X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=287847a855452d3fba03ce7f1f6cb22405556c6d;hb=3b76a8aa4e808b2e6bdb792c369fda72a61304de;hp=4078156863f34bcaaa37386a8cf046f2187f9395;hpb=18f6e8958244f938e9e9a03a4230cacf0d22a470;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 40781568..287847a8 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -1,6 +1,5 @@ /* PSPP - linear regression. Copyright (C) 2005 Free Software Foundation, Inc. - Written by Jason H Stover . This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as @@ -57,34 +56,34 @@ /* (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 +109,16 @@ 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. @@ -229,7 +229,7 @@ reg_stats_coeff (pspp_linreg_cache * c) label = var_to_string (v); /* Do not overwrite the variable's name. */ strncpy (tmp, label, MAX_STRING); - if (v->type == ALPHA) + if (var_is_alpha (v)) { /* Append the value associated with this coefficient. @@ -238,7 +238,7 @@ reg_stats_coeff (pspp_linreg_cache * c) */ val = pspp_coeff_get_value (c->coeff[j], v); - val_s = value_to_string (val, v); + val_s = var_get_value_name (v, val); strncat (tmp, val_s, MAX_STRING); } @@ -269,7 +269,7 @@ reg_stats_coeff (pspp_linreg_cache * c) /* P values for the test statistic above. */ - pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); + pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), (double) (c->n_obs - c->n_coeffs)); tab_float (t, 6, j + 1, 0, pval, 10, 2); } tab_title (t, _("Coefficients")); @@ -544,7 +544,8 @@ 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; @@ -564,12 +565,12 @@ regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) n_vals = (*model->get_vars) (model, vars); vals = xnmalloc (n_vals, sizeof (*vals)); - output = case_data_rw (c, model->pred->fv); + output = case_data_rw (c, model->pred); assert (output != NULL); for (i = 0; i < n_vals; i++) { - vals[i] = case_data (c, vars[i]->fv); + vals[i] = case_data (c, vars[i]); } output->f = (*model->predict) ((const struct variable **) vars, vals, model, n_vals); @@ -582,7 +583,8 @@ 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; @@ -603,14 +605,14 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) n_vals = (*model->get_vars) (model, vars); vals = xnmalloc (n_vals, sizeof (*vals)); - output = case_data_rw (c, model->resid->fv); + output = case_data_rw (c, model->resid); assert (output != NULL); for (i = 0; i < n_vals; i++) { - vals[i] = case_data (c, vars[i]->fv); + vals[i] = case_data (c, vars[i]); } - obs = case_data (c, model->depvar->fv); + obs = case_data (c, model->depvar); output->f = (*model->residual) ((const struct variable **) vars, vals, obs, model, n_vals); free (vals); @@ -619,32 +621,35 @@ 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 +659,16 @@ 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 +694,12 @@ 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 +713,7 @@ subcommand_save (int save, pspp_linreg_cache ** models) } } } + static int reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) { @@ -714,37 +721,34 @@ reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) for (i = 0; i < n_vars; i++) { - if (v->index == varlist[i]->index) + if (v == varlist[i]) { 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_coeff *coeff; - const struct variable *v; - 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]; - v = pspp_coeff_get_var (coeff, 0); - if (v->type == ALPHA) + 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", - v->name); + var_get_name (v)); varlist[n_vars] = (struct variable *) v; n_vars++; } @@ -755,23 +759,28 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) n_vars); for (i = 0; i < n_vars - 1; i++) { - fprintf (fp, "&%s,\n\t\t", varlist[i]->name); + fprintf (fp, "&%s,\n\t\t", var_get_name (varlist[i])); } - fprintf (fp, "&%s};\n\t", varlist[i]->name); + fprintf (fp, "&%s};\n\t", var_get_name (varlist[i])); 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++) + size_t n_categories = cat_get_n_categories (varlist[i]); + size_t 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++) { - 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])); + 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); @@ -789,11 +798,11 @@ reg_print_depvars (FILE * fp, pspp_linreg_cache * c) { coeff = c->coeff[i]; v = pspp_coeff_get_var (coeff, 0); - fprintf (fp, "\"%s\",\n\t\t", v->name); + 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", v->name); + fprintf (fp, "\"%s\"};\n\t", var_get_name (v)); } static void reg_print_getvar (FILE * fp, pspp_linreg_cache * c) @@ -815,10 +824,8 @@ reg_has_categorical (pspp_linreg_cache * c) for (i = 1; i < c->n_coeffs; i++) { v = pspp_coeff_get_var (c->coeff[i], 0); - if (v->type == ALPHA) - { - return 1; - } + if (var_is_alpha (v)) + return 1; } return 0; } @@ -830,7 +837,6 @@ subcommand_export (int export, pspp_linreg_cache * c) size_t i; size_t j; int n_quantiles = 100; - double increment; double tmp; struct pspp_coeff *coeff; @@ -847,7 +853,6 @@ 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; @@ -907,38 +912,39 @@ subcommand_export (int export, pspp_linreg_cache * c) fclose (fp); } } + static int -regression_custom_export (struct cmd_regression *cmd UNUSED, void *aux UNUSED) +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 ('(')) + if (!lex_force_match (lexer, '(')) return 0; - if (lex_match ('*')) + if (lex_match (lexer, '*')) model_file = NULL; else { - model_file = fh_parse (FH_REF_FILE); + model_file = fh_parse (lexer, FH_REF_FILE); if (model_file == NULL) return 0; } - if (!lex_force_match (')')) + if (!lex_force_match (lexer, ')')) return 0; return 1; } int -cmd_regression (void) +cmd_regression (struct lexer *lexer, struct dataset *ds) { - if (!parse_regression (&cmd, NULL)) + if (!parse_regression (lexer, 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; @@ -947,17 +953,10 @@ cmd_regression (void) /* Is variable k the dependent variable? */ -static int +static bool is_depvar (size_t k, const struct variable *v) { - /* - compare_var_names returns 0 if the variable - names match. - */ - if (!compare_var_names (v, v_variables[k], NULL)) - return 1; - - return 0; + return v == v_variables[k]; } /* @@ -972,14 +971,14 @@ mark_missing_cases (const struct casefile *cf, struct variable *v, size_t row; const union value *val; - for (r = casefile_get_reader (cf); + for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c); case_destroy (&c)) { row = casereader_cnum (r) - 1; - val = case_data (&c, v->fv); + val = case_data (&c, v); cat_value_update (v, val); - if (mv_is_value_missing (&v->miss, val)) + if (var_is_value_missing (v, val, MV_ANY)) { if (!is_missing_case[row]) { @@ -996,18 +995,20 @@ 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, - void *aux UNUSED) +regression_custom_variables (struct lexer *lexer, struct dataset *ds, + struct cmd_regression *cmd UNUSED, + void *aux UNUSED) { + const struct dictionary *dict = dataset_dict (ds); - lex_match ('='); + lex_match (lexer, '='); - if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL) - && token != T_ALL) + if ((lex_token (lexer) != T_ID || dict_lookup_var (dict, lex_tokid (lexer)) == NULL) + && lex_token (lexer) != T_ALL) return 2; - if (!parse_variables (default_dict, &v_variables, &n_variables, PV_NONE)) + if (!parse_variables (lexer, dict, &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; @@ -1061,7 +1062,7 @@ prepare_data (int n_data, int is_missing_case[], { indep_vars[j] = v_variables[i]; j++; - if (v_variables[i]->type == ALPHA) + if (var_is_alpha (v_variables[i])) { /* Make a place to hold the binary vectors corresponding to this variable's values. */ @@ -1078,10 +1079,18 @@ 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. */ @@ -1105,11 +1114,11 @@ 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); } @@ -1117,7 +1126,7 @@ run_regression (const struct ccase *first, for (i = 0; i < cmd.n_dependent; i++) { - if (cmd.v_dependent[i]->type != NUMERIC) + if (!var_is_numeric (cmd.v_dependent[i])) { msg (SE, gettext ("Dependent variable must be numeric.")); pspp_reg_rc = CMD_FAILURE; @@ -1168,7 +1177,7 @@ run_regression (const struct ccase *first, The second pass fills the design matrix. */ row = 0; - for (r = casefile_get_reader (cf); casereader_read (r, &c); + for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c); case_destroy (&c)) /* Iterate over the cases. */ { @@ -1180,7 +1189,7 @@ run_regression (const struct ccase *first, current case. */ { - val = case_data (&c, v_variables[i]->fv); + val = case_data (&c, v_variables[i]); /* Independent/dependent variable separation. The 'variables' subcommand specifies a varlist which contains @@ -1191,19 +1200,19 @@ run_regression (const struct ccase *first, */ if (!is_depvar (i, cmd.v_dependent[k])) { - if (v_variables[i]->type == ALPHA) + if (var_is_alpha (v_variables[i])) { design_matrix_set_categorical (X, row, v_variables[i], val); } - else if (v_variables[i]->type == NUMERIC) + else { design_matrix_set_numeric (X, row, v_variables[i], val); } } } - val = case_data (&c, cmd.v_dependent[k]->fv); + val = case_data (&c, cmd.v_dependent[k]); gsl_vector_set (Y, row, val->f); row++; } @@ -1213,7 +1222,7 @@ run_regression (const struct ccase *first, and store pointers to the variables that correspond to the coefficients. */ - pspp_coeff_init (models[k], X); + coeff_init (models[k], X); /* Find the least-squares estimates and other statistics.