X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=19aa0ee35c67a86a20846469783b71eae0d84136;hb=849f1db3053e27a2879542ffebddb55909ce26ae;hp=c10cc59e1f75409cea4bdd54153133024c0e1ff8;hpb=7ee429e606ed6e711cf8ddd10143e6e9e6bd0dd0;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index c10cc59e..19aa0ee3 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -22,7 +22,6 @@ #include #include -#include "regression-export.h" #include #include #include @@ -37,16 +36,17 @@ #include #include #include -#include #include #include #include #include #include -#include +#include #include #include +#include "xalloc.h" + #include "gettext.h" #define _(msgid) gettext (msgid) @@ -74,7 +74,6 @@ f, defaults, all; - export=custom; ^dependent=varlist; +save[sv_]=resid,pred; +method=enter. @@ -112,12 +111,6 @@ static const struct variable **v_variables; */ static size_t n_variables; -/* - File where the model will be saved if the EXPORT subcommand - is given. - */ -static struct file_handle *model_file; - static bool run_regression (struct casereader *, struct cmd_regression *, struct dataset *, pspp_linreg_cache **); @@ -155,7 +148,7 @@ reg_stats_r (pspp_linreg_cache * c) assert (c != NULL); rsq = c->ssm / c->sst; adjrsq = 1.0 - (1.0 - rsq) * (c->n_obs - 1.0) / (c->n_obs - c->n_indeps); - std_error = sqrt ((c->n_indeps - 1.0) / (c->n_obs - 1.0)); + std_error = sqrt (pspp_linreg_mse (c)); t = tab_create (n_cols, n_rows, 0); tab_dim (t, tab_natural_dimensions); tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1); @@ -184,21 +177,19 @@ reg_stats_coeff (pspp_linreg_cache * c) size_t j; int n_cols = 7; int n_rows; + int this_row; double t_stat; double pval; - double coeff; double std_err; double beta; const char *label; - char *tmp; + const struct variable *v; const union value *val; - const char *val_s; struct tab_table *t; assert (c != NULL); - tmp = xnmalloc (MAX_STRING, sizeof (*tmp)); - n_rows = c->n_coeffs + 2; + n_rows = c->n_coeffs + 3; t = tab_create (n_cols, n_rows, 0); tab_headers (t, 2, 0, 1, 0); @@ -214,22 +205,24 @@ 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; - tab_float (t, 2, 1, 0, coeff, 10, 2); + tab_float (t, 2, 1, 0, c->intercept, 10, 2); std_err = sqrt (gsl_matrix_get (c->cov, 0, 0)); tab_float (t, 3, 1, 0, std_err, 10, 2); - beta = coeff / c->depvar_std; - tab_float (t, 4, 1, 0, beta, 10, 2); - t_stat = coeff / std_err; + tab_float (t, 4, 1, 0, 0.0, 10, 2); + t_stat = c->intercept / std_err; tab_float (t, 5, 1, 0, t_stat, 10, 2); pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); tab_float (t, 6, 1, 0, pval, 10, 2); - for (j = 1; j <= c->n_indeps; j++) + for (j = 0; j < c->n_coeffs; j++) { + struct string tstr; + ds_init_empty (&tstr); + this_row = j + 2; + 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); + ds_put_cstr (&tstr, label); if (var_is_alpha (v)) { /* @@ -239,45 +232,44 @@ reg_stats_coeff (pspp_linreg_cache * c) */ val = pspp_coeff_get_value (c->coeff[j], v); - val_s = var_get_value_name (v, val); - strncat (tmp, val_s, MAX_STRING); + + var_append_value_name (v, val, &tstr); } - tab_text (t, 1, j + 1, TAB_CENTER, tmp); + tab_text (t, 1, this_row, TAB_CENTER, ds_cstr (&tstr)); /* Regression coefficients. */ - coeff = c->coeff[j]->estimate; - tab_float (t, 2, j + 1, 0, coeff, 10, 2); + tab_float (t, 2, this_row, 0, c->coeff[j]->estimate, 10, 2); /* Standard error of the coefficients. */ - std_err = sqrt (gsl_matrix_get (c->cov, j, j)); - tab_float (t, 3, j + 1, 0, std_err, 10, 2); + std_err = sqrt (gsl_matrix_get (c->cov, j + 1, j + 1)); + tab_float (t, 3, this_row, 0, std_err, 10, 2); /* - 'Standardized' coefficient, i.e., regression coefficient + Standardized coefficient, i.e., regression coefficient if all variables had unit variance. */ - beta = gsl_vector_get (c->indep_std, j); - beta *= coeff / c->depvar_std; - tab_float (t, 4, j + 1, 0, beta, 10, 2); + beta = pspp_coeff_get_sd (c->coeff[j]); + beta *= c->coeff[j]->estimate / c->depvar_std; + tab_float (t, 4, this_row, 0, beta, 10, 2); /* Test statistic for H0: coefficient is 0. */ - t_stat = coeff / std_err; - tab_float (t, 5, j + 1, 0, t_stat, 10, 2); + t_stat = c->coeff[j]->estimate / std_err; + tab_float (t, 5, this_row, 0, t_stat, 10, 2); /* P values for the test statistic above. */ 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_float (t, 6, this_row, 0, pval, 10, 2); + ds_destroy (&tstr); } tab_title (t, _("Coefficients")); tab_submit (t); - free (tmp); } /* @@ -289,7 +281,7 @@ reg_stats_anova (pspp_linreg_cache * c) int n_cols = 7; int n_rows = 4; const double msm = c->ssm / c->dfm; - const double mse = c->sse / c->dfe; + const double mse = pspp_linreg_mse (c); const double F = msm / mse; const double pval = gsl_cdf_fdist_Q (F, c->dfm, c->dfe); @@ -323,12 +315,11 @@ reg_stats_anova (pspp_linreg_cache * c) /* Degrees of freedom */ - tab_float (t, 3, 1, 0, c->dfm, 4, 0); - tab_float (t, 3, 2, 0, c->dfe, 4, 0); - tab_float (t, 3, 3, 0, c->dft, 4, 0); + tab_text (t, 3, 1, TAB_RIGHT | TAT_PRINTF, "%g", c->dfm); + tab_text (t, 3, 2, TAB_RIGHT | TAT_PRINTF, "%g", c->dfe); + tab_text (t, 3, 3, TAB_RIGHT | TAT_PRINTF, "%g", c->dft); /* Mean Squares */ - tab_float (t, 4, 1, TAB_RIGHT, msm, 8, 3); tab_float (t, 4, 2, TAB_RIGHT, mse, 8, 3); @@ -339,21 +330,25 @@ reg_stats_anova (pspp_linreg_cache * c) tab_title (t, _("ANOVA")); tab_submit (t); } + static void reg_stats_outs (pspp_linreg_cache * c) { assert (c != NULL); } + static void reg_stats_zpp (pspp_linreg_cache * c) { assert (c != NULL); } + static void reg_stats_label (pspp_linreg_cache * c) { assert (c != NULL); } + static void reg_stats_sha (pspp_linreg_cache * c) { @@ -393,7 +388,7 @@ reg_stats_bcov (pspp_linreg_cache * c) tab_vline (t, TAL_0, 1, 0, 0); tab_text (t, 0, 0, TAB_CENTER | TAT_TITLE, _("Model")); tab_text (t, 1, 1, TAB_CENTER | TAT_TITLE, _("Covariances")); - for (i = 1; i < c->n_coeffs; i++) + for (i = 0; i < c->n_coeffs; i++) { const struct variable *v = pspp_coeff_get_var (c->coeff[i], 0); label = var_to_string (v); @@ -636,16 +631,16 @@ 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[VAR_NAME_LEN], + const char prefix[VAR_NAME_LEN]) { int i = 1; - snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); + snprintf (name, VAR_NAME_LEN, "%s%d", prefix, i); while (!try_name (dict, name)) { i++; - snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); + snprintf (name, VAR_NAME_LEN, "%s%d", prefix, i); } } @@ -655,7 +650,7 @@ reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f, { struct dictionary *dict = dataset_dict (ds); static int trns_index = 1; - char name[LONG_NAME_LEN]; + char name[VAR_NAME_LEN]; struct variable *new_var; struct reg_trns *t = NULL; @@ -670,7 +665,6 @@ reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f, add_transformation (ds, f, regression_trns_free, t); trns_index++; } - static void subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) { @@ -720,226 +714,6 @@ subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) } } -static int -reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) -{ - int i; - - for (i = 0; i < n_vars; i++) - { - if (v == varlist[i]) - { - return 1; - } - } - return 0; -} - -static void -reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) -{ - int i; - int n_vars = 0; - struct variable **varlist; - - 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. */ - { - 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", - var_get_name (v)); - varlist[n_vars] = (struct variable *) v; - n_vars++; - } - } - } - fprintf (fp, "int n_vars = %d;\n\t", n_vars); - fprintf (fp, "struct pspp_reg_categorical_variable *varlist[%d] = {", - n_vars); - for (i = 0; i < n_vars - 1; i++) - { - fprintf (fp, "&%s,\n\t\t", var_get_name (varlist[i])); - } - fprintf (fp, "&%s};\n\t", var_get_name (varlist[i])); - - for (i = 0; i < n_vars; i++) - { - 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 < n_categories; j++) - { - 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); -} - -static void -reg_print_depvars (FILE * fp, pspp_linreg_cache * c) -{ - int i; - 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_coeff_get_var (coeff, 0); - 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", var_get_name (v)); -} -static void -reg_print_getvar (FILE * fp, pspp_linreg_cache * c) -{ - fprintf (fp, "static int\npspp_reg_getvar (char *v_name)\n{\n\t"); - fprintf (fp, "int i;\n\tint n_vars = %d;\n\t", c->n_indeps); - reg_print_depvars (fp, c); - fprintf (fp, "for (i = 0; i < n_vars; i++)\n\t{\n\t\t"); - fprintf (fp, - "if (strncmp (v_name, model_depvars[i], PSPP_REG_MAXLEN) == 0)\n\t\t{\n\t\t\t"); - fprintf (fp, "return i;\n\t\t}\n\t}\n}\n"); -} -static int -reg_has_categorical (pspp_linreg_cache * c) -{ - int i; - const struct variable *v; - - for (i = 1; i < c->n_coeffs; i++) - { - v = pspp_coeff_get_var (c->coeff[i], 0); - if (var_is_alpha (v)) - return 1; - } - return 0; -} - -static void -subcommand_export (int export, pspp_linreg_cache * c) -{ - FILE *fp; - size_t i; - size_t j; - int n_quantiles = 100; - double tmp; - struct pspp_coeff *coeff; - - if (export) - { - assert (c != NULL); - assert (model_file != NULL); - fp = fopen (fh_get_file_name (model_file), "w"); - assert (fp != NULL); - fprintf (fp, "%s", reg_preamble); - reg_print_getvar (fp, c); - if (reg_has_categorical (c)) - { - reg_print_categorical_encoding (fp, c); - } - fprintf (fp, "%s", reg_export_t_quantiles_1); - for (i = 0; i < n_quantiles - 1; i++) - { - tmp = 0.5 + 0.005 * (double) i; - fprintf (fp, "%.15e,\n\t\t", - gsl_cdf_tdist_Pinv (tmp, c->n_obs - c->n_indeps)); - } - fprintf (fp, "%.15e};\n\t", - gsl_cdf_tdist_Pinv (.9995, c->n_obs - c->n_indeps)); - fprintf (fp, "%s", reg_export_t_quantiles_2); - fprintf (fp, "%s", reg_mean_cmt); - fprintf (fp, "double\npspp_reg_estimate (const double *var_vals,"); - fprintf (fp, "const char *var_names[])\n{\n\t"); - fprintf (fp, "double model_coeffs[%d] = {", c->n_indeps); - for (i = 1; i < c->n_indeps; i++) - { - coeff = c->coeff[i]; - fprintf (fp, "%.15e,\n\t\t", coeff->estimate); - } - coeff = c->coeff[i]; - fprintf (fp, "%.15e};\n\t", coeff->estimate); - coeff = c->coeff[0]; - 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); - fprintf (fp, "const double cov[%d][%d] = {\n\t", c->n_coeffs, - c->n_coeffs); - for (i = 0; i < c->cov->size1 - 1; i++) - { - fprintf (fp, "{"); - for (j = 0; j < c->cov->size2 - 1; j++) - { - fprintf (fp, "%.15e, ", gsl_matrix_get (c->cov, i, j)); - } - fprintf (fp, "%.15e},\n\t", gsl_matrix_get (c->cov, i, j)); - } - fprintf (fp, "{"); - for (j = 0; j < c->cov->size2 - 1; j++) - { - fprintf (fp, "%.15e, ", - gsl_matrix_get (c->cov, c->cov->size1 - 1, j)); - } - fprintf (fp, "%.15e}\n\t", - gsl_matrix_get (c->cov, c->cov->size1 - 1, c->cov->size2 - 1)); - fprintf (fp, "};\n\tint n_vars = %d;\n\tint i;\n\tint j;\n\t", - c->n_indeps); - fprintf (fp, "double unshuffled_vals[%d];\n\t", c->n_indeps); - fprintf (fp, "%s", reg_variance); - fprintf (fp, "%s", reg_export_confidence_interval); - tmp = c->mse * c->mse; - fprintf (fp, "%s %.15e", reg_export_prediction_interval_1, tmp); - fprintf (fp, "%s %.15e", reg_export_prediction_interval_2, tmp); - fprintf (fp, "%s", reg_export_prediction_interval_3); - fclose (fp); - fp = fopen ("pspp_model_reg.h", "w"); - fprintf (fp, "%s", reg_header); - fclose (fp); - } -} - -static int -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, '(')) - return 0; - - if (lex_match (lexer, '*')) - model_file = NULL; - else - { - model_file = fh_parse (lexer, FH_REF_FILE); - if (model_file == NULL) - return 0; - } - - if (!lex_force_match (lexer, ')')) - return 0; - - return 1; -} - int cmd_regression (struct lexer *lexer, struct dataset *ds) { @@ -950,7 +724,9 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) size_t i; if (!parse_regression (lexer, ds, &cmd, NULL)) - return CMD_FAILURE; + { + return CMD_FAILURE; + } models = xnmalloc (cmd.n_dependent, sizeof *models); for (i = 0; i < cmd.n_dependent; i++) @@ -968,6 +744,8 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) subcommand_save (ds, cmd.sbc_save, models); free (v_variables); free (models); + free_regression (&cmd); + return ok ? CMD_SUCCESS : CMD_FAILURE; } @@ -1019,7 +797,7 @@ identify_indep_vars (const struct variable **indep_vars, for (i = 0; i < n_variables; i++) if (!is_depvar (i, depvar)) indep_vars[n_indep_vars++] = v_variables[i]; - if ((n_indep_vars < 2) && is_depvar (0, depvar)) + if ((n_indep_vars < 1) && is_depvar (0, depvar)) { /* There is only one independent variable, and it is the same @@ -1079,10 +857,8 @@ prepare_categories (struct casereader *input, 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); + c->coeff = xnmalloc (dm->m->size2, sizeof (*c->coeff)); + pspp_coeff_init (c->coeff, dm); } /* @@ -1111,8 +887,8 @@ compute_moments (pspp_linreg_cache * c, struct moments_var *mom, { 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)); + pspp_linreg_set_indep_variable_mean (c, (mom + j)->v, mean); + pspp_linreg_set_indep_variable_sd (c, (mom + j)->v, sqrt (variance)); } } } @@ -1136,14 +912,16 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, assert (models != NULL); if (!casereader_peek (input, 0, &c)) - return true; + { + casereader_destroy (input); + return true; + } output_split_file_values (ds, &c); case_destroy (&c); if (!v_variables) { - dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, - 1u << DC_SYSTEM); + dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, 0); } for (i = 0; i < cmd->n_dependent; i++) @@ -1196,8 +974,6 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, 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 = dep_var; /* For large data sets, use QR decomposition. @@ -1234,13 +1010,11 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, /* 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); + pspp_linreg ((const gsl_vector *) Y, X, &lopts, models[k]); if (!taint_has_tainted_successor (casereader_get_taint (input))) { subcommand_statistics (cmd->a_statistics, models[k]); - subcommand_export (cmd->sbc_export, models[k]); } gsl_vector_free (Y);