_FAILURE;
 
   models = xnmalloc (cmd.n_dependent, sizeof *models);
-  if (!multipass_procedure_with_splits (run_regression, &cmd))
+  if (!multipass_procedure_with_splits (current_dataset, run_regression, &cmd))
     return CMD_CASCADING_FAILURE;
   subcommand_save (cmd.sbc_save, models);
   free (v_variables);
@@ -947,7 +947,7 @@ cmd_regression (void)
 /*
   Is variable k the dependent variable?
  */
-static int
+static bool
 is_depvar (size_t k, const struct variable *v)
 {
   /*
@@ -955,9 +955,9 @@ is_depvar (size_t k, const struct variable *v)
      names match.
    */
   if (!compare_var_names (v, v_variables[k], NULL))
-    return 1;
+    return true;
 
-  return 0;
+  return false;
 }
 
 /*
@@ -996,17 +996,18 @@ mark_missing_cases (const struct casefile *cf, struct variable *v,
 
 /* Parser for the variables sub command */
 static int
-regression_custom_variables (struct cmd_regression *cmd UNUSED)
+regression_custom_variables (struct cmd_regression *cmd UNUSED,
+			     void *aux UNUSED)
 {
 
   lex_match ('=');
 
-  if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL)
+  if ((token != T_ID || dict_lookup_var (dataset_dict (current_dataset), tokid) == NULL)
       && token != T_ALL)
     return 2;
 
 
-  if (!parse_variables (default_dict, &v_variables, &n_variables, PV_NONE))
+  if (!parse_variables (dataset_dict (current_dataset), &v_variables, &n_variables, PV_NONE))
     {
       free (v_variables);
       return 0;
@@ -1077,10 +1078,18 @@ prepare_data (int n_data, int is_missing_case[],
 
   return n_data;
 }
+static void
+coeff_init (pspp_linreg_cache * c, struct design_matrix *dm)
+{
+  c->coeff = xnmalloc (dm->m->size2 + 1, sizeof (*c->coeff));
+  c->coeff[0] = xmalloc (sizeof (*(c->coeff[0])));	/* The first coefficient is the intercept. */
+  c->coeff[0]->v_info = NULL;	/* Intercept has no associated variable. */
+  pspp_coeff_init (c->coeff + 1, dm);
+}
 
 static bool
 run_regression (const struct ccase *first,
-                const struct casefile *cf, void *cmd_ UNUSED)
+		const struct casefile *cf, void *cmd_ UNUSED)
 {
   size_t i;
   size_t n_data = 0;		/* Number of valide cases. */
@@ -1108,7 +1117,7 @@ run_regression (const struct ccase *first,
 
   if (!v_variables)
     {
-      dict_get_vars (default_dict, &v_variables, &n_variables,
+      dict_get_vars (dataset_dict (current_dataset), &v_variables, &n_variables,
 		     1u << DC_SYSTEM);
     }
 
@@ -1212,7 +1221,7 @@ run_regression (const struct ccase *first,
          and store pointers to the variables that correspond to the
          coefficients.
        */
-      pspp_linreg_coeff_init (models[k], X);
+      coeff_init (models[k], X);
 
       /* 
          Find the least-squares estimates and other statistics.