X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Ffrequencies.q;h=b5ad8c47793eef15064a887023eead28732c8845;hb=5f86425ef29d236118667470f2a461818d7e55b2;hp=e397eb8760361fe70fa1a679f6955cc9585daebf;hpb=691c25e36fd1ee722dd35419d6110e3876b99f9c;p=pspp diff --git a/src/language/stats/frequencies.q b/src/language/stats/frequencies.q index e397eb8760..b5ad8c4779 100644 --- a/src/language/stats/frequencies.q +++ b/src/language/stats/frequencies.q @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 1997-9, 2000, 2007, 2009, 2010 Free Software Foundation, Inc. + Copyright (C) 1997-9, 2000, 2007, 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 @@ -23,9 +23,9 @@ #include "data/case.h" #include "data/casegrouper.h" #include "data/casereader.h" +#include "data/dataset.h" #include "data/dictionary.h" #include "data/format.h" -#include "data/procedure.h" #include "data/settings.h" #include "data/value-labels.h" #include "data/variable.h" @@ -43,6 +43,8 @@ #include "libpspp/str.h" #include "math/histogram.h" #include "math/moments.h" +#include "math/chart-geometry.h" + #include "output/chart-item.h" #include "output/charts/piechart.h" #include "output/charts/plot-hist.h" @@ -188,7 +190,6 @@ struct var_freqs /* Variable attributes. */ int width; - struct fmt_spec print; }; struct frq_proc @@ -498,14 +499,17 @@ postcalc (struct frq_proc *frq, const struct dataset *ds) histogram = freq_tab_to_hist (frq, &vf->tab, vf->var); - chart_item_submit (histogram_chart_create ( + if ( histogram) + { + chart_item_submit (histogram_chart_create ( histogram->gsl_hist, var_to_string(vf->var), vf->tab.valid_cases, d[FRQ_MEAN], d[FRQ_STDDEV], frq->hist->draw_normal)); - statistic_destroy (&histogram->parent); + statistic_destroy (&histogram->parent); + } } if (frq->pie) @@ -621,7 +625,7 @@ frq_custom_variables (struct lexer *lexer, struct dataset *ds, lex_match (lexer, T_EQUALS); if (lex_token (lexer) != T_ALL && (lex_token (lexer) != T_ID - || dict_lookup_var (dataset_dict (ds), lex_tokid (lexer)) == NULL)) + || dict_lookup_var (dataset_dict (ds), lex_tokcstr (lexer)) == NULL)) return 2; /* Get list of current variables, to avoid duplicates. */ @@ -646,7 +650,6 @@ frq_custom_variables (struct lexer *lexer, struct dataset *ds, vf->n_groups = 0; vf->groups = NULL; vf->width = var_get_width (var); - vf->print = *var_get_print_format (var); } frq->n_vars = n_vars; @@ -663,7 +666,8 @@ frq_custom_grouped (struct lexer *lexer, struct dataset *ds, struct cmd_frequenc struct frq_proc *frq = frq_; lex_match (lexer, T_EQUALS); - if ((lex_token (lexer) == T_ID && dict_lookup_var (dataset_dict (ds), lex_tokid (lexer)) != NULL) + if ((lex_token (lexer) == T_ID + && dict_lookup_var (dataset_dict (ds), lex_tokcstr (lexer)) != NULL) || lex_token (lexer) == T_ID) for (;;) { @@ -700,7 +704,7 @@ frq_custom_grouped (struct lexer *lexer, struct dataset *ds, struct cmd_frequenc if (!lex_match (lexer, T_RPAREN)) { free (v); - msg (SE, _("`)' expected after GROUPED interval list.")); + lex_error_expecting (lexer, "`)'", NULL_SENTINEL); return 0; } } @@ -737,14 +741,23 @@ frq_custom_grouped (struct lexer *lexer, struct dataset *ds, struct cmd_frequenc } free (v); - if (!lex_match (lexer, T_SLASH)) - break; - if ((lex_token (lexer) != T_ID || dict_lookup_var (dataset_dict (ds), lex_tokid (lexer)) != NULL) - && lex_token (lexer) != T_ALL) - { - lex_put_back (lexer, T_SLASH); - break; - } + if (lex_token (lexer) != T_SLASH) + break; + + if ((lex_next_token (lexer, 1) == T_ID + && dict_lookup_var (dataset_dict (ds), + lex_next_tokcstr (lexer, 1))) + || lex_next_token (lexer, 1) == T_ALL) + { + /* The token after the slash is a variable name. Keep parsing. */ + lex_get (lexer); + } + else + { + /* The token after the slash must be the start of a new + subcommand. Let the caller see the slash. */ + break; + } } return 1; @@ -840,7 +853,7 @@ dump_freq_table (const struct var_freqs *vf, const struct variable *wv) if (label != NULL) tab_text (t, 0, r, TAB_LEFT, label); - tab_value (t, 1, r, TAB_NONE, &f->value, ft->dict, &vf->print); + tab_value (t, 1, r, TAB_NONE, &f->value, vf->var, NULL); tab_double (t, 2, r, TAB_NONE, f->count, wfmt); tab_double (t, 3, r, TAB_NONE, percent, NULL); tab_double (t, 4, r, TAB_NONE, valid_percent, NULL); @@ -857,7 +870,7 @@ dump_freq_table (const struct var_freqs *vf, const struct variable *wv) if (label != NULL) tab_text (t, 0, r, TAB_LEFT, label); - tab_value (t, 1, r, TAB_NONE, &f->value, ft->dict, &vf->print); + tab_value (t, 1, r, TAB_NONE, &f->value, vf->var, NULL); tab_double (t, 2, r, TAB_NONE, f->count, wfmt); tab_double (t, 3, r, TAB_NONE, f->count / ft->total_cases * 100.0, NULL); @@ -921,8 +934,7 @@ calc_percentiles (const struct frq_proc *frq, const struct var_freqs *vf) if (rank <= tp) break; - if (f->count > 1 - && (rank - (f->count - 1) > tp || f + 1 >= ft->missing)) + if (tp + 1 < rank || f + 1 >= ft->missing) pc->value = f->value.f; else pc->value = calc_percentile (pc->p, W, f->value.f, f[1].value.f); @@ -1038,7 +1050,7 @@ dump_statistics (const struct frq_proc *frq, const struct var_freqs *vf, tab_double (t, 2, 0, TAB_NONE, ft->valid_cases, wfmt); tab_double (t, 2, 1, TAB_NONE, ft->total_cases - ft->valid_cases, wfmt); - for (i = 0; i < frq->n_percentiles; i++, r++) + for (i = 0; i < frq->n_percentiles; i++) { struct percentile *pc = &frq->percentiles[i]; @@ -1056,6 +1068,7 @@ dump_statistics (const struct frq_proc *frq, const struct var_freqs *vf, tab_fixed (t, 1, r, TAB_LEFT, pc->p * 100, 3, 0); tab_double (t, 2, r, TAB_NONE, pc->value, var_get_print_format (vf->var)); + r++; } tab_title (t, "%s", var_to_string (vf->var)); @@ -1106,10 +1119,9 @@ freq_tab_to_hist (const struct frq_proc *frq, const struct freq_tab *ft, { double x_min, x_max, valid_freq; int i; - + double bin_width; struct histogram *histogram; double iqr; - int bins; /* Find out the extremes of the x value, within the range to be included in the histogram, and sum the total frequency of those values. */ @@ -1129,19 +1141,13 @@ freq_tab_to_hist (const struct frq_proc *frq, const struct freq_tab *ft, /* Freedman-Diaconis' choice of bin width. */ iqr = calculate_iqr (frq); - if (iqr != SYSMIS) - { - double bin_width = 2 * iqr / pow (valid_freq, 1.0 / 3.0); - bins = (x_max - x_min) / bin_width; - if (bins < 5) - bins = 5; - else if (bins > 400) - bins = 400; - } - else - bins = 5; + bin_width = 2 * iqr / pow (valid_freq, 1.0 / 3.0); + + histogram = histogram_create (bin_width, x_min, x_max); + + if ( histogram == NULL) + return NULL; - histogram = histogram_create (bins, x_min, x_max); for (i = 0; i < ft->n_valid; i++) { const struct freq *f = &ft->valid[i];