Make cases simpler, faster, and easier to understand.

[pspp-builds.git] / src / language / stats / regression.q

diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q
index 0f8ae59433b615f3fb53fae51d04264bdbab88f1..595e7e750c54d4d996b85b71eb141f87b4ba8d52 100644 (file)
--- a/src/language/stats/regression.q
+++ b/src/language/stats/regression.q
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2005 Free Software Foundation, Inc.
+   Copyright (C) 2005, 2009 Free Software Foundation, Inc.
 
    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
@@ -542,7 +542,7 @@ regression_trns_free (void *t_)
   Gets the predicted values.
  */
 static int
-regression_trns_pred_proc (void *t_, struct ccase *c,
+regression_trns_pred_proc (void *t_, struct ccase **c,
                           casenumber case_idx UNUSED)
 {
   size_t i;
@@ -563,12 +563,12 @@ regression_trns_pred_proc (void *t_, struct ccase *c,
   n_vals = (*model->get_vars) (model, vars);
 
   vals = xnmalloc (n_vals, sizeof (*vals));
-  output = case_data_rw (c, model->pred);
-  assert (output != NULL);
+  *c = case_unshare (*c);
+  output = case_data_rw (*c, model->pred);
 
   for (i = 0; i < n_vals; i++)
     {
-      vals[i] = case_data (c, vars[i]);
+      vals[i] = case_data (*c, vars[i]);
     }
   output->f = (*model->predict) ((const struct variable **) vars,
                                 vals, model, n_vals);
@@ -581,7 +581,7 @@ regression_trns_pred_proc (void *t_, struct ccase *c,
   Gets the residuals.
  */
 static int
-regression_trns_resid_proc (void *t_, struct ccase *c,
+regression_trns_resid_proc (void *t_, struct ccase **c,
                            casenumber case_idx UNUSED)
 {
   size_t i;
@@ -603,14 +603,15 @@ regression_trns_resid_proc (void *t_, struct ccase *c,
   n_vals = (*model->get_vars) (model, vars);
 
   vals = xnmalloc (n_vals, sizeof (*vals));
-  output = case_data_rw (c, model->resid);
+  *c = case_unshare (*c);
+  output = case_data_rw (*c, model->resid);
   assert (output != NULL);
 
   for (i = 0; i < n_vals; i++)
     {
-      vals[i] = case_data (c, vars[i]);
+      vals[i] = case_data (*c, vars[i]);
     }
-  obs = case_data (c, model->depvar);
+  obs = case_data (*c, model->depvar);
   output->f = (*model->residual) ((const struct variable **) vars,
                                  vals, obs, model, n_vals);
   free (vals);
@@ -821,7 +822,7 @@ prepare_categories (struct casereader *input,
                    struct moments_var *mom)
 {
   int n_data;
-  struct ccase c;
+  struct ccase *c;
   size_t i;
 
   assert (vars != NULL);
@@ -832,7 +833,7 @@ prepare_categories (struct casereader *input,
       cat_stored_values_create (vars[i]);
 
   n_data = 0;
-  for (; casereader_read (input, &c); case_destroy (&c))
+  for (; (c = casereader_read (input)) != NULL; case_unref (c))
     {
       /*
          The second condition ensures the program will run even if
@@ -841,7 +842,7 @@ prepare_categories (struct casereader *input,
        */
       for (i = 0; i < n_vars; i++)
        {
-         const union value *val = case_data (&c, vars[i]);
+         const union value *val = case_data (c, vars[i]);
          if (var_is_alpha (vars[i]))
            cat_value_update (vars[i], val);
          else
@@ -861,39 +862,6 @@ coeff_init (pspp_linreg_cache * c, struct design_matrix *dm)
   pspp_coeff_init (c->coeff, 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 (design_matrix_col_to_var (dm, i) == (mom + j)->v)
-           {
-             moments1_calculate ((mom + j)->m, &weight, &mean, &variance,
-                                 &skewness, &kurtosis);
-             pspp_linreg_set_indep_variable_mean (c, (mom + j)->v, mean);
-             pspp_linreg_set_indep_variable_sd (c, (mom + j)->v, sqrt (variance));
-           }
-       }
-    }
-}
-
 static bool
 run_regression (struct casereader *input, struct cmd_regression *cmd,
                struct dataset *ds, pspp_linreg_cache **models)
@@ -901,7 +869,7 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
   size_t i;
   int n_indep = 0;
   int k;
-  struct ccase c;
+  struct ccase *c;
   const struct variable **indep_vars;
   struct design_matrix *X;
   struct moments_var *mom;
@@ -911,13 +879,14 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
 
   assert (models != NULL);
 
-  if (!casereader_peek (input, 0, &c))
+  c = casereader_peek (input, 0);
+  if (c == NULL)
     {
       casereader_destroy (input);
       return true;
     }
-  output_split_file_values (ds, &c);
-  case_destroy (&c);
+  output_split_file_values (ds, c);
+  case_unref (c);
 
   if (!v_variables)
     {
@@ -949,7 +918,7 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
       const struct variable *dep_var;
       struct casereader *reader;
       casenumber row;
-      struct ccase c;
+      struct ccase *c;
       size_t n_data;           /* Number of valid cases. */
 
       dep_var = cmd->v_dependent[k];
@@ -973,7 +942,8 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
            {
              lopts.get_indep_mean_std[i] = 1;
            }
-         models[k] = pspp_linreg_cache_alloc (X->m->size1, X->m->size2);
+         models[k] = pspp_linreg_cache_alloc (dep_var, (const struct variable **) indep_vars,
+                                              X->m->size1, X->m->size2);
          models[k]->depvar = dep_var;
          /*
             For large data sets, use QR decomposition.
@@ -987,18 +957,18 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
             The second pass fills the design matrix.
           */
          reader = casereader_create_counter (reader, &row, -1);
-         for (; casereader_read (reader, &c); case_destroy (&c))
+         for (; (c = casereader_read (reader)) != NULL; case_unref (c))
            {
              for (i = 0; i < n_indep; ++i)
                {
                  const struct variable *v = indep_vars[i];
-                 const union value *val = case_data (&c, v);
+                 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);
                }
-             gsl_vector_set (Y, row, case_num (&c, dep_var));
+             gsl_vector_set (Y, row, case_num (c, dep_var));
            }
          /*
             Now that we know the number of coefficients, allocate space