X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=2487b9021d08bb14d86a14ed84e3b99dd6f5bad6;hb=0c40cc9355d2ce0d88d3937b1bfe0cb9927510a3;hp=32ac1815ea95c42d471ba3a4c280469a14a36113;hpb=005ac6d163e0e535a06e9bfb223f2f75f9320c9a;p=pspp diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 32ac1815ea..2487b9021d 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -43,7 +43,7 @@ #include #include #include -#include +#include #include "xalloc.h" @@ -149,8 +149,7 @@ reg_stats_r (pspp_linreg_cache * c) 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 (pspp_linreg_mse (c)); - t = tab_create (n_cols, n_rows, 0); - tab_dim (t, tab_natural_dimensions); + 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); @@ -191,9 +190,8 @@ reg_stats_coeff (pspp_linreg_cache * c) assert (c != NULL); n_rows = c->n_coeffs + 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); 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); @@ -288,9 +286,8 @@ reg_stats_anova (pspp_linreg_cache * c) 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); tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1); @@ -315,9 +312,9 @@ reg_stats_anova (pspp_linreg_cache * c) /* Degrees of freedom */ - 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); + 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); @@ -379,9 +376,8 @@ reg_stats_bcov (pspp_linreg_cache * c) 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); 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); @@ -542,7 +538,7 @@ 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; @@ -563,12 +559,12 @@ 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); @@ -581,7 +577,7 @@ 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; @@ -603,14 +599,15 @@ 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); @@ -688,17 +685,21 @@ subcommand_save (struct dataset *ds, 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]) - { - reg_save_var (ds, "RES", regression_trns_resid_proc, *lc, - &(*lc)->resid, n_trns); - } - if (cmd.a_save[REGRESSION_SV_PRED]) + if (*lc != NULL) { - reg_save_var (ds, "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); + } + } } } } @@ -821,7 +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); @@ -832,7 +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 @@ -841,7 +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 @@ -861,39 +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); - pspp_linreg_set_indep_variable_mean (c, (mom + j)->v, mean); - pspp_linreg_set_indep_variable_sd (c, (mom + j)->v, sqrt (variance)); - } - } - } -} - static bool run_regression (struct casereader *input, struct cmd_regression *cmd, struct dataset *ds, pspp_linreg_cache **models) @@ -901,7 +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; @@ -911,13 +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) { @@ -949,16 +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); @@ -974,7 +943,8 @@ 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, n_indep); models[k]->depvar = dep_var; /* For large data sets, use QR decomposition. @@ -988,18 +958,18 @@ 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