X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fregression.q;h=1fe9cdec0b692f33d1b0642c428f87d1470f5e5d;hb=65e4b2dda3939a9c35913a79b7e79c3120713a6c;hp=44ce252881e986a9b94ff83360adba1cc25aa37d;hpb=9ca8b579de593d1df5b6ff45db222aac050ae700;p=pspp diff --git a/src/regression.q b/src/regression.q index 44ce252881..1fe9cdec0b 100644 --- a/src/regression.q +++ b/src/regression.q @@ -36,8 +36,9 @@ #include "lexer.h" #include #include "missing-values.h" -#include "reg_export_comments.h" +#include "regression_export.h" #include "tab.h" +#include "value-labels.h" #include "var.h" #include "vfm.h" @@ -472,11 +473,103 @@ 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) @@ -486,16 +579,21 @@ 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 \n\n"); - fprintf (fp, "%s", reg_mean_cmt); - fprintf (fp, "double\npspp_reg_estimate (const double *var_vals, const char *var_names[])\n{\n\tchar *model_depvars[%d] = {", c->n_indeps); - for (i = 1; i < c->n_indeps; i++) + fprintf (fp, "#include \n#include \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++) { - coeff = c->coeff[i]; - fprintf (fp, "\"%s\",\n\t\t", coeff.v->name); + tmp = 0.5 + 0.005 * (double) i; + fprintf (fp, "%.15e,\n\t\t", gsl_cdf_tdist_Pinv (tmp, c->n_obs - c->n_indeps)); } - coeff = c->coeff[i]; - fprintf (fp, "\"%s\"};\n\t", coeff.v->name); + 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++) { @@ -508,10 +606,34 @@ 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\tfor (j = 0; j < %d; j++)\n\t\t", c->n_indeps); - fprintf (fp, "{\n\t\t\tif (strcmp (var_names[i], model_depvars[j]) == 0)\n"); - fprintf (fp, "\t\t\t{\n\t\t\t\testimate += var_vals[i] * model_coeffs[j];\n"); - fprintf (fp, "\t\t\t}\n\t\t}\n\t}\n\treturn estimate;\n}\n"); + 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); } }