-static int
-reg_inserted (const struct variable *v, struct variable **varlist, int n_vars)
-{
- int i;
-
- for (i = 0; i < n_vars; i++)
- {
- if (v == varlist[i])
- {
- return 1;
- }
- }
- return 0;
-}
-
-static void
-reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c)
-{
- int i;
- int n_vars = 0;
- struct variable **varlist;
-
- 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. */
- {
- struct pspp_coeff *coeff = c->coeff[i];
- const struct variable *v = pspp_coeff_get_var (coeff, 0);
- if (var_is_alpha (v))
- {
- if (!reg_inserted (v, varlist, n_vars))
- {
- fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t",
- var_get_name (v));
- varlist[n_vars] = (struct variable *) 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", var_get_name (varlist[i]));
- }
- fprintf (fp, "&%s};\n\t", var_get_name (varlist[i]));
-
- for (i = 0; i < n_vars; i++)
- {
- int n_categories = cat_get_n_categories (varlist[i]);
- int j;
-
- fprintf (fp, "%s.name = \"%s\";\n\t",
- var_get_name (varlist[i]), var_get_name (varlist[i]));
- fprintf (fp, "%s.n_vals = %d;\n\t",
- var_get_name (varlist[i]), n_categories);
-
- for (j = 0; j < n_categories; j++)
- {
- const union value *val = cat_subscript_to_value (j, varlist[i]);
- fprintf (fp, "%s.values[%d] = \"%s\";\n\t",
- var_get_name (varlist[i]), j,
- var_get_value_name (varlist[i], val));
- }
- }
- fprintf (fp, "%s", reg_export_categorical_encode_2);
-}
-
-static void
-reg_print_depvars (FILE * fp, pspp_linreg_cache * c)
-{
- int i;
- struct pspp_coeff *coeff;
- const struct variable *v;
-
- fprintf (fp, "char *model_depvars[%d] = {", c->n_indeps);
- for (i = 1; i < c->n_indeps; i++)
- {
- coeff = c->coeff[i];
- v = pspp_coeff_get_var (coeff, 0);
- fprintf (fp, "\"%s\",\n\t\t", var_get_name (v));
- }
- coeff = c->coeff[i];
- v = pspp_coeff_get_var (coeff, 0);
- fprintf (fp, "\"%s\"};\n\t", var_get_name (v));
-}
-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 (strncmp (v_name, model_depvars[i], PSPP_REG_MAXLEN) == 0)\n\t\t{\n\t\t\t");
- fprintf (fp, "return i;\n\t\t}\n\t}\n}\n");
-}
-static int
-reg_has_categorical (pspp_linreg_cache * c)
-{
- int i;
- const struct variable *v;
-
- for (i = 1; i < c->n_coeffs; i++)
- {
- v = pspp_coeff_get_var (c->coeff[i], 0);
- if (var_is_alpha (v))
- return 1;
- }
- return 0;
-}
-
-static void
-subcommand_export (int export, pspp_linreg_cache * c)
-{
- FILE *fp;
- size_t i;
- size_t j;
- int n_quantiles = 100;
- double tmp;
- struct pspp_coeff *coeff;
-
- if (export)
- {
- assert (c != NULL);
- assert (model_file != NULL);
- fp = fopen (fh_get_file_name (model_file), "w");
- assert (fp != NULL);
- fprintf (fp, "%s", reg_preamble);
- reg_print_getvar (fp, c);
- if (reg_has_categorical (c))
- {
- reg_print_categorical_encoding (fp, c);
- }
- fprintf (fp, "%s", reg_export_t_quantiles_1);
- 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 lexer *lexer, struct dataset *ds UNUSED,
- struct cmd_regression *cmd UNUSED, void *aux UNUSED)
-{
- /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */
- if (!lex_force_match (lexer, '('))
- return 0;
-
- if (lex_match (lexer, '*'))
- model_file = NULL;
- else
- {
- model_file = fh_parse (lexer, FH_REF_FILE);
- if (model_file == NULL)
- return 0;
- }
-
- if (!lex_force_match (lexer, ')'))
- return 0;
-
- return 1;
-}
-