#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.
*/
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;
struct casereader *r2;
struct ccase c;
struct variable *v;
+ struct variable **indep_vars;
struct design_matrix *X;
gsl_vector *Y;
pspp_linreg_cache *lcache;
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++)
{
- v = cmd.v_variables[i];
- if (v->type == ALPHA)
+ if (!is_depvar (i))
{
- /* 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))
+ v = cmd.v_variables[i];
+ indep_vars[j] = v;
+ j++;
+ if (v->type == ALPHA)
{
- if (!is_missing_case[row])
+ /* 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))
{
- /* Now it is missing. */
- n_data--;
- is_missing_case[row] = 1;
+ if (!is_missing_case[row])
+ {
+ /* Now it is missing. */
+ n_data--;
+ is_missing_case[row] = 1;
+ }
}
}
}
Y = gsl_vector_alloc (n_data);
X =
- design_matrix_create (n_indep, (const struct variable **) cmd.v_variables,
+ 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);
case_destroy (&c))
/* Iterate over the cases. */
{
- k = 0;
case_num = casereader_cnum (r2) - 1;
if (!is_missing_case[case_num])
{
design_matrix_set_numeric (X, row, v, val);
}
- indep_vars[k] = i;
- k++;
lopts.get_indep_mean_std[i] = 1;
}
}
(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);
projects / pspp-builds.git / blobdiff