X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fregression.q;h=74befc2e77589ef85bf22c5f1f8465335888c1e0;hb=e5b7f2cd903c84efa0e73449cbcda6d135da1a23;hp=ee7c0075442288cc32afb9e2aa9f8ff48982cd64;hpb=c38b1e667a1fdb12df302ce54872dee88c04e65e;p=pspp

diff --git a/src/regression.q b/src/regression.q
index ee7c007544..74befc2e77 100644
--- a/src/regression.q
+++ b/src/regression.q
@@ -26,7 +26,9 @@
 #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"
@@ -34,12 +36,14 @@
 #include "lexer.h"
 #include <linreg/pspp_linreg.h>
 #include "missing-values.h"
+#include "regression_export.h"
 #include "tab.h"
 #include "var.h"
 #include "vfm.h"
 
-/* (headers) */
+#define REG_LARGE_DATA 1000
 
+/* (headers) */
 
 /* (specification)
    "REGRESSION" (regression_):
@@ -61,6 +65,7 @@
    f,
    defaults,
    all;
+   export=custom;
    ^dependent=varlist;
    ^method=enter.
 */
@@ -73,6 +78,12 @@ 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.
  */
@@ -462,6 +473,166 @@ subcommand_statistics (int *keywords, pspp_linreg_cache * c)
   statistics_keyword_output (reg_stats_selection, keywords[selection], c);
 }
 
+static void
+reg_print_categorical_encoding (FILE *fp, pspp_linreg_cache *c)
+{
+  int i;
+  size_t j;
+  struct pspp_linreg_coeff coeff;
+  union value *val;
+  
+  fprintf (fp, "%s", reg_export_categorical_encode_1);
+
+  for (i = 1; i < c->n_indeps; i++)   /* c->coeff[0] is the intercept. */
+    {
+      coeff = c->coeff[i];
+      if (coeff.v->type == ALPHA)
+	{
+	  fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t", coeff.v->name);
+	}
+    }
+  for (i = 1; i < c->n_indeps; i++)
+    {
+      coeff = c->coeff[i];
+      if (coeff.v->type == ALPHA)
+	{
+	  fprintf (fp, "%s.name = \"%s\";\n\t", coeff.v->name, coeff.v->name);
+	  fprintf (fp, "%s.n_vals = %d;\n\t", coeff.v->name, coeff.v->obs_vals->n_categories);
+	  fprintf (fp, "%s.values = {", coeff.v->name);
+	  for (j = 0; j < coeff.v->obs_vals->n_categories - 1; j++)
+	    {
+	      val = cat_subscript_to_value ( (const size_t) j, coeff.v);
+	      fprintf (fp, "\"%s\",\n\t\t", val->s);
+	    }
+	  val = cat_subscript_to_value ( (const size_t) j, coeff.v);
+	  fprintf (fp, "\"%s\"};\n\n\t", val->s);
+	}
+    }
+}
+
+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)
 {
@@ -497,7 +668,6 @@ 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;
@@ -512,6 +682,7 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
   struct casereader *r2;
   struct ccase c;
   struct variable *v;
+  struct variable **indep_vars;
   struct design_matrix *X;
   gsl_vector *Y;
   pspp_linreg_cache *lcache;
@@ -534,29 +705,35 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
      Read from the active file. The first pass encodes categorical
      variables and drops cases with missing values.
    */
+  j = 0;
   for (i = 0; i < cmd.n_variables; i++)
     {
-      v = cmd.v_variables[i];
-      if (v->type == ALPHA)
+      if (!is_depvar (i))
 	{
-	  /* 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))
+	  v = cmd.v_variables[i];
+	  indep_vars[j] = v;
+	  j++;
+	  if (v->type == ALPHA)
 	    {
-	      if (!is_missing_case[row])
+	      /* 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))
 		{
-		  /* Now it is missing. */
-		  n_data--;
-		  is_missing_case[row] = 1;
+		  if (!is_missing_case[row])
+		    {
+		      /* Now it is missing. */
+		      n_data--;
+		      is_missing_case[row] = 1;
+		    }
 		}
 	    }
 	}
@@ -564,7 +741,7 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
 
   Y = gsl_vector_alloc (n_data);
   X =
-    design_matrix_create (n_indep, (const struct variable **) cmd.v_variables,
+    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);
@@ -578,7 +755,6 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
        case_destroy (&c))
     /* Iterate over the cases. */
     {
-      k = 0;
       case_num = casereader_cnum (r2) - 1;
       if (!is_missing_case[case_num])
 	{
@@ -604,7 +780,7 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
 		      pspp_reg_rc = CMD_FAILURE;
 		      return;
 		    }
-		  lcache->depvar = (const struct var *) v;
+		  lcache->depvar = (const struct variable *) v;
 		  gsl_vector_set (Y, row, val->f);
 		}
 	      else
@@ -618,8 +794,6 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
 		      design_matrix_set_numeric (X, row, v, val);
 		    }
 
-		  indep_vars[k] = i;
-		  k++;
 		  lopts.get_indep_mean_std[i] = 1;
 		}
 	    }
@@ -639,11 +813,19 @@ 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);