From 65e4b2dda3939a9c35913a79b7e79c3120713a6c Mon Sep 17 00:00:00 2001
From: Jason Stover <jhs@math.gcsu.edu>
Date: Sun, 1 Jan 2006 00:03:51 +0000
Subject: [PATCH] Categorical dependent variables for EXPORTed models
---
src/regression.q | 52 ++++++++++++++++++++++++++++++-----------
src/regression_export.h | 23 +++++++++++++-----
2 files changed, 56 insertions(+), 19 deletions(-)
diff --git a/src/regression.q b/src/regression.q
index 74befc2e..1fe9cdec 100644
--- a/src/regression.q
+++ b/src/regression.q
@@ -38,6 +38,7 @@
#include "missing-values.h"
#include "regression_export.h"
#include "tab.h"
+#include "value-labels.h"
#include "var.h"
#include "vfm.h"
@@ -472,42 +473,67 @@ 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)
{
- fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t", coeff.v->name);
+ 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++;
+ }
}
}
- for (i = 1; i < c->n_indeps; i++)
+ 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];
- if (coeff.v->type == ALPHA)
+ 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++)
{
- 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);
+ 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
diff --git a/src/regression_export.h b/src/regression_export.h
index 8798027a..a9583d7b 100644
--- a/src/regression_export.h
+++ b/src/regression_export.h
@@ -127,10 +127,21 @@ const char reg_export_prediction_interval_3[] = " + pspp_reg_variance (var_vals,
a vector which does not match its categorical value in the model.
*/
const char reg_export_categorical_encode_1[] = "struct pspp_reg_categorical_variable\n"
-"{\n\tchar * name;\n\tsize_t n_vals;\n\tchar *[] values;\n};\n\n"
-"static\ndouble * get_value_vector (char *v)\n{\n\tdouble *result;\n\t";
-
-const char reg_export_categorical_encode_2[] = "; i++)\n\t{\n\t\tif (strcmp (v, values[i]) == 0)"
-"\n\t\t{\n\t\t\tresult[i] = 1.0;\n\t\t}\n\t}\n\treturn result;\n}\n";
-
+"{\n\tchar * name;\n\tsize_t n_vals;\n\tchar *values[1024];\n};\n\n"
+"/*\n This function returns the binary vector which corresponds to the value\n"
+" of the categorical variable stored in 'value'. The name of the variable is\n"
+" stored in the 'var' argument. Notice the values stored in the\n"
+" pspp_categorical_variable structures all end with a space character.\n"
+" That means the values of the categorical variables you pass to any function\n"
+" in this program should also end with a space character.\n*/\n"
+"static\ndouble * pspp_reg_get_value_vector (char *var, char *value)\n{\n\tdouble *result;\n\t"
+"int i;\n\t";
+
+const char reg_export_categorical_encode_2[] = "int v_index = 0;\n\t"
+"while (v_index < n_vars && strcmp (var, varlist[i]->name) != 0)\n\t{\n\t\t"
+"v_index++;\n\t}\n\tresult = (double *) malloc (varlist[v_index]->n_vals * sizeof (*result));\n\t"
+"for (i = 0; i < varlist[v_index]->n_vals; i++)\n\t{\n\t\t"
+"if (strcmp ( (varlist[v_index]->values)[i], value) == 0)\n\t\t{\n\t\t\t"
+"result[i] = 1.0;\n\t\t}\n\t\telse result[i] = 0.0;\n\t}\n\n\t"
+"return result;\n}\n\n";
#endif
--
2.30.2