#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 "gettext.h"
#include "lexer.h"
#include <linreg/pspp_linreg.h>
+#include "missing-values.h"
#include "tab.h"
#include "var.h"
#include "vfm.h"
-/* (headers) */
+#define REG_LARGE_DATA 1000
+/* (headers) */
/* (specification)
"REGRESSION" (regression_):
f,
defaults,
all;
+ export=custom;
^dependent=varlist;
^method=enter.
*/
*/
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.
*/
struct tab_table *t;
assert (c != NULL);
- n_rows = 2;
+ n_rows = c->n_coeffs + 2;
t = tab_create (n_cols, n_rows, 0);
tab_headers (t, 2, 0, 1, 0);
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);
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);
statistics_keyword_output (reg_stats_tol, keywords[tol], c);
statistics_keyword_output (reg_stats_selection, keywords[selection], c);
}
+static void
+subcommand_export (int export, pspp_linreg_cache *c)
+{
+ FILE *fp;
+ size_t i;
+ 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, "#include <string.h>\n\n");
+ fprintf (fp, "/*\n Estimate the mean of Y, the dependent variable for\n");
+ fprintf (fp, " the linear model of the form \n\n");
+ fprintf (fp, " Y = b0 + b1 * X1 + b2 * X2 + ... + bk * X2 + error\n\n");
+ fprintf (fp, " where X1, ..., Xk are the independent variables\n");
+ fprintf (fp, " whose values are stored in var_vals and whose names, \n");
+ fprintf (fp, " as known by PSPP, are stored in var_names. The estimated \n");
+ fprintf (fp, " regression coefficients (i.e., the estimates of b0,...,bk) \n");
+ fprintf (fp, " are stored in model_coeffs.\n*/\n");
+ fprintf (fp, "double\npspp_reg_estimate (const double *var_vals, const char *var_names[])\n{\n\tchar *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);
+ 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, "{\n\t\tfor (j = 0; j < %d; j++)\n\t\t", c->n_indeps);
+ fprintf (fp, "{\n\t\t\tif (strcmp (var_names[i], model_depvars[j]) == 0)\n");
+ fprintf (fp, "\t\t\t{\n\t\t\t\testimate += var_vals[i] * model_coeffs[j];\n");
+ fprintf (fp, "\t\t\t}\n\t\t}\n\t}\n\treturn estimate;\n}\n");
+ 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)
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;
+ /*
+ 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 **indep_vars;
struct design_matrix *X;
gsl_vector *Y;
pspp_linreg_cache *lcache;
pspp_linreg_opts lopts;
n_data = casefile_get_case_cnt (cf);
+
+ 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);
- Y = gsl_vector_alloc (n_data);
lopts.get_depvar_mean_std = 1;
lopts.get_indep_mean_std = xnmalloc (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);
/*
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);
+ }
+ 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;
+ }
+ }
+ }
}
}
- cr_create_value_matrices (ca);
+
+ Y = gsl_vector_alloc (n_data);
X =
- design_matrix_create (n_indep, (const struct variable **) cmd.v_variables,
- ca, n_data);
+ design_matrix_create (n_indep, (const struct variable **) indep_vars,
+ n_data);
+ 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);
/*
The second pass creates the design matrix.
*/
+ row = 0;
for (r2 = casefile_get_reader (cf); casereader_read (r2, &c);
case_destroy (&c))
/* Iterate over the cases. */
{
- k = 0;
- row = casereader_cnum (r2) - 1;
- for (i = 0; i < cmd.n_variables; ++i) /* Iterate over the variables
+ case_num = casereader_cnum (r2) - 1;
+ if (!is_missing_case[case_num])
+ {
+ for (i = 0; i < cmd.n_variables; ++i) /* Iterate over the variables
for the current case.
*/
- {
- 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)
- {
- msg (SE, gettext ("Dependent variable must be numeric."));
- pspp_reg_rc = CMD_FAILURE;
- return;
- }
- lcache->depvar = (const struct var *) v;
- gsl_vector_set (Y, row, val->f);
- }
- else
{
- if (v->type == ALPHA)
+ 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))
{
- rc = cr_var_to_recoded_categorical (v, ca);
- design_matrix_set_categorical (X, row, v, val, rc);
+ if (v->type != NUMERIC)
+ {
+ msg (SE,
+ gettext ("Dependent variable must be numeric."));
+ pspp_reg_rc = CMD_FAILURE;
+ return;
+ }
+ lcache->depvar = (const struct variable *) v;
+ gsl_vector_set (Y, row, val->f);
}
- else if (v->type == NUMERIC)
+ else
{
- design_matrix_set_numeric (X, row, v, val);
+ 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);
+ }
+
+ lopts.get_indep_mean_std[i] = 1;
}
-
- indep_vars[k] = i;
- k++;
- lopts.get_indep_mean_std[i] = 1;
}
+ row++;
}
}
/*
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);
+ }
+ /*
+ For large data sets, use QR decomposition.
+ */
+ if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
+ {
+ lcache->method = PSPP_LINREG_SVD;
}
/*
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);
free (indep_vars);
+ free (is_missing_case);
casereader_destroy (r);
return;
}
projects / pspp-builds.git / blobdiff