X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.c;h=a534a8e8eaced2556a34fdd77dce7c687bb654f9;hb=c875597832d56353461bafd46e268f0ba5fbb5da;hp=07188663fed2fe50793b10affb7b3f31f7aad958;hpb=5f86425ef29d236118667470f2a461818d7e55b2;p=pspp diff --git a/src/language/stats/regression.c b/src/language/stats/regression.c index 07188663fe..a534a8e8ea 100644 --- a/src/language/stats/regression.c +++ b/src/language/stats/regression.c @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 2005, 2009, 2010, 2011, 2012, 2013, 2014 Free Software Foundation, Inc. + Copyright (C) 2005, 2009, 2010, 2011, 2012, 2013, 2014, 2016 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 @@ -16,6 +16,7 @@ #include +#include #include #include @@ -224,8 +225,7 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) if (lex_match_id (lexer, "DEPENDENT")) { - if (!lex_force_match (lexer, T_EQUALS)) - goto error; + lex_match (lexer, T_EQUALS); free (regression.dep_vars); regression.n_dep_vars = 0; @@ -247,6 +247,7 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) } else if (lex_match_id (lexer, "STATISTICS")) { + unsigned long statistics = 0; lex_match (lexer, T_EQUALS); while (lex_token (lexer) != T_ENDCMD @@ -254,37 +255,39 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) { if (lex_match (lexer, T_ALL)) { - regression.stats = ~0; + statistics = ~0; } else if (lex_match_id (lexer, "DEFAULTS")) { - regression.stats |= STATS_DEFAULT; + statistics |= STATS_DEFAULT; } else if (lex_match_id (lexer, "R")) { - regression.stats |= STATS_R; + statistics |= STATS_R; } else if (lex_match_id (lexer, "COEFF")) { - regression.stats |= STATS_COEFF; + statistics |= STATS_COEFF; } else if (lex_match_id (lexer, "ANOVA")) { - regression.stats |= STATS_ANOVA; + statistics |= STATS_ANOVA; } else if (lex_match_id (lexer, "BCOV")) { - regression.stats |= STATS_BCOV; + statistics |= STATS_BCOV; } else if (lex_match_id (lexer, "CI")) { - regression.stats |= STATS_CI; + statistics |= STATS_CI; - if (lex_match (lexer, T_LPAREN)) + if (lex_match (lexer, T_LPAREN) && + lex_force_num (lexer)) { regression.ci = lex_number (lexer) / 100.0; lex_get (lexer); - lex_force_match (lexer, T_RPAREN); + if (! lex_force_match (lexer, T_RPAREN)) + goto error; } } else @@ -293,6 +296,10 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) goto error; } } + + if (statistics) + regression.stats = statistics; + } else if (lex_match_id (lexer, "SAVE")) { @@ -334,6 +341,8 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) workspace.pred_idx = -1; workspace.writer = NULL; workspace.reader = NULL; + workspace.residvars = NULL; + workspace.predvars = NULL; if (save) { int i; @@ -341,8 +350,7 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) if (regression.resid) { - workspace.extras ++; - workspace.res_idx = 0; + workspace.res_idx = workspace.extras ++; workspace.residvars = xcalloc (regression.n_dep_vars, sizeof (*workspace.residvars)); for (i = 0; i < regression.n_dep_vars; ++i) @@ -354,8 +362,7 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) if (regression.pred) { - workspace.extras ++; - workspace.pred_idx = 1; + workspace.pred_idx = workspace.extras ++; workspace.predvars = xcalloc (regression.n_dep_vars, sizeof (*workspace.predvars)); for (i = 0; i < regression.n_dep_vars; ++i) @@ -369,6 +376,10 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) msg (SW, _("REGRESSION with SAVE ignores TEMPORARY. " "Temporary transformations will be made permanent.")); + if (dict_get_filter (dict)) + msg (SW, _("REGRESSION with SAVE ignores FILTER. " + "All cases will be processed.")); + workspace.writer = autopaging_writer_create (proto); caseproto_unref (proto); } @@ -698,7 +709,7 @@ run_regression (const struct regression *cmd, for (; (c = casereader_read (r)) != NULL; case_unref (c)) { - struct ccase *outc = case_clone (c); + struct ccase *outc = case_create (casewriter_get_proto (ws->writer)); for (k = 0; k < cmd->n_dep_vars; k++) { const struct variable **vars = xnmalloc (cmd->n_vars, sizeof (*vars)); @@ -774,10 +785,10 @@ reg_stats_r (const linreg * c, const struct variable *var) 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_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_double (t, 1, 1, TAB_RIGHT, sqrt (rsq), NULL, RC_OTHER); + tab_double (t, 2, 1, TAB_RIGHT, rsq, NULL, RC_OTHER); + tab_double (t, 3, 1, TAB_RIGHT, adjrsq, NULL, RC_OTHER); + tab_double (t, 4, 1, TAB_RIGHT, std_error, NULL, RC_OTHER); tab_title (t, _("Model Summary (%s)"), var_to_string (var)); tab_submit (t); } @@ -829,29 +840,29 @@ reg_stats_coeff (const linreg * c, const gsl_matrix *cov, const struct variable tab_text (t, 5, 1, TAB_CENTER | TAT_TITLE, _("t")); tab_text (t, 6, 1, TAB_CENTER | TAT_TITLE, _("Sig.")); tab_text (t, 1, heading_rows, TAB_LEFT | TAT_TITLE, _("(Constant)")); - tab_double (t, 2, heading_rows, 0, linreg_intercept (c), NULL); + tab_double (t, 2, heading_rows, 0, linreg_intercept (c), NULL, RC_OTHER); std_err = sqrt (gsl_matrix_get (linreg_cov (c), 0, 0)); if (cmd->stats & STATS_CI) { double lower = linreg_intercept (c) - tval * std_err ; double upper = linreg_intercept (c) + tval * std_err ; - tab_double (t, 7, heading_rows, 0, lower, NULL); - tab_double (t, 8, heading_rows, 0, upper, NULL); + tab_double (t, 7, heading_rows, 0, lower, NULL, RC_OTHER); + tab_double (t, 8, heading_rows, 0, upper, NULL, RC_OTHER); tab_joint_text_format (t, 7, 0, 8, 0, TAB_CENTER | TAT_TITLE, _("%g%% Confidence Interval for B"), cmd->ci * 100); tab_hline (t, TAL_1, 7, 8, 1); tab_text (t, 7, 1, TAB_CENTER | TAT_TITLE, _("Lower Bound")); tab_text (t, 8, 1, TAB_CENTER | TAT_TITLE, _("Upper Bound")); } - tab_double (t, 3, heading_rows, 0, std_err, NULL); - tab_double (t, 4, heading_rows, 0, 0.0, NULL); + tab_double (t, 3, heading_rows, 0, std_err, NULL, RC_OTHER); + tab_double (t, 4, heading_rows, 0, 0.0, NULL, RC_OTHER); t_stat = linreg_intercept (c) / std_err; - tab_double (t, 5, heading_rows, 0, t_stat, NULL); + tab_double (t, 5, heading_rows, 0, t_stat, NULL, RC_OTHER); pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), (double) (linreg_n_obs (c) - linreg_n_coeffs (c))); - tab_double (t, 6, heading_rows, 0, pval, NULL); + tab_double (t, 6, heading_rows, 0, pval, NULL, RC_PVALUE); for (j = 0; j < linreg_n_coeffs (c); j++) { @@ -867,12 +878,12 @@ reg_stats_coeff (const linreg * c, const gsl_matrix *cov, const struct variable /* Regression coefficients. */ - tab_double (t, 2, this_row, 0, linreg_coeff (c, j), NULL); + tab_double (t, 2, this_row, 0, linreg_coeff (c, j), NULL, RC_OTHER); /* Standard error of the coefficients. */ std_err = sqrt (gsl_matrix_get (linreg_cov (c), j + 1, j + 1)); - tab_double (t, 3, this_row, 0, std_err, NULL); + tab_double (t, 3, this_row, 0, std_err, NULL, RC_OTHER); /* Standardized coefficient, i.e., regression coefficient if all variables had unit variance. @@ -880,18 +891,18 @@ reg_stats_coeff (const linreg * c, const gsl_matrix *cov, const struct variable beta = sqrt (gsl_matrix_get (cov, j, j)); beta *= linreg_coeff (c, j) / sqrt (gsl_matrix_get (cov, cov->size1 - 1, cov->size2 - 1)); - tab_double (t, 4, this_row, 0, beta, NULL); + tab_double (t, 4, this_row, 0, beta, NULL, RC_OTHER); /* Test statistic for H0: coefficient is 0. */ t_stat = linreg_coeff (c, j) / std_err; - tab_double (t, 5, this_row, 0, t_stat, NULL); + tab_double (t, 5, this_row, 0, t_stat, NULL, RC_OTHER); /* P values for the test statistic above. */ pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), df); - tab_double (t, 6, this_row, 0, pval, NULL); + tab_double (t, 6, this_row, 0, pval, NULL, RC_PVALUE); ds_destroy (&tstr); if (cmd->stats & STATS_CI) @@ -899,8 +910,8 @@ reg_stats_coeff (const linreg * c, const gsl_matrix *cov, const struct variable double lower = linreg_coeff (c, j) - tval * std_err ; double upper = linreg_coeff (c, j) + tval * std_err ; - tab_double (t, 7, this_row, 0, lower, NULL); - tab_double (t, 8, this_row, 0, upper, NULL); + tab_double (t, 7, this_row, 0, lower, NULL, RC_OTHER); + tab_double (t, 8, this_row, 0, upper, NULL, RC_OTHER); } } tab_title (t, _("Coefficients (%s)"), var_to_string (var)); @@ -943,23 +954,23 @@ reg_stats_anova (const linreg * c, const struct variable *var) tab_text (t, 1, 3, TAB_LEFT | TAT_TITLE, _("Total")); /* Sums of Squares */ - tab_double (t, 2, 1, 0, linreg_ssreg (c), NULL); - tab_double (t, 2, 3, 0, linreg_sst (c), NULL); - tab_double (t, 2, 2, 0, linreg_sse (c), NULL); + tab_double (t, 2, 1, 0, linreg_ssreg (c), NULL, RC_OTHER); + tab_double (t, 2, 3, 0, linreg_sst (c), NULL, RC_OTHER); + tab_double (t, 2, 2, 0, linreg_sse (c), NULL, RC_OTHER); /* Degrees of freedom */ - 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); + tab_text_format (t, 3, 1, TAB_RIGHT, "%.*g", DBL_DIG + 1, c->dfm); + tab_text_format (t, 3, 2, TAB_RIGHT, "%.*g", DBL_DIG + 1, c->dfe); + tab_text_format (t, 3, 3, TAB_RIGHT, "%.*g", DBL_DIG + 1, c->dft); /* Mean Squares */ - tab_double (t, 4, 1, TAB_RIGHT, msm, NULL); - tab_double (t, 4, 2, TAB_RIGHT, mse, NULL); + tab_double (t, 4, 1, TAB_RIGHT, msm, NULL, RC_OTHER); + tab_double (t, 4, 2, TAB_RIGHT, mse, NULL, RC_OTHER); - tab_double (t, 5, 1, 0, F, NULL); + tab_double (t, 5, 1, 0, F, NULL, RC_OTHER); - tab_double (t, 6, 1, 0, pval, NULL); + tab_double (t, 6, 1, 0, pval, NULL, RC_PVALUE); tab_title (t, _("ANOVA (%s)"), var_to_string (var)); tab_submit (t); @@ -1000,7 +1011,7 @@ reg_stats_bcov (const linreg * c, const struct variable *var) col = (i <= k) ? k : i; row = (i <= k) ? i : k; tab_double (t, k + 2, i, TAB_CENTER, - gsl_matrix_get (c->cov, row, col), NULL); + gsl_matrix_get (c->cov, row, col), NULL, RC_OTHER); } } tab_title (t, _("Coefficient Correlations (%s)"), var_to_string (var));