1 /* PSPP - computes sample statistics.
2 Copyright (C) 1997-9, 2000 Free Software Foundation, Inc.
4 This program is free software; you can redistribute it and/or
5 modify it under the terms of the GNU General Public License as
6 published by the Free Software Foundation; either version 2 of the
7 License, or (at your option) any later version.
9 This program is distributed in the hope that it will be useful, but
10 WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
12 General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program; if not, write to the Free Software
16 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
21 #include <gsl/gsl_rng.h>
26 #include <data/procedure.h>
27 #include <data/variable.h>
28 #include <language/command.h>
29 #include <language/lexer/lexer.h>
30 #include <libpspp/alloc.h>
31 #include <libpspp/compiler.h>
32 #include <libpspp/message.h>
33 #include <libpspp/str.h>
34 #include <math/random.h>
37 #define _(msgid) gettext (msgid)
39 /* The two different types of samples. */
42 TYPE_A_FROM_B, /* 5 FROM 10 */
43 TYPE_FRACTION /* 0.5 */
46 /* SAMPLE transformation. */
49 int type; /* One of TYPE_*. */
50 int n, N; /* TYPE_A_FROM_B: n from N. */
51 int m, t; /* TYPE_A_FROM_B: # picked so far; # so far. */
52 unsigned frac; /* TYPE_FRACTION: a fraction of UINT_MAX. */
55 static trns_proc_func sample_trns_proc;
56 static trns_free_func sample_trns_free;
59 cmd_sample (struct lexer *lexer, struct dataset *ds)
61 struct sample_trns *trns;
67 if (!lex_force_num (lexer))
69 if (!lex_is_integer (lexer))
71 unsigned long min = gsl_rng_min (get_rng ());
72 unsigned long max = gsl_rng_max (get_rng ());
75 if (lex_tokval (lexer) <= 0 || lex_tokval (lexer) >= 1)
77 msg (SE, _("The sampling factor must be between 0 and 1 "
82 frac = lex_tokval (lexer) * (max - min) + min;
88 a = lex_integer (lexer);
90 if (!lex_force_match_id (lexer, "FROM"))
92 if (!lex_force_int (lexer))
94 b = lex_integer (lexer);
97 msg (SE, _("Cannot sample %d observations from a population of "
107 trns = xmalloc (sizeof *trns);
111 trns->m = trns->t = 0;
113 add_transformation (ds, sample_trns_proc, sample_trns_free, trns);
115 return lex_end_of_command (lexer);
118 /* Executes a SAMPLE transformation. */
120 sample_trns_proc (void *t_, struct ccase *c UNUSED,
121 casenumber case_num UNUSED)
123 struct sample_trns *t = t_;
126 if (t->type == TYPE_FRACTION)
128 if (gsl_rng_get (get_rng ()) <= t->frac)
129 return TRNS_CONTINUE;
131 return TRNS_DROP_CASE;
135 return TRNS_DROP_CASE;
137 U = gsl_rng_uniform (get_rng ());
138 if ((t->N - t->t) * U >= t->n - t->m)
141 return TRNS_DROP_CASE;
147 return TRNS_CONTINUE;
152 sample_trns_free (void *t_)
154 struct sample_trns *t = t_;