X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fregression.q;h=60f3c39f121075fee4d8e514b7197d9aea779eff;hb=f3cf52b51e6d89e94190de22b1fa813e8d3746f7;hp=d6ebc5200e313878515ac4aef77c6fdca11bd240;hpb=1f8dd363d6c20d07fcca14cb948018465fa5ed8b;p=pspp-builds.git diff --git a/src/regression.q b/src/regression.q index d6ebc520..60f3c39f 100644 --- a/src/regression.q +++ b/src/regression.q @@ -24,18 +24,27 @@ #include #include "alloc.h" #include "case.h" +#include "casefile.h" +#include "cat.h" +#include "cat-routines.h" +#include "command.h" +#include "design-matrix.h" #include "dictionary.h" +#include "error.h" #include "file-handle.h" -#include "command.h" +#include "gettext.h" #include "lexer.h" +#include +#include "missing-values.h" +#include "regression_export.h" #include "tab.h" +#include "value-labels.h" #include "var.h" #include "vfm.h" -#include "casefile.h" -#include -#include "cat.h" -/* (headers) */ +#define REG_LARGE_DATA 1000 + +/* (headers) */ /* (specification) "REGRESSION" (regression_): @@ -57,8 +66,9 @@ f, defaults, all; + export=custom; ^dependent=varlist; - ^method=enter. + method=enter. */ /* (declarations) */ /* (functions) */ @@ -69,6 +79,17 @@ static struct cmd_regression cmd; */ size_t *indep_vars; +/* + File where the model will be saved if the EXPORT subcommand + is given. + */ +struct file_handle *model_file; + +/* + Return value for the procedure. + */ +int pspp_reg_rc = CMD_SUCCESS; + static void run_regression (const struct casefile *, void *); /* STATISTICS subcommand output functions. @@ -94,7 +115,34 @@ static void statistics_keyword_output (void (*)(pspp_linreg_cache *), static void reg_stats_r (pspp_linreg_cache * c) { + struct tab_table *t; + int n_rows = 2; + int n_cols = 5; + double rsq; + double adjrsq; + double std_error; + assert (c != NULL); + 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 ((c->n_indeps - 1.0) / (c->n_obs - 1.0)); + t = tab_create (n_cols, n_rows, 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); + tab_vline (t, TAL_0, 1, 0, 0); + + tab_text (t, 1, 0, TAB_CENTER | TAT_TITLE, _("R")); + tab_text (t, 2, 0, TAB_CENTER | TAT_TITLE, _("R Square")); + tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Adjusted R Square")); + tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Std. Error of the Estimate")); + tab_float (t, 1, 1, TAB_RIGHT, sqrt (rsq), 10, 2); + 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_submit (t); } /* @@ -116,7 +164,8 @@ reg_stats_coeff (pspp_linreg_cache * c) struct tab_table *t; assert (c != NULL); - n_rows = 2 + c->param_estimates->size; + n_rows = c->n_coeffs + 2; + t = tab_create (n_cols, n_rows, 0); tab_headers (t, 2, 0, 1, 0); tab_dim (t, tab_natural_dimensions); @@ -131,7 +180,7 @@ 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 = gsl_vector_get (c->param_estimates, 0); + 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); @@ -141,40 +190,39 @@ reg_stats_coeff (pspp_linreg_cache * c) 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 = 0; j < c->n_indeps; j++) + for (j = 1; j <= c->n_indeps; j++) { i = indep_vars[j]; - struct variable *v = cmd.v_variables[i]; - label = var_to_string (v); - tab_text (t, 1, j + 2, TAB_CENTER, label); + label = var_to_string (c->coeff[j].v); + tab_text (t, 1, j + 1, TAB_CENTER, label); /* Regression coefficients. */ - coeff = gsl_vector_get (c->param_estimates, j + 1); - tab_float (t, 2, j + 2, 0, coeff, 10, 2); + coeff = c->coeff[j].estimate; + tab_float (t, 2, j + 1, 0, coeff, 10, 2); /* Standard error of the coefficients. */ - std_err = sqrt (gsl_matrix_get (c->cov, j + 1, j + 1)); - tab_float (t, 3, j + 2, 0, std_err, 10, 2); + std_err = sqrt (gsl_matrix_get (c->cov, j, j)); + tab_float (t, 3, j + 1, 0, std_err, 10, 2); /* 'Standardized' coefficient, i.e., regression coefficient if all variables had unit variance. */ - beta = gsl_vector_get (c->indep_std, j + 1); + beta = gsl_vector_get (c->indep_std, j); beta *= coeff / c->depvar_std; - tab_float (t, 4, j + 2, 0, beta, 10, 2); + tab_float (t, 4, j + 1, 0, beta, 10, 2); /* Test statistic for H0: coefficient is 0. */ t_stat = coeff / std_err; - tab_float (t, 5, j + 2, 0, t_stat, 10, 2); + tab_float (t, 5, j + 1, 0, t_stat, 10, 2); /* P values for the test statistic above. */ pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0); - tab_float (t, 6, j + 2, 0, pval, 10, 2); + tab_float (t, 6, j + 1, 0, pval, 10, 2); } tab_title (t, 0, _("Coefficients")); tab_submit (t); @@ -272,7 +320,45 @@ reg_stats_f (pspp_linreg_cache * c) static void reg_stats_bcov (pspp_linreg_cache * c) { + int n_cols; + int n_rows; + int i; + int j; + int k; + int row; + int col; + const char *label; + struct tab_table *t; + 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); + 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); + 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++) + { + j = indep_vars[(i - 1)]; + struct variable *v = cmd.v_variables[j]; + 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++) + { + col = (i <= k) ? k : i; + row = (i <= k) ? i : k; + tab_float (t, k + 2, i, TAB_CENTER, + gsl_matrix_get (c->cov, row, col), 8, 3); + } + } + tab_title (t, 0, _("Coefficient Correlations")); + tab_submit (t); } static void reg_stats_ses (pspp_linreg_cache * c) @@ -346,7 +432,7 @@ subcommand_statistics (int *keywords, pspp_linreg_cache * c) */ for (i = 0; i < f; i++) { - *(keywords + i) = 1; + keywords[i] = 1; } } else @@ -365,10 +451,10 @@ subcommand_statistics (int *keywords, pspp_linreg_cache * c) */ if (keywords[defaults] | d) { - *(keywords + anova) = 1; - *(keywords + outs) = 1; - *(keywords + coeff) = 1; - *(keywords + r) = 1; + keywords[anova] = 1; + keywords[outs] = 1; + keywords[coeff] = 1; + keywords[r] = 1; } } statistics_keyword_output (reg_stats_r, keywords[r], c); @@ -387,6 +473,202 @@ 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); } +static int +reg_inserted (struct variable *v, struct variable **varlist, int n_vars) +{ + int i; + + for (i = 0; i < n_vars; i++) + { + if (v->index == varlist[i]->index) + { + 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; + 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]; + if (coeff.v->type == ALPHA) + { + if (!reg_inserted (coeff.v, varlist, n_vars)) + { + fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t", + coeff.v->name); + varlist[n_vars] = coeff.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", varlist[i]->name); + } + fprintf (fp, "&%s};\n\t", varlist[i]->name); + + 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); + + for (j = 0; j < varlist[i]->obs_vals->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])); + } + } + fprintf (fp, "%s", reg_export_categorical_encode_2); +} + +static void +reg_print_depvars (FILE * fp, pspp_linreg_cache * c) +{ + int i; + struct pspp_linreg_coeff coeff; + + fprintf (fp, "char *model_depvars[%d] = {", c->n_indeps); + for (i = 1; i < c->n_indeps; i++) + { + coeff = c->coeff[i]; + fprintf (fp, "\"%s\",\n\t\t", coeff.v->name); + } + coeff = c->coeff[i]; + fprintf (fp, "\"%s\"};\n\t", coeff.v->name); +} +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 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; + + if (export) + { + assert (c != NULL); + assert (model_file != NULL); + assert (fp != NULL); + fp = fopen (handle_get_filename (model_file), "w"); + fprintf (fp, "%s", reg_preamble); + reg_print_getvar (fp, 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; + 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 cmd_regression *cmd) +{ + /* 0 on failure, 1 on success, 2 on failure that should result in syntax error */ + if (!lex_force_match ('(')) + return 0; + + if (lex_match ('*')) + model_file = NULL; + else + { + model_file = fh_parse (); + if (model_file == NULL) + return 0; + } + + if (!lex_force_match (')')) + return 0; + + return 1; +} int cmd_regression (void) @@ -397,7 +679,7 @@ cmd_regression (void) } multipass_procedure_with_splits (run_regression, &cmd); - return CMD_SUCCESS; + return pspp_reg_rc; } /* @@ -419,124 +701,215 @@ is_depvar (size_t k) return 0; } +/* + Mark missing cases. Return the number of non-missing cases. + */ +static size_t +mark_missing_cases (const struct casefile *cf, struct variable *v, + double *is_missing_case, double n_data) +{ + struct casereader *r; + struct ccase c; + size_t row; + union value *val; + + for (r = casefile_get_reader (cf); + casereader_read (r, &c); case_destroy (&c)) + { + row = casereader_cnum (r) - 1; + + val = case_data (&c, v->fv); + cat_value_update (v, val); + if (mv_is_value_missing (&v->miss, val)) + { + if (!is_missing_case[row]) + { + /* Now it is missing. */ + n_data--; + is_missing_case[row] = 1; + } + } + } + casereader_destroy (r); + + return n_data; +} static void -run_regression (const struct casefile *cf, void *cmd_) +run_regression (const struct casefile *cf, void *cmd_ UNUSED) { size_t i; - size_t k; size_t n_data = 0; size_t row; + size_t case_num; int n_indep; + int j = 0; + int k; + /* + Keep track of the missing cases. + */ + int *is_missing_case; const union value *val; struct casereader *r; - struct casereader *r2; struct ccase c; - const struct variable *v; - struct recoded_categorical_array *ca; - struct recoded_categorical *rc; + 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); + + for (i = 0; i < cmd.n_dependent; i++) + { + if (cmd.v_dependent[i]->type != NUMERIC) + { + msg (SE, gettext ("Dependent variable must be numeric.")); + pspp_reg_rc = CMD_FAILURE; + return; + } + } + + 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 = (size_t *) malloc (n_indep * sizeof (*indep_vars)); + indep_vars = xnmalloc (n_indep, sizeof *indep_vars); - Y = gsl_vector_alloc (n_data); lopts.get_depvar_mean_std = 1; - lopts.get_indep_mean_std = (int *) malloc (n_indep * sizeof (int)); - - lcache = pspp_linreg_cache_alloc (n_data, n_indep); - lcache->indep_means = gsl_vector_alloc (n_indep); - lcache->indep_std = gsl_vector_alloc (n_indep); + lopts.get_indep_mean_std = xnmalloc (n_indep, sizeof (int)); /* Read from the active file. The first pass encodes categorical - variables. + variables and drops cases with missing values. */ - ca = cr_recoded_cat_ar_create (cmd.n_variables, cmd.v_variables); - for (r = casefile_get_reader (cf); - casereader_read (r, &c); case_destroy (&c)) + j = 0; + for (i = 0; i < cmd.n_variables; i++) { - for (i = 0; i < ca->n_vars; i++) + if (!is_depvar (i)) { - v = (*(ca->a + i))->v; - val = case_data (&c, v->fv); - cr_value_update (*(ca->a + i), val); + 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); } } - cr_create_value_matrices (ca); - X = - design_matrix_create (n_indep, (const struct variable **) cmd.v_variables, - ca, n_data); /* - The second pass creates the design matrix. + Drop cases with missing values for any dependent variable. */ - for (r2 = casefile_get_reader (cf); casereader_read (r2, &c); - case_destroy (&c)) - /* Iterate over the cases. */ + 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++) { - k = 0; - row = casereader_cnum (r2) - 1; - for (i = 0; i < cmd.n_variables; ++i) /* Iterate over the variables - for the current case. - */ + depvar = cmd.v_dependent[k]; + 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++) { - v = cmd.v_variables[i]; - val = case_data (&c, v->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. We need to separate the two. - */ - if (is_depvar (i)) - { - if (v->type == NUMERIC) - { - gsl_vector_set (Y, row, val->f); - } - else - { - errno = EINVAL; - fprintf (stderr, - "%s:%d: Dependent variable should be numeric: %s\n", - __FILE__, __LINE__, strerror (errno)); - err_cond_fail (); - } - } - else + 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; + /* + 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. */ + { + case_num = casereader_cnum (r) - 1; + if (!is_missing_case[case_num]) { - if (v->type == ALPHA) - { - rc = cr_var_to_recoded_categorical (v, ca); - design_matrix_set_categorical (X, row, v, val, rc); - } - else if (v->type == NUMERIC) + for (i = 0; i < cmd.n_variables; ++i) /* Iterate over the variables + for the current case. + */ { - design_matrix_set_numeric (X, row, v, val); + v = cmd.v_variables[i]; + val = case_data (&c, v->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)) + { + if (v->type == ALPHA) + { + design_matrix_set_categorical (X, row, v, val); + } + else if (v->type == NUMERIC) + { + design_matrix_set_numeric (X, row, v, val); + } + } } - - indep_vars[k] = i; - k++; - lopts.get_indep_mean_std[i] = 1; + val = case_data (&c, depvar->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. + */ + lcache->coeff = xnmalloc (X->m->size2 + 1, sizeof (*lcache->coeff)); + for (i = 0; i < X->m->size2; i++) + { + j = i + 1; /* The first coeff is the intercept. */ + lcache->coeff[j].v = + (const struct variable *) design_matrix_col_to_var (X, i); + assert (lcache->coeff[j].v != NULL); + } + + /* + 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); + gsl_vector_free (Y); + design_matrix_destroy (X); + pspp_linreg_cache_free (lcache); + free (lopts.get_indep_mean_std); + casereader_destroy (r); } - /* - Find the least-squares estimates and other statistics. - */ - pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, lcache); - subcommand_statistics (cmd.a_statistics, lcache); - gsl_vector_free (Y); - design_matrix_destroy (X); - pspp_linreg_cache_free (lcache); - free (lopts.get_indep_mean_std); free (indep_vars); - casereader_destroy (r); + free (is_missing_case); + + return; } /*