/* PSPP - a program for statistical analysis.
- Copyright (C) 2004, 2008 Free Software Foundation, Inc.
+ Copyright (C) 2004, 2008, 2009 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 <data/casegrouper.h>
#include <data/casereader.h>
#include <data/casewriter.h>
-#include <data/case-ordering.h>
#include <data/dictionary.h>
#include <data/procedure.h>
+#include <data/subcase.h>
#include <data/value-labels.h>
#include <data/variable.h>
#include <language/command.h>
/* Sum of all weights, including those for missing values */
double n;
+ /* Sum of weights of non_missing values */
+ double n_valid;
+
double mean;
double variance;
}
static struct xfactor level0_factor;
-static struct ll_list factor_list = LL_INITIALIZER (factor_list);
+static struct ll_list factor_list;
/* Parse the clause specifying the factors */
static int examine_parse_independent_vars (struct lexer *lexer,
/* Output functions */
static void show_summary (const struct variable **dependent_var, int n_dep_var,
+ const struct dictionary *dict,
const struct xfactor *f);
static void run_examine (struct cmd_examine *, struct casereader *,
struct dataset *);
-static void output_examine (void);
+static void output_examine (const struct dictionary *dict);
void factor_calc (const struct ccase *c, int case_no,
subc_list_double_create (&percentile_list);
percentile_algorithm = PC_HAVERAGE;
+ ll_init (&factor_list);
+
if ( !parse_examine (lexer, ds, &cmd, NULL) )
{
subc_list_double_destroy (&percentile_list);
chart_write_yscale (dnp_chart, np->dns_min, np->dns_max, 5);
{
- struct ccase c;
struct casereader *reader = casewriter_make_reader (np->writer);
- while (casereader_read (reader, &c))
+ struct ccase *c;
+ while ((c = casereader_read (reader)) != NULL)
{
- chart_datum (np_chart, 0, case_data_idx (&c, NP_IDX_Y)->f, case_data_idx (&c, NP_IDX_NS)->f);
- chart_datum (dnp_chart, 0, case_data_idx (&c, NP_IDX_Y)->f, case_data_idx (&c, NP_IDX_DNS)->f);
+ chart_datum (np_chart, 0, case_data_idx (c, NP_IDX_Y)->f, case_data_idx (c, NP_IDX_NS)->f);
+ chart_datum (dnp_chart, 0, case_data_idx (c, NP_IDX_Y)->f, case_data_idx (c, NP_IDX_DNS)->f);
- case_destroy (&c);
+ case_unref (c);
}
casereader_destroy (reader);
}
/* Show all the appropriate tables */
static void
-output_examine (void)
+output_examine (const struct dictionary *dict)
{
struct ll *ll;
- show_summary (dependent_vars, n_dependent_vars, &level0_factor);
+ show_summary (dependent_vars, n_dependent_vars, dict, &level0_factor);
if ( cmd.a_statistics[XMN_ST_EXTREME] )
show_extremes (dependent_vars, n_dependent_vars, &level0_factor);
ll != ll_null (&factor_list); ll = ll_next (ll))
{
struct xfactor *factor = ll_data (ll, struct xfactor, ll);
- show_summary (dependent_vars, n_dependent_vars, factor);
+ show_summary (dependent_vars, n_dependent_vars, dict, factor);
if ( cmd.a_statistics[XMN_ST_EXTREME] )
show_extremes (dependent_vars, n_dependent_vars, factor);
examine_group (struct cmd_examine *cmd, struct casereader *reader, int level,
const struct dictionary *dict, struct xfactor *factor)
{
- struct ccase c;
+ struct ccase *c;
const struct variable *wv = dict_get_weight (dict);
int v;
int n_extrema = 1;
n_extrema = cmd->st_n;
- if (casereader_peek (reader, 0, &c))
+ c = casereader_peek (reader, 0);
+ if (c != NULL)
{
if ( level > 0)
{
result->value[0] =
- value_dup (case_data (&c, factor->indep_var[0]),
+ value_dup (case_data (c, factor->indep_var[0]),
var_get_width (factor->indep_var[0]));
if ( level > 1)
result->value[1] =
- value_dup (case_data (&c, factor->indep_var[1]),
+ value_dup (case_data (c, factor->indep_var[1]),
var_get_width (factor->indep_var[1]));
}
- case_destroy (&c);
+ case_unref (c);
}
for (v = 0; v < n_dependent_vars; ++v)
{
/* In this case, we need to sort the data, so we create a sorting
casewriter */
- struct case_ordering *up_ordering = case_ordering_create ();
-
- case_ordering_add_var (up_ordering, dependent_vars[v], SRT_ASCEND);
- writer = sort_create_writer (up_ordering,
+ struct subcase up_ordering;
+ subcase_init_var (&up_ordering, dependent_vars[v], SC_ASCEND);
+ writer = sort_create_writer (&up_ordering,
casereader_get_value_cnt (reader));
+ subcase_destroy (&up_ordering);
}
else
{
/* Sort or just iterate, whilst calculating moments etc */
- while (casereader_read (input, &c))
+ while ((c = casereader_read (input)) != NULL)
{
const casenumber loc =
- case_data_idx (&c, casereader_get_value_cnt (reader) - 1)->f;
+ case_data_idx (c, casereader_get_value_cnt (reader) - 1)->f;
- const double weight = wv ? case_data (&c, wv)->f : 1.0;
+ const double weight = wv ? case_data (c, wv)->f : 1.0;
+ const union value *value = case_data (c, dependent_vars[v]);
if (weight != SYSMIS)
minimize (&result->metrics[v].cmin, weight);
moments1_add (result->metrics[v].moments,
- case_data (&c, dependent_vars[v])->f,
+ value->f,
weight);
result->metrics[v].n += weight;
+ if ( ! var_is_value_missing (dependent_vars[v], value, MV_ANY) )
+ result->metrics[v].n_valid += weight;
+
extrema_add (result->metrics[v].maxima,
- case_data (&c, dependent_vars[v])->f,
+ value->f,
weight,
loc);
extrema_add (result->metrics[v].minima,
- case_data (&c, dependent_vars[v])->f,
+ value->f,
weight,
loc);
- casewriter_write (writer, &c);
+ casewriter_write (writer, c);
}
casereader_destroy (input);
result->metrics[v].up_reader = casewriter_make_reader (writer);
for (i = 0 ; i < metric->n_ptiles; ++i)
{
metric->ptl[i] = (struct percentile *)
- percentile_create (percentile_list.data[i] / 100.0, metric->n);
+ percentile_create (percentile_list.data[i] / 100.0, metric->n_valid);
if ( percentile_list.data[i] == 25)
metric->quartiles[0] = metric->ptl[i];
metric->quartiles[2] = metric->ptl[i];
}
- metric->tukey_hinges = tukey_hinges_create (metric->n, metric->cmin);
- metric->trimmed_mean = trimmed_mean_create (metric->n, 0.05);
+ metric->tukey_hinges = tukey_hinges_create (metric->n_valid, metric->cmin);
+ metric->trimmed_mean = trimmed_mean_create (metric->n_valid, 0.05);
n_os = metric->n_ptiles + 2;
/* FIXME: Do this in the above loop */
if ( cmd->a_plot[XMN_PLT_HISTOGRAM] )
{
- struct ccase c;
+ struct ccase *c;
struct casereader *input = casereader_clone (reader);
for (v = 0; v < n_dependent_vars; ++v)
metric->histogram = histogram_create (10, min->value, max->value);
}
- while (casereader_read (input, &c))
+ while ((c = casereader_read (input)) != NULL)
{
- const double weight = wv ? case_data (&c, wv)->f : 1.0;
+ const double weight = wv ? case_data (c, wv)->f : 1.0;
for (v = 0; v < n_dependent_vars; ++v)
{
struct factor_metrics *metric = &result->metrics[v];
if ( metric->histogram)
histogram_add ((struct histogram *) metric->histogram,
- case_data (&c, dependent_vars[v])->f, weight);
+ case_data (c, dependent_vars[v])->f, weight);
}
- case_destroy (&c);
+ case_unref (c);
}
casereader_destroy (input);
}
{
struct ll *ll;
const struct dictionary *dict = dataset_dict (ds);
- struct ccase c;
+ struct ccase *c;
struct casereader *level0 = casereader_clone (input);
- if (!casereader_peek (input, 0, &c))
+ c = casereader_peek (input, 0);
+ if (c == NULL)
{
casereader_destroy (input);
return;
}
- output_split_file_values (ds, &c);
- case_destroy (&c);
+ output_split_file_values (ds, c);
+ case_unref (c);
ll_init (&level0_factor.result_list);
struct casereader *group = NULL;
struct casereader *level1;
struct casegrouper *grouper1 = NULL;
- struct case_ordering *ordering1 = case_ordering_create ();
- case_ordering_add_var (ordering1, factor->indep_var[0], SRT_ASCEND);
level1 = casereader_clone (input);
-
- level1 = sort_execute (level1,
- case_ordering_clone (ordering1));
- grouper1 = casegrouper_create_case_ordering (level1, ordering1);
- case_ordering_destroy (ordering1);
+ level1 = sort_execute_1var (level1, factor->indep_var[0]);
+ grouper1 = casegrouper_create_vars (level1, &factor->indep_var[0], 1);
while (casegrouper_get_next_group (grouper1, &group))
{
int n_groups = 0;
struct casereader *group2 = NULL;
struct casegrouper *grouper2 = NULL;
- struct case_ordering *ordering2 = case_ordering_create ();
- case_ordering_add_var (ordering2,
- factor->indep_var[1], SRT_ASCEND);
- group_copy = sort_execute (group_copy,
- case_ordering_clone (ordering2));
- grouper2 =
- casegrouper_create_case_ordering (group_copy, ordering2);
+ group_copy = sort_execute_1var (group_copy,
+ factor->indep_var[1]);
- case_ordering_destroy (ordering2);
+ grouper2 = casegrouper_create_vars (group_copy,
+ &factor->indep_var[1], 1);
while (casegrouper_get_next_group (grouper2, &group2))
{
casereader_destroy (input);
- output_examine ();
+ output_examine (dict);
factor_destroy (&level0_factor);
static void
show_summary (const struct variable **dependent_var, int n_dep_var,
+ const struct dictionary *dict,
const struct xfactor *fctr)
{
+ const struct variable *wv = dict_get_weight (dict);
+ const struct fmt_spec *wfmt = wv ? var_get_print_format (wv) : & F_8_0;
+
static const char *subtitle[]=
{
N_("Valid"),
tbl = tab_create (n_cols, n_rows, 0);
tab_headers (tbl, heading_columns, 0, heading_rows, 0);
- tab_dim (tbl, tab_natural_dimensions);
+ tab_dim (tbl, tab_natural_dimensions, NULL);
/* Outline the box */
tab_box (tbl,
{
if ( last_value == NULL ||
- compare_values (last_value, result->value[0],
- fctr->indep_var[0]))
+ compare_values_short (last_value, result->value[0],
+ fctr->indep_var[0]))
{
struct string str;
result->metrics[v].se_mean = sqrt (result->metrics[v].variance / n) ;
/* Total Valid */
- tab_float (tbl, heading_columns,
+ tab_double (tbl, heading_columns,
heading_rows + j + v * ll_count (&fctr->result_list),
TAB_LEFT,
- n, 8, 0);
+ n, wfmt);
tab_text (tbl, heading_columns + 1,
heading_rows + j + v * ll_count (&fctr->result_list),
"%g%%", n * 100.0 / result->metrics[v].n);
/* Total Missing */
- tab_float (tbl, heading_columns + 2,
+ tab_double (tbl, heading_columns + 2,
heading_rows + j + v * ll_count (&fctr->result_list),
TAB_LEFT,
result->metrics[v].n - n,
- 8, 0);
+ wfmt);
tab_text (tbl, heading_columns + 3,
heading_rows + j + v * ll_count (&fctr->result_list),
);
/* Total Valid + Missing */
- tab_float (tbl, heading_columns + 4,
+ tab_double (tbl, heading_columns + 4,
heading_rows + j + v * ll_count (&fctr->result_list),
TAB_LEFT,
result->metrics[v].n,
- 8, 0);
+ wfmt);
tab_text (tbl, heading_columns + 5,
heading_rows + j + v * ll_count (&fctr->result_list),
tbl = tab_create (n_cols, n_rows, 0);
tab_headers (tbl, heading_columns, 0, heading_rows, 0);
- tab_dim (tbl, tab_natural_dimensions);
+ tab_dim (tbl, tab_natural_dimensions, NULL);
/* Outline the box */
tab_box (tbl,
/* Now the statistics ... */
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].mean,
- 8, 2);
+ NULL);
- tab_float (tbl, n_cols - 1,
+ tab_double (tbl, n_cols - 1,
heading_rows + row_var_start + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].se_mean,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 1 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].mean - t *
result->metrics[v].se_mean,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 2 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].mean + t *
result->metrics[v].se_mean,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 3 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
trimmed_mean_calculate ((struct trimmed_mean *) result->metrics[v].trimmed_mean),
- 8, 2);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 4 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
percentile_calculate (result->metrics[v].quartiles[1], percentile_algorithm),
- 8, 2);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 5 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].variance,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 6 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
sqrt (result->metrics[v].variance),
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 10 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
percentile_calculate (result->metrics[v].quartiles[2],
percentile_algorithm) -
percentile_calculate (result->metrics[v].quartiles[0],
percentile_algorithm),
- 8, 2);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 11 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].skewness,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 12 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
result->metrics[v].kurtosis,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 1,
+ tab_double (tbl, n_cols - 1,
heading_rows + row_var_start + 11 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
calc_seskew (result->metrics[v].n),
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 1,
+ tab_double (tbl, n_cols - 1,
heading_rows + row_var_start + 12 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
calc_sekurt (result->metrics[v].n),
- 8, 3);
+ NULL);
{
struct extremum *minimum, *maximum ;
maximum = ll_data (max_ll, struct extremum, ll);
minimum = ll_data (min_ll, struct extremum, ll);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 7 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
minimum->value,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 8 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
maximum->value,
- 8, 3);
+ NULL);
- tab_float (tbl, n_cols - 2,
+ tab_double (tbl, n_cols - 2,
heading_rows + row_var_start + 9 + i * DESCRIPTIVE_ROWS,
TAB_CENTER,
maximum->value - minimum->value,
- 8, 3);
+ NULL);
}
}
}
tbl = tab_create (n_cols, n_rows, 0);
tab_headers (tbl, heading_columns, 0, heading_rows, 0);
- tab_dim (tbl, tab_natural_dimensions);
+ tab_dim (tbl, tab_natural_dimensions, NULL);
/* Outline the box */
tab_box (tbl,
while (weight-- > 0 && e < cmd.st_n)
{
- tab_float (tbl, n_cols - 1,
+ tab_double (tbl, n_cols - 1,
heading_rows + row_var_start + row_result_start + cmd.st_n + e,
TAB_RIGHT,
minimum->value,
- 8, 2);
+ NULL);
- tab_float (tbl, n_cols - 2,
- heading_rows + row_var_start + row_result_start + cmd.st_n + e,
+ tab_fixed (tbl, n_cols - 2,
+ heading_rows + row_var_start +
+ row_result_start + cmd.st_n + e,
TAB_RIGHT,
minimum->location,
- 8, 0);
+ 10, 0);
++e;
}
while (weight-- > 0 && e < cmd.st_n)
{
- tab_float (tbl, n_cols - 1,
- heading_rows + row_var_start + row_result_start + e,
+ tab_double (tbl, n_cols - 1,
+ heading_rows + row_var_start +
+ row_result_start + e,
TAB_RIGHT,
maximum->value,
- 8, 2);
+ NULL);
- tab_float (tbl, n_cols - 2,
- heading_rows + row_var_start + row_result_start + e,
+ tab_fixed (tbl, n_cols - 2,
+ heading_rows + row_var_start +
+ row_result_start + e,
TAB_RIGHT,
maximum->location,
- 8, 0);
+ 10, 0);
++e;
}
tbl = tab_create (n_cols, n_rows, 0);
tab_headers (tbl, heading_columns, 0, heading_rows, 0);
- tab_dim (tbl, tab_natural_dimensions);
+ tab_dim (tbl, tab_natural_dimensions, NULL);
/* Outline the box */
tab_box (tbl,
for (j = 0; j < n_percentiles; ++j)
{
double hinge = SYSMIS;
- tab_float (tbl, n_cols - n_percentiles + j,
+ tab_double (tbl, n_cols - n_percentiles + j,
heading_rows + row_var_start + i * PERCENTILE_ROWS,
TAB_CENTER,
percentile_calculate (result->metrics[v].ptl[j],
percentile_algorithm),
- 8, 2
+ NULL
);
if ( result->metrics[v].ptl[j]->ptile == 0.5)
hinge = hinges[2];
if ( hinge != SYSMIS)
- tab_float (tbl, n_cols - n_percentiles + j,
+ tab_double (tbl, n_cols - n_percentiles + j,
heading_rows + row_var_start + 1 + i * PERCENTILE_ROWS,
TAB_CENTER,
hinge,
- 8, 2
+ NULL
);
}
projects / pspp-builds.git / blobdiff