X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=2c259d0f904c1834c7d7e1614fe4f47084bab5ee;hb=2cf38ce51a9f34961d68a75e0b312a591b5c9abf;hp=9c3d1457c7e751b3d298341f16c5b2660979d7f6;hpb=4bb4de2196cae312aeb7223e8b08af3235675607;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 9c3d1457..2c259d0f 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -1,21 +1,18 @@ -/* PSPP - linear regression. - Copyright (C) 2005 Free Software Foundation, Inc. - Written by Jason H Stover . +/* PSPP - a program for statistical analysis. + Copyright (C) 2005, 2009 Free Software Foundation, Inc. - This program is free software; you can redistribute it and/or - modify it under the terms of the GNU General Public License as - published by the Free Software Foundation; either version 2 of the - License, or (at your option) any later version. + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with this program. If not, see . */ #include @@ -25,10 +22,9 @@ #include #include -#include "regression-export.h" #include -#include -#include +#include +#include #include #include #include @@ -40,15 +36,19 @@ #include #include #include -#include #include #include +#include #include -#include -#include +#include +#include +#include #include +#include "xalloc.h" + #include "gettext.h" +#define _(msgid) gettext (msgid) #define REG_LARGE_DATA 1000 @@ -57,34 +57,39 @@ /* (specification) "REGRESSION" (regression_): *variables=custom; - statistics[st_]=r, - coeff, - anova, - outs, - zpp, - label, - sha, - ci, - bcov, - ses, - xtx, - collin, - tol, - selection, - f, - defaults, - all; - export=custom; + +statistics[st_]=r, + coeff, + anova, + outs, + zpp, + label, + sha, + ci, + bcov, + ses, + xtx, + collin, + tol, + selection, + f, + defaults, + all; ^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; +/* + Moments for each of the variables used. + */ +struct moments_var +{ + struct moments1 *m; + const struct variable *v; +}; /* Transformations for saving predicted values @@ -99,28 +104,17 @@ struct reg_trns /* Variables used (both explanatory and response). */ -static struct variable **v_variables; +static const struct variable **v_variables; /* Number of variables. */ static size_t n_variables; -/* - File where the model will be saved if the EXPORT subcommand - is given. - */ -struct file_handle *model_file; +static bool run_regression (struct casereader *, struct cmd_regression *, + struct dataset *, pspp_linreg_cache **); /* - Return value for the procedure. - */ -int pspp_reg_rc = CMD_SUCCESS; - -static bool run_regression (const struct ccase *, - const struct casefile *, void *); - -/* STATISTICS subcommand output functions. */ static void reg_stats_r (pspp_linreg_cache *); @@ -154,9 +148,9 @@ 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_dim (t, tab_natural_dimensions, NULL); tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1); tab_hline (t, TAL_2, 0, n_cols - 1, 1); tab_vline (t, TAL_2, 2, 0, n_rows - 1); @@ -166,10 +160,10 @@ reg_stats_r (pspp_linreg_cache * c) tab_text (t, 2, 0, TAB_CENTER | TAT_TITLE, _("R Square")); tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Adjusted R Square")); tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Std. Error of the Estimate")); - tab_float (t, 1, 1, TAB_RIGHT, sqrt (rsq), 10, 2); - tab_float (t, 2, 1, TAB_RIGHT, rsq, 10, 2); - tab_float (t, 3, 1, TAB_RIGHT, adjrsq, 10, 2); - tab_float (t, 4, 1, TAB_RIGHT, std_error, 10, 2); + tab_double (t, 1, 1, TAB_RIGHT, sqrt (rsq), NULL); + tab_double (t, 2, 1, TAB_RIGHT, rsq, NULL); + tab_double (t, 3, 1, TAB_RIGHT, adjrsq, NULL); + tab_double (t, 4, 1, TAB_RIGHT, std_error, NULL); tab_title (t, _("Model Summary")); tab_submit (t); } @@ -183,25 +177,23 @@ 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); - tab_dim (t, tab_natural_dimensions); + tab_dim (t, tab_natural_dimensions, NULL); tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1); tab_hline (t, TAL_2, 0, n_cols - 1, 1); tab_vline (t, TAL_2, 2, 0, n_rows - 1); @@ -213,23 +205,25 @@ 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_double (t, 2, 1, 0, c->intercept, NULL); 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, 5, 1, 0, t_stat, 10, 2); + tab_double (t, 3, 1, 0, std_err, NULL); + tab_double (t, 4, 1, 0, 0.0, NULL); + t_stat = c->intercept / std_err; + tab_double (t, 5, 1, 0, t_stat, NULL); 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++) + tab_double (t, 6, 1, 0, pval, NULL); + for (j = 0; j < c->n_coeffs; j++) { - v = pspp_linreg_coeff_get_var (c->coeff[j], 0); + 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); - if (v->type == ALPHA) + ds_put_cstr (&tstr, label); + if (var_is_alpha (v)) { /* Append the value associated with this coefficient. @@ -237,44 +231,45 @@ reg_stats_coeff (pspp_linreg_cache * c) for that value. */ - val = pspp_linreg_coeff_get_value (c->coeff[j], v); - val_s = value_to_string (val, v); - strncat (tmp, val_s, MAX_STRING); + val = pspp_coeff_get_value (c->coeff[j], v); + + 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_double (t, 2, this_row, 0, c->coeff[j]->estimate, NULL); /* 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_double (t, 3, this_row, 0, std_err, NULL); /* - '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_double (t, 4, this_row, 0, beta, NULL); /* 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_double (t, 5, this_row, 0, t_stat, NULL); /* P values for the test statistic above. */ - pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); - tab_float (t, 6, j + 1, 0, pval, 10, 2); + pval = + 2 * gsl_cdf_tdist_Q (fabs (t_stat), + (double) (c->n_obs - c->n_coeffs)); + tab_double (t, 6, this_row, 0, pval, NULL); + ds_destroy (&tstr); } tab_title (t, _("Coefficients")); tab_submit (t); - free (tmp); } /* @@ -286,7 +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); @@ -295,7 +290,7 @@ reg_stats_anova (pspp_linreg_cache * c) assert (c != NULL); t = tab_create (n_cols, n_rows, 0); tab_headers (t, 2, 0, 1, 0); - tab_dim (t, tab_natural_dimensions); + tab_dim (t, tab_natural_dimensions, NULL); tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1); @@ -314,43 +309,46 @@ reg_stats_anova (pspp_linreg_cache * c) tab_text (t, 1, 3, TAB_LEFT | TAT_TITLE, _("Total")); /* Sums of Squares */ - tab_float (t, 2, 1, 0, c->ssm, 10, 2); - tab_float (t, 2, 3, 0, c->sst, 10, 2); - tab_float (t, 2, 2, 0, c->sse, 10, 2); + tab_double (t, 2, 1, 0, c->ssm, NULL); + tab_double (t, 2, 3, 0, c->sst, NULL); + tab_double (t, 2, 2, 0, c->sse, NULL); /* 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_format (t, 3, 1, TAB_RIGHT, "%g", c->dfm); + tab_text_format (t, 3, 2, TAB_RIGHT, "%g", c->dfe); + tab_text_format (t, 3, 3, TAB_RIGHT, "%g", c->dft); /* Mean Squares */ + tab_double (t, 4, 1, TAB_RIGHT, msm, NULL); + tab_double (t, 4, 2, TAB_RIGHT, mse, NULL); - tab_float (t, 4, 1, TAB_RIGHT, msm, 8, 3); - tab_float (t, 4, 2, TAB_RIGHT, mse, 8, 3); + tab_double (t, 5, 1, 0, F, NULL); - tab_float (t, 5, 1, 0, F, 8, 3); - - tab_float (t, 6, 1, 0, pval, 8, 3); + tab_double (t, 6, 1, 0, pval, NULL); 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) { @@ -383,16 +381,16 @@ reg_stats_bcov (pspp_linreg_cache * c) n_rows = 2 * (c->n_indeps + 1); t = tab_create (n_cols, n_rows, 0); tab_headers (t, 2, 0, 1, 0); - tab_dim (t, tab_natural_dimensions); + tab_dim (t, tab_natural_dimensions, NULL); tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1); tab_hline (t, TAL_2, 0, n_cols - 1, 1); tab_vline (t, TAL_2, 2, 0, n_rows - 1); 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_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); @@ -400,8 +398,8 @@ reg_stats_bcov (pspp_linreg_cache * c) { col = (i <= k) ? k : i; row = (i <= k) ? i : k; - tab_float (t, k + 2, i, TAB_CENTER, - gsl_matrix_get (c->cov, row, col), 8, 3); + tab_double (t, k + 2, i, TAB_CENTER, + gsl_matrix_get (c->cov, row, col), NULL); } } tab_title (t, _("Coefficient Correlations")); @@ -446,8 +444,8 @@ statistics_keyword_output (void (*function) (pspp_linreg_cache *), static void subcommand_statistics (int *keywords, pspp_linreg_cache * c) { - /* - The order here must match the order in which the STATISTICS + /* + The order here must match the order in which the STATISTICS keywords appear in the specification section above. */ enum @@ -544,7 +542,8 @@ 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; @@ -552,7 +551,7 @@ regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) 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; @@ -564,12 +563,12 @@ 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); - assert (output != NULL); + *c = case_unshare (*c); + output = case_data_rw (*c, model->pred); 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 +581,8 @@ 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; @@ -591,7 +591,7 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) 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; @@ -603,14 +603,15 @@ 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); + *c = case_unshare (*c); + 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); @@ -618,35 +619,39 @@ regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) return TRNS_CONTINUE; } -/* - 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[VAR_NAME_LEN], + const char prefix[VAR_NAME_LEN]) { int i = 1; - snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); - while (!try_name (name)) + 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); } } + 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]; + char name[VAR_NAME_LEN]; struct variable *new_var; struct reg_trns *t = NULL; @@ -654,15 +659,15 @@ 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; @@ -684,17 +689,21 @@ subcommand_save (int save, pspp_linreg_cache ** models) for (lc = models; lc < models + cmd.n_dependent; lc++) { - assert (*lc != NULL); - assert ((*lc)->depvar != NULL); - if (cmd.a_save[REGRESSION_SV_RESID]) + if (*lc != NULL) { - 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); + if ((*lc)->depvar != NULL) + { + if (cmd.a_save[REGRESSION_SV_RESID]) + { + reg_save_var (ds, "RES", regression_trns_resid_proc, *lc, + &(*lc)->resid, n_trns); + } + if (cmd.a_save[REGRESSION_SV_PRED]) + { + reg_save_var (ds, "PRED", regression_trns_pred_proc, *lc, + &(*lc)->pred, n_trns); + } + } } } } @@ -702,311 +711,76 @@ subcommand_save (int save, pspp_linreg_cache ** models) { for (lc = models; lc < models + cmd.n_dependent; lc++) { - assert (*lc != NULL); - pspp_linreg_cache_free (*lc); - } - } -} -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->index == varlist[i]->index) - { - 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_linreg_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_linreg_coeff_get_var (coeff, 0); - if (v->type == ALPHA) - { - if (!reg_inserted (v, varlist, n_vars)) + if (*lc != NULL) { - fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t", - v->name); - varlist[n_vars] = (struct variable *) v; - n_vars++; + pspp_linreg_cache_free (*lc); } } } - 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", varlist[i]->name); - } - fprintf (fp, "&%s};\n\t", varlist[i]->name); - - 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++) - { - 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])); - } - } - fprintf (fp, "%s", reg_export_categorical_encode_2); -} - -static void -reg_print_depvars (FILE * fp, pspp_linreg_cache * c) -{ - int i; - struct pspp_linreg_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); - fprintf (fp, "\"%s\",\n\t\t", v->name); - } - coeff = c->coeff[i]; - v = pspp_linreg_coeff_get_var (coeff, 0); - fprintf (fp, "\"%s\"};\n\t", v->name); } -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_linreg_coeff_get_var (c->coeff[i], 0); - if (v->type == ALPHA) - { - return 1; - } - } - return 0; -} - -static void -subcommand_export (int export, pspp_linreg_cache * c) +int +cmd_regression (struct lexer *lexer, struct dataset *ds) { - FILE *fp; + struct casegrouper *grouper; + struct casereader *group; + pspp_linreg_cache **models; + bool ok; size_t i; - size_t j; - int n_quantiles = 100; - double increment; - double tmp; - struct pspp_linreg_coeff *coeff; - if (export) + if (!parse_regression (lexer, ds, &cmd, NULL)) { - 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); - increment = 0.5 / (double) increment; - 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); + return CMD_FAILURE; } -} -static int -regression_custom_export (struct cmd_regression *cmd UNUSED) -{ - /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */ - if (!lex_force_match ('(')) - return 0; - if (lex_match ('*')) - model_file = NULL; - else + models = xnmalloc (cmd.n_dependent, sizeof *models); + for (i = 0; i < cmd.n_dependent; i++) { - model_file = fh_parse (FH_REF_FILE); - if (model_file == NULL) - return 0; + models[i] = NULL; } - if (!lex_force_match (')')) - return 0; + /* Data pass. */ + grouper = casegrouper_create_splits (proc_open (ds), dataset_dict (ds)); + while (casegrouper_get_next_group (grouper, &group)) + run_regression (group, &cmd, ds, models); + ok = casegrouper_destroy (grouper); + ok = proc_commit (ds) && ok; - return 1; -} - -int -cmd_regression (void) -{ - if (!parse_regression (&cmd)) - return CMD_FAILURE; - - models = xnmalloc (cmd.n_dependent, sizeof *models); - if (!multipass_procedure_with_splits (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; + free_regression (&cmd); + + return ok ? CMD_SUCCESS : CMD_FAILURE; } /* 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; -} - -/* - Mark missing cases. Return the number of non-missing cases. - */ -static size_t -mark_missing_cases (const struct casefile *cf, struct variable *v, - int *is_missing_case, double n_data) -{ - struct casereader *r; - struct ccase c; - size_t row; - const union value *val; - - for (r = casefile_get_reader (cf); - casereader_read (r, &c); case_destroy (&c)) - { - row = casereader_cnum (r) - 1; - - val = case_data (&c, v->fv); - cat_value_update (v, val); - if (mv_is_value_missing (&v->miss, val)) - { - if (!is_missing_case[row]) - { - /* Now it is missing. */ - n_data--; - is_missing_case[row] = 1; - } - } - } - casereader_destroy (r); - - return n_data; + return v == v_variables[k]; } /* 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 (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_const + (lexer, dict, &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; @@ -1016,225 +790,231 @@ regression_custom_variables (struct cmd_regression *cmd UNUSED) return 1; } -/* - Count the explanatory variables. The user may or may - not have specified a response variable in the syntax. - */ +/* Identify the explanatory variables in v_variables. Returns + the number of independent variables. */ static int -get_n_indep (const struct variable *v) +identify_indep_vars (const struct variable **indep_vars, + const struct variable *depvar) { - int result; - int i = 0; + int n_indep_vars = 0; + int i; - result = n_variables; - while (i < n_variables) + for (i = 0; i < n_variables; i++) + if (!is_depvar (i, depvar)) + indep_vars[n_indep_vars++] = v_variables[i]; + if ((n_indep_vars < 1) && is_depvar (0, depvar)) { - if (is_depvar (i, v)) - { - result--; - i = n_variables; - } - i++; + /* + There is only one independent variable, and it is the same + as the dependent variable. Print a warning and continue. + */ + msg (SE, + gettext ("The dependent variable is equal to the independent variable." + "The least squares line is therefore Y=X." + "Standard errors and related statistics may be meaningless.")); + n_indep_vars = 1; + indep_vars[0] = v_variables[0]; } - return result; + return n_indep_vars; } -/* - Read from the active file. Identify the explanatory variables in - v_variables. Encode categorical variables. Drop cases with missing - values. -*/ +/* Encode categorical variables. + Returns number of valid cases. */ static int -prepare_data (int n_data, int is_missing_case[], - struct variable **indep_vars, - struct variable *depvar, const struct casefile *cf) +prepare_categories (struct casereader *input, + const struct variable **vars, size_t n_vars, + struct moments_var *mom) { - int i; - int j; + int n_data; + struct ccase *c; + size_t i; - assert (indep_vars != NULL); - j = 0; - for (i = 0; i < n_variables; i++) + assert (vars != NULL); + assert (mom != NULL); + + for (i = 0; i < n_vars; i++) + if (var_is_alpha (vars[i])) + cat_stored_values_create (vars[i]); + + n_data = 0; + for (; (c = casereader_read (input)) != NULL; case_unref (c)) { - 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. + */ + for (i = 0; i < n_vars; i++) { - indep_vars[j] = v_variables[i]; - j++; - if (v_variables[i]->type == ALPHA) - { - /* 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); + const union value *val = case_data (c, vars[i]); + if (var_is_alpha (vars[i])) + cat_value_update (vars[i], val); + else + moments1_add (mom[i].m, val->f, 1.0); } + n_data++; } - /* - Mark missing cases for the dependent variable. - */ - n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data); + casereader_destroy (input); return n_data; } +static void +coeff_init (pspp_linreg_cache * c, struct design_matrix *dm) +{ + c->coeff = xnmalloc (dm->m->size2, sizeof (*c->coeff)); + pspp_coeff_init (c->coeff, dm); +} + static bool -run_regression (const struct ccase *first, - const struct casefile *cf, void *cmd_ UNUSED) +run_regression (struct casereader *input, struct cmd_regression *cmd, + struct dataset *ds, pspp_linreg_cache **models) { size_t i; - 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; int k; - /* - Keep track of the missing cases. - */ - int *is_missing_case; - const union value *val; - struct casereader *r; - struct ccase c; - struct variable **indep_vars; + struct ccase *c; + const struct variable **indep_vars; struct design_matrix *X; + struct moments_var *mom; gsl_vector *Y; pspp_linreg_opts lopts; assert (models != NULL); - output_split_file_values (first); + c = casereader_peek (input, 0); + if (c == NULL) + { + casereader_destroy (input); + return true; + } + output_split_file_values (ds, c); + case_unref (c); if (!v_variables) { - dict_get_vars (default_dict, &v_variables, &n_variables, - 1u << DC_SYSTEM); + dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, 0); } - n_cases = casefile_get_case_cnt (cf); - - for (i = 0; i < cmd.n_dependent; i++) + 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; - return true; + msg (SE, _("Dependent variable must be numeric.")); + return false; } } - 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++) - { - 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); - assert (indep_vars != NULL); + lopts.get_indep_mean_std = xnmalloc (n_variables, sizeof (int)); + indep_vars = xnmalloc (n_variables, sizeof *indep_vars); - 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], - (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++) - { - 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) + for (k = 0; k < cmd->n_dependent; k++) + { + const struct variable *dep_var; + struct casereader *reader; + casenumber row; + struct ccase *c; + size_t n_data; /* Number of valid cases. */ + + dep_var = cmd->v_dependent[k]; + n_indep = identify_indep_vars (indep_vars, dep_var); + reader = casereader_clone (input); + reader = casereader_create_filter_missing (reader, indep_vars, n_indep, + MV_ANY, NULL, NULL); + reader = casereader_create_filter_missing (reader, &dep_var, 1, + MV_ANY, NULL, NULL); + n_data = prepare_categories (casereader_clone (reader), + indep_vars, n_indep, mom); + + if ((n_data > 0) && (n_indep > 0)) { - 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 (dep_var, (const struct variable **) indep_vars, + X->m->size1, n_indep); + models[k]->depvar = dep_var; + /* + For large data sets, use QR decomposition. + */ + if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA) + { + models[k]->method = PSPP_LINREG_QR; + } - /* - The second pass fills the design matrix. - */ - row = 0; - for (r = casefile_get_reader (cf); 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. + */ + reader = casereader_create_counter (reader, &row, -1); + for (; (c = casereader_read (reader)) != NULL; case_unref (c)) { - for (i = 0; i < n_variables; ++i) /* Iterate over the - variables for the - current case. - */ + for (i = 0; i < n_indep; ++i) { - 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])) - { - if (v_variables[i]->type == ALPHA) - { - 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); - } - } + const struct variable *v = indep_vars[i]; + const union value *val = case_data (c, v); + if (var_is_alpha (v)) + design_matrix_set_categorical (X, row, v, val); + else + design_matrix_set_numeric (X, row, v, val); } - val = case_data (&c, cmd.v_dependent[k]->fv); - gsl_vector_set (Y, row, val->f); - row++; + gsl_vector_set (Y, row, case_num (c, dep_var)); } - } - /* - Now that we know the number of coefficients, allocate space - and store pointers to the variables that correspond to the - coefficients. - */ - pspp_linreg_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, &lopts, models[k]); - free (is_missing_case); + if (!taint_has_tainted_successor (casereader_get_taint (input))) + { + subcommand_statistics (cmd->a_statistics, models[k]); + } + + gsl_vector_free (Y); + design_matrix_destroy (X); + } + else + { + msg (SE, + gettext ("No valid data found. This command was skipped.")); + } + casereader_destroy (reader); + } + for (i = 0; i < n_variables; i++) + { + moments1_destroy ((mom + i)->m); + } + free (mom); + free (indep_vars); + free (lopts.get_indep_mean_std); + casereader_destroy (input); return true; } /* - Local Variables: + Local Variables: mode: c End: */