X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=2c74e3ceefe346f3270d9017fd840de95a3fd15c;hb=b5b474193e450bba97610065df0518c08074a7fb;hp=2c1c9aa8a0f5df9e2cf3d211fb5f23f54be2a487;hpb=56728c4e740a15c66266f54bed1307299f723f56;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 2c1c9aa8..2c74e3ce 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -22,7 +22,6 @@ #include #include -#include "regression-export.h" #include #include #include @@ -37,16 +36,17 @@ #include #include #include -#include #include #include #include #include #include -#include +#include #include #include +#include "xalloc.h" + #include "gettext.h" #define _(msgid) gettext (msgid) @@ -74,7 +74,6 @@ f, defaults, all; - export=custom; ^dependent=varlist; +save[sv_]=resid,pred; +method=enter. @@ -92,9 +91,6 @@ struct moments_var const struct variable *v; }; -/* Linear regression models. */ -static pspp_linreg_cache **models = NULL; - /* Transformations for saving predicted values and residuals, etc. @@ -115,14 +111,8 @@ static const struct variable **v_variables; */ static size_t n_variables; -/* - File where the model will be saved if the EXPORT subcommand - is given. - */ -static struct file_handle *model_file; - static bool run_regression (struct casereader *, struct cmd_regression *, - struct dataset *); + struct dataset *, pspp_linreg_cache **); /* STATISTICS subcommand output functions. @@ -187,21 +177,20 @@ 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); @@ -217,22 +206,25 @@ 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_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 = coeff / c->depvar_std; + beta = c->intercept / c->depvar_std; tab_float (t, 4, 1, 0, beta, 10, 2); - t_stat = coeff / std_err; + 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); tab_float (t, 6, 1, 0, pval, 10, 2); - for (j = 1; j <= c->n_indeps; j++) + for (j = 0; j < c->n_coeffs; j++) { + 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); + ds_put_cstr (&tstr, label); if (var_is_alpha (v)) { /* @@ -242,45 +234,45 @@ reg_stats_coeff (pspp_linreg_cache * c) */ val = pspp_coeff_get_value (c->coeff[j], v); - val_s = var_get_value_name (v, val); - strncat (tmp, val_s, MAX_STRING); + + 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_float (t, 2, this_row, 0, coeff, 10, 2); /* 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_float (t, 3, this_row, 0, std_err, 10, 2); /* - '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 = gsl_vector_get (c->indep_std, j + 1); beta *= coeff / c->depvar_std; - tab_float (t, 4, j + 1, 0, beta, 10, 2); + tab_float (t, 4, this_row, 0, beta, 10, 2); /* Test statistic for H0: coefficient is 0. */ t_stat = coeff / std_err; - tab_float (t, 5, j + 1, 0, t_stat, 10, 2); + tab_float (t, 5, this_row, 0, t_stat, 10, 2); /* P values for the test statistic above. */ pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), (double) (c->n_obs - c->n_coeffs)); - tab_float (t, 6, j + 1, 0, pval, 10, 2); + tab_float (t, 6, this_row, 0, pval, 10, 2); + ds_destroy (&tstr); } tab_title (t, _("Coefficients")); tab_submit (t); - free (tmp); } /* @@ -326,12 +318,11 @@ reg_stats_anova (pspp_linreg_cache * c) /* 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 (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); /* Mean Squares */ - tab_float (t, 4, 1, TAB_RIGHT, msm, 8, 3); tab_float (t, 4, 2, TAB_RIGHT, mse, 8, 3); @@ -342,21 +333,25 @@ reg_stats_anova (pspp_linreg_cache * c) 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) { @@ -396,7 +391,7 @@ reg_stats_bcov (pspp_linreg_cache * c) 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_coeff_get_var (c->coeff[i], 0); label = var_to_string (v); @@ -639,16 +634,16 @@ try_name (const struct dictionary *dict, const char *name) } static void -reg_get_name (const struct dictionary *dict, 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); + 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); } } @@ -658,7 +653,7 @@ 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[LONG_NAME_LEN]; + char name[VAR_NAME_LEN]; struct variable *new_var; struct reg_trns *t = NULL; @@ -673,7 +668,6 @@ reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f, add_transformation (ds, f, regression_trns_free, t); trns_index++; } - static void subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) { @@ -723,236 +717,19 @@ subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) } } -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 == varlist[i]) - { - return 1; - } - } - return 0; -} - -static void -reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) -{ - int i; - int n_vars = 0; - struct variable **varlist; - - 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. */ - { - struct pspp_coeff *coeff = c->coeff[i]; - const struct variable *v = pspp_coeff_get_var (coeff, 0); - if (var_is_alpha (v)) - { - if (!reg_inserted (v, varlist, n_vars)) - { - fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t", - var_get_name (v)); - varlist[n_vars] = (struct variable *) v; - n_vars++; - } - } - } - 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", var_get_name (varlist[i])); - } - fprintf (fp, "&%s};\n\t", var_get_name (varlist[i])); - - for (i = 0; i < n_vars; i++) - { - int n_categories = cat_get_n_categories (varlist[i]); - int j; - - fprintf (fp, "%s.name = \"%s\";\n\t", - var_get_name (varlist[i]), var_get_name (varlist[i])); - fprintf (fp, "%s.n_vals = %d;\n\t", - var_get_name (varlist[i]), n_categories); - - for (j = 0; j < n_categories; j++) - { - const union value *val = cat_subscript_to_value (j, varlist[i]); - fprintf (fp, "%s.values[%d] = \"%s\";\n\t", - var_get_name (varlist[i]), j, - var_get_value_name (varlist[i], val)); - } - } - fprintf (fp, "%s", reg_export_categorical_encode_2); -} - -static void -reg_print_depvars (FILE * fp, pspp_linreg_cache * c) -{ - int i; - struct pspp_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_coeff_get_var (coeff, 0); - fprintf (fp, "\"%s\",\n\t\t", var_get_name (v)); - } - coeff = c->coeff[i]; - v = pspp_coeff_get_var (coeff, 0); - fprintf (fp, "\"%s\"};\n\t", var_get_name (v)); -} -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_coeff_get_var (c->coeff[i], 0); - if (var_is_alpha (v)) - return 1; - } - return 0; -} - -static void -subcommand_export (int export, pspp_linreg_cache * c) -{ - FILE *fp; - size_t i; - size_t j; - int n_quantiles = 100; - double tmp; - struct pspp_coeff *coeff; - - if (export) - { - 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); - 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); - } -} - -static int -regression_custom_export (struct lexer *lexer, struct dataset *ds UNUSED, - struct cmd_regression *cmd UNUSED, void *aux UNUSED) -{ - /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */ - if (!lex_force_match (lexer, '(')) - return 0; - - if (lex_match (lexer, '*')) - model_file = NULL; - else - { - model_file = fh_parse (lexer, FH_REF_FILE); - if (model_file == NULL) - return 0; - } - - if (!lex_force_match (lexer, ')')) - return 0; - - return 1; -} - int cmd_regression (struct lexer *lexer, struct dataset *ds) { struct casegrouper *grouper; struct casereader *group; + pspp_linreg_cache **models; bool ok; size_t i; if (!parse_regression (lexer, ds, &cmd, NULL)) - return CMD_FAILURE; + { + return CMD_FAILURE; + } models = xnmalloc (cmd.n_dependent, sizeof *models); for (i = 0; i < cmd.n_dependent; i++) @@ -963,13 +740,15 @@ cmd_regression (struct lexer *lexer, struct dataset *ds) /* Data pass. */ grouper = casegrouper_create_splits (proc_open (ds), dataset_dict (ds)); while (casegrouper_get_next_group (grouper, &group)) - run_regression (group, &cmd, ds); + run_regression (group, &cmd, ds, models); ok = casegrouper_destroy (grouper); ok = proc_commit (ds) && ok; subcommand_save (ds, cmd.sbc_save, models); free (v_variables); free (models); + free_regression (&cmd); + return ok ? CMD_SUCCESS : CMD_FAILURE; } @@ -1012,7 +791,8 @@ regression_custom_variables (struct lexer *lexer, struct dataset *ds, /* Identify the explanatory variables in v_variables. Returns the number of independent variables. */ static int -identify_indep_vars (const struct variable **indep_vars, const struct variable *depvar) +identify_indep_vars (const struct variable **indep_vars, + const struct variable *depvar) { int n_indep_vars = 0; int i; @@ -1020,7 +800,19 @@ identify_indep_vars (const struct variable **indep_vars, const struct variable * 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)) + { + /* + 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 n_indep_vars; } @@ -1028,13 +820,16 @@ identify_indep_vars (const struct variable **indep_vars, const struct variable * Returns number of valid cases. */ static int prepare_categories (struct casereader *input, - const struct variable **vars, size_t n_vars, - struct moments_var *mom) + const struct variable **vars, size_t n_vars, + struct moments_var *mom) { int n_data; struct ccase c; size_t 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]); @@ -1043,20 +838,20 @@ prepare_categories (struct casereader *input, for (; casereader_read (input, &c); case_destroy (&c)) { /* - The second condition ensures the program will run even if - there is only one variable to act as both explanatory and - response. + 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++) - { - 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); - } + { + 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++; - } + } casereader_destroy (input); return n_data; @@ -1065,10 +860,8 @@ prepare_categories (struct casereader *input, static void coeff_init (pspp_linreg_cache * c, struct design_matrix *dm) { - c->coeff = xnmalloc (dm->m->size2 + 1, sizeof (*c->coeff)); - c->coeff[0] = xmalloc (sizeof (*(c->coeff[0]))); /* The first coefficient is the intercept. */ - c->coeff[0]->v_info = NULL; /* Intercept has no associated variable. */ - pspp_coeff_init (c->coeff + 1, dm); + c->coeff = xnmalloc (dm->m->size2, sizeof (*c->coeff)); + pspp_coeff_init (c->coeff, dm); } /* @@ -1106,7 +899,7 @@ compute_moments (pspp_linreg_cache * c, struct moments_var *mom, static bool run_regression (struct casereader *input, struct cmd_regression *cmd, - struct dataset *ds) + struct dataset *ds, pspp_linreg_cache **models) { size_t i; int n_indep = 0; @@ -1122,14 +915,16 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, assert (models != NULL); if (!casereader_peek (input, 0, &c)) - return true; + { + casereader_destroy (input); + return true; + } output_split_file_values (ds, &c); case_destroy (&c); if (!v_variables) { - dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, - 1u << DC_SYSTEM); + dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, 0); } for (i = 0; i < cmd->n_dependent; i++) @@ -1162,14 +957,13 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, 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); reader = casereader_create_filter_missing (reader, &dep_var, 1, - MV_ANY, NULL); - n_data = prepare_categories (casereader_clone (reader), - indep_vars, n_indep, mom); + MV_ANY, NULL); + n_data = prepare_categories (casereader_clone (reader), + indep_vars, n_indep, mom); if ((n_data > 0) && (n_indep > 0)) { @@ -1183,34 +977,32 @@ 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]->indep_means = gsl_vector_alloc (X->m->size2); - models[k]->indep_std = gsl_vector_alloc (X->m->size2); - models[k]->depvar = dep_var; - /* + 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_SVD; + models[k]->method = PSPP_LINREG_QR; } /* - The second pass fills the design matrix. - */ - reader = casereader_create_counter (reader, &row, -1); - for (; casereader_read (reader, &c); case_destroy (&c)) - { - for (i = 0; i < n_indep; ++i) - { - 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); - } - gsl_vector_set (Y, row, case_num (&c, dep_var)); - } + The second pass fills the design matrix. + */ + reader = casereader_create_counter (reader, &row, -1); + for (; casereader_read (reader, &c); case_destroy (&c)) + { + for (i = 0; i < n_indep; ++i) + { + 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); + } + 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 @@ -1224,21 +1016,26 @@ run_regression (struct casereader *input, struct cmd_regression *cmd, pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]); compute_moments (models[k], mom, X, n_variables); - if (!taint_has_tainted_successor (casereader_get_taint (input))) - { - subcommand_statistics (cmd->a_statistics, models[k]); - subcommand_export (cmd->sbc_export, models[k]); - } + 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.")); + 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);