X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=7baaef9109f9a1a66a71c82e687c828deaa3df16;hb=9105b67fe006fe41c044e3659325594a52d0c899;hp=11a1f211c87c35889413634a652ab715825c5b8a;hpb=7706bddea46fd0f90e8b74214d05639f53702c11;p=pspp-builds.git diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q index 11a1f211..7baaef91 100644 --- a/src/language/stats/regression.q +++ b/src/language/stats/regression.q @@ -1,6 +1,5 @@ /* PSPP - linear regression. Copyright (C) 2005 Free Software Foundation, Inc. - Written by Jason H Stover . This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as @@ -18,32 +17,38 @@ 02110-1301, USA. */ #include -#include + #include -#include #include +#include #include -#include +#include + +#include "regression-export.h" #include #include -#include #include -#include -#include -#include +#include #include -#include +#include +#include +#include +#include +#include +#include +#include #include -#include "gettext.h" #include +#include +#include +#include +#include +#include #include -#include -#include -#include "regression-export.h" +#include #include -#include -#include -#include "procedure.h" + +#include "gettext.h" #define REG_LARGE_DATA 1000 @@ -52,36 +57,58 @@ /* (specification) "REGRESSION" (regression_): *variables=custom; - statistics[st_]=r, - coeff, - anova, - outs, - zpp, - label, - sha, - ci, - bcov, - ses, - xtx, - collin, - tol, - selection, - f, - defaults, - all; + +statistics[st_]=r, + coeff, + anova, + outs, + zpp, + label, + sha, + ci, + bcov, + ses, + xtx, + collin, + tol, + selection, + f, + defaults, + all; export=custom; ^dependent=varlist; - save=residuals; - method=enter. + +save[sv_]=resid,pred; + +method=enter. */ /* (declarations) */ /* (functions) */ static struct cmd_regression cmd; +/* + Moments for each of the variables used. + */ +struct moments_var +{ + struct moments1 *m; + const struct variable *v; +}; + +/* Linear regression models. */ +static 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. */ +}; /* Variables used (both explanatory and response). */ -static struct variable **v_variables; +static const struct variable **v_variables; /* Number of variables. @@ -92,14 +119,16 @@ static size_t n_variables; File where the model will be saved if the EXPORT subcommand is given. */ -struct file_handle *model_file; +static struct file_handle *model_file; /* Return value for the procedure. */ -int pspp_reg_rc = CMD_SUCCESS; +static 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 *, + const struct dataset *); /* STATISTICS subcommand output functions. @@ -194,7 +223,7 @@ 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); @@ -206,11 +235,11 @@ reg_stats_coeff (pspp_linreg_cache * c) tab_float (t, 6, 1, 0, pval, 10, 2); for (j = 1; j <= c->n_indeps; j++) { - v = pspp_linreg_coeff_get_var (c->coeff + j, 0); + 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); - if (v->type == ALPHA) + if (var_is_alpha (v)) { /* Append the value associated with this coefficient. @@ -218,8 +247,8 @@ reg_stats_coeff (pspp_linreg_cache * c) for that value. */ - val = pspp_linreg_coeff_get_value (c->coeff + j, v); - val_s = value_to_string (val, v); + val = pspp_coeff_get_value (c->coeff[j], v); + val_s = var_get_value_name (v, val); strncat (tmp, val_s, MAX_STRING); } @@ -227,7 +256,7 @@ 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. @@ -250,7 +279,9 @@ reg_stats_coeff (pspp_linreg_cache * c) /* P values for the test statistic above. */ - pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); + 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_title (t, _("Coefficients")); @@ -373,7 +404,7 @@ reg_stats_bcov (pspp_linreg_cache * c) tab_text (t, 1, 1, TAB_CENTER | TAT_TITLE, _("Covariances")); for (i = 1; i < c->n_coeffs; i++) { - const struct variable *v = pspp_linreg_coeff_get_var (c->coeff + i, 0); + const struct variable *v = pspp_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); @@ -501,37 +532,203 @@ 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, + casenumber 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); + assert (output != NULL); + + for (i = 0; i < n_vals; i++) + { + vals[i] = case_data (c, vars[i]); + } + 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, + casenumber 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); + assert (output != NULL); + + for (i = 0; i < n_vals; i++) + { + vals[i] = case_data (c, vars[i]); + } + obs = case_data (c, model->depvar); + output->f = (*model->residual) ((const struct variable **) vars, + vals, obs, model, n_vals); + free (vals); + free (vars); + return TRNS_CONTINUE; +} + +/* + Returns false if NAME is a duplicate of any existing variable name. +*/ +static bool +try_name (const struct dictionary *dict, const char *name) +{ + if (dict_lookup_var (dict, name) != NULL) + return false; + + return true; +} + +static void +reg_get_name (const struct dictionary *dict, 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 (dict, name)) + { + i++; + snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i); + } +} + +static void +reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f, + pspp_linreg_cache * c, struct variable **v, int n_trns) +{ + struct dictionary *dict = dataset_dict (ds); + 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 (dict, name, prefix); + new_var = dict_create_var (dict, name, 0); + assert (new_var != NULL); + *v = new_var; + add_transformation (ds, f, regression_trns_free, t); + trns_index++; +} + static void -subcommand_save (int save, pspp_linreg_cache *lc, const struct casefile *cf, int *is_missing) +subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models) { + pspp_linreg_cache **lc; + int n_trns = 0; int i; - int k; - int case_num; - double residual; - const union value **vals; - struct casereader *r; - struct ccase c; - assert (lc != NULL); + assert (models != NULL); + if (save) { - vals = xnmalloc (n_variables, sizeof (*vals)); - for (r = casefile_get_reader (cf); casereader_read (r, &c); - case_destroy (&c)) + /* Count the number of transformations we will need. */ + for (i = 0; i < REGRESSION_SV_count; i++) { - case_num = casereader_cnum (r) - 1; - if (!is_missing[case_num]) + if (cmd.a_save[i]) { - for (i = 0; i < n_variables; ++i) - { - vals[i] = case_data (&c, v_variables[i]->fv); - } - residual = (*lc->predict) (v_variables, vals, lc, n_variables); + 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 (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); + } + } + } + else + { + for (lc = models; lc < models + cmd.n_dependent; lc++) + { + if (*lc != NULL) + { + pspp_linreg_cache_free (*lc); } } - free (vals); } } + static int reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) { @@ -539,37 +736,34 @@ reg_inserted (const struct variable *v, struct variable **varlist, int n_vars) for (i = 0; i < n_vars; i++) { - if (v->index == varlist[i]->index) + if (v == varlist[i]) { return 1; } } return 0; } + static void reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) { int i; - size_t j; int n_vars = 0; struct variable **varlist; - struct pspp_linreg_coeff *coeff; - const struct variable *v; - union value *val; 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. */ { - coeff = c->coeff + i; - v = pspp_linreg_coeff_get_var (coeff, 0); - if (v->type == ALPHA) + 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", - v->name); + var_get_name (v)); varlist[n_vars] = (struct variable *) v; n_vars++; } @@ -580,23 +774,26 @@ reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c) n_vars); for (i = 0; i < n_vars - 1; i++) { - fprintf (fp, "&%s,\n\t\t", varlist[i]->name); + fprintf (fp, "&%s,\n\t\t", var_get_name (varlist[i])); } - fprintf (fp, "&%s};\n\t", varlist[i]->name); + fprintf (fp, "&%s};\n\t", var_get_name (varlist[i])); for (i = 0; i < n_vars; 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, - varlist[i]->obs_vals->n_categories); + int n_categories = cat_get_n_categories (varlist[i]); + int j; - for (j = 0; j < varlist[i]->obs_vals->n_categories; 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++) { - val = cat_subscript_to_value ((const size_t) j, varlist[i]); - fprintf (fp, "%s.values[%d] = \"%s\";\n\t", varlist[i]->name, j, - value_to_string (val, varlist[i])); + 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); @@ -606,19 +803,19 @@ static void reg_print_depvars (FILE * fp, pspp_linreg_cache * c) { int i; - struct pspp_linreg_coeff *coeff; + 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_linreg_coeff_get_var (coeff, 0); - fprintf (fp, "\"%s\",\n\t\t", v->name); + 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_linreg_coeff_get_var (coeff, 0); - fprintf (fp, "\"%s\"};\n\t", v->name); + 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) @@ -636,14 +833,12 @@ 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; - } + v = pspp_coeff_get_var (c->coeff[i], 0); + if (var_is_alpha (v)) + return 1; } return 0; } @@ -655,15 +850,14 @@ subcommand_export (int export, pspp_linreg_cache * c) size_t i; size_t j; int n_quantiles = 100; - double increment; double tmp; - struct pspp_linreg_coeff coeff; + struct pspp_coeff *coeff; if (export) { assert (c != NULL); assert (model_file != NULL); - fp = fopen (fh_get_filename (model_file), "w"); + fp = fopen (fh_get_file_name (model_file), "w"); assert (fp != NULL); fprintf (fp, "%s", reg_preamble); reg_print_getvar (fp, c); @@ -672,7 +866,6 @@ subcommand_export (int export, pspp_linreg_cache * 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++) { tmp = 0.5 + 0.005 * (double) i; @@ -689,12 +882,12 @@ 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); @@ -732,77 +925,87 @@ subcommand_export (int export, pspp_linreg_cache * c) fclose (fp); } } + static int -regression_custom_export (struct cmd_regression *cmd UNUSED) +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 ('(')) + if (!lex_force_match (lexer, '(')) return 0; - if (lex_match ('*')) + if (lex_match (lexer, '*')) model_file = NULL; else { - model_file = fh_parse (FH_REF_FILE); + model_file = fh_parse (lexer, FH_REF_FILE); if (model_file == NULL) return 0; } - if (!lex_force_match (')')) + if (!lex_force_match (lexer, ')')) return 0; return 1; } int -cmd_regression (void) +cmd_regression (struct lexer *lexer, struct dataset *ds) { - if (!parse_regression (&cmd)) + size_t i; + + if (!parse_regression (lexer, ds, &cmd, NULL)) return CMD_FAILURE; - if (!multipass_procedure_with_splits (run_regression, &cmd)) - return CMD_CASCADING_FAILURE; + models = xnmalloc (cmd.n_dependent, sizeof *models); + for (i = 0; i < cmd.n_dependent; i++) + { + models[i] = NULL; + } + if (!multipass_procedure_with_splits (ds, run_regression, &cmd)) + return CMD_CASCADING_FAILURE; + subcommand_save (ds, cmd.sbc_save, models); free (v_variables); - + free (models); return pspp_reg_rc; } /* Is variable k the dependent variable? */ -static int +static bool is_depvar (size_t k, const struct variable *v) { - /* - compare_var_names returns 0 if the variable - names match. - */ - if (!compare_var_names (v, v_variables[k], NULL)) - return 1; - - return 0; + return v == v_variables[k]; } /* Mark missing cases. Return the number of non-missing cases. + Compute the first two moments. */ static size_t -mark_missing_cases (const struct casefile *cf, struct variable *v, - int *is_missing_case, double n_data) +mark_missing_cases (const struct casefile *cf, const struct variable *v, + int *is_missing_case, double n_data, + struct moments_var *mom) { struct casereader *r; struct ccase c; size_t row; const union value *val; + double w = 1.0; - for (r = casefile_get_reader (cf); + for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c); case_destroy (&c)) { row = casereader_cnum (r) - 1; - val = case_data (&c, v->fv); + val = case_data (&c, v); + if (mom != NULL) + { + moments1_add (mom->m, val->f, w); + } cat_value_update (v, val); - if (mv_is_value_missing (&v->miss, val)) + if (var_is_value_missing (v, val, MV_ANY)) { if (!is_missing_case[row]) { @@ -819,32 +1022,37 @@ mark_missing_cases (const struct casefile *cf, struct variable *v, /* Parser for the variables sub command */ static int -regression_custom_variables(struct cmd_regression *cmd UNUSED) +regression_custom_variables (struct lexer *lexer, struct dataset *ds, + struct cmd_regression *cmd UNUSED, + void *aux UNUSED) { + const struct dictionary *dict = dataset_dict (ds); - lex_match('='); + lex_match (lexer, '='); - if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL) - && token != T_ALL) + if ((lex_token (lexer) != T_ID + || dict_lookup_var (dict, lex_tokid (lexer)) == NULL) + && lex_token (lexer) != T_ALL) return 2; - - if (!parse_variables (default_dict, &v_variables, &n_variables, - PV_NONE )) + + if (!parse_variables_const + (lexer, dict, &v_variables, &n_variables, PV_NONE)) { free (v_variables); return 0; } - assert(n_variables); + 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) +static int +get_n_indep (const struct variable *v) { int result; int i = 0; @@ -861,16 +1069,17 @@ int get_n_indep (const struct variable *v) } 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) +static int +prepare_data (int n_data, int is_missing_case[], + const struct variable **indep_vars, + const struct variable *depvar, const struct casefile *cf, + struct moments_var *mom) { int i; int j; @@ -878,33 +1087,78 @@ int prepare_data (int n_data, int is_missing_case[], 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) + if (var_is_alpha (v_variables[i])) { /* Make a place to hold the binary vectors - corresponding to this variable's values. */ + 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); + n_data = + mark_missing_cases (cf, v_variables[i], is_missing_case, n_data, + mom + i); } } /* - Mark missing cases for the dependent variable. + Mark missing cases for the dependent variable. */ - n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data); + n_data = mark_missing_cases (cf, depvar, is_missing_case, n_data, NULL); return n_data; } +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); +} + +/* + 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 (const struct casefile *cf, void *cmd_ UNUSED) +run_regression (const struct ccase *first, + const struct casefile *cf, void *cmd_ UNUSED, + const struct dataset *ds) { size_t i; - size_t n_data = 0; /* Number of valide cases. */ - size_t n_cases; /* Number of cases. */ + 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 = 0; @@ -916,15 +1170,20 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) const union value *val; struct casereader *r; struct ccase c; - struct variable **indep_vars; + const struct variable **indep_vars; struct design_matrix *X; + struct moments_var *mom; gsl_vector *Y; - pspp_linreg_cache *lcache; + pspp_linreg_opts lopts; + assert (models != NULL); + + output_split_file_values (ds, first); + if (!v_variables) { - dict_get_vars (default_dict, &v_variables, &n_variables, + dict_get_vars (dataset_dict (ds), &v_variables, &n_variables, 1u << DC_SYSTEM); } @@ -932,7 +1191,7 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) for (i = 0; i < cmd.n_dependent; i++) { - if (cmd.v_dependent[i]->type != NUMERIC) + if (!var_is_numeric (cmd.v_dependent[i])) { msg (SE, gettext ("Dependent variable must be numeric.")); pspp_reg_rc = CMD_FAILURE; @@ -941,109 +1200,122 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED) } is_missing_case = xnmalloc (n_cases, sizeof (*is_missing_case)); - + mom = xnmalloc (n_variables, sizeof (*mom)); + for (i = 0; i < n_variables; i++) + { + (mom + i)->m = moments1_create (MOMENT_VARIANCE); + (mom + i)->v = v_variables[i]; + } lopts.get_depvar_mean_std = 1; - for (k = 0; k < cmd.n_dependent; k++) { 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); + indep_vars = xnmalloc (n_indep, sizeof *indep_vars); assert (indep_vars != NULL); for (i = 0; i < n_cases; i++) { is_missing_case[i] = 0; } - 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 = - design_matrix_create (n_indep, (const struct variable **) indep_vars, - n_data); - for (i = 0; i < X->m->size2; i++) - { - 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 *) 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; - } - - /* - The second pass creates the design matrix. - */ - row = 0; - for (r = casefile_get_reader (cf); casereader_read (r, &c); - case_destroy (&c)) - /* Iterate over the cases. */ + n_data = prepare_data (n_cases, is_missing_case, indep_vars, + cmd.v_dependent[k], + (const struct casefile *) cf, mom); + if (n_data > 0) { - case_num = casereader_cnum (r) - 1; - if (!is_missing_case[case_num]) + Y = gsl_vector_alloc (n_data); + + X = + design_matrix_create (n_indep, (const struct variable **) indep_vars, + n_data); + for (i = 0; i < X->m->size2; i++) + { + 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 = (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) + { + models[k]->method = PSPP_LINREG_SVD; + } + + /* + The second pass fills the design matrix. + */ + row = 0; + for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c); + case_destroy (&c)) + /* Iterate over the cases. */ { - for (i = 0; i < n_variables; ++i) /* Iterate over the - variables for the - current case. - */ + case_num = casereader_cnum (r) - 1; + if (!is_missing_case[case_num]) { - val = case_data (&c, v_variables[i]->fv); - /* - Independent/dependent variable separation. The - 'variables' subcommand specifies a varlist which contains - both dependent and independent variables. The dependent - variables are specified with the 'dependent' - subcommand, and maybe also in the 'variables' subcommand. - We need to separate the two. - */ - if (!is_depvar (i, cmd.v_dependent[k])) + for (i = 0; i < n_variables; ++i) /* Iterate over the + variables for the + current case. + */ { - if (v_variables[i]->type == ALPHA) - { - design_matrix_set_categorical (X, row, v_variables[i], val); - } - else if (v_variables[i]->type == NUMERIC) + val = case_data (&c, v_variables[i]); + /* + Independent/dependent variable separation. The + 'variables' subcommand specifies a varlist which contains + both dependent and independent variables. The dependent + variables are specified with the 'dependent' + subcommand, and maybe also in the 'variables' subcommand. + We need to separate the two. + */ + if (!is_depvar (i, cmd.v_dependent[k])) { - design_matrix_set_numeric (X, row, v_variables[i], val); + if (var_is_alpha (v_variables[i])) + { + design_matrix_set_categorical (X, row, + v_variables[i], val); + } + else + { + design_matrix_set_numeric (X, row, v_variables[i], + val); + } } } + val = case_data (&c, cmd.v_dependent[k]); + gsl_vector_set (Y, row, val->f); + row++; } - val = case_data (&c, cmd.v_dependent[k]->fv); - gsl_vector_set (Y, row, val->f); - row++; } + /* + Now that we know the number of coefficients, allocate space + and store pointers to the variables that correspond to the + coefficients. + */ + coeff_init (models[k], X); + + /* + 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); + subcommand_statistics (cmd.a_statistics, models[k]); + subcommand_export (cmd.sbc_export, models[k]); + + gsl_vector_free (Y); + design_matrix_destroy (X); + free (indep_vars); + free (lopts.get_indep_mean_std); + casereader_destroy (r); } - /* - Now that we know the number of coefficients, allocate space - and store pointers to the variables that correspond to the - coefficients. - */ - pspp_linreg_coeff_init (lcache, 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_save (cmd.sbc_save, lcache, cf, is_missing_case); - subcommand_export (cmd.sbc_export, lcache); - gsl_vector_free (Y); - design_matrix_destroy (X); - free (indep_vars); - pspp_linreg_cache_free (lcache); - free (lopts.get_indep_mean_std); - casereader_destroy (r); } - + for (i = 0; i < n_variables; i++) + { + moments1_destroy ((mom + i)->m); + } + free (mom); free (is_missing_case); return true;