X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=463d18f9ad16dc26eef74dfd015a4989cd8aa8fc;hb=6f135ae2a14a178f850c25cb4bad6c0aae88c920;hp=c7dc7d504f660a0034a53ecd210eb308d4f64f75;hpb=08703a888d1cc31459e6028a61e3940f6d4b2c5f;p=pspp

diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q
index c7dc7d504f..463d18f9ad 100644
--- a/src/language/stats/regression.q
+++ b/src/language/stats/regression.q
@@ -18,32 +18,37 @@
    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/procedure.h>
+#include <data/transformations.h>
+#include <data/value-labels.h>
+#include <data/variable.h>
+#include <language/command.h>
+#include <language/dictionary/split-file.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 "gettext.h"
 
 #define REG_LARGE_DATA 1000
 
@@ -112,7 +117,8 @@ struct file_handle *model_file;
  */
 int pspp_reg_rc = CMD_SUCCESS;
 
-static bool run_regression (const struct casefile *, void *);
+static bool run_regression (const struct ccase *,
+                            const struct casefile *, void *);
 
 /* 
    STATISTICS subcommand output functions.
@@ -539,58 +545,34 @@ 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_;
+  size_t n_vals;
+  struct reg_trns *trns = t_;
   pspp_linreg_cache *model;
-  union value *output;
+  union value *output = NULL;
   const union value **vals = NULL;
   struct variable **vars = NULL;
-  struct variable **model_vars = NULL;
   
-  assert (t != NULL);
-  model = t->c;
+  assert (trns!= NULL);
+  model = trns->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);
+
+  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_vars; i++)
+  for (i = 0; i < n_vals; 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++;
-	    }
-	}
+      vals[i] = case_data (c, vars[i]->fv);
     }
   output->f = (*model->predict) ((const struct variable **) vars, 
 				  vals, model, n_vals);
   free (vals);
-  free (model_vars);
+  free (vars);
   return TRNS_CONTINUE;
 }
 /*
@@ -600,64 +582,36 @@ 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_;
+  size_t n_vals;
+  struct reg_trns *trns = t_;
   pspp_linreg_cache *model;
-  union value *output;
-  union value *tmp;
+  union value *output = NULL;
   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 (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_SYSTEM);
-  vals = xnmalloc (n_vars, sizeof (*vals));
-  model_vars = xnmalloc (n_vars, sizeof (*model_vars));
-  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++)
     {
-      /* 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);
-	}
+      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, n_vals);
   free (vals);
-  free (model_vars);
+  free (vars);
   return TRNS_CONTINUE;
 }
 /* 
@@ -689,12 +643,11 @@ reg_save_var (const char *prefix, trns_proc_func *f,
 	      int n_trns)
 {
   static int trns_index = 1;
-  char name[LONG_NAME_LEN + 1];
+  char name[LONG_NAME_LEN];
   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;
@@ -1119,7 +1072,8 @@ int prepare_data (int n_data, int is_missing_case[],
   return n_data;
 }
 static bool
-run_regression (const struct casefile *cf, void *cmd_ UNUSED)
+run_regression (const struct ccase *first,
+                const struct casefile *cf, void *cmd_ UNUSED)
 {
   size_t i;
   size_t n_data = 0; /* Number of valide cases. */
@@ -1142,6 +1096,9 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
   pspp_linreg_opts lopts;
 
   assert (models != NULL);
+
+  output_split_file_values (first);
+
   if (!v_variables)
     {
       dict_get_vars (default_dict, &v_variables, &n_variables,