/* PSPP - a program for statistical analysis.
- Copyright (C) 2009 Free Software Foundation, Inc.
+ Copyright (C) 2009, 2010, 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
#include <config.h>
-#include <libpspp/assertion.h>
-#include <math/covariance.h>
-#include <math/design-matrix.h>
+#include <gsl/gsl_cdf.h>
#include <gsl/gsl_matrix.h>
-#include <data/casegrouper.h>
-#include <data/casereader.h>
-#include <data/dictionary.h>
-#include <data/procedure.h>
-#include <data/variable.h>
-#include <language/command.h>
-#include <language/dictionary/split-file.h>
-#include <language/lexer/lexer.h>
-#include <language/lexer/variable-parser.h>
-#include <output/manager.h>
-#include <output/table.h>
-#include <libpspp/message.h>
-#include <data/format.h>
-#include <math/moments.h>
-
#include <math.h>
-#include "xalloc.h"
-#include "minmax.h"
-#include <libpspp/misc.h>
-#include <gsl/gsl_cdf.h>
+
+#include "data/casegrouper.h"
+#include "data/casereader.h"
+#include "data/dataset.h"
+#include "data/dictionary.h"
+#include "data/format.h"
+#include "data/variable.h"
+#include "language/command.h"
+#include "language/dictionary/split-file.h"
+#include "language/lexer/lexer.h"
+#include "language/lexer/variable-parser.h"
+#include "libpspp/assertion.h"
+#include "libpspp/message.h"
+#include "libpspp/misc.h"
+#include "math/correlation.h"
+#include "math/covariance.h"
+#include "math/moments.h"
+#include "output/tab.h"
+
+#include "gl/xalloc.h"
+#include "gl/minmax.h"
#include "gettext.h"
#define _(msgid) gettext (msgid)
#define N_(msgid) msgid
-static double
-significance_of_correlation (double rho, double w)
-{
- double t = w - 2;
- t /= 1 - MIN (1, pow2 (rho));
- t = sqrt (t);
- t *= rho;
-
- if (t > 0)
- return gsl_cdf_tdist_Q (t, w - 2);
- else
- return gsl_cdf_tdist_P (t, w - 2);
-}
-
-
struct corr
{
size_t n_vars_total;
const int heading_columns = 1;
const int heading_rows = 1;
- struct tab_table *t = tab_create (nc, nr, 0);
+ struct tab_table *t = tab_create (nc, nr);
tab_title (t, _("Descriptive Statistics"));
- tab_dim (t, tab_natural_dimensions, NULL);
tab_headers (t, heading_columns, 0, heading_rows, 0);
/* One header row */
nr += heading_rows;
- t = tab_create (nc, nr, 0);
+ t = tab_create (nc, nr);
tab_title (t, _("Correlations"));
- tab_dim (t, tab_natural_dimensions, NULL);
tab_headers (t, heading_columns, 0, heading_rows, 0);
}
-static gsl_matrix *
-correlation_from_covariance (const gsl_matrix *cv, const gsl_matrix *v)
-{
- size_t i, j;
- gsl_matrix *corr = gsl_matrix_calloc (cv->size1, cv->size2);
-
- for (i = 0 ; i < cv->size1; ++i)
- {
- for (j = 0 ; j < cv->size2; ++j)
- {
- double rho = gsl_matrix_get (cv, i, j);
-
- rho /= sqrt (gsl_matrix_get (v, i, j))
- *
- sqrt (gsl_matrix_get (v, j, i));
-
- gsl_matrix_set (corr, i, j, rho);
- }
- }
-
- return corr;
-}
-
-
-
-
static void
run_corr (struct casereader *r, const struct corr_opts *opts, const struct corr *corr)
{
struct ccase *c;
const gsl_matrix *var_matrix, *samples_matrix, *mean_matrix;
- const gsl_matrix *cov_matrix;
+ gsl_matrix *cov_matrix;
gsl_matrix *corr_matrix;
- struct covariance *cov = covariance_create (corr->n_vars_total, corr->vars,
- opts->wv, opts->exclude);
+ struct covariance *cov = covariance_2pass_create (corr->n_vars_total, corr->vars,
+ NULL,
+ opts->wv, opts->exclude);
+ struct casereader *rc = casereader_clone (r);
for ( ; (c = casereader_read (r) ); case_unref (c))
{
- covariance_accumulate (cov, c);
+ covariance_accumulate_pass1 (cov, c);
+ }
+
+ for ( ; (c = casereader_read (rc) ); case_unref (c))
+ {
+ covariance_accumulate_pass2 (cov, c);
}
cov_matrix = covariance_calculate (cov);
+ casereader_destroy (rc);
+
samples_matrix = covariance_moments (cov, MOMENT_NONE);
var_matrix = covariance_moments (cov, MOMENT_VARIANCE);
mean_matrix = covariance_moments (cov, MOMENT_MEAN);
covariance_destroy (cov);
gsl_matrix_free (corr_matrix);
+ gsl_matrix_free (cov_matrix);
}
int
opts.statistics = 0;
/* Parse CORRELATIONS. */
- while (lex_token (lexer) != '.')
+ while (lex_token (lexer) != T_ENDCMD)
{
- lex_match (lexer, '/');
+ lex_match (lexer, T_SLASH);
if (lex_match_id (lexer, "MISSING"))
{
- lex_match (lexer, '=');
- while (lex_token (lexer) != '.' && lex_token (lexer) != '/')
+ lex_match (lexer, T_EQUALS);
+ while (lex_token (lexer) != T_ENDCMD && lex_token (lexer) != T_SLASH)
{
if (lex_match_id (lexer, "PAIRWISE"))
opts.missing_type = CORR_PAIRWISE;
lex_error (lexer, NULL);
goto error;
}
- lex_match (lexer, ',');
+ lex_match (lexer, T_COMMA);
}
}
else if (lex_match_id (lexer, "PRINT"))
{
- lex_match (lexer, '=');
- while (lex_token (lexer) != '.' && lex_token (lexer) != '/')
+ lex_match (lexer, T_EQUALS);
+ while (lex_token (lexer) != T_ENDCMD && lex_token (lexer) != T_SLASH)
{
if ( lex_match_id (lexer, "TWOTAIL"))
opts.tails = 2;
goto error;
}
- lex_match (lexer, ',');
+ lex_match (lexer, T_COMMA);
}
}
else if (lex_match_id (lexer, "STATISTICS"))
{
- lex_match (lexer, '=');
- while (lex_token (lexer) != '.' && lex_token (lexer) != '/')
+ lex_match (lexer, T_EQUALS);
+ while (lex_token (lexer) != T_ENDCMD && lex_token (lexer) != T_SLASH)
{
if ( lex_match_id (lexer, "DESCRIPTIVES"))
opts.statistics = STATS_DESCRIPTIVES;
goto error;
}
- lex_match (lexer, ',');
+ lex_match (lexer, T_COMMA);
}
}
else
{
if (lex_match_id (lexer, "VARIABLES"))
{
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
}
corr = xrealloc (corr, sizeof (*corr) * (n_corrs + 1));
/* Done. */
+ free (corr->vars);
free (corr);
+
return ok ? CMD_SUCCESS : CMD_CASCADING_FAILURE;
error:
+ free (corr->vars);
free (corr);
return CMD_FAILURE;
}