X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=947f82854663e96d3adf1132cfe79fb87fcd02cf;hb=e40c90b1b6dbd03ce58046ada7f4ddb5a6b4b354;hp=463d18f9ad16dc26eef74dfd015a4989cd8aa8fc;hpb=a4ae68f966bc574326d429119878e733069ced14;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 463d18f9..947f8285 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -44,7 +44,7 @@ #include #include #include -#include +#include #include #include @@ -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 @@ -92,9 +92,9 @@ pspp_linreg_cache **models = NULL; */ struct reg_trns { - int n_trns; /* Number of transformations. */ - int trns_id; /* Which trns is this one? */ - pspp_linreg_cache *c; /* Linear model for this trns. */ + int n_trns; /* Number of transformations. */ + int trns_id; /* Which trns is this one? */ + pspp_linreg_cache *c; /* Linear model for this trns. */ }; /* Variables used (both explanatory and response). @@ -110,15 +110,15 @@ 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 *); /* STATISTICS subcommand output functions. @@ -213,7 +213,7 @@ reg_stats_coeff (pspp_linreg_cache * c) tab_text (t, 5, 0, TAB_CENTER | TAT_TITLE, _("t")); tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Significance")); tab_text (t, 1, 1, TAB_LEFT | TAT_TITLE, _("(Constant)")); - coeff = c->coeff[0].estimate; + coeff = c->coeff[0]->estimate; tab_float (t, 2, 1, 0, coeff, 10, 2); std_err = sqrt (gsl_matrix_get (c->cov, 0, 0)); tab_float (t, 3, 1, 0, std_err, 10, 2); @@ -225,7 +225,7 @@ 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 +237,7 @@ 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); } @@ -246,7 +246,7 @@ reg_stats_coeff (pspp_linreg_cache * c) /* Regression coefficients. */ - coeff = c->coeff[j].estimate; + coeff = c->coeff[j]->estimate; tab_float (t, 2, j + 1, 0, coeff, 10, 2); /* Standard error of the coefficients. @@ -392,7 +392,7 @@ 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); @@ -520,12 +520,13 @@ 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); } + /* Free the transformation. Free its linear model if this transformation is the last one. */ -static -bool regression_trns_free (void *t_) +static bool +regression_trns_free (void *t_) { bool result = true; struct reg_trns *t = t_; @@ -538,11 +539,13 @@ bool regression_trns_free (void *t_) return result; } + /* 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, + casenum_t case_idx UNUSED) { size_t i; size_t n_vals; @@ -551,8 +554,8 @@ regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) union value *output = NULL; const union value **vals = NULL; struct variable **vars = NULL; - - assert (trns!= NULL); + + assert (trns != NULL); model = trns->c; assert (model != NULL); assert (model->depvar != NULL); @@ -569,17 +572,19 @@ regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) { vals[i] = case_data (c, vars[i]->fv); } - output->f = (*model->predict) ((const struct variable **) vars, - vals, model, n_vals); + output->f = (*model->predict) ((const struct variable **) vars, + vals, model, n_vals); free (vals); free (vars); return TRNS_CONTINUE; } + /* 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, + casenum_t case_idx UNUSED) { size_t i; size_t n_vals; @@ -589,8 +594,8 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) const union value **vals = NULL; const union value *obs = NULL; struct variable **vars = NULL; - - assert (trns!= NULL); + + assert (trns != NULL); model = trns->c; assert (model != NULL); assert (model->depvar != NULL); @@ -608,39 +613,39 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) vals[i] = case_data (c, vars[i]->fv); } obs = case_data (c, model->depvar->fv); - output->f = (*model->residual) ((const struct variable **) vars, + output->f = (*model->residual) ((const struct variable **) vars, vals, obs, model, n_vals); free (vals); free (vars); return TRNS_CONTINUE; } + /* Returns 0 if NAME is a duplicate of any existing variable name. */ static int try_name (char *name) { - if (dict_lookup_var (default_dict, name) != NULL) + if (dict_lookup_var (dataset_dict (current_dataset), name) != NULL) return 0; return 1; } -static -void reg_get_name (char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN]) +static void +reg_get_name (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 (name)) { i++; snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); } } -static void -reg_save_var (const char *prefix, trns_proc_func *f, - pspp_linreg_cache *c, struct variable **v, - int n_trns) +static void +reg_save_var (const char *prefix, trns_proc_func * f, + pspp_linreg_cache * c, struct variable **v, int n_trns) { static int trns_index = 1; char name[LONG_NAME_LEN]; @@ -652,14 +657,14 @@ reg_save_var (const char *prefix, trns_proc_func *f, t->n_trns = n_trns; t->c = c; reg_get_name (name, prefix); - new_var = dict_create_var (default_dict, name, 0); + new_var = dict_create_var (dataset_dict (current_dataset), name, 0); assert (new_var != NULL); *v = new_var; - add_transformation (f, regression_trns_free, t); + add_transformation (current_dataset, f, regression_trns_free, t); trns_index++; } static void -subcommand_save (int save, pspp_linreg_cache **models) +subcommand_save (int save, pspp_linreg_cache ** models) { pspp_linreg_cache **lc; int n_trns = 0; @@ -685,15 +690,17 @@ 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, &(*lc)->resid, n_trns); + reg_save_var ("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, &(*lc)->pred, n_trns); + reg_save_var ("PRED", regression_trns_pred_proc, *lc, + &(*lc)->pred, n_trns); } } } - else + else { for (lc = models; lc < models + cmd.n_dependent; lc++) { @@ -723,7 +730,7 @@ 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; @@ -732,8 +739,8 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) 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_linreg_coeff_get_var (coeff, 0); + coeff = c->coeff[i]; + v = pspp_coeff_get_var (coeff, 0); if (v->type == ALPHA) { if (!reg_inserted (v, varlist, n_vars)) @@ -756,7 +763,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) for (i = 0; i < n_vars; i++) { - coeff = c->coeff + 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, @@ -776,18 +783,18 @@ 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); + coeff = c->coeff[i]; + 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); + coeff = c->coeff[i]; + v = pspp_coeff_get_var (coeff, 0); fprintf (fp, "\"%s\"};\n\t", v->name); } static void @@ -806,10 +813,10 @@ reg_has_categorical (pspp_linreg_cache * c) { int i; const struct variable *v; - + 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; @@ -825,9 +832,8 @@ 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) { @@ -842,7 +848,6 @@ 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; @@ -859,12 +864,12 @@ subcommand_export (int export, pspp_linreg_cache * c) for (i = 1; i < c->n_indeps; i++) { coeff = c->coeff[i]; - fprintf (fp, "%.15e,\n\t\t", coeff.estimate); + fprintf (fp, "%.15e,\n\t\t", coeff->estimate); } coeff = c->coeff[i]; - fprintf (fp, "%.15e};\n\t", coeff.estimate); + fprintf (fp, "%.15e};\n\t", coeff->estimate); coeff = c->coeff[0]; - fprintf (fp, "double estimate = %.15e;\n\t", coeff.estimate); + 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); @@ -903,7 +908,7 @@ subcommand_export (int export, pspp_linreg_cache * c) } } static int -regression_custom_export (struct cmd_regression *cmd UNUSED) +regression_custom_export (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 ('(')) @@ -927,11 +932,11 @@ regression_custom_export (struct cmd_regression *cmd UNUSED) int cmd_regression (void) { - if (!parse_regression (&cmd)) + if (!parse_regression (&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 (current_dataset, run_regression, &cmd)) return CMD_CASCADING_FAILURE; subcommand_save (cmd.sbc_save, models); free (v_variables); @@ -942,17 +947,17 @@ 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. - */ + compare_var_names returns 0 if the variable + names match. + */ if (!compare_var_names (v, v_variables[k], NULL)) - return 1; + return true; - return 0; + return false; } /* @@ -991,32 +996,33 @@ 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 cmd_regression *cmd UNUSED, + void *aux UNUSED) { - lex_match('='); + lex_match ('='); - if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL) + if ((token != T_ID || dict_lookup_var (dataset_dict (current_dataset), tokid) == NULL) && token != T_ALL) return 2; - - if (!parse_variables (default_dict, &v_variables, &n_variables, - PV_NONE )) + + if (!parse_variables (dataset_dict (current_dataset), &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; } - assert(n_variables); + assert (n_variables); return 1; } + /* Count the explanatory variables. The user may or may not have specified a response variable in the syntax. */ -static -int get_n_indep (const struct variable *v) +static int +get_n_indep (const struct variable *v) { int result; int i = 0; @@ -1033,16 +1039,16 @@ int get_n_indep (const struct variable *v) } return result; } + /* Read from the active file. Identify the explanatory variables in v_variables. Encode categorical variables. Drop cases with missing values. */ -static -int prepare_data (int n_data, int is_missing_case[], - struct variable **indep_vars, - struct variable *depvar, - const struct casefile *cf) +static int +prepare_data (int n_data, int is_missing_case[], + struct variable **indep_vars, + struct variable *depvar, const struct casefile *cf) { int i; int j; @@ -1050,7 +1056,7 @@ int prepare_data (int n_data, int is_missing_case[], assert (indep_vars != NULL); j = 0; for (i = 0; i < n_variables; i++) - { + { if (!is_depvar (i, depvar)) { indep_vars[j] = v_variables[i]; @@ -1058,26 +1064,36 @@ int prepare_data (int n_data, int is_missing_case[], if (v_variables[i]->type == ALPHA) { /* Make a place to hold the binary vectors - corresponding to this variable's values. */ + corresponding to this variable's values. */ cat_stored_values_create (v_variables[i]); } - n_data = mark_missing_cases (cf, v_variables[i], is_missing_case, n_data); + n_data = + mark_missing_cases (cf, v_variables[i], is_missing_case, n_data); } } /* - Mark missing cases for the dependent variable. + Mark missing cases for the dependent variable. */ n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data); 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) { size_t i; - size_t n_data = 0; /* Number of valide cases. */ - size_t n_cases; /* Number of cases. */ + size_t n_data = 0; /* Number of valide cases. */ + size_t n_cases; /* Number of cases. */ size_t row; size_t case_num; int n_indep = 0; @@ -1101,7 +1117,7 @@ run_regression (const struct ccase *first, if (!v_variables) { - dict_get_vars (default_dict, &v_variables, &n_variables, + dict_get_vars (dataset_dict (current_dataset), &v_variables, &n_variables, 1u << DC_SYSTEM); } @@ -1125,15 +1141,15 @@ run_regression (const struct ccase *first, { n_indep = get_n_indep ((const struct variable *) cmd.v_dependent[k]); lopts.get_indep_mean_std = xnmalloc (n_indep, sizeof (int)); - indep_vars = xnmalloc (n_indep, sizeof *indep_vars); + indep_vars = xnmalloc (n_indep, sizeof *indep_vars); assert (indep_vars != NULL); for (i = 0; i < n_cases; i++) { is_missing_case[i] = 0; } - n_data = prepare_data (n_cases, is_missing_case, indep_vars, - cmd.v_dependent[k], + n_data = prepare_data (n_cases, is_missing_case, indep_vars, + cmd.v_dependent[k], (const struct casefile *) cf); Y = gsl_vector_alloc (n_data); @@ -1170,7 +1186,7 @@ run_regression (const struct ccase *first, for (i = 0; i < n_variables; ++i) /* Iterate over the variables for the current case. - */ + */ { val = case_data (&c, v_variables[i]->fv); /* @@ -1185,11 +1201,13 @@ run_regression (const struct ccase *first, { if (v_variables[i]->type == ALPHA) { - design_matrix_set_categorical (X, row, v_variables[i], val); + design_matrix_set_categorical (X, row, + v_variables[i], val); } else if (v_variables[i]->type == NUMERIC) { - design_matrix_set_numeric (X, row, v_variables[i], val); + design_matrix_set_numeric (X, row, v_variables[i], + val); } } } @@ -1203,7 +1221,7 @@ 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.