math: Make 'accumulate' a feature of order statistics, not all stats.

[pspp] / src / math / order-stats.h

diff --git a/src/math/order-stats.h b/src/math/order-stats.h
index fc5889504a6c1360d1026047e68760fefa2f70d5..4bb69383fb7944a22b12f0ce3d8328e2d27abfff 100644 (file)
--- a/src/math/order-stats.h
+++ b/src/math/order-stats.h
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2004, 2008 Free Software Foundation, Inc.
+   Copyright (C) 2004, 2008, 2011 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
@@ -17,50 +17,90 @@
 #ifndef __ORDER_STATS_H__
 #define __ORDER_STATS_H__
 
+/* Support for order statistics.
+
+   The kth order statistic of a statistical sample is equal to its kth-smallest
+   value.  The minimum is the first order statistic and the maximum is the
+   largest.  This code and data structure supplies infrastructure for
+   higher-level statistics that rely on order statistics.  It is a kind of
+   "abstract base class" that is not useful on its own.
+
+   This is implemented here as a kind of "partial frequency table".  The
+   order_stats_accumulate() and order_stats_accumulate_idx() functions
+   effectively generate all of the frequency table entries for the variable,
+   one by one, and pass them to the "accumulate" function, if any.  They can
+   also record pairs of frequency tables entries surrounding desired target
+   cumulative weights in 'k' data structures.
+
+   Client use
+   ==========
+
+   The common pattern for clients to use statistics based on order statistics
+   is this:
+
+   - Create the higher-level statistic with, for example, percentile_create().
+
+   - Feed in all the data with order_stats_accumulate() or
+     order_stats_accumulate_idx(). The data must be in sorted order: if
+     necessary, use one of the sorting functions from sort.h to sort them.
+
+   - Obtain the desired results by examining the higher-level data structure or
+     by calling an appropriate function, e.g. percentile_calculate().
+
+   - Destroy the data structure with statistic_destroy().
+*/
+
 #include <stddef.h>
-#include <math/statistic.h>
+#include "data/missing-values.h"
+#include "math/statistic.h"
 
 struct casereader;
 struct variable;
 
-/*
-  cc <= tc < cc_p1
+/* A pair of adjacent frequency table entries.
+
+   cc <= tc < cc_p1
 */
 struct k
 {
+  /* Target cumulative weight.
+     Set by the client before invoking order_stats_accumulate{,_idx}. */
   double tc;
 
-  double cc;
-
-  double cc_p1;
+  /* Lower order statistics. */
+  double cc;                    /* Largest cumulative weight <= tc. */
+  double c;                     /* Weight for data values equal to 'y'. */
+  double y;                     /* Data value. */
 
-  double c;
-
-  double c_p1;
-
-  double y;
-
-  double y_p1;
+  /* Upper order statistics. */
+  double cc_p1;                 /* Smallest cumulative weight > tc. */
+  double c_p1;                  /* Weight for data values equal to 'y_p1'. */
+  double y_p1;                  /* Data value. */
 };
 
-
+/* Order statistics calculation data structure.  See the comment at the top of
+   this file for usage details. */
 struct order_stats
 {
   struct statistic parent;
-  int n_k;
-  struct k *k;
-};
 
+  void (*accumulate) (struct statistic *, const struct ccase *, double c, double cc, double y);
 
+  struct k *k;
+  size_t n_k;
+};
 
-void dump_ptile_k1 (const struct order_stats *ptl);
-
-void dump_ptile_k2 (const struct order_stats *ptl);
-
-
-void order_stats_accumulate (struct order_stats **ptl, size_t nos,
-                        struct casereader *reader,
-                        const struct variable *wv,
-                        const struct variable *var);
+void order_stats_accumulate_idx (struct order_stats **os, size_t n_os,
+                                 struct casereader *reader,
+                                 int weight_idx,
+                                 int data_idx);
+void order_stats_accumulate (struct order_stats **os, size_t n_os,
+                            struct casereader *,
+                            const struct variable *weight_var,
+                            const struct variable *data_var,
+                            enum mv_class exclude);
+
+/* Debugging support. */
+void order_stats_dump (const struct order_stats *);
 
 #endif