X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fmath%2Flinreg%2Flinreg.c;h=3c086a98f22ce1868ac581e1cdc4bc359671483f;hb=c17ea35a73b7a690a54c5c6a213de19f0376e74f;hp=e496150e71ca27140bcaefc7538e5822aa4c7696;hpb=2e5ba1599578af2f13aa483db3ee49d591aed42f;p=pspp-builds.git

diff --git a/src/math/linreg/linreg.c b/src/math/linreg/linreg.c
index e496150e..3c086a98 100644
--- a/src/math/linreg/linreg.c
+++ b/src/math/linreg/linreg.c
@@ -1,23 +1,20 @@
-/*
-  lib/linreg/linreg.c
-  
-  Copyright (C) 2005 Free Software Foundation, Inc. Written by Jason H. Stover.
-  
-  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 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 02111-1307, USA.
- */
+/* PSPP - a program for statistical analysis.
+   Copyright (C) 2005 Free Software Foundation, Inc. Written by Jason H. Stover.
+
+   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.
+
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>. */
+
+#include <config.h>
 #include <gsl/gsl_fit.h>
 #include <gsl/gsl_multifit.h>
 
@@ -94,10 +91,10 @@ linreg_mean_std (gsl_vector_const_view v, double *mp, double *sp, double *ssp)
   The return value is the number of distinct variables found.
  */
 int
-pspp_linreg_get_vars (const void *c_, struct variable **v)
+pspp_linreg_get_vars (const void *c_, const struct variable **v)
 {
   const pspp_linreg_cache *c = c_;
-  struct pspp_linreg_coeff *coef = NULL;
+  struct pspp_coeff *coef = NULL;
   const struct variable *tmp;
   int i;
   int result = 0;
@@ -113,23 +110,23 @@ pspp_linreg_get_vars (const void *c_, struct variable **v)
   /*
      Start at c->coeff[1] to avoid the intercept.
    */
-  v[result] = (struct variable *) pspp_linreg_coeff_get_var (c->coeff[1], 0);
+  v[result] = pspp_coeff_get_var (c->coeff[1], 0);
   result = (v[result] == NULL) ? 0 : 1;
 
   for (coef = c->coeff[2]; coef < c->coeff[c->n_coeffs]; coef++)
     {
-      tmp = pspp_linreg_coeff_get_var (coef, 0);
+      tmp = pspp_coeff_get_var (coef, 0);
       assert (tmp != NULL);
       /* Repeated variables are likely to bunch together, at the end
          of the array. */
       i = result - 1;
-      while (i >= 0 && (v[i]->index != tmp->index))
+      while (i >= 0 && v[i] != tmp)
 	{
 	  i--;
 	}
       if (i < 0 && result < c->n_coeffs)
 	{
-	  v[result] = (struct variable *) tmp;
+	  v[result] = tmp;
 	  result++;
 	}
     }
@@ -151,10 +148,10 @@ pspp_linreg_cache_alloc (size_t n, size_t p)
   c->indep_means = gsl_vector_alloc (p);
   c->indep_std = gsl_vector_alloc (p);
   c->ssx = gsl_vector_alloc (p);	/* Sums of squares for the
-					   independent variables. 
+					   independent variables.
 					 */
   c->ss_indeps = gsl_vector_alloc (p);	/* Sums of squares for the
-					   model parameters. 
+					   model parameters.
 					 */
   c->cov = gsl_matrix_alloc (p + 1, p + 1);	/* Covariance matrix. */
   c->n_obs = n;
@@ -181,15 +178,18 @@ pspp_linreg_cache_free (void *m)
   int i;
 
   pspp_linreg_cache *c = m;
-  gsl_vector_free (c->indep_means);
-  gsl_vector_free (c->indep_std);
-  gsl_vector_free (c->ss_indeps);
-  gsl_matrix_free (c->cov);
-  for (i = 0; i < c->n_coeffs; i++)
+  if (c != NULL)
     {
-      pspp_linreg_coeff_free (c->coeff[i]);
+      gsl_vector_free (c->indep_means);
+      gsl_vector_free (c->indep_std);
+      gsl_vector_free (c->ss_indeps);
+      gsl_matrix_free (c->cov);
+      for (i = 0; i < c->n_coeffs; i++)
+	{
+	  pspp_coeff_free (c->coeff[i]);
+	}
+      free (c);
     }
-  free (c);
   return true;
 }
 
@@ -245,7 +245,7 @@ pspp_linreg (const gsl_vector * Y, const gsl_matrix * X,
   cache->dfm = cache->n_indeps;
   cache->dfe = cache->dft - cache->dfm;
   cache->n_coeffs = X->size2 + 1;	/* Adjust this later to allow for
-					   regression through the origin. 
+					   regression through the origin.
 					 */
   if (cache->method == PSPP_LINREG_SWEEP)
     {
@@ -366,6 +366,18 @@ pspp_linreg (const gsl_vector * Y, const gsl_matrix * X,
 	}
       gsl_matrix_free (sw);
     }
+  else if (cache->method == PSPP_LINREG_CONDITIONAL_INVERSE)
+    {
+      /*
+	Use the SVD of X^T X to find a conditional inverse of X^TX. If
+	the SVD is X^T X = U D V^T, then set the conditional inverse
+	to (X^T X)^c = V D^- U^T. D^- is defined as follows: If entry
+	(i, i) has value sigma_i, then entry (i, i) of D^- is 1 /
+	sigma_i if sigma_i > 0, and 0 otherwise. Then solve the normal
+	equations by setting the estimated parameter vector to 
+	(X^TX)^c X^T Y.
+       */
+    }
   else
     {
       gsl_multifit_linear_workspace *wk;