X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=595e7e750c54d4d996b85b71eb141f87b4ba8d52;hb=cc57a28ef6796ae9a64ef80d453f72126956d49d;hp=2c74e3ceefe346f3270d9017fd840de95a3fd15c;hpb=b5b474193e450bba97610065df0518c08074a7fb;p=pspp diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 2c74e3ceef..595e7e750c 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 Free Software Foundation, Inc. + 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 @@ -180,7 +180,6 @@ reg_stats_coeff (pspp_linreg_cache * c) int this_row; double t_stat; double pval; - double coeff; double std_err; double beta; const char *label; @@ -209,8 +208,7 @@ reg_stats_coeff (pspp_linreg_cache * c) 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 = c->intercept / c->depvar_std; - tab_float (t, 4, 1, 0, beta, 10, 2); + 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); @@ -242,8 +240,7 @@ reg_stats_coeff (pspp_linreg_cache * c) /* Regression coefficients. */ - coeff = c->coeff[j]->estimate; - tab_float (t, 2, this_row, 0, coeff, 10, 2); + tab_float (t, 2, this_row, 0, c->coeff[j]->estimate, 10, 2); /* Standard error of the coefficients. */ @@ -253,14 +250,14 @@ reg_stats_coeff (pspp_linreg_cache * c) Standardized coefficient, i.e., regression coefficient if all variables had unit variance. */ - beta = gsl_vector_get (c->indep_std, j + 1); - beta *= coeff / c->depvar_std; + 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; + 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. @@ -545,7 +542,7 @@ regression_trns_free (void *t_) Gets the predicted values. */ static int -regression_trns_pred_proc (void *t_, struct ccase *c, +regression_trns_pred_proc (void *t_, struct ccase **c, casenumber case_idx UNUSED) { size_t i; @@ -566,12 +563,12 @@ 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); - 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]); + vals[i] = case_data (*c, vars[i]); } output->f = (*model->predict) ((const struct variable **) vars, vals, model, n_vals); @@ -584,7 +581,7 @@ regression_trns_pred_proc (void *t_, struct ccase *c, Gets the residuals. */ static int -regression_trns_resid_proc (void *t_, struct ccase *c, +regression_trns_resid_proc (void *t_, struct ccase **c, casenumber case_idx UNUSED) { size_t i; @@ -606,14 +603,15 @@ 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); + *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]); + vals[i] = case_data (*c, vars[i]); } - obs = case_data (c, model->depvar); + obs = case_data (*c, model->depvar); output->f = (*model->residual) ((const struct variable **) vars, vals, obs, model, n_vals); free (vals); @@ -824,7 +822,7 @@ prepare_categories (struct casereader *input, struct moments_var *mom) { int n_data; - struct ccase c; + struct ccase *c; size_t i; assert (vars != NULL); @@ -835,7 +833,7 @@ prepare_categories (struct casereader *input, cat_stored_values_create (vars[i]); n_data = 0; - for (; casereader_read (input, &c); case_destroy (&c)) + for (; (c = casereader_read (input)) != NULL; case_unref (c)) { /* The second condition ensures the program will run even if @@ -844,7 +842,7 @@ prepare_categories (struct casereader *input, */ for (i = 0; i < n_vars; i++) { - const union value *val = case_data (&c, vars[i]); + const union value *val = case_data (c, vars[i]); if (var_is_alpha (vars[i])) cat_value_update (vars[i], val); else @@ -864,39 +862,6 @@ coeff_init (pspp_linreg_cache * c, struct design_matrix *dm) pspp_coeff_init (c->coeff, 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 (struct casereader *input, struct cmd_regression *cmd, struct dataset *ds, pspp_linreg_cache **models) @@ -904,7 +869,7 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, size_t i; int n_indep = 0; int k; - struct ccase c; + struct ccase *c; const struct variable **indep_vars; struct design_matrix *X; struct moments_var *mom; @@ -914,13 +879,14 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, assert (models != NULL); - if (!casereader_peek (input, 0, &c)) + c = casereader_peek (input, 0); + if (c == NULL) { casereader_destroy (input); return true; } - output_split_file_values (ds, &c); - case_destroy (&c); + output_split_file_values (ds, c); + case_unref (c); if (!v_variables) { @@ -952,16 +918,16 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, const struct variable *dep_var; struct casereader *reader; casenumber row; - struct ccase c; + 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); + MV_ANY, NULL, NULL); reader = casereader_create_filter_missing (reader, &dep_var, 1, - MV_ANY, NULL); + MV_ANY, NULL, NULL); n_data = prepare_categories (casereader_clone (reader), indep_vars, n_indep, mom); @@ -976,7 +942,8 @@ 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] = pspp_linreg_cache_alloc (dep_var, (const struct variable **) indep_vars, + X->m->size1, X->m->size2); models[k]->depvar = dep_var; /* For large data sets, use QR decomposition. @@ -990,18 +957,18 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, The second pass fills the design matrix. */ reader = casereader_create_counter (reader, &row, -1); - for (; casereader_read (reader, &c); case_destroy (&c)) + for (; (c = casereader_read (reader)) != NULL; case_unref (c)) { for (i = 0; i < n_indep; ++i) { const struct variable *v = indep_vars[i]; - const union value *val = case_data (&c, v); + 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); } - gsl_vector_set (Y, row, case_num (&c, dep_var)); + gsl_vector_set (Y, row, case_num (c, dep_var)); } /* Now that we know the number of coefficients, allocate space @@ -1013,8 +980,7 @@ 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))) {