/* PSPP - a program for statistical analysis.
- Copyright (C) 2005 Free Software Foundation, Inc.
+ Copyright (C) 2005, 2009 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
#include <math.h>
#include <stdlib.h>
-#include "regression-export.h"
#include <data/case.h>
#include <data/casegrouper.h>
#include <data/casereader.h>
#include <language/dictionary/split-file.h>
#include <language/data-io/file-handle.h>
#include <language/lexer/lexer.h>
-#include <libpspp/alloc.h>
#include <libpspp/compiler.h>
#include <libpspp/message.h>
#include <libpspp/taint.h>
#include <math/design-matrix.h>
#include <math/coefficient.h>
-#include <math/linreg/linreg.h>
+#include <math/linreg.h>
#include <math/moments.h>
#include <output/table.h>
+#include "xalloc.h"
+
#include "gettext.h"
#define _(msgid) gettext (msgid)
f,
defaults,
all;
- export=custom;
^dependent=varlist;
+save[sv_]=resid,pred;
+method=enter.
const struct variable *v;
};
-/* Linear regression models. */
-static pspp_linreg_cache **models = NULL;
-
/*
Transformations for saving predicted values
and residuals, etc.
*/
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.
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));
+ std_error = sqrt (pspp_linreg_mse (c));
t = tab_create (n_cols, n_rows, 0);
- tab_dim (t, tab_natural_dimensions);
+ tab_dim (t, tab_natural_dimensions, NULL);
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_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_double (t, 1, 1, TAB_RIGHT, sqrt (rsq), NULL);
+ tab_double (t, 2, 1, TAB_RIGHT, rsq, NULL);
+ tab_double (t, 3, 1, TAB_RIGHT, adjrsq, NULL);
+ tab_double (t, 4, 1, TAB_RIGHT, std_error, NULL);
tab_title (t, _("Model Summary"));
tab_submit (t);
}
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);
- tab_dim (t, tab_natural_dimensions);
+ tab_dim (t, tab_natural_dimensions, NULL);
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_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_double (t, 2, 1, 0, c->intercept, NULL);
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;
- tab_float (t, 4, 1, 0, beta, 10, 2);
- t_stat = coeff / std_err;
- tab_float (t, 5, 1, 0, t_stat, 10, 2);
+ tab_double (t, 3, 1, 0, std_err, NULL);
+ tab_double (t, 4, 1, 0, 0.0, NULL);
+ t_stat = c->intercept / std_err;
+ tab_double (t, 5, 1, 0, t_stat, NULL);
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++)
+ tab_double (t, 6, 1, 0, pval, NULL);
+ 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))
{
/*
*/
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_double (t, 2, this_row, 0, c->coeff[j]->estimate, NULL);
/*
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_double (t, 3, this_row, 0, std_err, NULL);
/*
- '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 *= coeff / c->depvar_std;
- tab_float (t, 4, j + 1, 0, beta, 10, 2);
+ beta = pspp_coeff_get_sd (c->coeff[j]);
+ beta *= c->coeff[j]->estimate / c->depvar_std;
+ tab_double (t, 4, this_row, 0, beta, NULL);
/*
Test statistic for H0: coefficient is 0.
*/
- t_stat = coeff / std_err;
- tab_float (t, 5, j + 1, 0, t_stat, 10, 2);
+ t_stat = c->coeff[j]->estimate / std_err;
+ tab_double (t, 5, this_row, 0, t_stat, NULL);
/*
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_double (t, 6, this_row, 0, pval, NULL);
+ ds_destroy (&tstr);
}
tab_title (t, _("Coefficients"));
tab_submit (t);
- free (tmp);
}
/*
int n_cols = 7;
int n_rows = 4;
const double msm = c->ssm / c->dfm;
- const double mse = c->sse / c->dfe;
+ const double mse = pspp_linreg_mse (c);
const double F = msm / mse;
const double pval = gsl_cdf_fdist_Q (F, c->dfm, c->dfe);
assert (c != NULL);
t = tab_create (n_cols, n_rows, 0);
tab_headers (t, 2, 0, 1, 0);
- tab_dim (t, tab_natural_dimensions);
+ tab_dim (t, tab_natural_dimensions, NULL);
tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1);
tab_text (t, 1, 3, TAB_LEFT | TAT_TITLE, _("Total"));
/* Sums of Squares */
- tab_float (t, 2, 1, 0, c->ssm, 10, 2);
- tab_float (t, 2, 3, 0, c->sst, 10, 2);
- tab_float (t, 2, 2, 0, c->sse, 10, 2);
+ tab_double (t, 2, 1, 0, c->ssm, NULL);
+ tab_double (t, 2, 3, 0, c->sst, NULL);
+ tab_double (t, 2, 2, 0, c->sse, NULL);
/* 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_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);
+ tab_double (t, 4, 2, TAB_RIGHT, mse, NULL);
- tab_float (t, 4, 1, TAB_RIGHT, msm, 8, 3);
- tab_float (t, 4, 2, TAB_RIGHT, mse, 8, 3);
+ tab_double (t, 5, 1, 0, F, NULL);
- tab_float (t, 5, 1, 0, F, 8, 3);
-
- tab_float (t, 6, 1, 0, pval, 8, 3);
+ tab_double (t, 6, 1, 0, pval, NULL);
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)
{
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_dim (t, tab_natural_dimensions, NULL);
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_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);
{
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_double (t, k + 2, i, TAB_CENTER,
+ gsl_matrix_get (c->cov, row, col), NULL);
}
}
tab_title (t, _("Coefficient Correlations"));
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;
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);
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;
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);
}
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);
}
}
{
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;
add_transformation (ds, f, regression_trns_free, t);
trns_index++;
}
-
static void
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);
+ }
+ }
}
}
}
}
}
-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++)
/* 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;
}
/* 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;
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;
}
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;
+ 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]);
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
- 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;
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));
- }
- }
- }
+ c->coeff = xnmalloc (dm->m->size2, sizeof (*c->coeff));
+ pspp_coeff_init (c->coeff, dm);
}
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;
int k;
- struct ccase c;
+ struct ccase *c;
const struct variable **indep_vars;
struct design_matrix *X;
struct moments_var *mom;
assert (models != NULL);
- if (!casereader_peek (input, 0, &c))
- return true;
- output_split_file_values (ds, &c);
- case_destroy (&c);
+ c = casereader_peek (input, 0);
+ if (c == NULL)
+ {
+ casereader_destroy (input);
+ return true;
+ }
+ output_split_file_values (ds, c);
+ case_unref (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++)
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);
- n_data = prepare_categories (casereader_clone (reader),
- indep_vars, n_indep, mom);
+ MV_ANY, NULL, NULL);
+ n_data = prepare_categories (casereader_clone (reader),
+ indep_vars, n_indep, mom);
if ((n_data > 0) && (n_indep > 0))
{
{
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] = 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.
*/
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 (; (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);
+ 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
/*
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);
+ pspp_linreg ((const gsl_vector *) Y, X, &lopts, models[k]);
- 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);
projects / pspp-builds.git / blobdiff