X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Ffactor.c;h=49bc8a4d67f5334fa4af3737edd99b1d4c368acd;hb=43a78c57c1e204b982d870ec0589c6eb8cdfdc04;hp=38c66cc751d7b920e698b540224cf6ee64241b46;hpb=7635ce0697c163bd9c80adb8b382df7a9aa97f42;p=pspp diff --git a/src/language/stats/factor.c b/src/language/stats/factor.c index 38c66cc751..49bc8a4d67 100644 --- a/src/language/stats/factor.c +++ b/src/language/stats/factor.c @@ -1,5 +1,6 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 2009, 2010, 2011, 2012, 2014, 2015, 2016 Free Software Foundation, Inc. + Copyright (C) 2009, 2010, 2011, 2012, 2014, 2015, + 2016, 2017 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 @@ -19,11 +20,12 @@ #include #include #include -#include -#include +#include +#include #include #include +#include "data/any-reader.h" #include "data/casegrouper.h" #include "data/casereader.h" #include "data/casewriter.h" @@ -35,6 +37,8 @@ #include "language/lexer/lexer.h" #include "language/lexer/value-parser.h" #include "language/lexer/variable-parser.h" +#include "language/data-io/file-handle.h" +#include "language/data-io/matrix-reader.h" #include "libpspp/cast.h" #include "libpspp/message.h" #include "libpspp/misc.h" @@ -45,6 +49,7 @@ #include "output/charts/scree.h" #include "output/tab.h" + #include "gettext.h" #define _(msgid) gettext (msgid) #define N_(msgid) msgid @@ -87,7 +92,7 @@ enum print_opts PRINT_EXTRACTION = 0x0100, PRINT_INITIAL = 0x0200, PRINT_KMO = 0x0400, - PRINT_REPR = 0x0800, + PRINT_REPR = 0x0800, PRINT_FSCORE = 0x1000 }; @@ -142,7 +147,7 @@ static const rotation_coefficients rotation_coeff[] = { /* return diag (C'C) ^ {-0.5} */ static gsl_matrix * -diag_rcp_sqrt (const gsl_matrix *C) +diag_rcp_sqrt (const gsl_matrix *C) { int j; gsl_matrix *d = gsl_matrix_calloc (C->size1, C->size2); @@ -170,7 +175,7 @@ diag_rcp_sqrt (const gsl_matrix *C) /* return diag ((C'C)^-1) ^ {-0.5} */ static gsl_matrix * -diag_rcp_inv_sqrt (const gsl_matrix *CCinv) +diag_rcp_inv_sqrt (const gsl_matrix *CCinv) { int j; gsl_matrix *r = gsl_matrix_calloc (CCinv->size1, CCinv->size2); @@ -191,7 +196,7 @@ diag_rcp_inv_sqrt (const gsl_matrix *CCinv) -struct cmd_factor +struct cmd_factor { size_t n_vars; const struct variable **vars; @@ -221,13 +226,13 @@ struct cmd_factor bool sort; }; + struct idata { /* Intermediate values used in calculation */ + struct matrix_material mm; - const gsl_matrix *corr ; /* The correlation matrix */ - gsl_matrix *cov ; /* The covariance matrix */ - const gsl_matrix *n ; /* Matrix of number of samples */ + gsl_matrix *analysis_matrix; /* A pointer to either mm.corr or mm.cov */ gsl_vector *eval ; /* The eigenvalues */ gsl_matrix *evec ; /* The eigenvectors */ @@ -237,6 +242,8 @@ struct idata gsl_vector *msr ; /* Multiple Squared Regressions */ double detR; /* The determinant of the correlation matrix */ + + struct covariance *cvm; }; static struct idata * @@ -259,10 +266,6 @@ idata_free (struct idata *id) gsl_vector_free (id->msr); gsl_vector_free (id->eval); gsl_matrix_free (id->evec); - if (id->cov != NULL) - gsl_matrix_free (id->cov); - if (id->corr != NULL) - gsl_matrix_free (CONST_CAST (gsl_matrix *, id->corr)); free (id); } @@ -276,7 +279,7 @@ anti_image (const gsl_matrix *m) assert (m->size1 == m->size2); a = gsl_matrix_alloc (m->size1, m->size2); - + for (i = 0; i < m->size1; ++i) { for (j = 0; j < m->size2; ++j) @@ -301,7 +304,7 @@ ssq_od_n (const gsl_matrix *m, int n) assert (m->size1 == m->size2); assert (n < m->size1); - + for (i = 0; i < m->size1; ++i) { if (i == n ) continue; @@ -357,11 +360,11 @@ dump_vector (const gsl_vector *v) #endif -static int +static int n_extracted_factors (const struct cmd_factor *factor, struct idata *idata) { int i; - + /* If there is a cached value, then return that. */ if ( idata->n_extractions != 0) return idata->n_extractions; @@ -373,7 +376,7 @@ n_extracted_factors (const struct cmd_factor *factor, struct idata *idata) idata->n_extractions = factor->n_factors; goto finish; } - + /* Use the MIN_EIGEN setting. */ for (i = 0 ; i < idata->eval->size; ++i) { @@ -408,7 +411,7 @@ struct smr_workspace { /* Copy of the subject */ gsl_matrix *m; - + gsl_matrix *inverse; gsl_permutation *perm; @@ -421,7 +424,7 @@ struct smr_workspace static struct smr_workspace *ws_create (const gsl_matrix *input) { struct smr_workspace *ws = xmalloc (sizeof (*ws)); - + ws->m = gsl_matrix_alloc (input->size1, input->size2); ws->inverse = gsl_matrix_calloc (input->size1 - 1, input->size2 - 1); ws->perm = gsl_permutation_alloc (input->size1 - 1); @@ -444,13 +447,13 @@ ws_destroy (struct smr_workspace *ws) } -/* +/* Return the square of the regression coefficient for VAR regressed against all other variables. */ static double squared_multiple_correlation (const gsl_matrix *corr, int var, struct smr_workspace *ws) { - /* For an explanation of what this is doing, see + /* For an explanation of what this is doing, see http://www.visualstatistics.net/Visual%20Statistics%20Multimedia/multiple_regression_analysis.htm */ @@ -462,7 +465,7 @@ squared_multiple_correlation (const gsl_matrix *corr, int var, struct smr_worksp gsl_matrix_swap_rows (ws->m, 0, var); gsl_matrix_swap_columns (ws->m, 0, var); - rxx = gsl_matrix_submatrix (ws->m, 1, 1, ws->m->size1 - 1, ws->m->size1 - 1); + rxx = gsl_matrix_submatrix (ws->m, 1, 1, ws->m->size1 - 1, ws->m->size1 - 1); gsl_linalg_LU_decomp (&rxx.matrix, ws->perm, &signum); @@ -511,7 +514,7 @@ factor_matrix_workspace_alloc (size_t n, size_t nf) ws->eval = gsl_vector_alloc (n); ws->evec = gsl_matrix_alloc (n, n); ws->r = gsl_matrix_alloc (n, n); - + return ws; } @@ -546,10 +549,10 @@ perm_shift_apply (gsl_permutation *target, const gsl_permutation *p, } -/* +/* Indirectly sort the rows of matrix INPUT, storing the sort order in PERM. The sort criteria are as follows: - + Rows are sorted on the first column, until the absolute value of an element in a subsequent column is greater than that of the first column. Thereafter, rows will be sorted on the second column, @@ -582,7 +585,7 @@ sort_matrix_indirect (const gsl_matrix *input, gsl_permutation *perm) } } - while (column_n < m && row_n < n) + while (column_n < m && row_n < n) { gsl_vector_const_view columni = gsl_matrix_const_column (mat, column_n); gsl_sort_vector_index (p, &columni.vector); @@ -591,7 +594,7 @@ sort_matrix_indirect (const gsl_matrix *input, gsl_permutation *perm) { gsl_vector_view row = gsl_matrix_row (mat, p->data[n - 1 - i]); size_t maxindex = gsl_vector_max_index (&row.vector); - + if ( maxindex > column_n ) break; @@ -609,11 +612,11 @@ sort_matrix_indirect (const gsl_matrix *input, gsl_permutation *perm) gsl_permutation_free (p); gsl_matrix_free (mat); - + assert ( 0 == gsl_permutation_valid (perm)); /* We want the biggest value to be first */ - gsl_permutation_reverse (perm); + gsl_permutation_reverse (perm); } @@ -647,7 +650,7 @@ clone_matrix (const gsl_matrix *m) } -static double +static double initial_sv (const gsl_matrix *fm) { int j, k; @@ -738,7 +741,7 @@ rotate (const struct cmd_factor *cf, const gsl_matrix *unrot, { double jv = gsl_matrix_get (normalised, p, j); double kv = gsl_matrix_get (normalised, p, k); - + double u = jv * jv - kv * kv; double v = 2 * jv * kv; a += u; @@ -787,10 +790,10 @@ rotate (const struct cmd_factor *cf, const gsl_matrix *unrot, gsl_matrix_free (h_sqrt); gsl_matrix_free (normalised); - if (cf->rotation == ROT_PROMAX) + if (cf->rotation == ROT_PROMAX) { /* general purpose m by m matrix, where m is the number of factors */ - gsl_matrix *mm1 = gsl_matrix_calloc (unrot->size2, unrot->size2); + gsl_matrix *mm1 = gsl_matrix_calloc (unrot->size2, unrot->size2); gsl_matrix *mm2 = gsl_matrix_calloc (unrot->size2, unrot->size2); /* general purpose m by p matrix, where p is the number of variables */ @@ -814,7 +817,7 @@ rotate (const struct cmd_factor *cf, const gsl_matrix *unrot, /* Vector of length p containing (indexed by i) \Sum^m_j {\lambda^2_{ij}} */ - gsl_vector *rssq = gsl_vector_calloc (unrot->size1); + gsl_vector *rssq = gsl_vector_calloc (unrot->size1); for (i = 0; i < P->size1; ++i) { @@ -823,9 +826,9 @@ rotate (const struct cmd_factor *cf, const gsl_matrix *unrot, { sum += gsl_matrix_get (result, i, j) * gsl_matrix_get (result, i, j); - + } - + gsl_vector_set (rssq, i, sqrt (sum)); } @@ -898,7 +901,7 @@ rotate (const struct cmd_factor *cf, const gsl_matrix *unrot, gsl_linalg_matmult_mod (mm1, GSL_LINALG_MOD_NONE, C, GSL_LINALG_MOD_TRANSPOSE, factor_correlation_matrix); - + gsl_linalg_matmult_mod (pattern_matrix, GSL_LINALG_MOD_NONE, factor_correlation_matrix, GSL_LINALG_MOD_NONE, pm1); @@ -954,7 +957,7 @@ rotate (const struct cmd_factor *cf, const gsl_matrix *unrot, WS is a pointer to a structure which must have been initialised with factor_matrix_workspace_init. */ static void -iterate_factor_matrix (const gsl_matrix *r, gsl_vector *communalities, gsl_matrix *factors, +iterate_factor_matrix (const gsl_matrix *r, gsl_vector *communalities, gsl_matrix *factors, struct factor_matrix_workspace *ws) { size_t i; @@ -1002,11 +1005,14 @@ iterate_factor_matrix (const gsl_matrix *r, gsl_vector *communalities, gsl_matri static bool run_factor (struct dataset *ds, const struct cmd_factor *factor); +static bool do_factor_by_matrix (const struct cmd_factor *factor, struct idata *idata); + + int cmd_factor (struct lexer *lexer, struct dataset *ds) { - const struct dictionary *dict = dataset_dict (ds); + struct dictionary *dict = NULL; int n_iterations = 25; struct cmd_factor factor; factor.n_vars = 0; @@ -1026,26 +1032,77 @@ cmd_factor (struct lexer *lexer, struct dataset *ds) factor.sort = false; factor.plot = 0; factor.rotation = ROT_VARIMAX; + factor.wv = NULL; factor.rconverge = 0.0001; - factor.wv = dict_get_weight (dict); - lex_match (lexer, T_SLASH); - if (!lex_force_match_id (lexer, "VARIABLES")) + struct matrix_reader *mr = NULL; + struct casereader *matrix_reader = NULL; + + if (lex_match_id (lexer, "VARIABLES")) { - goto error; + lex_match (lexer, T_EQUALS); + dict = dataset_dict (ds); + factor.wv = dict_get_weight (dict); + + if (!parse_variables_const (lexer, dict, &factor.vars, &factor.n_vars, + PV_NO_DUPLICATE | PV_NUMERIC)) + goto error; } + else if (lex_match_id (lexer, "MATRIX")) + { + lex_match (lexer, T_EQUALS); + if (! lex_force_match_id (lexer, "IN")) + goto error; + if (!lex_force_match (lexer, T_LPAREN)) + { + goto error; + } + if (lex_match_id (lexer, "CORR")) + { + } + else if (lex_match_id (lexer, "COV")) + { + } + else + { + lex_error (lexer, _("Matrix input for %s must be either COV or CORR"), "FACTOR"); + goto error; + } + if (! lex_force_match (lexer, T_EQUALS)) + goto error; + if (lex_match (lexer, T_ASTERISK)) + { + dict = dataset_dict (ds); + matrix_reader = casereader_clone (dataset_source (ds)); + } + else + { + struct file_handle *fh = fh_parse (lexer, FH_REF_FILE, NULL); + if (fh == NULL) + goto error; - lex_match (lexer, T_EQUALS); + matrix_reader + = any_reader_open_and_decode (fh, NULL, &dict, NULL); - if (!parse_variables_const (lexer, dict, &factor.vars, &factor.n_vars, - PV_NO_DUPLICATE | PV_NUMERIC)) - goto error; + if (! (matrix_reader && dict)) + { + goto error; + } + } - if (factor.n_vars < 2) - msg (MW, _("Factor analysis on a single variable is not useful.")); + if (! lex_force_match (lexer, T_RPAREN)) + goto error; + + mr = create_matrix_reader_from_case_reader (dict, matrix_reader, + &factor.vars, &factor.n_vars); + } + else + { + goto error; + } while (lex_token (lexer) != T_ENDCMD) { @@ -1320,11 +1377,10 @@ cmd_factor (struct lexer *lexer, struct dataset *ds) { factor.print |= PRINT_CORRELATION; } -#if FACTOR_FULLY_IMPLEMENTED else if (lex_match_id (lexer, "COVARIANCE")) { + factor.print |= PRINT_COVARIANCE; } -#endif else if (lex_match_id (lexer, "ROTATION")) { factor.print |= PRINT_ROTATION; @@ -1408,13 +1464,37 @@ cmd_factor (struct lexer *lexer, struct dataset *ds) if ( factor.rotation == ROT_NONE ) factor.print &= ~PRINT_ROTATION; - if ( ! run_factor (ds, &factor)) - goto error; + if (factor.n_vars < 2) + msg (MW, _("Factor analysis on a single variable is not useful.")); + + if (matrix_reader) + { + struct idata *id = idata_alloc (factor.n_vars); + + while (next_matrix_from_reader (&id->mm, mr, + factor.vars, factor.n_vars)) + { + do_factor_by_matrix (&factor, id); + + gsl_matrix_free (id->mm.corr); + id->mm.corr = NULL; + gsl_matrix_free (id->mm.cov); + id->mm.cov = NULL; + } + + idata_free (id); + } + else + if ( ! run_factor (ds, &factor)) + goto error; + + destroy_matrix_reader (mr); free (factor.vars); return CMD_SUCCESS; error: + destroy_matrix_reader (mr); free (factor.vars); return CMD_FAILURE; } @@ -1474,14 +1554,14 @@ the_communality (const gsl_matrix *evec, const gsl_vector *eval, int n, int n_fa /* Return the communality of variable N, calculated to N_FACTORS */ static double -communality (struct idata *idata, int n, int n_factors) +communality (const struct idata *idata, int n, int n_factors) { return the_communality (idata->evec, idata->eval, n, n_factors); } static void -show_scree (const struct cmd_factor *f, struct idata *idata) +show_scree (const struct cmd_factor *f, const struct idata *idata) { struct scree *s; const char *label ; @@ -1566,7 +1646,7 @@ show_communalities (const struct cmd_factor * factor, static void -show_factor_matrix (const struct cmd_factor *factor, struct idata *idata, const char *title, const gsl_matrix *fm) +show_factor_matrix (const struct cmd_factor *factor, const struct idata *idata, const char *title, const gsl_matrix *fm) { int i; @@ -1580,10 +1660,10 @@ show_factor_matrix (const struct cmd_factor *factor, struct idata *idata, const struct tab_table *t = tab_create (nc, nr); - /* + /* if ( factor->extraction == EXTRACTION_PC ) tab_title (t, _("Component Matrix")); - else + else tab_title (t, _("Factor Matrix")); */ @@ -1659,7 +1739,8 @@ show_factor_matrix (const struct cmd_factor *factor, struct idata *idata, const static void -show_explained_variance (const struct cmd_factor * factor, struct idata *idata, +show_explained_variance (const struct cmd_factor * factor, + const struct idata *idata, const gsl_vector *initial_eigenvalues, const gsl_vector *extracted_eigenvalues, const gsl_vector *rotated_loadings) @@ -1887,7 +1968,7 @@ show_factor_correlation (const struct cmd_factor * factor, const gsl_matrix *fcm for (i = 0 ; i < fcm->size1; ++i) { for (j = 0 ; j < fcm->size2; ++j) - tab_double (t, heading_columns + i, heading_rows +j, 0, + tab_double (t, heading_columns + j, heading_rows + i, 0, gsl_matrix_get (fcm, i, j), NULL, RC_OTHER); } @@ -1983,7 +2064,7 @@ show_correlation_matrix (const struct cmd_factor *factor, const struct idata *id for (i = 0; i < factor->n_vars; ++i) { for (j = 0; j < factor->n_vars; ++j) - tab_double (t, heading_columns + i, y + j, 0, gsl_matrix_get (idata->corr, i, j), NULL, RC_OTHER); + tab_double (t, heading_columns + j, y + i, 0, gsl_matrix_get (idata->mm.corr, i, j), NULL, RC_OTHER); } } @@ -1996,13 +2077,13 @@ show_correlation_matrix (const struct cmd_factor *factor, const struct idata *id { for (j = 0; j < factor->n_vars; ++j) { - double rho = gsl_matrix_get (idata->corr, i, j); - double w = gsl_matrix_get (idata->n, i, j); + double rho = gsl_matrix_get (idata->mm.corr, i, j); + double w = gsl_matrix_get (idata->mm.n, i, j); if (i == j) continue; - tab_double (t, heading_columns + i, y + j, 0, significance_of_correlation (rho, w), NULL, RC_PVALUE); + tab_double (t, heading_columns + j, y + i, 0, significance_of_correlation (rho, w), NULL, RC_PVALUE); } } } @@ -2018,59 +2099,155 @@ show_correlation_matrix (const struct cmd_factor *factor, const struct idata *id tab_submit (t); } +static void +show_covariance_matrix (const struct cmd_factor *factor, const struct idata *idata) +{ + struct tab_table *t ; + size_t i, j; + int y_pos_corr = -1; + int suffix_rows = 0; + + const int heading_rows = 1; + const int heading_columns = 1; + + int nc = heading_columns ; + int nr = heading_rows ; + int n_data_sets = 0; + + if (factor->print & PRINT_COVARIANCE) + { + y_pos_corr = n_data_sets; + n_data_sets++; + nc = heading_columns + factor->n_vars; + } + + nr += n_data_sets * factor->n_vars; + + /* If the table would contain only headings, don't bother rendering it */ + if (nr <= heading_rows && suffix_rows == 0) + return; + + t = tab_create (nc, nr + suffix_rows); + + tab_title (t, _("Covariance Matrix")); + + tab_hline (t, TAL_1, 0, nc - 1, heading_rows); + + if (nr > heading_rows) + { + tab_headers (t, heading_columns, 0, heading_rows, 0); + + tab_vline (t, TAL_2, heading_columns, 0, nr - 1); + + /* Outline the box */ + tab_box (t, + TAL_2, TAL_2, + -1, -1, + 0, 0, + nc - 1, nr - 1); + + /* Vertical lines */ + tab_box (t, + -1, -1, + -1, TAL_1, + heading_columns, 0, + nc - 1, nr - 1); + + + for (i = 0; i < factor->n_vars; ++i) + tab_text (t, heading_columns + i, 0, TAT_TITLE, var_to_string (factor->vars[i])); + + + for (i = 0 ; i < n_data_sets; ++i) + { + int y = heading_rows + i * factor->n_vars; + size_t v; + for (v = 0; v < factor->n_vars; ++v) + tab_text (t, heading_columns -1, y + v, TAT_TITLE, var_to_string (factor->vars[v])); + + tab_hline (t, TAL_1, 0, nc - 1, y); + } + + if (factor->print & PRINT_COVARIANCE) + { + const double y = heading_rows + y_pos_corr; + + for (i = 0; i < factor->n_vars; ++i) + { + for (j = 0; j < factor->n_vars; ++j) + tab_double (t, heading_columns + j, y + i, 0, gsl_matrix_get (idata->mm.cov, i, j), NULL, RC_OTHER); + } + } + } + + tab_submit (t); +} static void do_factor (const struct cmd_factor *factor, struct casereader *r) { struct ccase *c; - const gsl_matrix *var_matrix; - const gsl_matrix *mean_matrix; - - const gsl_matrix *analysis_matrix; struct idata *idata = idata_alloc (factor->n_vars); - struct covariance *cov = covariance_1pass_create (factor->n_vars, factor->vars, + idata->cvm = covariance_1pass_create (factor->n_vars, factor->vars, factor->wv, factor->exclude); for ( ; (c = casereader_read (r) ); case_unref (c)) { - covariance_accumulate (cov, c); + covariance_accumulate (idata->cvm, c); } - idata->cov = covariance_calculate (cov); + idata->mm.cov = covariance_calculate (idata->cvm); - if (idata->cov == NULL) + if (idata->mm.cov == NULL) { msg (MW, _("The dataset contains no complete observations. No analysis will be performed.")); - covariance_destroy (cov); + covariance_destroy (idata->cvm); goto finish; } - var_matrix = covariance_moments (cov, MOMENT_VARIANCE); - mean_matrix = covariance_moments (cov, MOMENT_MEAN); - idata->n = covariance_moments (cov, MOMENT_NONE); - + idata->mm.var_matrix = covariance_moments (idata->cvm, MOMENT_VARIANCE); + idata->mm.mean_matrix = covariance_moments (idata->cvm, MOMENT_MEAN); + idata->mm.n = covariance_moments (idata->cvm, MOMENT_NONE); + + do_factor_by_matrix (factor, idata); - if ( factor->method == METHOD_CORR) + finish: + gsl_matrix_free (idata->mm.corr); + gsl_matrix_free (idata->mm.cov); + + idata_free (idata); + casereader_destroy (r); +} + +static bool +do_factor_by_matrix (const struct cmd_factor *factor, struct idata *idata) +{ + if (!idata->mm.cov && !idata->mm.corr) { - idata->corr = correlation_from_covariance (idata->cov, var_matrix); - - analysis_matrix = idata->corr; + msg (ME, _("The dataset has no complete covariance or correlation matrix.")); + return false; } - else - analysis_matrix = idata->cov; + if (idata->mm.cov && !idata->mm.corr) + idata->mm.corr = correlation_from_covariance (idata->mm.cov, idata->mm.var_matrix); + if (idata->mm.corr && !idata->mm.cov) + idata->mm.cov = covariance_from_correlation (idata->mm.corr, idata->mm.var_matrix); + if (factor->method == METHOD_CORR) + idata->analysis_matrix = idata->mm.corr; + else + idata->analysis_matrix = idata->mm.cov; if (factor->print & PRINT_DETERMINANT || factor->print & PRINT_KMO) { int sign = 0; - const int size = idata->corr->size1; + const int size = idata->mm.corr->size1; gsl_permutation *p = gsl_permutation_calloc (size); gsl_matrix *tmp = gsl_matrix_calloc (size, size); - gsl_matrix_memcpy (tmp, idata->corr); + gsl_matrix_memcpy (tmp, idata->mm.corr); gsl_linalg_LU_decomp (tmp, p, &sign); idata->detR = gsl_linalg_LU_det (tmp, sign); @@ -2121,9 +2298,9 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) const struct variable *v = factor->vars[i]; tab_text (t, 0, i + heading_rows, TAB_LEFT | TAT_TITLE, var_to_string (v)); - tab_double (t, 1, i + heading_rows, 0, gsl_matrix_get (mean_matrix, i, i), NULL, RC_OTHER); - tab_double (t, 2, i + heading_rows, 0, sqrt (gsl_matrix_get (var_matrix, i, i)), NULL, RC_OTHER); - tab_double (t, 3, i + heading_rows, 0, gsl_matrix_get (idata->n, i, i), NULL, RC_WEIGHT); + tab_double (t, 1, i + heading_rows, 0, gsl_matrix_get (idata->mm.mean_matrix, i, i), NULL, RC_OTHER); + tab_double (t, 2, i + heading_rows, 0, sqrt (gsl_matrix_get (idata->mm.var_matrix, i, i)), NULL, RC_OTHER); + tab_double (t, 3, i + heading_rows, 0, gsl_matrix_get (idata->mm.n, i, i), NULL, RC_WEIGHT); } tab_submit (t); @@ -2135,7 +2312,7 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) double sum_ssq_r = 0; double sum_ssq_a = 0; - double df = factor->n_vars * ( factor->n_vars - 1) / 2; + double df = factor->n_vars * (factor->n_vars - 1) / 2; double w = 0; @@ -2153,7 +2330,7 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) struct tab_table *t = tab_create (nc, nr); tab_title (t, _("KMO and Bartlett's Test")); - x = clone_matrix (idata->corr); + x = clone_matrix (idata->mm.corr); gsl_linalg_cholesky_decomp (x); gsl_linalg_cholesky_invert (x); @@ -2190,13 +2367,13 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) tab_text (t, 1, 3, TAT_TITLE, _("Sig.")); - /* The literature doesn't say what to do for the value of W when + /* The literature doesn't say what to do for the value of W when missing values are involved. The best thing I can think of is to take the mean average. */ w = 0; - for (i = 0; i < idata->n->size1; ++i) - w += gsl_matrix_get (idata->n, i, i); - w /= idata->n->size1; + for (i = 0; i < idata->mm.n->size1; ++i) + w += gsl_matrix_get (idata->mm.n, i, i); + w /= idata->mm.n->size1; xsq = w - 1 - (2 * factor->n_vars + 5) / 6.0; xsq *= -log (idata->detR); @@ -2204,18 +2381,20 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) tab_double (t, 2, 1, 0, xsq, NULL, RC_OTHER); tab_double (t, 2, 2, 0, df, NULL, RC_INTEGER); tab_double (t, 2, 3, 0, gsl_cdf_chisq_Q (xsq, df), NULL, RC_PVALUE); - + tab_submit (t); } show_correlation_matrix (factor, idata); - covariance_destroy (cov); + show_covariance_matrix (factor, idata); + if (idata->cvm) + covariance_destroy (idata->cvm); { - gsl_matrix *am = matrix_dup (analysis_matrix); + gsl_matrix *am = matrix_dup (idata->analysis_matrix); gsl_eigen_symmv_workspace *workspace = gsl_eigen_symmv_alloc (factor->n_vars); - + gsl_eigen_symmv (am, idata->eval, idata->evec, workspace); gsl_eigen_symmv_free (workspace); @@ -2234,12 +2413,12 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) if (idata->n_extractions > factor->n_vars) { - msg (MW, - _("The %s criteria result in more factors than variables, which is not meaningful. No analysis will be performed."), + msg (MW, + _("The %s criteria result in more factors than variables, which is not meaningful. No analysis will be performed."), "FACTOR"); goto finish; } - + { gsl_matrix *rotated_factors = NULL; gsl_matrix *pattern_matrix = NULL; @@ -2256,11 +2435,11 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) if ( factor->extraction == EXTRACTION_PAF) { gsl_vector *diff = gsl_vector_alloc (idata->msr->size); - struct smr_workspace *ws = ws_create (analysis_matrix); + struct smr_workspace *ws = ws_create (idata->analysis_matrix); for (i = 0 ; i < factor->n_vars ; ++i) { - double r2 = squared_multiple_correlation (analysis_matrix, i, ws); + double r2 = squared_multiple_correlation (idata->analysis_matrix, i, ws); gsl_vector_set (idata->msr, i, r2); } @@ -2273,12 +2452,12 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) double min, max; gsl_vector_memcpy (diff, idata->msr); - iterate_factor_matrix (analysis_matrix, idata->msr, factor_matrix, fmw); - + iterate_factor_matrix (idata->analysis_matrix, idata->msr, factor_matrix, fmw); + gsl_vector_sub (diff, idata->msr); gsl_vector_minmax (diff, &min, &max); - + if ( fabs (min) < factor->econverge && fabs (max) < factor->econverge) break; } @@ -2296,7 +2475,7 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) gsl_vector_memcpy (extracted_communalities, initial_communalities); - iterate_factor_matrix (analysis_matrix, extracted_communalities, factor_matrix, fmw); + iterate_factor_matrix (idata->analysis_matrix, extracted_communalities, factor_matrix, fmw); extracted_eigenvalues = idata->eval; @@ -2315,11 +2494,11 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) pattern_matrix = gsl_matrix_calloc (factor_matrix->size1, factor_matrix->size2); fcm = gsl_matrix_calloc (factor_matrix->size2, factor_matrix->size2); } - + rotate (factor, factor_matrix, extracted_communalities, rotated_factors, rotated_loadings, pattern_matrix, fcm); } - + show_explained_variance (factor, idata, idata->eval, extracted_eigenvalues, rotated_loadings); factor_matrix_workspace_free (fmw); @@ -2340,7 +2519,8 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) { show_factor_matrix (factor, idata, (factor->rotation == ROT_PROMAX) ? _("Structure Matrix") : - (factor->extraction == EXTRACTION_PC ? _("Rotated Component Matrix") : _("Rotated Factor Matrix")), + (factor->extraction == EXTRACTION_PC ? _("Rotated Component Matrix") : + _("Rotated Factor Matrix")), rotated_factors); gsl_matrix_free (rotated_factors); @@ -2359,10 +2539,7 @@ do_factor (const struct cmd_factor *factor, struct casereader *r) } finish: - - idata_free (idata); - - casereader_destroy (r); + return; }