-/* PSPP - linear regression.
+/* PSPP - a program for statistical analysis.
Copyright (C) 2005 Free Software Foundation, Inc.
- Written by Jason H Stover <jason@sakla.net>.
- 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 the Free Software Foundation; either version 2 of the
- License, or (at your option) any later version.
+ 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
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
- This program is distributed in the hope that it will be useful, but
- WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- General Public License for more details.
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- 02110-1301, USA. */
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
-#include <stdlib.h>
+
#include <gsl/gsl_cdf.h>
-#include <gsl/gsl_vector.h>
#include <gsl/gsl_matrix.h>
+#include <gsl/gsl_vector.h>
#include <math.h>
-#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 <stdlib.h>
+
#include "regression-export.h"
-#include "table.h"
-#include "value-labels.h"
-#include "variable.h"
-#include "procedure.h"
+#include <data/case.h>
+#include <data/casegrouper.h>
+#include <data/casereader.h>
+#include <data/category.h>
+#include <data/dictionary.h>
+#include <data/missing-values.h>
+#include <data/procedure.h>
+#include <data/transformations.h>
+#include <data/value-labels.h>
+#include <data/variable.h>
+#include <language/command.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/moments.h>
+#include <output/table.h>
+
+#include "gettext.h"
+#define _(msgid) gettext (msgid)
#define REG_LARGE_DATA 1000
/* (specification)
"REGRESSION" (regression_):
- *variables=varlist;
- statistics[st_]=r,
- coeff,
- anova,
- outs,
- zpp,
- label,
- sha,
- ci,
- bcov,
- ses,
- xtx,
- collin,
- tol,
- selection,
- f,
- defaults,
- all;
+ *variables=custom;
+ +statistics[st_]=r,
+ coeff,
+ anova,
+ outs,
+ zpp,
+ label,
+ sha,
+ ci,
+ bcov,
+ ses,
+ xtx,
+ collin,
+ tol,
+ selection,
+ f,
+ defaults,
+ all;
export=custom;
^dependent=varlist;
- method=enter.
+ +save[sv_]=resid,pred;
+ +method=enter.
*/
/* (declarations) */
/* (functions) */
static struct cmd_regression cmd;
/*
- Array holding the subscripts of the independent variables.
+ Moments for each of the variables used.
*/
-size_t *indep_vars;
+struct moments_var
+{
+ struct moments1 *m;
+ const struct variable *v;
+};
+
+/* Linear regression models. */
+static pspp_linreg_cache **models = NULL;
/*
- File where the model will be saved if the EXPORT subcommand
- is given.
+ Transformations for saving predicted values
+ and residuals, etc.
*/
-struct file_handle *model_file;
+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 const struct variable **v_variables;
/*
- Return value for the procedure.
+ Number of variables.
*/
-int pspp_reg_rc = CMD_SUCCESS;
+static size_t n_variables;
-static bool run_regression (const struct casefile *, void *);
+/*
+ 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 *);
+
+/*
STATISTICS subcommand output functions.
*/
static void reg_stats_r (pspp_linreg_cache *);
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);
}
static void
reg_stats_coeff (pspp_linreg_cache * c)
{
- size_t i;
size_t j;
int n_cols = 7;
int n_rows;
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);
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_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.
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);
}
/*
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.
/*
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, 0, _("Coefficients"));
+ tab_title (t, _("Coefficients"));
tab_submit (t);
free (tmp);
}
tab_float (t, 6, 1, 0, pval, 8, 3);
- tab_title (t, 0, _("ANOVA"));
+ tab_title (t, _("ANOVA"));
tab_submit (t);
}
static void
int n_cols;
int n_rows;
int i;
- int j;
int k;
int row;
int col;
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_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;
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
static void
subcommand_statistics (int *keywords, pspp_linreg_cache * c)
{
- /*
- The order here must match the order in which the STATISTICS
+ /*
+ The order here must match the order in which the STATISTICS
keywords appear in the specification section above.
*/
enum
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;
+ const 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;
+ const 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 (struct dataset *ds, 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 (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);
+ }
+ }
+ }
+}
+
static int
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++;
}
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;
+
+ 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 < varlist[i]->obs_vals->n_categories; j++)
+ 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]));
+ 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);
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)
"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 increment;
double tmp;
- struct pspp_linreg_coeff coeff;
+ struct pspp_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++)
{
tmp = 0.5 + 0.005 * (double) i;
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);
fclose (fp);
}
}
+
static int
-regression_custom_export (struct cmd_regression *cmd)
+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))
+ struct casegrouper *grouper;
+ struct casereader *group;
+ bool ok;
+ 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;
- return pspp_reg_rc;
+ models = xnmalloc (cmd.n_dependent, sizeof *models);
+ for (i = 0; i < cmd.n_dependent; i++)
+ {
+ models[i] = NULL;
+ }
+
+ /* Data pass. */
+ grouper = casegrouper_create_splits (proc_open (ds), dataset_dict (ds));
+ while (casegrouper_get_next_group (grouper, &group))
+ run_regression (group, &cmd, ds);
+ ok = casegrouper_destroy (grouper);
+ ok = proc_commit (ds) && ok;
+
+ subcommand_save (ds, cmd.sbc_save, models);
+ free (v_variables);
+ free (models);
+ return ok ? CMD_SUCCESS : CMD_FAILURE;
}
/*
- Is variable k one of the dependent variables?
+ Is variable k the dependent variable?
*/
+static bool
+is_depvar (size_t k, const struct variable *v)
+{
+ return v == v_variables[k];
+}
+
+/* Parser for the variables sub command */
static int
-is_depvar (size_t k)
+regression_custom_variables (struct lexer *lexer, struct dataset *ds,
+ struct cmd_regression *cmd UNUSED,
+ void *aux UNUSED)
{
- size_t j = 0;
- for (j = 0; j < cmd.n_dependent; j++)
+ const struct dictionary *dict = dataset_dict (ds);
+
+ lex_match (lexer, '=');
+
+ if ((lex_token (lexer) != T_ID
+ || dict_lookup_var (dict, lex_tokid (lexer)) == NULL)
+ && lex_token (lexer) != T_ALL)
+ return 2;
+
+
+ if (!parse_variables_const
+ (lexer, dict, &v_variables, &n_variables, PV_NONE))
+ {
+ free (v_variables);
+ return 0;
+ }
+ assert (n_variables);
+
+ return 1;
+}
+
+/* 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)
+{
+ 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 < 2) && is_depvar (0, depvar))
{
/*
- compare_var_names returns 0 if the variable
- names match.
+ There is only one independent variable, and it is the same
+ as the dependent variable. Print a warning and continue.
*/
- if (!compare_var_names (cmd.v_dependent[j], cmd.v_variables[k], NULL))
- return 1;
+ msg (SE,
+ gettext ("The dependent variable is equal to the independent variable. The least sequares line is therefore Y=X. Standard errors and related statistics may be meaningless."));
+ n_indep_vars = 1;
+ indep_vars[0] = v_variables[0];
}
- return 0;
+ return n_indep_vars;
}
-/*
- Mark missing cases. Return the number of non-missing cases.
- */
-static size_t
-mark_missing_cases (const struct casefile *cf, struct variable *v,
- int *is_missing_case, double n_data)
+/* Encode categorical variables.
+ Returns number of valid cases. */
+static int
+prepare_categories (struct casereader *input,
+ const struct variable **vars, size_t n_vars,
+ struct moments_var *mom)
{
- struct casereader *r;
+ int n_data;
struct ccase c;
- size_t row;
- const union value *val;
+ 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]);
- for (r = casefile_get_reader (cf);
- casereader_read (r, &c); case_destroy (&c))
+ n_data = 0;
+ for (; casereader_read (input, &c); case_destroy (&c))
{
- row = casereader_cnum (r) - 1;
+ /*
+ 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);
+ }
+ n_data++;
+ }
+ casereader_destroy (input);
+
+ return n_data;
+}
- val = case_data (&c, v->fv);
- cat_value_update (v, val);
- if (mv_is_value_missing (&v->miss, val))
+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 (!is_missing_case[row])
+ if (design_matrix_col_to_var (dm, i) == (mom + j)->v)
{
- /* Now it is missing. */
- n_data--;
- is_missing_case[row] = 1;
+ 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));
}
}
}
- casereader_destroy (r);
-
- return n_data;
}
static bool
-run_regression (const struct casefile *cf, void *cmd_ UNUSED)
+run_regression (struct casereader *input, struct cmd_regression *cmd,
+ struct dataset *ds)
{
size_t i;
- size_t n_data = 0;
- 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.
- */
- int *is_missing_case;
- const union value *val;
- struct casereader *r;
struct ccase c;
- struct variable *v;
- struct variable *depvar;
- 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;
- n_data = casefile_get_case_cnt (cf);
+ assert (models != NULL);
- for (i = 0; i < cmd.n_dependent; i++)
+ if (!casereader_peek (input, 0, &c))
+ return true;
+ output_split_file_values (ds, &c);
+ case_destroy (&c);
+
+ if (!v_variables)
{
- if (cmd.v_dependent[i]->type != NUMERIC)
- {
- msg (SE, gettext ("Dependent variable must be numeric."));
- pspp_reg_rc = CMD_FAILURE;
- return true;
- }
+ dict_get_vars (dataset_dict (ds), &v_variables, &n_variables,
+ 1u << DC_SYSTEM);
}
- 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);
-
- 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 (i = 0; i < cmd->n_dependent; i++)
{
- if (!is_depvar (i))
+ if (!var_is_numeric (cmd->v_dependent[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);
+ msg (SE, _("Dependent variable must be numeric."));
+ return false;
}
}
- /*
- Drop cases with missing values for any dependent variable.
- */
- j = 0;
- for (i = 0; i < cmd.n_dependent; i++)
+ mom = xnmalloc (n_variables, sizeof (*mom));
+ for (i = 0; i < n_variables; i++)
{
- v = cmd.v_dependent[i];
- j++;
- n_data = mark_missing_cases (cf, v, is_missing_case, n_data);
+ (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++)
- {
- depvar = cmd.v_dependent[k];
- Y = gsl_vector_alloc (n_data);
+ lopts.get_indep_mean_std = xnmalloc (n_variables, sizeof (int));
+ indep_vars = xnmalloc (n_variables, sizeof *indep_vars);
- 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 *) depvar;
- /*
- For large data sets, use QR decomposition.
- */
- if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
+ for (k = 0; k < cmd->n_dependent; k++)
+ {
+ const struct variable *dep_var;
+ struct casereader *reader;
+ casenumber row;
+ 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);
+ reader = casereader_create_filter_missing (reader, &dep_var, 1,
+ MV_ANY, NULL);
+ n_data = prepare_categories (casereader_clone (reader),
+ indep_vars, n_indep, mom);
+
+ if ((n_data > 0) && (n_indep > 0))
{
- lcache->method = PSPP_LINREG_SVD;
- }
+ 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 = 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_QR;
+ }
- /*
- 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])
+ /*
+ 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 < cmd.n_variables; ++i) /* Iterate over the variables
- for the current case.
- */
+ for (i = 0; i < n_indep; ++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, 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);
- }
- }
+ 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);
}
- val = case_data (&c, depvar->fv);
- gsl_vector_set (Y, row, val->f);
- row++;
+ 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
- coefficients.
- */
- pspp_linreg_coeff_init (lcache, X);
+ /*
+ 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, 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, models[k]);
+ compute_moments (models[k], mom, X, n_variables);
+
+ if (!taint_has_tainted_successor (casereader_get_taint (input)))
+ {
+ subcommand_statistics (cmd->a_statistics, models[k]);
+ subcommand_export (cmd->sbc_export, models[k]);
+ }
+
+ gsl_vector_free (Y);
+ design_matrix_destroy (X);
+ }
+ else
+ {
+ msg (SE,
+ gettext ("No valid data found. This command was skipped."));
+ }
+ casereader_destroy (reader);
}
free (indep_vars);
- free (is_missing_case);
+ free (lopts.get_indep_mean_std);
+ casereader_destroy (input);
return true;
}
/*
- Local Variables:
+ Local Variables:
mode: c
End:
*/
projects / pspp-builds.git / blobdiff