X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=9c3d1457c7e751b3d298341f16c5b2660979d7f6;hb=4bb4de2196cae312aeb7223e8b08af3235675607;hp=874e7bc2a145ae320570c83367c5586b8f1c7b21;hpb=2322678e8fddbbf158b01b2720db2636404bba3b;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 874e7bc2..9c3d1457 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -18,32 +18,37 @@ 02110-1301, USA. */ #include -#include + #include -#include #include +#include #include -#include "alloc.h" -#include "case.h" -#include "casefile.h" -#include "category.h" -#include "cat-routines.h" -#include "command.h" -#include "compiler.h" -#include "design-matrix.h" -#include "dictionary.h" -#include "message.h" -#include "file-handle-def.h" -#include "gettext.h" -#include "lexer.h" -#include "linreg.h" -#include "coefficient.h" -#include "missing-values.h" +#include + #include "regression-export.h" -#include "table.h" -#include "value-labels.h" -#include "variable.h" -#include "procedure.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "gettext.h" #define REG_LARGE_DATA 1000 @@ -51,7 +56,7 @@ /* (specification) "REGRESSION" (regression_): - *variables=varlist; + *variables=custom; statistics[st_]=r, coeff, anova, @@ -71,16 +76,35 @@ all; export=custom; ^dependent=varlist; + save[sv_]=resid,pred; method=enter. */ /* (declarations) */ /* (functions) */ static struct cmd_regression cmd; +/* Linear regression models. */ +pspp_linreg_cache **models = NULL; + +/* + Transformations for saving predicted values + and residuals, etc. + */ +struct reg_trns +{ + int n_trns; /* Number of transformations. */ + int trns_id; /* Which trns is this one? */ + pspp_linreg_cache *c; /* Linear model for this trns. */ +}; /* - Array holding the subscripts of the independent variables. + Variables used (both explanatory and response). */ -size_t *indep_vars; +static struct variable **v_variables; + +/* + Number of variables. + */ +static size_t n_variables; /* File where the model will be saved if the EXPORT subcommand @@ -93,7 +117,8 @@ struct file_handle *model_file; */ int pspp_reg_rc = CMD_SUCCESS; -static bool run_regression (const struct casefile *, void *); +static bool run_regression (const struct ccase *, + const struct casefile *, void *); /* STATISTICS subcommand output functions. @@ -145,7 +170,7 @@ reg_stats_r (pspp_linreg_cache * c) tab_float (t, 2, 1, TAB_RIGHT, rsq, 10, 2); tab_float (t, 3, 1, TAB_RIGHT, adjrsq, 10, 2); tab_float (t, 4, 1, TAB_RIGHT, std_error, 10, 2); - tab_title (t, 0, _("Model Summary")); + tab_title (t, _("Model Summary")); tab_submit (t); } @@ -155,7 +180,6 @@ reg_stats_r (pspp_linreg_cache * c) static void reg_stats_coeff (pspp_linreg_cache * c) { - size_t i; size_t j; int n_cols = 7; int n_rows; @@ -189,7 +213,7 @@ 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; + coeff = c->coeff[0]->estimate; tab_float (t, 2, 1, 0, coeff, 10, 2); std_err = sqrt (gsl_matrix_get (c->cov, 0, 0)); tab_float (t, 3, 1, 0, std_err, 10, 2); @@ -201,8 +225,7 @@ reg_stats_coeff (pspp_linreg_cache * c) tab_float (t, 6, 1, 0, pval, 10, 2); for (j = 1; j <= c->n_indeps; j++) { - i = indep_vars[j]; - v = pspp_linreg_coeff_get_var (c->coeff + j, 0); + v = pspp_linreg_coeff_get_var (c->coeff[j], 0); label = var_to_string (v); /* Do not overwrite the variable's name. */ strncpy (tmp, label, MAX_STRING); @@ -214,7 +237,7 @@ reg_stats_coeff (pspp_linreg_cache * c) for that value. */ - val = pspp_linreg_coeff_get_value (c->coeff + j, v); + val = pspp_linreg_coeff_get_value (c->coeff[j], v); val_s = value_to_string (val, v); strncat (tmp, val_s, MAX_STRING); } @@ -223,7 +246,7 @@ reg_stats_coeff (pspp_linreg_cache * c) /* Regression coefficients. */ - coeff = c->coeff[j].estimate; + coeff = c->coeff[j]->estimate; tab_float (t, 2, j + 1, 0, coeff, 10, 2); /* Standard error of the coefficients. @@ -249,7 +272,7 @@ reg_stats_coeff (pspp_linreg_cache * c) pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); tab_float (t, 6, j + 1, 0, pval, 10, 2); } - tab_title (t, 0, _("Coefficients")); + tab_title (t, _("Coefficients")); tab_submit (t); free (tmp); } @@ -310,7 +333,7 @@ reg_stats_anova (pspp_linreg_cache * c) tab_float (t, 6, 1, 0, pval, 8, 3); - tab_title (t, 0, _("ANOVA")); + tab_title (t, _("ANOVA")); tab_submit (t); } static void @@ -349,7 +372,6 @@ reg_stats_bcov (pspp_linreg_cache * c) int n_cols; int n_rows; int i; - int j; int k; int row; int col; @@ -368,14 +390,13 @@ 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_indeps + 1; i++) + for (i = 1; i < c->n_coeffs; i++) { - j = indep_vars[(i - 1)]; - struct variable *v = cmd.v_variables[j]; + const struct variable *v = pspp_linreg_coeff_get_var (c->coeff[i], 0); label = var_to_string (v); tab_text (t, 2, i, TAB_CENTER, label); tab_text (t, i + 2, 0, TAB_CENTER, label); - for (k = 1; k < c->n_indeps + 1; k++) + for (k = 1; k < c->n_coeffs; k++) { col = (i <= k) ? k : i; row = (i <= k) ? i : k; @@ -383,7 +404,7 @@ reg_stats_bcov (pspp_linreg_cache * c) gsl_matrix_get (c->cov, row, col), 8, 3); } } - tab_title (t, 0, _("Coefficient Correlations")); + tab_title (t, _("Coefficient Correlations")); tab_submit (t); } static void @@ -499,6 +520,193 @@ subcommand_statistics (int *keywords, pspp_linreg_cache * c) statistics_keyword_output (reg_stats_tol, keywords[tol], c); statistics_keyword_output (reg_stats_selection, keywords[selection], c); } + +/* + Free the transformation. Free its linear model if this + transformation is the last one. + */ +static bool +regression_trns_free (void *t_) +{ + bool result = true; + struct reg_trns *t = t_; + + if (t->trns_id == t->n_trns) + { + result = pspp_linreg_cache_free (t->c); + } + free (t); + + return result; +} + +/* + Gets the predicted values. + */ +static int +regression_trns_pred_proc (void *t_, struct ccase *c, int case_idx UNUSED) +{ + size_t i; + size_t n_vals; + struct reg_trns *trns = t_; + pspp_linreg_cache *model; + union value *output = NULL; + const union value **vals = NULL; + struct variable **vars = NULL; + + assert (trns != NULL); + model = trns->c; + assert (model != NULL); + assert (model->depvar != NULL); + assert (model->pred != NULL); + + vars = xnmalloc (model->n_coeffs, sizeof (*vars)); + n_vals = (*model->get_vars) (model, vars); + + vals = xnmalloc (n_vals, sizeof (*vals)); + output = case_data_rw (c, model->pred->fv); + assert (output != NULL); + + for (i = 0; i < n_vals; i++) + { + vals[i] = case_data (c, vars[i]->fv); + } + output->f = (*model->predict) ((const struct variable **) vars, + vals, model, n_vals); + free (vals); + free (vars); + return TRNS_CONTINUE; +} + +/* + Gets the residuals. + */ +static int +regression_trns_resid_proc (void *t_, struct ccase *c, int case_idx UNUSED) +{ + size_t i; + size_t n_vals; + struct reg_trns *trns = t_; + pspp_linreg_cache *model; + union value *output = NULL; + const union value **vals = NULL; + const union value *obs = NULL; + struct variable **vars = NULL; + + assert (trns != NULL); + model = trns->c; + assert (model != NULL); + assert (model->depvar != NULL); + assert (model->resid != NULL); + + vars = xnmalloc (model->n_coeffs, sizeof (*vars)); + n_vals = (*model->get_vars) (model, vars); + + vals = xnmalloc (n_vals, sizeof (*vals)); + output = case_data_rw (c, model->resid->fv); + assert (output != NULL); + + for (i = 0; i < n_vals; i++) + { + vals[i] = case_data (c, vars[i]->fv); + } + obs = case_data (c, model->depvar->fv); + output->f = (*model->residual) ((const struct variable **) vars, + vals, obs, model, n_vals); + free (vals); + free (vars); + return TRNS_CONTINUE; +} + +/* + Returns 0 if NAME is a duplicate of any existing variable name. +*/ +static int +try_name (char *name) +{ + if (dict_lookup_var (default_dict, name) != NULL) + return 0; + + return 1; +} +static void +reg_get_name (char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN]) +{ + int i = 1; + + snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); + while (!try_name (name)) + { + i++; + snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); + } +} +static void +reg_save_var (const char *prefix, trns_proc_func * f, + pspp_linreg_cache * c, struct variable **v, int n_trns) +{ + static int trns_index = 1; + char name[LONG_NAME_LEN]; + struct variable *new_var; + struct reg_trns *t = NULL; + + t = xmalloc (sizeof (*t)); + t->trns_id = trns_index; + t->n_trns = n_trns; + t->c = c; + reg_get_name (name, prefix); + new_var = dict_create_var (default_dict, name, 0); + assert (new_var != NULL); + *v = new_var; + add_transformation (f, regression_trns_free, t); + trns_index++; +} +static void +subcommand_save (int save, pspp_linreg_cache ** models) +{ + pspp_linreg_cache **lc; + int n_trns = 0; + int i; + + assert (models != NULL); + + if (save) + { + /* Count the number of transformations we will need. */ + for (i = 0; i < REGRESSION_SV_count; i++) + { + if (cmd.a_save[i]) + { + n_trns++; + } + } + n_trns *= cmd.n_dependent; + + 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 ("RES", regression_trns_resid_proc, *lc, + &(*lc)->resid, n_trns); + } + if (cmd.a_save[REGRESSION_SV_PRED]) + { + reg_save_var ("PRED", regression_trns_pred_proc, *lc, + &(*lc)->pred, n_trns); + } + } + } + else + { + for (lc = models; lc < models + cmd.n_dependent; lc++) + { + assert (*lc != NULL); + pspp_linreg_cache_free (*lc); + } + } +} static int reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) { @@ -529,7 +737,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) varlist = xnmalloc (c->n_indeps, sizeof (*varlist)); for (i = 1; i < c->n_indeps; i++) /* c->coeff[0] is the intercept. */ { - coeff = c->coeff + i; + coeff = c->coeff[i]; v = pspp_linreg_coeff_get_var (coeff, 0); if (v->type == ALPHA) { @@ -553,7 +761,7 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) for (i = 0; i < n_vars; i++) { - coeff = c->coeff + i; + coeff = c->coeff[i]; fprintf (fp, "%s.name = \"%s\";\n\t", varlist[i]->name, varlist[i]->name); fprintf (fp, "%s.n_vals = %d;\n\t", varlist[i]->name, @@ -579,11 +787,11 @@ reg_print_depvars (FILE * fp, pspp_linreg_cache * c) fprintf (fp, "char *model_depvars[%d] = {", c->n_indeps); for (i = 1; i < c->n_indeps; i++) { - coeff = c->coeff + i; + coeff = c->coeff[i]; v = pspp_linreg_coeff_get_var (coeff, 0); fprintf (fp, "\"%s\",\n\t\t", v->name); } - coeff = c->coeff + i; + coeff = c->coeff[i]; v = pspp_linreg_coeff_get_var (coeff, 0); fprintf (fp, "\"%s\"};\n\t", v->name); } @@ -598,26 +806,46 @@ reg_print_getvar (FILE * fp, pspp_linreg_cache * c) "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_linreg_coeff_get_var (c->coeff[i], 0); + if (v->type == ALPHA) + { + 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 increment; double tmp; - struct pspp_linreg_coeff coeff; + struct pspp_linreg_coeff *coeff; if (export) { - FILE *fp; assert (c != NULL); assert (model_file != NULL); + fp = fopen (fh_get_file_name (model_file), "w"); assert (fp != NULL); - fp = fopen (fh_get_filename (model_file), "w"); fprintf (fp, "%s", reg_preamble); reg_print_getvar (fp, c); - reg_print_categorical_encoding (fp, c); + if (reg_has_categorical (c)) + { + reg_print_categorical_encoding (fp, c); + } fprintf (fp, "%s", reg_export_t_quantiles_1); increment = 0.5 / (double) increment; for (i = 0; i < n_quantiles - 1; i++) @@ -636,12 +864,12 @@ subcommand_export (int export, pspp_linreg_cache * c) for (i = 1; i < c->n_indeps; i++) { coeff = c->coeff[i]; - fprintf (fp, "%.15e,\n\t\t", coeff.estimate); + fprintf (fp, "%.15e,\n\t\t", coeff->estimate); } coeff = c->coeff[i]; - fprintf (fp, "%.15e};\n\t", coeff.estimate); + fprintf (fp, "%.15e};\n\t", coeff->estimate); coeff = c->coeff[0]; - fprintf (fp, "double estimate = %.15e;\n\t", coeff.estimate); + 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); @@ -680,7 +908,7 @@ subcommand_export (int export, pspp_linreg_cache * c) } } static int -regression_custom_export (struct cmd_regression *cmd) +regression_custom_export (struct cmd_regression *cmd UNUSED) { /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */ if (!lex_force_match ('(')) @@ -706,28 +934,29 @@ cmd_regression (void) { if (!parse_regression (&cmd)) return CMD_FAILURE; + + models = xnmalloc (cmd.n_dependent, sizeof *models); if (!multipass_procedure_with_splits (run_regression, &cmd)) return CMD_CASCADING_FAILURE; - + subcommand_save (cmd.sbc_save, models); + free (v_variables); + free (models); return pspp_reg_rc; } /* - Is variable k one of the dependent variables? + Is variable k the dependent variable? */ static int -is_depvar (size_t k) +is_depvar (size_t k, const struct variable *v) { - size_t j = 0; - for (j = 0; j < cmd.n_dependent; j++) - { - /* - compare_var_names returns 0 if the variable - names match. - */ - if (!compare_var_names (cmd.v_dependent[j], cmd.v_variables[k], NULL)) - return 1; - } + /* + compare_var_names returns 0 if the variable + names match. + */ + if (!compare_var_names (v, v_variables[k], NULL)) + return 1; + return 0; } @@ -765,15 +994,100 @@ mark_missing_cases (const struct casefile *cf, struct variable *v, return n_data; } +/* Parser for the variables sub command */ +static int +regression_custom_variables (struct cmd_regression *cmd UNUSED) +{ + + lex_match ('='); + + if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL) + && token != T_ALL) + return 2; + + + if (!parse_variables (default_dict, &v_variables, &n_variables, PV_NONE)) + { + free (v_variables); + return 0; + } + assert (n_variables); + + return 1; +} + +/* + Count the explanatory variables. The user may or may + not have specified a response variable in the syntax. + */ +static int +get_n_indep (const struct variable *v) +{ + int result; + int i = 0; + + result = n_variables; + while (i < n_variables) + { + if (is_depvar (i, v)) + { + result--; + i = n_variables; + } + i++; + } + return result; +} + +/* + Read from the active file. Identify the explanatory variables in + v_variables. Encode categorical variables. Drop cases with missing + values. +*/ +static int +prepare_data (int n_data, int is_missing_case[], + struct variable **indep_vars, + struct variable *depvar, const struct casefile *cf) +{ + int i; + int j; + + assert (indep_vars != NULL); + j = 0; + for (i = 0; i < n_variables; i++) + { + if (!is_depvar (i, depvar)) + { + indep_vars[j] = v_variables[i]; + j++; + if (v_variables[i]->type == ALPHA) + { + /* Make a place to hold the binary vectors + corresponding to this variable's values. */ + cat_stored_values_create (v_variables[i]); + } + n_data = + mark_missing_cases (cf, v_variables[i], is_missing_case, n_data); + } + } + /* + Mark missing cases for the dependent variable. + */ + n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data); + + return n_data; +} + static bool -run_regression (const struct casefile *cf, void *cmd_ UNUSED) +run_regression (const struct ccase *first, + const struct casefile *cf, void *cmd_ UNUSED) { size_t i; - size_t n_data = 0; + size_t n_data = 0; /* Number of valide cases. */ + size_t n_cases; /* Number of cases. */ size_t row; size_t case_num; - int n_indep; - int j = 0; + int n_indep = 0; int k; /* Keep track of the missing cases. @@ -782,15 +1096,23 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) const union value *val; struct casereader *r; struct ccase c; - struct variable *v; - struct variable *depvar; struct variable **indep_vars; struct design_matrix *X; gsl_vector *Y; - pspp_linreg_cache *lcache; + pspp_linreg_opts lopts; - n_data = casefile_get_case_cnt (cf); + assert (models != NULL); + + output_split_file_values (first); + + if (!v_variables) + { + dict_get_vars (default_dict, &v_variables, &n_variables, + 1u << DC_SYSTEM); + } + + n_cases = casefile_get_case_cnt (cf); for (i = 0; i < cmd.n_dependent; i++) { @@ -802,52 +1124,24 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) } } - is_missing_case = xnmalloc (n_data, sizeof (*is_missing_case)); - for (i = 0; i < n_data; i++) - is_missing_case[i] = 0; - - n_indep = cmd.n_variables - cmd.n_dependent; - indep_vars = xnmalloc (n_indep, sizeof *indep_vars); + is_missing_case = xnmalloc (n_cases, sizeof (*is_missing_case)); lopts.get_depvar_mean_std = 1; - lopts.get_indep_mean_std = xnmalloc (n_indep, sizeof (int)); - /* - Read from the active file. The first pass encodes categorical - variables and drops cases with missing values. - */ - j = 0; - for (i = 0; i < cmd.n_variables; i++) + for (k = 0; k < cmd.n_dependent; k++) { - if (!is_depvar (i)) + n_indep = get_n_indep ((const struct variable *) cmd.v_dependent[k]); + lopts.get_indep_mean_std = xnmalloc (n_indep, sizeof (int)); + indep_vars = xnmalloc (n_indep, sizeof *indep_vars); + assert (indep_vars != NULL); + + for (i = 0; i < n_cases; i++) { - v = cmd.v_variables[i]; - indep_vars[j] = v; - j++; - if (v->type == ALPHA) - { - /* Make a place to hold the binary vectors - corresponding to this variable's values. */ - cat_stored_values_create (v); - } - n_data = mark_missing_cases (cf, v, is_missing_case, n_data); + is_missing_case[i] = 0; } - } - - /* - Drop cases with missing values for any dependent variable. - */ - j = 0; - for (i = 0; i < cmd.n_dependent; i++) - { - v = cmd.v_dependent[i]; - j++; - n_data = mark_missing_cases (cf, v, is_missing_case, n_data); - } - - for (k = 0; k < cmd.n_dependent; k++) - { - depvar = cmd.v_dependent[k]; + n_data = prepare_data (n_cases, is_missing_case, indep_vars, + cmd.v_dependent[k], + (const struct casefile *) cf); Y = gsl_vector_alloc (n_data); X = @@ -857,20 +1151,20 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) { lopts.get_indep_mean_std[i] = 1; } - lcache = pspp_linreg_cache_alloc (X->m->size1, X->m->size2); - lcache->indep_means = gsl_vector_alloc (X->m->size2); - lcache->indep_std = gsl_vector_alloc (X->m->size2); - lcache->depvar = (const struct variable *) depvar; + 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 = (const struct variable *) cmd.v_dependent[k]; /* For large data sets, use QR decomposition. */ if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA) { - lcache->method = PSPP_LINREG_SVD; + models[k]->method = PSPP_LINREG_SVD; } /* - The second pass creates the design matrix. + The second pass fills the design matrix. */ row = 0; for (r = casefile_get_reader (cf); casereader_read (r, &c); @@ -880,12 +1174,12 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) case_num = casereader_cnum (r) - 1; if (!is_missing_case[case_num]) { - for (i = 0; i < cmd.n_variables; ++i) /* Iterate over the variables - for the current case. - */ + for (i = 0; i < n_variables; ++i) /* Iterate over the + variables for the + current case. + */ { - v = cmd.v_variables[i]; - val = case_data (&c, v->fv); + val = case_data (&c, v_variables[i]->fv); /* Independent/dependent variable separation. The 'variables' subcommand specifies a varlist which contains @@ -894,19 +1188,21 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) subcommand, and maybe also in the 'variables' subcommand. We need to separate the two. */ - if (!is_depvar (i)) + if (!is_depvar (i, cmd.v_dependent[k])) { - if (v->type == ALPHA) + if (v_variables[i]->type == ALPHA) { - design_matrix_set_categorical (X, row, v, val); + design_matrix_set_categorical (X, row, + v_variables[i], val); } - else if (v->type == NUMERIC) + else if (v_variables[i]->type == NUMERIC) { - design_matrix_set_numeric (X, row, v, val); + design_matrix_set_numeric (X, row, v_variables[i], + val); } } } - val = case_data (&c, depvar->fv); + val = case_data (&c, cmd.v_dependent[k]->fv); gsl_vector_set (Y, row, val->f); row++; } @@ -916,21 +1212,22 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) and store pointers to the variables that correspond to the coefficients. */ - pspp_linreg_coeff_init (lcache, X); + pspp_linreg_coeff_init (models[k], X); /* Find the least-squares estimates and other statistics. */ - pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, lcache); - subcommand_statistics (cmd.a_statistics, lcache); - subcommand_export (cmd.sbc_export, lcache); + pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]); + subcommand_statistics (cmd.a_statistics, models[k]); + subcommand_export (cmd.sbc_export, models[k]); + gsl_vector_free (Y); design_matrix_destroy (X); - pspp_linreg_cache_free (lcache); + free (indep_vars); free (lopts.get_indep_mean_std); casereader_destroy (r); } - free (indep_vars); + free (is_missing_case); return true;