X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=c41f9e7895e7e05595331b767994a725cf417914;hb=b2be34cda6c4adf4cf396bf1805059eb6ed13646;hp=c27d8a40a7e1eb0314d5d8c088d86ec5988d88c1;hpb=e80304e52b4c7cb2e2924570f97c34c2f69f8aae;p=pspp diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index c27d8a40a7..c41f9e7895 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 2005, 2009 Free Software Foundation, Inc. + Copyright (C) 2005, 2009, 2010, 2011 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 @@ -21,29 +21,30 @@ #include #include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "xalloc.h" + +#include "data/case.h" +#include "data/casegrouper.h" +#include "data/casereader.h" +#include "data/dataset.h" +#include "data/dictionary.h" +#include "data/missing-values.h" +#include "data/transformations.h" +#include "data/value-labels.h" +#include "data/variable.h" +#include "language/command.h" +#include "language/data-io/file-handle.h" +#include "language/dictionary/split-file.h" +#include "language/lexer/lexer.h" +#include "libpspp/compiler.h" +#include "libpspp/message.h" +#include "libpspp/taint.h" +#include "math/covariance.h" +#include "math/linreg.h" +#include "math/moments.h" +#include "output/tab.h" + +#include "gl/intprops.h" +#include "gl/xalloc.h" #include "gettext.h" #define _(msgid) gettext (msgid) @@ -147,8 +148,7 @@ reg_stats_r (linreg *c, void *aux UNUSED) rsq = linreg_ssreg (c) / linreg_sst (c); adjrsq = 1.0 - (1.0 - rsq) * (linreg_n_obs (c) - 1.0) / (linreg_n_obs (c) - linreg_n_coeffs (c)); std_error = sqrt (linreg_mse (c)); - t = tab_create (n_cols, n_rows, 0); - tab_dim (t, tab_natural_dimensions, NULL); + t = tab_create (n_cols, n_rows); 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); @@ -184,14 +184,13 @@ reg_stats_coeff (linreg * c, void *aux_) const struct variable *v; struct tab_table *t; + gsl_matrix *cov = aux_; assert (c != NULL); - gsl_matrix *cov = (gsl_matrix *) aux_; n_rows = linreg_n_coeffs (c) + 3; - t = tab_create (n_cols, n_rows, 0); + t = tab_create (n_cols, n_rows); tab_headers (t, 2, 0, 1, 0); - 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); @@ -209,7 +208,7 @@ reg_stats_coeff (linreg * c, void *aux_) tab_double (t, 4, 1, 0, 0.0, NULL); t_stat = linreg_intercept (c) / std_err; tab_double (t, 5, 1, 0, t_stat, NULL); - pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); + pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), (double) (linreg_n_obs (c) - linreg_n_coeffs (c))); tab_double (t, 6, 1, 0, pval, NULL); for (j = 0; j < linreg_n_coeffs (c); j++) { @@ -274,9 +273,8 @@ reg_stats_anova (linreg * c, void *aux UNUSED) struct tab_table *t; assert (c != NULL); - t = tab_create (n_cols, n_rows, 0); + t = tab_create (n_cols, n_rows); tab_headers (t, 2, 0, 1, 0); - 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); @@ -365,9 +363,8 @@ reg_stats_bcov (linreg * c, void *aux UNUSED) assert (c != NULL); n_cols = c->n_indeps + 1 + 2; n_rows = 2 * (c->n_indeps + 1); - t = tab_create (n_cols, n_rows, 0); + t = tab_create (n_cols, n_rows); tab_headers (t, 2, 0, 1, 0); - 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); @@ -607,29 +604,19 @@ regression_trns_resid_proc (void *t_, struct ccase **c, return TRNS_CONTINUE; } -/* - Returns false if NAME is a duplicate of any existing variable name. -*/ -static bool -try_name (const struct dictionary *dict, const char *name) +static char * +reg_get_name (const struct dictionary *dict, const char *prefix) { - if (dict_lookup_var (dict, name) != NULL) - return false; - - return true; -} - -static void -reg_get_name (const struct dictionary *dict, char name[VAR_NAME_LEN], - const char prefix[VAR_NAME_LEN]) -{ - int i = 1; + char *name; + int i; - snprintf (name, VAR_NAME_LEN, "%s%d", prefix, i); - while (!try_name (dict, name)) + /* XXX handle too-long prefixes */ + name = xmalloc (strlen (prefix) + INT_BUFSIZE_BOUND (i) + 1); + for (i = 1; ; i++) { - i++; - snprintf (name, VAR_NAME_LEN, "%s%d", prefix, i); + sprintf (name, "%s%d", prefix, i); + if (dict_lookup_var (dict, name) == NULL) + return name; } } @@ -639,7 +626,7 @@ 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[VAR_NAME_LEN]; + char *name; struct variable *new_var; struct reg_trns *t = NULL; @@ -647,9 +634,11 @@ reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f, t->trns_id = trns_index; t->n_trns = n_trns; t->c = c; - reg_get_name (dict, name, prefix); - new_var = dict_create_var (dict, name, 0); - assert (new_var != NULL); + + name = reg_get_name (dict, prefix); + new_var = dict_create_var_assert (dict, name, 0); + free (name); + *v = new_var; add_transformation (ds, f, regression_trns_free, t); trns_index++; @@ -757,10 +746,10 @@ regression_custom_variables (struct lexer *lexer, struct dataset *ds, { const struct dictionary *dict = dataset_dict (ds); - lex_match (lexer, '='); + lex_match (lexer, T_EQUALS); if ((lex_token (lexer) != T_ID - || dict_lookup_var (dict, lex_tokid (lexer)) == NULL) + || dict_lookup_var (dict, lex_tokcstr (lexer)) == NULL) && lex_token (lexer) != T_ALL) return 2; @@ -815,7 +804,7 @@ fill_covariance (gsl_matrix *cov, struct covariance *all_cov, size_t dep_subscript; size_t *rows; const gsl_matrix *ssizes; - const gsl_matrix *cm; + gsl_matrix *cm; const gsl_matrix *mean_matrix; const gsl_matrix *ssize_matrix; double result = 0.0; @@ -867,9 +856,57 @@ fill_covariance (gsl_matrix *cov, struct covariance *all_cov, gsl_matrix_set (cov, cov->size1 - 1, cov->size1 - 1, gsl_matrix_get (cm, dep_subscript, dep_subscript)); free (rows); + gsl_matrix_free (cm); return result; } +static size_t +get_n_all_vars (struct cmd_regression *cmd) +{ + size_t result = n_variables; + size_t i; + size_t j; + result += cmd->n_dependent; + for (i = 0; i < cmd->n_dependent; i++) + { + for (j = 0; j < n_variables; j++) + { + if (v_variables[j] == cmd->v_dependent[i]) + { + result--; + } + } + } + return result; +} +static void +fill_all_vars (const struct variable **vars, struct cmd_regression *cmd) +{ + size_t i; + size_t j; + bool absent; + + for (i = 0; i < n_variables; i++) + { + vars[i] = v_variables[i]; + } + for (i = 0; i < cmd->n_dependent; i++) + { + absent = true; + for (j = 0; j < n_variables; j++) + { + if (cmd->v_dependent[i] == v_variables[j]) + { + absent = false; + break; + } + } + if (absent) + { + vars[i + n_variables] = cmd->v_dependent[i]; + } + } +} static bool run_regression (struct casereader *input, struct cmd_regression *cmd, struct dataset *ds, linreg **models) @@ -882,10 +919,11 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, struct ccase *c; struct covariance *cov; const struct variable **vars; + const struct variable **all_vars; const struct variable *dep_var; struct casereader *reader; const struct dictionary *dict; - gsl_matrix *this_cm; + size_t n_all_vars; assert (models != NULL); @@ -912,9 +950,12 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, { dict_get_vars (dict, &v_variables, &n_variables, 0); } + n_all_vars = get_n_all_vars (cmd); + all_vars = xnmalloc (n_all_vars, sizeof (*all_vars)); + fill_all_vars (all_vars, cmd); vars = xnmalloc (n_variables, sizeof (*vars)); - means = xnmalloc (n_variables, sizeof (*means)); - cov = covariance_1pass_create (n_variables, v_variables, + means = xnmalloc (n_all_vars, sizeof (*means)); + cov = covariance_1pass_create (n_all_vars, all_vars, dict_get_weight (dict), MV_ANY); reader = casereader_clone (input); @@ -927,12 +968,13 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, for (k = 0; k < cmd->n_dependent; k++) { + gsl_matrix *this_cm; dep_var = cmd->v_dependent[k]; n_indep = identify_indep_vars (vars, dep_var); this_cm = gsl_matrix_alloc (n_indep + 1, n_indep + 1); n_data = fill_covariance (this_cm, cov, vars, n_indep, - dep_var, v_variables, n_variables, means); + dep_var, all_vars, n_all_vars, means); models[k] = linreg_alloc (dep_var, (const struct variable **) vars, n_data, n_indep); models[k]->depvar = dep_var; @@ -968,10 +1010,12 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, linreg_free (models[k]); models[k] = NULL; } + gsl_matrix_free (this_cm); } casereader_destroy (reader); free (vars); + free (all_vars); free (means); casereader_destroy (input); covariance_destroy (cov);