X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fregression.q;h=1fe9cdec0b692f33d1b0642c428f87d1470f5e5d;hb=65e4b2dda3939a9c35913a79b7e79c3120713a6c;hp=e69761e3d39a21176728868ec951d93317f811e2;hpb=4aa81a07a03b3322e3bcf2ce141fe119c02f87f7;p=pspp

diff --git a/src/regression.q b/src/regression.q
index e69761e3d3..1fe9cdec0b 100644
--- a/src/regression.q
+++ b/src/regression.q
@@ -26,19 +26,25 @@
 #include "case.h"
 #include "casefile.h"
 #include "cat.h"
+#include "cat-routines.h"
 #include "command.h"
+#include "design-matrix.h"
 #include "dictionary.h"
 #include "error.h"
 #include "file-handle.h"
 #include "gettext.h"
 #include "lexer.h"
 #include <linreg/pspp_linreg.h>
+#include "missing-values.h"
+#include "regression_export.h"
 #include "tab.h"
+#include "value-labels.h"
 #include "var.h"
 #include "vfm.h"
 
-/* (headers) */
+#define REG_LARGE_DATA 1000
 
+/* (headers) */
 
 /* (specification)
    "REGRESSION" (regression_):
@@ -60,6 +66,7 @@
    f,
    defaults,
    all;
+   export=custom;
    ^dependent=varlist;
    ^method=enter.
 */
@@ -72,6 +79,12 @@ static struct cmd_regression cmd;
  */
 size_t *indep_vars;
 
+/*
+  File where the model will be saved if the EXPORT subcommand
+  is given. 
+ */
+struct file_handle *model_file;
+
 /*
   Return value for the procedure.
  */
@@ -460,6 +473,191 @@ subcommand_statistics (int *keywords, pspp_linreg_cache * c)
   statistics_keyword_output (reg_stats_tol, keywords[tol], c);
   statistics_keyword_output (reg_stats_selection, keywords[selection], c);
 }
+static
+int reg_inserted (struct variable *v, struct variable **varlist, int n_vars)
+{
+  int i;
+
+  for (i = 0; i < n_vars; i++)
+    {
+      if (v->index == varlist[i]->index)
+	{
+	  return 1;
+	}
+    }
+  return 0;
+}
+static void
+reg_print_categorical_encoding (FILE *fp, pspp_linreg_cache *c)
+{
+  int i;
+  size_t j;
+  int n_vars = 0;
+  struct variable **varlist;
+  struct pspp_linreg_coeff coeff;
+  union value *val;
+  
+  fprintf (fp, "%s", reg_export_categorical_encode_1);
+
+  varlist = xnmalloc (c->n_indeps, sizeof (*varlist));
+  for (i = 1; i < c->n_indeps; i++)   /* c->coeff[0] is the intercept. */
+    {
+      coeff = c->coeff[i];
+      if (coeff.v->type == ALPHA)
+	{
+	  if (!reg_inserted (coeff.v, varlist, n_vars))
+	  {
+	    fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t", coeff.v->name);
+	    varlist[n_vars] = coeff.v;
+	    n_vars++;
+	  }
+	}
+    }
+  fprintf (fp, "int n_vars = %d;\n\t", n_vars);
+  fprintf (fp, "struct pspp_reg_categorical_variable *varlist[%d] = {", n_vars);
+  for (i = 0; i < n_vars - 1; i++)
+    {
+      fprintf (fp, "&%s,\n\t\t", varlist[i]->name);
+    }
+  fprintf (fp, "&%s};\n\t", varlist[i]->name);
+
+  for (i = 0; i < n_vars; i++)
+    {
+      coeff = c->coeff[i];
+      fprintf (fp, "%s.name = \"%s\";\n\t", varlist[i]->name, varlist[i]->name);
+      fprintf (fp, "%s.n_vals = %d;\n\t", varlist[i]->name, varlist[i]->obs_vals->n_categories);
+
+      for (j = 0; j < varlist[i]->obs_vals->n_categories; j++)
+	{
+	  val = cat_subscript_to_value ( (const size_t) j, varlist[i]);
+	  fprintf (fp, "%s.values[%d] = \"%s\";\n\t", varlist[i]->name, j, value_to_string (val, varlist[i]));
+	}
+    }
+  fprintf (fp, "%s", reg_export_categorical_encode_2);
+}
+
+static void
+reg_print_depvars (FILE *fp, pspp_linreg_cache *c)
+{
+  int i;
+  struct pspp_linreg_coeff coeff;
+
+  fprintf (fp, "char *model_depvars[%d] = {", c->n_indeps);
+  for (i = 1; i < c->n_indeps; i++)
+    {
+      coeff = c->coeff[i];
+      fprintf (fp, "\"%s\",\n\t\t", coeff.v->name);
+    }
+  coeff = c->coeff[i];
+  fprintf (fp, "\"%s\"};\n\t", coeff.v->name);
+}
+static void
+reg_print_getvar (FILE *fp, pspp_linreg_cache *c)
+{
+  fprintf (fp, "static int\npspp_reg_getvar (char *v_name)\n{\n\t");
+  fprintf (fp, "int i;\n\tint n_vars = %d;\n\t",c->n_indeps);
+  reg_print_depvars (fp, c);
+  fprintf (fp, "for (i = 0; i < n_vars; i++)\n\t{\n\t\t");
+  fprintf (fp, "if (strcmp (v_name, model_depvars[i]) == 0)\n\t\t{\n\t\t\t");
+  fprintf (fp, "return i;\n\t\t}\n\t}\n}\n");
+}
+static void
+subcommand_export (int export, pspp_linreg_cache *c)
+{
+  FILE *fp;
+  size_t i;
+  size_t j;
+  int n_quantiles = 100;
+  double increment;
+  double tmp;
+  struct pspp_linreg_coeff coeff;
+
+  if (export)
+    {
+      assert (c != NULL);
+      assert (model_file != NULL);
+      assert (fp != NULL);
+      fp = fopen (handle_get_filename (model_file), "w");
+      fprintf (fp, "%s", reg_preamble);
+      fprintf (fp, "#include <string.h>\n#include <math.h>\n\n");
+      reg_print_getvar (fp, 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;
+	  fprintf (fp, "%.15e,\n\t\t", gsl_cdf_tdist_Pinv (tmp, c->n_obs - c->n_indeps));
+	}
+      fprintf (fp, "%.15e};\n\t", gsl_cdf_tdist_Pinv (.9995, c->n_obs - c->n_indeps));
+      fprintf (fp, "%s", reg_export_t_quantiles_2);
+      fprintf (fp, "%s", reg_mean_cmt);
+      fprintf (fp, "double\npspp_reg_estimate (const double *var_vals,");
+      fprintf (fp, "const char *var_names[])\n{\n\t");
+      fprintf (fp, "double model_coeffs[%d] = {", c->n_indeps);
+      for (i = 1; i < c->n_indeps; i++)
+	{
+	  coeff = c->coeff[i];
+	  fprintf (fp, "%.15e,\n\t\t", coeff.estimate);
+	}
+      coeff = c->coeff[i];
+      fprintf (fp, "%.15e};\n\t", coeff.estimate);
+      coeff = c->coeff[0];
+      fprintf (fp, "double estimate = %.15e;\n\t", coeff.estimate);
+      fprintf (fp, "int i;\n\tint j;\n\n\t");
+      fprintf (fp, "for (i = 0; i < %d; i++)\n\t", c->n_indeps);
+      fprintf (fp, "%s", reg_getvar);
+      fprintf (fp, "const double cov[%d][%d] = {\n\t", c->n_coeffs, c->n_coeffs);	  
+      for (i = 0; i < c->cov->size1 - 1; i++)
+	{
+	  fprintf (fp, "{");
+	  for (j = 0; j < c->cov->size2 - 1; j++)
+	    {
+	      fprintf (fp, "%.15e, ", gsl_matrix_get (c->cov, i, j));
+	    }
+	  fprintf (fp, "%.15e},\n\t", gsl_matrix_get (c->cov, i, j));
+	}
+      fprintf (fp, "{");
+      for (j = 0; j < c->cov->size2 - 1; j++)
+	{
+	  fprintf (fp, "%.15e, ", gsl_matrix_get (c->cov, c->cov->size1 - 1, j));
+	}
+      fprintf (fp, "%.15e}\n\t", gsl_matrix_get (c->cov, c->cov->size1 - 1, c->cov->size2 - 1));
+      fprintf (fp, "};\n\tint n_vars = %d;\n\tint i;\n\tint j;\n\t", c->n_indeps);
+      fprintf (fp, "double unshuffled_vals[%d];\n\t",c->n_indeps);
+      fprintf (fp, "%s", reg_variance);
+      fprintf (fp, "%s", reg_export_confidence_interval);
+      tmp = c->mse * c->mse;
+      fprintf (fp, "%s %.15e", reg_export_prediction_interval_1, tmp);
+      fprintf (fp, "%s %.15e", reg_export_prediction_interval_2, tmp);
+      fprintf (fp, "%s", reg_export_prediction_interval_3);
+      fclose (fp);
+      fp = fopen ("pspp_model_reg.h", "w");
+      fprintf (fp, "%s", reg_header);
+      fclose (fp);
+    }
+}
+static int
+regression_custom_export (struct cmd_regression *cmd)
+{
+  /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */
+  if (!lex_force_match ('('))
+    return 0;
+  
+  if (lex_match ('*'))
+    model_file = NULL;
+  else 
+    {
+      model_file = fh_parse ();
+      if (model_file == NULL)
+        return 0; 
+    }
+  
+  if (!lex_force_match (')'))
+    return 0;
+
+  return 1;
+}
 
 int
 cmd_regression (void)
@@ -496,104 +694,136 @@ static void
 run_regression (const struct casefile *cf, void *cmd_ UNUSED)
 {
   size_t i;
-  size_t k;
   size_t n_data = 0;
   size_t row;
+  size_t case_num;
   int n_indep;
   int j = 0;
+  /*
+     Keep track of the missing cases.
+   */
+  int *is_missing_case;
   const union value *val;
   struct casereader *r;
   struct casereader *r2;
   struct ccase c;
-  const struct variable *v;
-  struct recoded_categorical_array *ca;
-  struct recoded_categorical *rc;
+  struct variable *v;
+  struct variable **indep_vars;
   struct design_matrix *X;
   gsl_vector *Y;
   pspp_linreg_cache *lcache;
   pspp_linreg_opts lopts;
 
   n_data = casefile_get_case_cnt (cf);
+
+  is_missing_case = xnmalloc (n_data, sizeof (*is_missing_case));
+  for (i = 0; i < n_data; i++)
+    is_missing_case[i] = 0;
+
   n_indep = cmd.n_variables - cmd.n_dependent;
   indep_vars = xnmalloc (n_indep, sizeof *indep_vars);
 
-  Y = gsl_vector_alloc (n_data);
   lopts.get_depvar_mean_std = 1;
   lopts.get_indep_mean_std = xnmalloc (n_indep, sizeof (int));
 
-  lcache = pspp_linreg_cache_alloc (n_data, n_indep);
-  lcache->indep_means = gsl_vector_alloc (n_indep);
-  lcache->indep_std = gsl_vector_alloc (n_indep);
 
   /*
      Read from the active file. The first pass encodes categorical
-     variables.
+     variables and drops cases with missing values.
    */
-  ca = cr_recoded_cat_ar_create (cmd.n_variables, cmd.v_variables);
-  for (r = casefile_get_reader (cf);
-       casereader_read (r, &c); case_destroy (&c))
+  j = 0;
+  for (i = 0; i < cmd.n_variables; i++)
     {
-      for (i = 0; i < ca->n_vars; i++)
+      if (!is_depvar (i))
 	{
-	  v = (*(ca->a + i))->v;
-	  val = case_data (&c, v->fv);
-	  cr_value_update (*(ca->a + i), val);
+	  v = cmd.v_variables[i];
+	  indep_vars[j] = v;
+	  j++;
+	  if (v->type == ALPHA)
+	    {
+	      /* Make a place to hold the binary vectors 
+		 corresponding to this variable's values. */
+	      cat_stored_values_create (v);
+	    }
+	  for (r = casefile_get_reader (cf);
+	       casereader_read (r, &c); case_destroy (&c))
+	    {
+	      row = casereader_cnum (r) - 1;
+	      
+	      val = case_data (&c, v->fv);
+	      cat_value_update (v, val);
+	      if (mv_is_value_missing (&v->miss, val))
+		{
+		  if (!is_missing_case[row])
+		    {
+		      /* Now it is missing. */
+		      n_data--;
+		      is_missing_case[row] = 1;
+		    }
+		}
+	    }
 	}
     }
-  cr_create_value_matrices (ca);
+
+  Y = gsl_vector_alloc (n_data);
   X =
-    design_matrix_create (n_indep, (const struct variable **) cmd.v_variables,
-			  ca, n_data);
+    design_matrix_create (n_indep, (const struct variable **) indep_vars,
+			  n_data);
+  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);
 
   /*
      The second pass creates the design matrix.
    */
+  row = 0;
   for (r2 = casefile_get_reader (cf); casereader_read (r2, &c);
        case_destroy (&c))
     /* Iterate over the cases. */
     {
-      k = 0;
-      row = casereader_cnum (r2) - 1;
-      for (i = 0; i < cmd.n_variables; ++i)	/* Iterate over the variables
+      case_num = casereader_cnum (r2) - 1;
+      if (!is_missing_case[case_num])
+	{
+	  for (i = 0; i < cmd.n_variables; ++i)	/* Iterate over the variables
 						   for the current case. 
 						 */
-	{
-	  v = cmd.v_variables[i];
-	  val = case_data (&c, v->fv);
-	  /*
-	     Independent/dependent variable separation. The
-	     'variables' subcommand specifies a varlist which contains
-	     both dependent and independent variables. The dependent
-	     variables are specified with the 'dependent'
-	     subcommand. We need to separate the two.
-	   */
-	  if (is_depvar (i))
-	    {
-	      if (v->type != NUMERIC)
-		{
-		  msg (SE, gettext ("Dependent variable must be numeric."));
-		  pspp_reg_rc = CMD_FAILURE;
-		  return;
-		}
-	      lcache->depvar = (const struct var *) v;
-	      gsl_vector_set (Y, row, val->f);
-	    }
-	  else
 	    {
-	      if (v->type == ALPHA)
+	      v = cmd.v_variables[i];
+	      val = case_data (&c, v->fv);
+	      /*
+	         Independent/dependent variable separation. The
+	         'variables' subcommand specifies a varlist which contains
+	         both dependent and independent variables. The dependent
+	         variables are specified with the 'dependent'
+	         subcommand. We need to separate the two.
+	       */
+	      if (is_depvar (i))
 		{
-		  rc = cr_var_to_recoded_categorical (v, ca);
-		  design_matrix_set_categorical (X, row, v, val, rc);
+		  if (v->type != NUMERIC)
+		    {
+		      msg (SE,
+			   gettext ("Dependent variable must be numeric."));
+		      pspp_reg_rc = CMD_FAILURE;
+		      return;
+		    }
+		  lcache->depvar = (const struct variable *) v;
+		  gsl_vector_set (Y, row, val->f);
 		}
-	      else if (v->type == NUMERIC)
+	      else
 		{
-		  design_matrix_set_numeric (X, row, v, val);
+		  if (v->type == ALPHA)
+		    {
+		      design_matrix_set_categorical (X, row, v, val);
+		    }
+		  else if (v->type == NUMERIC)
+		    {
+		      design_matrix_set_numeric (X, row, v, val);
+		    }
+
+		  lopts.get_indep_mean_std[i] = 1;
 		}
-
-	      indep_vars[k] = i;
-	      k++;
-	      lopts.get_indep_mean_std[i] = 1;
 	    }
+	  row++;
 	}
     }
   /*
@@ -609,16 +839,25 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
 	(const struct variable *) design_matrix_col_to_var (X, i);
       assert (lcache->coeff[j].v != NULL);
     }
+  /*
+    For large data sets, use QR decomposition.
+   */
+  if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
+    {
+      lcache->method = PSPP_LINREG_SVD;
+    }
   /* 
      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);
   gsl_vector_free (Y);
   design_matrix_destroy (X);
   pspp_linreg_cache_free (lcache);
   free (lopts.get_indep_mean_std);
   free (indep_vars);
+  free (is_missing_case);
   casereader_destroy (r);
   return;
 }