X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=e10b89623dbe1c10cec387e9579b7955b47fd1d3;hb=f4810d3c8656b3b3ab26303d2dae70fc361db7fb;hp=1b35970366b0a1bd449b40d66913e20f03bb0bcc;hpb=3816248a008a4af75aac6319d0c9929cb7ff679e;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 1b359703..e10b8962 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 @@ -28,7 +27,6 @@ #include "regression-export.h" #include #include -#include #include #include #include @@ -46,6 +44,7 @@ #include #include #include +#include #include #include "gettext.h" @@ -83,6 +82,15 @@ /* (functions) */ static struct cmd_regression cmd; +/* + Moments for each of the variables used. + */ +struct moments_var +{ + struct moments1 *m; + const struct variable *v; +}; + /* Linear regression models. */ static pspp_linreg_cache **models = NULL; @@ -99,7 +107,7 @@ struct reg_trns /* Variables used (both explanatory and response). */ -static struct variable **v_variables; +static const struct variable **v_variables; /* Number of variables. @@ -118,7 +126,7 @@ 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 *); /* @@ -230,7 +238,7 @@ 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. @@ -239,7 +247,7 @@ 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); } @@ -270,7 +278,9 @@ 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")); @@ -554,7 +564,7 @@ regression_trns_pred_proc (void *t_, struct ccase *c, pspp_linreg_cache *model; union value *output = NULL; const union value **vals = NULL; - struct variable **vars = NULL; + const struct variable **vars = NULL; assert (trns != NULL); model = trns->c; @@ -566,12 +576,12 @@ 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); @@ -594,7 +604,7 @@ regression_trns_resid_proc (void *t_, struct ccase *c, union value *output = NULL; const union value **vals = NULL; const union value *obs = NULL; - struct variable **vars = NULL; + const struct variable **vars = NULL; assert (trns != NULL); model = trns->c; @@ -606,14 +616,14 @@ 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); @@ -634,7 +644,8 @@ try_name (const struct dictionary *dict, const char *name) } static void -reg_get_name (const struct dictionary *dict, 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; @@ -709,8 +720,10 @@ subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) { for (lc = models; lc < models + cmd.n_dependent; lc++) { - assert (*lc != NULL); - pspp_linreg_cache_free (*lc); + if (*lc != NULL) + { + pspp_linreg_cache_free (*lc); + } } } } @@ -722,7 +735,7 @@ 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; } @@ -734,26 +747,22 @@ 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++; } @@ -764,23 +773,26 @@ 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); + int n_categories = cat_get_n_categories (varlist[i]); + int 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 < varlist[i]->obs_vals->n_categories; j++) + 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])); + const 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); @@ -798,11 +810,11 @@ 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) @@ -824,10 +836,8 @@ 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; } @@ -916,7 +926,8 @@ subcommand_export (int export, pspp_linreg_cache * c) } static int -regression_custom_export (struct lexer *lexer, struct dataset *ds UNUSED, 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 (lexer, '(')) @@ -940,10 +951,16 @@ regression_custom_export (struct lexer *lexer, struct dataset *ds UNUSED, struct int cmd_regression (struct lexer *lexer, struct dataset *ds) { + size_t i; + if (!parse_regression (lexer, ds, &cmd, NULL)) return CMD_FAILURE; models = xnmalloc (cmd.n_dependent, sizeof *models); + for (i = 0; i < cmd.n_dependent; i++) + { + models[i] = NULL; + } if (!multipass_procedure_with_splits (ds, run_regression, &cmd)) return CMD_CASCADING_FAILURE; subcommand_save (ds, cmd.sbc_save, models); @@ -958,36 +975,36 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) 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]; } /* Mark missing cases. Return the number of non-missing cases. + Compute the first two moments. */ static size_t -mark_missing_cases (const struct casefile *cf, struct variable *v, - int *is_missing_case, double n_data) +mark_missing_cases (const struct casefile *cf, const struct variable *v, + int *is_missing_case, double n_data, + struct moments_var *mom) { struct casereader *r; struct ccase c; size_t row; const union value *val; + double w = 1.0; 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); + if (mom != NULL) + { + moments1_add (mom->m, val->f, w); + } 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]) { @@ -1004,7 +1021,7 @@ mark_missing_cases (const struct casefile *cf, struct variable *v, /* Parser for the variables sub command */ static int -regression_custom_variables (struct lexer *lexer, struct dataset *ds, +regression_custom_variables (struct lexer *lexer, struct dataset *ds, struct cmd_regression *cmd UNUSED, void *aux UNUSED) { @@ -1012,12 +1029,14 @@ regression_custom_variables (struct lexer *lexer, struct dataset *ds, lex_match (lexer, '='); - if ((lex_token (lexer) != T_ID || dict_lookup_var (dict, lex_tokid (lexer)) == NULL) + if ((lex_token (lexer) != T_ID + || dict_lookup_var (dict, lex_tokid (lexer)) == NULL) && lex_token (lexer) != T_ALL) return 2; - if (!parse_variables (lexer, dict, &v_variables, &n_variables, PV_NONE)) + if (!parse_variables_const + (lexer, dict, &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; @@ -1047,7 +1066,7 @@ get_n_indep (const struct variable *v) } i++; } - return result; + return (result == 0) ? 1 : result; } /* @@ -1057,8 +1076,9 @@ get_n_indep (const struct variable *v) */ static int prepare_data (int n_data, int is_missing_case[], - struct variable **indep_vars, - struct variable *depvar, const struct casefile *cf) + const struct variable **indep_vars, + const struct variable *depvar, const struct casefile *cf, + struct moments_var *mom) { int i; int j; @@ -1067,24 +1087,30 @@ prepare_data (int n_data, int is_missing_case[], j = 0; for (i = 0; i < n_variables; i++) { - if (!is_depvar (i, depvar)) + /* + The second condition ensures the program will run even if + there is only one variable to act as both explanatory and + response. + */ + if ((!is_depvar (i, depvar)) || (n_variables == 1)) { 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 + /* Make a place to hold the binary vectors 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); + mark_missing_cases (cf, v_variables[i], is_missing_case, n_data, + mom + i); } } /* Mark missing cases for the dependent variable. */ - n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data); + n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data, NULL); return n_data; } @@ -1097,9 +1123,42 @@ coeff_init (pspp_linreg_cache * c, struct design_matrix *dm) pspp_coeff_init (c->coeff + 1, dm); } +/* + Put the moments in the linreg cache. + */ +static void +compute_moments (pspp_linreg_cache * c, struct moments_var *mom, + struct design_matrix *dm, size_t n) +{ + size_t i; + size_t j; + double weight; + double mean; + double variance; + double skewness; + double kurtosis; + /* + Scan the variable names in the columns of the design matrix. + When we find the variable we need, insert its mean in the cache. + */ + for (i = 0; i < dm->m->size2; i++) + { + for (j = 0; j < n; j++) + { + if (design_matrix_col_to_var (dm, i) == (mom + j)->v) + { + moments1_calculate ((mom + j)->m, &weight, &mean, &variance, + &skewness, &kurtosis); + gsl_vector_set (c->indep_means, i, mean); + gsl_vector_set (c->indep_std, i, sqrt (variance)); + } + } + } +} static bool run_regression (const struct ccase *first, - const struct casefile *cf, void *cmd_ UNUSED, const struct dataset *ds) + const struct casefile *cf, void *cmd_ UNUSED, + const struct dataset *ds) { size_t i; size_t n_data = 0; /* Number of valide cases. */ @@ -1115,8 +1174,9 @@ run_regression (const struct ccase *first, const union value *val; struct casereader *r; struct ccase c; - struct variable **indep_vars; + const struct variable **indep_vars; struct design_matrix *X; + struct moments_var *mom; gsl_vector *Y; pspp_linreg_opts lopts; @@ -1135,7 +1195,7 @@ 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; @@ -1144,7 +1204,12 @@ run_regression (const struct ccase *first, } is_missing_case = xnmalloc (n_cases, sizeof (*is_missing_case)); - + mom = xnmalloc (n_variables, sizeof (*mom)); + for (i = 0; i < n_variables; i++) + { + (mom + i)->m = moments1_create (MOMENT_VARIANCE); + (mom + i)->v = v_variables[i]; + } lopts.get_depvar_mean_std = 1; for (k = 0; k < cmd.n_dependent; k++) @@ -1160,93 +1225,106 @@ run_regression (const struct ccase *first, } 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); - - X = - design_matrix_create (n_indep, (const struct variable **) indep_vars, - n_data); - for (i = 0; i < X->m->size2; i++) + (const struct casefile *) cf, mom); + if ((n_data > 0) && (n_indep > 0)) { - lopts.get_indep_mean_std[i] = 1; - } - models[k] = pspp_linreg_cache_alloc (X->m->size1, X->m->size2); - models[k]->indep_means = gsl_vector_alloc (X->m->size2); - models[k]->indep_std = gsl_vector_alloc (X->m->size2); - models[k]->depvar = (const struct variable *) cmd.v_dependent[k]; - /* - For large data sets, use QR decomposition. - */ - if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA) - { - models[k]->method = PSPP_LINREG_SVD; - } + Y = gsl_vector_alloc (n_data); + X = + design_matrix_create (n_indep, + (const struct variable **) indep_vars, + n_data); + for (i = 0; i < X->m->size2; i++) + { + lopts.get_indep_mean_std[i] = 1; + } + models[k] = pspp_linreg_cache_alloc (X->m->size1, X->m->size2); + models[k]->indep_means = gsl_vector_alloc (X->m->size2); + models[k]->indep_std = gsl_vector_alloc (X->m->size2); + models[k]->depvar = (const struct variable *) cmd.v_dependent[k]; + /* + For large data sets, use QR decomposition. + */ + if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA) + { + models[k]->method = PSPP_LINREG_SVD; + } - /* - The second pass fills the design matrix. - */ - row = 0; - for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c); - case_destroy (&c)) - /* Iterate over the cases. */ - { - case_num = casereader_cnum (r) - 1; - if (!is_missing_case[case_num]) + /* + The second pass fills the design matrix. + */ + row = 0; + for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c); + case_destroy (&c)) + /* Iterate over the cases. */ { - for (i = 0; i < n_variables; ++i) /* Iterate over the - variables for the - current case. - */ + case_num = casereader_cnum (r) - 1; + if (!is_missing_case[case_num]) { - val = case_data (&c, v_variables[i]->fv); - /* - Independent/dependent variable separation. The - 'variables' subcommand specifies a varlist which contains - both dependent and independent variables. The dependent - variables are specified with the 'dependent' - subcommand, and maybe also in the 'variables' subcommand. - We need to separate the two. - */ - if (!is_depvar (i, cmd.v_dependent[k])) + for (i = 0; i < n_variables; ++i) /* Iterate over the + variables for the + current case. + */ { - if (v_variables[i]->type == ALPHA) + val = case_data (&c, v_variables[i]); + /* + Independent/dependent variable separation. The + 'variables' subcommand specifies a varlist which contains + both dependent and independent variables. The dependent + variables are specified with the 'dependent' + subcommand, and maybe also in the 'variables' subcommand. + We need to separate the two. + */ + if (!is_depvar (i, cmd.v_dependent[k])) { - design_matrix_set_categorical (X, row, + if (var_is_alpha (v_variables[i])) + { + design_matrix_set_categorical (X, row, + v_variables[i], + val); + } + else + { + design_matrix_set_numeric (X, row, v_variables[i], val); - } - else if (v_variables[i]->type == NUMERIC) - { - design_matrix_set_numeric (X, row, v_variables[i], - val); + } } } + val = case_data (&c, cmd.v_dependent[k]); + gsl_vector_set (Y, row, val->f); + row++; } - val = case_data (&c, cmd.v_dependent[k]->fv); - gsl_vector_set (Y, row, val->f); - row++; } - } - /* - Now that we know the number of coefficients, allocate space - and store pointers to the variables that correspond to the - coefficients. - */ - coeff_init (models[k], X); + /* + Now that we know the number of coefficients, allocate space + and store pointers to the variables that correspond to the + coefficients. + */ + coeff_init (models[k], X); - /* - Find the least-squares estimates and other statistics. - */ - pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]); - subcommand_statistics (cmd.a_statistics, models[k]); - subcommand_export (cmd.sbc_export, models[k]); - - gsl_vector_free (Y); - design_matrix_destroy (X); - free (indep_vars); - free (lopts.get_indep_mean_std); - casereader_destroy (r); + /* + Find the least-squares estimates and other statistics. + */ + pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]); + compute_moments (models[k], mom, X, n_variables); + subcommand_statistics (cmd.a_statistics, models[k]); + subcommand_export (cmd.sbc_export, models[k]); + + gsl_vector_free (Y); + design_matrix_destroy (X); + free (indep_vars); + free (lopts.get_indep_mean_std); + casereader_destroy (r); + } + else + { + msg (SE, gettext ("No valid data found. This command was skipped.")); + } } - + for (i = 0; i < n_variables; i++) + { + moments1_destroy ((mom + i)->m); + } + free (mom); free (is_missing_case); return true;