X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fcorrelations.c;h=c76f5984abfcfe76ac6abff735dc6f3d064b0e42;hb=c91f650b47f33cfbd4b7ed45dbfa7eb012c7e6fb;hp=277cfea5bb15a57648679dcc96b39a07a14dd0d5;hpb=3bbe45fcc70f8d059b4bf6715d629209b50fa48e;p=pspp diff --git a/src/language/stats/correlations.c b/src/language/stats/correlations.c index 277cfea5bb..c76f5984ab 100644 --- a/src/language/stats/correlations.c +++ b/src/language/stats/correlations.c @@ -1,5 +1,5 @@ /* 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 @@ -16,51 +16,36 @@ #include -#include -#include -#include +#include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - #include -#include "xalloc.h" -#include "minmax.h" -#include -#include + +#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; @@ -108,9 +93,8 @@ output_descriptives (const struct corr *corr, const gsl_matrix *means, 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); @@ -203,9 +187,8 @@ output_correlation (const struct corr *corr, const struct corr_opts *opts, /* 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); @@ -224,6 +207,7 @@ output_correlation (const struct corr *corr, const struct corr_opts *opts, nc - 1, nr - 1); tab_vline (t, TAL_2, heading_columns, 0, nr - 1); + tab_vline (t, TAL_1, 1, heading_rows, nr - 1); for (r = 0 ; r < corr->n_vars1 ; ++r) @@ -249,7 +233,8 @@ output_correlation (const struct corr *corr, const struct corr_opts *opts, for (c = 0 ; c < matrix_cols ; ++c) { - const struct variable *v = corr->n_vars_total > corr->n_vars1 ? corr->vars[corr->n_vars_total - corr->n_vars1 + c] : corr->vars[c]; + const struct variable *v = corr->n_vars_total > corr->n_vars1 ? + corr->vars[corr->n_vars1 + c] : corr->vars[c]; tab_text (t, heading_columns + c, 0, TAB_LEFT | TAT_TITLE, var_to_string (v)); } @@ -259,7 +244,9 @@ output_correlation (const struct corr *corr, const struct corr_opts *opts, for (c = 0 ; c < matrix_cols ; ++c) { unsigned char flags = 0; - const int col_index = corr->n_vars_total - corr->n_vars1 + c; + const int col_index = corr->n_vars_total > corr->n_vars1 ? + corr->n_vars_total - corr->n_vars1 - 1 + c : + c; double pearson = gsl_matrix_get (cm, r, col_index); double w = gsl_matrix_get (samples, r, col_index); double sig = opts->tails * significance_of_correlation (pearson, w); @@ -291,42 +278,16 @@ output_correlation (const struct corr *corr, const struct corr_opts *opts, } -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, 2); - + 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)) @@ -343,7 +304,6 @@ run_corr (struct casereader *r, const struct corr_opts *opts, const struct corr casereader_destroy (rc); - samples_matrix = covariance_moments (cov, MOMENT_NONE); var_matrix = covariance_moments (cov, MOMENT_VARIANCE); mean_matrix = covariance_moments (cov, MOMENT_MEAN); @@ -353,13 +313,12 @@ run_corr (struct casereader *r, const struct corr_opts *opts, const struct corr if ( opts->statistics & STATS_DESCRIPTIVES) output_descriptives (corr, mean_matrix, var_matrix, samples_matrix); - output_correlation (corr, opts, - corr_matrix, - samples_matrix, - cov_matrix); + output_correlation (corr, opts, corr_matrix, + samples_matrix, cov_matrix); covariance_destroy (cov); gsl_matrix_free (corr_matrix); + gsl_matrix_free (cov_matrix); } int @@ -386,13 +345,13 @@ cmd_correlation (struct lexer *lexer, struct dataset *ds) 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; @@ -408,13 +367,13 @@ cmd_correlation (struct lexer *lexer, struct dataset *ds) 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; @@ -430,13 +389,13 @@ cmd_correlation (struct lexer *lexer, struct dataset *ds) 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; @@ -453,14 +412,14 @@ cmd_correlation (struct lexer *lexer, struct dataset *ds) 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)); @@ -543,10 +502,13 @@ cmd_correlation (struct lexer *lexer, struct dataset *ds) /* Done. */ + free (corr->vars); free (corr); + return ok ? CMD_SUCCESS : CMD_CASCADING_FAILURE; error: + free (corr->vars); free (corr); return CMD_FAILURE; }