X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fmath%2Flinreg%2Flinreg.c;h=c717e4ada4bd690ea7b0938f6c1289525cb24542;hb=945fd370f9fb880b310fb88f868ad47c2ae84533;hp=a5d0936597d7bac275149b08490fb9487d798cb7;hpb=3fc7b08b53d3a07385327d6f2aff11a2f9abce08;p=pspp-builds.git

diff --git a/src/math/linreg/linreg.c b/src/math/linreg/linreg.c
index a5d09365..c717e4ad 100644
--- a/src/math/linreg/linreg.c
+++ b/src/math/linreg/linreg.c
@@ -53,7 +53,7 @@
 */
 
 #include <math/linreg/linreg.h>
-#include <math/linreg/coefficient.h>
+#include <math/coefficient.h>
 #include <gsl/gsl_errno.h>
 #include <linreg/sweep.h>
 /*
@@ -88,6 +88,54 @@ linreg_mean_std (gsl_vector_const_view v, double *mp, double *sp, double *ssp)
   return GSL_SUCCESS;
 }
 
+/*
+  Set V to contain an array of pointers to the variables
+  used in the model. V must be at least C->N_COEFFS in length.
+  The return value is the number of distinct variables found.
+ */
+int
+pspp_linreg_get_vars (const void *c_, struct variable **v)
+{
+  const pspp_linreg_cache *c = c_;
+  struct pspp_coeff *coef = NULL;
+  const struct variable *tmp;
+  int i;
+  int result = 0;
+
+  /*
+     Make sure the caller doesn't try to sneak a variable
+     into V that is not in the model.
+   */
+  for (i = 0; i < c->n_coeffs; i++)
+    {
+      v[i] = NULL;
+    }
+  /*
+     Start at c->coeff[1] to avoid the intercept.
+   */
+  v[result] = (struct variable *) 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_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))
+	{
+	  i--;
+	}
+      if (i < 0 && result < c->n_coeffs)
+	{
+	  v[result] = (struct variable *) tmp;
+	  result++;
+	}
+    }
+  return result;
+}
+
 /*
   Allocate a pspp_linreg_cache and return a pointer
   to it. n is the number of cases, p is the number of
@@ -104,10 +152,10 @@ pspp_linreg_cache_alloc (size_t n, size_t p)
   c->indep_std = gsl_vector_alloc (p);
   c->ssx = gsl_vector_alloc (p);	/* Sums of squares for the
 					   independent variables. 
-					*/
+					 */
   c->ss_indeps = gsl_vector_alloc (p);	/* Sums of squares for the
 					   model parameters. 
-					*/
+					 */
   c->cov = gsl_matrix_alloc (p + 1, p + 1);	/* Covariance matrix. */
   c->n_obs = n;
   c->n_indeps = p;
@@ -116,22 +164,31 @@ pspp_linreg_cache_alloc (size_t n, size_t p)
    */
   c->method = PSPP_LINREG_SWEEP;
   c->predict = pspp_linreg_predict;
-  c->residual = pspp_linreg_residual; /* The procedure to comput my residuals. */
-  c->resid = NULL; /* The variable storing my residuals. */
-  c->pred = NULL; /* The variable storing my predicted values. */
+  c->residual = pspp_linreg_residual;	/* The procedure to compute my
+					   residuals. */
+  c->get_vars = pspp_linreg_get_vars;	/* The procedure that returns
+					   pointers to model
+					   variables. */
+  c->resid = NULL;		/* The variable storing my residuals. */
+  c->pred = NULL;		/* The variable storing my predicted values. */
 
   return c;
 }
 
 bool
-pspp_linreg_cache_free (void * m)
+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);
-  pspp_linreg_coeff_free (c->coeff);
+  for (i = 0; i < c->n_coeffs; i++)
+    {
+      pspp_coeff_free (c->coeff[i]);
+    }
   free (c);
   return true;
 }
@@ -189,7 +246,7 @@ pspp_linreg (const gsl_vector * Y, const gsl_matrix * X,
   cache->dfe = cache->dft - cache->dfm;
   cache->n_coeffs = X->size2 + 1;	/* Adjust this later to allow for
 					   regression through the origin. 
-					*/
+					 */
   if (cache->method == PSPP_LINREG_SWEEP)
     {
       gsl_matrix *sw;
@@ -263,7 +320,7 @@ pspp_linreg (const gsl_vector * Y, const gsl_matrix * X,
       for (i = 0; i < cache->n_indeps; i++)
 	{
 	  tmp = gsl_matrix_get (sw, i, cache->n_indeps);
-	  cache->coeff[i + 1].estimate = tmp;
+	  cache->coeff[i + 1]->estimate = tmp;
 	  m -= tmp * gsl_vector_get (cache->indep_means, i);
 	}
       /*
@@ -299,7 +356,7 @@ pspp_linreg (const gsl_vector * Y, const gsl_matrix * X,
 	    }
 	  gsl_matrix_set (cache->cov, 0, 0, tmp);
 
-	  cache->coeff[0].estimate = m;
+	  cache->coeff[0]->estimate = m;
 	}
       else
 	{
@@ -334,7 +391,7 @@ pspp_linreg (const gsl_vector * Y, const gsl_matrix * X,
 				cache->cov, &(cache->sse), wk);
       for (i = 0; i < cache->n_coeffs; i++)
 	{
-	  cache->coeff[i].estimate = gsl_vector_get (param_estimates, i);
+	  cache->coeff[i]->estimate = gsl_vector_get (param_estimates, i);
 	}
       if (rc == GSL_SUCCESS)
 	{