Added categorical variable support for model export

[pspp] / src / regression.q

diff --git a/src/regression.q b/src/regression.q
index bf99a5fb5cf5c2a3ff91e5e052c9456c3fe7300b..74befc2e77589ef85bf22c5f1f8465335888c1e0 100644 (file)
--- a/src/regression.q
+++ b/src/regression.q
@@ -36,7 +36,7 @@
 #include "lexer.h"
 #include <linreg/pspp_linreg.h>
 #include "missing-values.h"
-#include "reg_export_comments.h"
+#include "regression_export.h"
 #include "tab.h"
 #include "var.h"
 #include "vfm.h"
@@ -472,6 +472,44 @@ 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 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)
 {
@@ -502,6 +540,10 @@ 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)
@@ -511,8 +553,18 @@ subcommand_export (int export, pspp_linreg_cache *c)
       assert (fp != NULL);
       fp = fopen (handle_get_filename (model_file), "w");
       fprintf (fp, "%s", reg_preamble);
-      fprintf (fp, "#include <string.h>\n\n");
+      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");
@@ -528,11 +580,34 @@ subcommand_export (int export, pspp_linreg_cache *c)
       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, "{\n\t\tj = pspp_reg_getvar (var_names[i]);\n");
-      fprintf (fp, "\t\testimate += var_vals[j] * model_coeffs[j];\n");
-      fprintf (fp, "\t}\n\t\n\treturn estimate;\n}\n\n");
-      fprintf (fp, "double\npspp_reg_standard_error (const double *var_vals,");
-      fprintf (fp, "const char *var_names[])\n{\n\t");
+      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);
     }
 }