X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=cbb1031d1b6c7d0dfa634a5335ed792322cf996b;hb=e7d0a9f16192ceeff9243f0ede8e399ee1ef0d44;hp=3f41e16aad3e5e9d489f850100b193ec649219e0;hpb=8266aff290c15d0bfc89f054582451070562c5f3;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 3f41e16a..cbb1031d 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -57,34 +57,34 @@ /* (specification) "REGRESSION" (regression_): *variables=custom; - statistics[st_]=r, - coeff, - anova, - outs, - zpp, - label, - sha, - ci, - bcov, - ses, - xtx, - collin, - tol, - selection, - f, - defaults, - all; + +statistics[st_]=r, + coeff, + anova, + outs, + zpp, + label, + sha, + ci, + bcov, + ses, + xtx, + collin, + tol, + selection, + f, + defaults, + all; export=custom; ^dependent=varlist; - save[sv_]=resid,pred; - method=enter. + +save[sv_]=resid,pred; + +method=enter. */ /* (declarations) */ /* (functions) */ static struct cmd_regression cmd; /* Linear regression models. */ -pspp_linreg_cache **models = NULL; +static pspp_linreg_cache **models = NULL; /* Transformations for saving predicted values @@ -110,15 +110,16 @@ static size_t n_variables; File where the model will be saved if the EXPORT subcommand is given. */ -struct file_handle *model_file; +static struct file_handle *model_file; /* Return value for the procedure. */ -int pspp_reg_rc = CMD_SUCCESS; +static int pspp_reg_rc = CMD_SUCCESS; static bool run_regression (const struct ccase *, - const struct casefile *, void *); + const struct casefile *, void *, + const struct dataset *); /* STATISTICS subcommand output functions. @@ -225,7 +226,7 @@ reg_stats_coeff (pspp_linreg_cache * c) tab_float (t, 6, 1, 0, pval, 10, 2); for (j = 1; j <= c->n_indeps; j++) { - v = pspp_linreg_coeff_get_var (c->coeff[j], 0); + v = pspp_coeff_get_var (c->coeff[j], 0); label = var_to_string (v); /* Do not overwrite the variable's name. */ strncpy (tmp, label, MAX_STRING); @@ -237,7 +238,7 @@ reg_stats_coeff (pspp_linreg_cache * c) for that value. */ - val = pspp_linreg_coeff_get_value (c->coeff[j], v); + val = pspp_coeff_get_value (c->coeff[j], v); val_s = value_to_string (val, v); strncat (tmp, val_s, MAX_STRING); } @@ -392,7 +393,7 @@ reg_stats_bcov (pspp_linreg_cache * c) tab_text (t, 1, 1, TAB_CENTER | TAT_TITLE, _("Covariances")); for (i = 1; i < c->n_coeffs; i++) { - const struct variable *v = pspp_linreg_coeff_get_var (c->coeff[i], 0); + const struct variable *v = pspp_coeff_get_var (c->coeff[i], 0); label = var_to_string (v); tab_text (t, 2, i, TAB_CENTER, label); tab_text (t, i + 2, 0, TAB_CENTER, label); @@ -544,7 +545,8 @@ regression_trns_free (void *t_) Gets the predicted values. */ static int -regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) +regression_trns_pred_proc (void *t_, struct ccase *c, + casenumber case_idx UNUSED) { size_t i; size_t n_vals; @@ -582,7 +584,8 @@ regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) Gets the residuals. */ static int -regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) +regression_trns_resid_proc (void *t_, struct ccase *c, + casenumber case_idx UNUSED) { size_t i; size_t n_vals; @@ -619,32 +622,35 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) } /* - Returns 0 if NAME is a duplicate of any existing variable name. + Returns false if NAME is a duplicate of any existing variable name. */ -static int -try_name (char *name) +static bool +try_name (const struct dictionary *dict, const char *name) { - if (dict_lookup_var (default_dict, name) != NULL) - return 0; + if (dict_lookup_var (dict, name) != NULL) + return false; - return 1; + return true; } + static void -reg_get_name (char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN]) +reg_get_name (const struct dictionary *dict, char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN]) { int i = 1; snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); - while (!try_name (name)) + while (!try_name (dict, name)) { i++; snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); } } + static void -reg_save_var (const char *prefix, trns_proc_func * f, +reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f, pspp_linreg_cache * c, struct variable **v, int n_trns) { + struct dictionary *dict = dataset_dict (ds); static int trns_index = 1; char name[LONG_NAME_LEN]; struct variable *new_var; @@ -654,15 +660,16 @@ reg_save_var (const char *prefix, trns_proc_func * f, t->trns_id = trns_index; t->n_trns = n_trns; t->c = c; - reg_get_name (name, prefix); - new_var = dict_create_var (default_dict, name, 0); + reg_get_name (dict, name, prefix); + new_var = dict_create_var (dict, name, 0); assert (new_var != NULL); *v = new_var; - add_transformation (f, regression_trns_free, t); + add_transformation (ds, f, regression_trns_free, t); trns_index++; } + static void -subcommand_save (int save, pspp_linreg_cache ** models) +subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) { pspp_linreg_cache **lc; int n_trns = 0; @@ -688,12 +695,12 @@ subcommand_save (int save, pspp_linreg_cache ** models) assert ((*lc)->depvar != NULL); if (cmd.a_save[REGRESSION_SV_RESID]) { - reg_save_var ("RES", regression_trns_resid_proc, *lc, + reg_save_var (ds, "RES", regression_trns_resid_proc, *lc, &(*lc)->resid, n_trns); } if (cmd.a_save[REGRESSION_SV_PRED]) { - reg_save_var ("PRED", regression_trns_pred_proc, *lc, + reg_save_var (ds, "PRED", regression_trns_pred_proc, *lc, &(*lc)->pred, n_trns); } } @@ -707,6 +714,7 @@ subcommand_save (int save, pspp_linreg_cache ** models) } } } + static int reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) { @@ -721,6 +729,7 @@ reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) } return 0; } + static void reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) { @@ -728,7 +737,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) size_t j; int n_vars = 0; struct variable **varlist; - struct pspp_linreg_coeff *coeff; + struct pspp_coeff *coeff; const struct variable *v; union value *val; @@ -738,7 +747,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) for (i = 1; i < c->n_indeps; i++) /* c->coeff[0] is the intercept. */ { coeff = c->coeff[i]; - v = pspp_linreg_coeff_get_var (coeff, 0); + v = pspp_coeff_get_var (coeff, 0); if (v->type == ALPHA) { if (!reg_inserted (v, varlist, n_vars)) @@ -781,18 +790,18 @@ static void reg_print_depvars (FILE * fp, pspp_linreg_cache * c) { int i; - struct pspp_linreg_coeff *coeff; + 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_linreg_coeff_get_var (coeff, 0); + v = pspp_coeff_get_var (coeff, 0); fprintf (fp, "\"%s\",\n\t\t", v->name); } coeff = c->coeff[i]; - v = pspp_linreg_coeff_get_var (coeff, 0); + v = pspp_coeff_get_var (coeff, 0); fprintf (fp, "\"%s\"};\n\t", v->name); } static void @@ -814,7 +823,7 @@ reg_has_categorical (pspp_linreg_cache * c) for (i = 1; i < c->n_coeffs; i++) { - v = pspp_linreg_coeff_get_var (c->coeff[i], 0); + v = pspp_coeff_get_var (c->coeff[i], 0); if (v->type == ALPHA) { return 1; @@ -830,9 +839,8 @@ subcommand_export (int export, pspp_linreg_cache * c) size_t i; size_t j; int n_quantiles = 100; - double increment; double tmp; - struct pspp_linreg_coeff *coeff; + struct pspp_coeff *coeff; if (export) { @@ -847,7 +855,6 @@ subcommand_export (int export, pspp_linreg_cache * 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; @@ -907,8 +914,9 @@ subcommand_export (int export, pspp_linreg_cache * c) fclose (fp); } } + static int -regression_custom_export (struct cmd_regression *cmd UNUSED) +regression_custom_export (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 ('(')) @@ -930,15 +938,15 @@ regression_custom_export (struct cmd_regression *cmd UNUSED) } int -cmd_regression (void) +cmd_regression (struct dataset *ds) { - if (!parse_regression (&cmd)) + if (!parse_regression (ds, &cmd, NULL)) return CMD_FAILURE; models = xnmalloc (cmd.n_dependent, sizeof *models); - if (!multipass_procedure_with_splits (run_regression, &cmd)) + if (!multipass_procedure_with_splits (ds, run_regression, &cmd)) return CMD_CASCADING_FAILURE; - subcommand_save (cmd.sbc_save, models); + subcommand_save (ds, cmd.sbc_save, models); free (v_variables); free (models); return pspp_reg_rc; @@ -947,7 +955,7 @@ cmd_regression (void) /* Is variable k the dependent variable? */ -static int +static bool is_depvar (size_t k, const struct variable *v) { /* @@ -955,9 +963,9 @@ is_depvar (size_t k, const struct variable *v) names match. */ if (!compare_var_names (v, v_variables[k], NULL)) - return 1; + return true; - return 0; + return false; } /* @@ -996,17 +1004,20 @@ mark_missing_cases (const struct casefile *cf, struct variable *v, /* Parser for the variables sub command */ static int -regression_custom_variables (struct cmd_regression *cmd UNUSED) +regression_custom_variables (struct dataset *ds, + struct cmd_regression *cmd UNUSED, + void *aux UNUSED) { + const struct dictionary *dict = dataset_dict (ds); lex_match ('='); - if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL) + if ((token != T_ID || dict_lookup_var (dict, tokid) == NULL) && token != T_ALL) return 2; - if (!parse_variables (default_dict, &v_variables, &n_variables, PV_NONE)) + if (!parse_variables (dict, &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; @@ -1077,10 +1088,18 @@ prepare_data (int n_data, int is_missing_case[], return n_data; } +static void +coeff_init (pspp_linreg_cache * c, struct design_matrix *dm) +{ + c->coeff = xnmalloc (dm->m->size2 + 1, sizeof (*c->coeff)); + c->coeff[0] = xmalloc (sizeof (*(c->coeff[0]))); /* The first coefficient is the intercept. */ + c->coeff[0]->v_info = NULL; /* Intercept has no associated variable. */ + pspp_coeff_init (c->coeff + 1, dm); +} static bool run_regression (const struct ccase *first, - const struct casefile *cf, void *cmd_ UNUSED) + const struct casefile *cf, void *cmd_ UNUSED, const struct dataset *ds) { size_t i; size_t n_data = 0; /* Number of valide cases. */ @@ -1104,11 +1123,11 @@ run_regression (const struct ccase *first, assert (models != NULL); - output_split_file_values (first); + output_split_file_values (ds, first); if (!v_variables) { - dict_get_vars (default_dict, &v_variables, &n_variables, + dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, 1u << DC_SYSTEM); } @@ -1212,7 +1231,7 @@ run_regression (const struct ccase *first, and store pointers to the variables that correspond to the coefficients. */ - pspp_linreg_coeff_init (models[k], X); + coeff_init (models[k], X); /* Find the least-squares estimates and other statistics.