X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=src%2Flanguage%2Fstats%2Fregression.q;h=c779ae1e43a8e407c353728887843e9d3fcd9132;hb=c03a42996cfd422728e85631682ed13a8c298f2a;hp=947f82854663e96d3adf1132cfe79fb87fcd02cf;hpb=e40c90b1b6dbd03ce58046ada7f4ddb5a6b4b354;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 947f8285..c779ae1e 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -118,7 +118,8 @@ static struct file_handle *model_file; 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 +230,7 @@ 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 +239,7 @@ 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); } @@ -545,7 +546,7 @@ regression_trns_free (void *t_) */ static int regression_trns_pred_proc (void *t_, struct ccase *c, - casenum_t case_idx UNUSED) + casenumber case_idx UNUSED) { size_t i; size_t n_vals; @@ -565,12 +566,12 @@ regression_trns_pred_proc (void *t_, struct ccase *c, 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); @@ -584,7 +585,7 @@ regression_trns_pred_proc (void *t_, struct ccase *c, */ static int regression_trns_resid_proc (void *t_, struct ccase *c, - casenum_t case_idx UNUSED) + casenumber case_idx UNUSED) { size_t i; size_t n_vals; @@ -605,14 +606,14 @@ regression_trns_resid_proc (void *t_, struct ccase *c, 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); @@ -621,32 +622,35 @@ regression_trns_resid_proc (void *t_, struct ccase *c, } /* - 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 (dataset_dict (current_dataset), 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; @@ -656,15 +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 (dataset_dict (current_dataset), 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 (current_dataset, 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; @@ -690,12 +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); } } @@ -709,6 +714,7 @@ subcommand_save (int save, pspp_linreg_cache ** models) } } } + static int reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) { @@ -716,37 +722,34 @@ 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++; } @@ -757,23 +760,28 @@ 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); @@ -791,11 +799,11 @@ 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) @@ -817,10 +825,8 @@ 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; } @@ -907,38 +913,39 @@ 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 (current_dataset, 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; @@ -950,14 +957,7 @@ cmd_regression (void) 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 true; - - return false; + return v == v_variables[k]; } /* @@ -972,14 +972,14 @@ 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)) { if (!is_missing_case[row]) { @@ -996,18 +996,20 @@ 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 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 (dataset_dict (current_dataset), 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 (dataset_dict (current_dataset), &v_variables, &n_variables, PV_NONE)) + if (!parse_variables (lexer, dict, &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; @@ -1061,7 +1063,7 @@ 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. */ @@ -1089,7 +1091,7 @@ coeff_init (pspp_linreg_cache * c, struct design_matrix *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. */ @@ -1113,11 +1115,11 @@ 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 (dataset_dict (current_dataset), &v_variables, &n_variables, + dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, 1u << DC_SYSTEM); } @@ -1125,7 +1127,7 @@ 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; @@ -1176,7 +1178,7 @@ 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. */ { @@ -1188,7 +1190,7 @@ 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 @@ -1199,19 +1201,19 @@ 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++; }