#define REG_LARGE_DATA 1000
+#define STATS_R 1
+#define STATS_COEFF 2
+#define STATS_ANOVA 4
+#define STATS_OUTS 8
+#define STATS_CI 16
+#define STATS_BCOV 32
+
+#define STATS_DEFAULT (STATS_R | STATS_COEFF | STATS_ANOVA | STATS_OUTS)
+
+
+
struct regression
{
struct dataset *ds;
const struct variable **dep_vars;
size_t n_dep_vars;
- bool r;
- bool coeff;
- bool anova;
- bool bcov;
-
+ unsigned int stats;
bool resid;
bool pred;
};
-struct per_split_ws
-{
- linreg **models;
-};
-
struct regression_workspace
{
- struct per_split_ws *psw;
+ /* The new variables which will be introduced by /SAVE */
+ const struct variable **predvars;
+ const struct variable **residvars;
+ /* A reader/writer pair to temporarily hold the
+ values of the new variables */
struct casewriter *writer;
struct casereader *reader;
+ /* Indeces of the new values in the reader/writer (-1 if not applicable) */
int res_idx;
int pred_idx;
- int extras;
- const struct variable **predvars;
- const struct variable **residvars;
+ /* 0, 1 or 2 depending on what new variables are to be created */
+ int extras;
};
static void run_regression (const struct regression *cmd,
- struct per_split_ws *psw,
struct regression_workspace *ws,
struct casereader *input);
-
+/* Return a string based on PREFIX which may be used as the name
+ of a new variable in DICT */
static char *
reg_get_name (const struct dictionary *dict, const char *prefix)
{
return var;
}
-struct thing
+/* Auxilliary data for transformation when /SAVE is entered */
+struct save_trans_data
{
int n_dep_vars;
struct regression_workspace *ws;
};
+static bool
+save_trans_free (void *aux)
+{
+ struct save_trans_data *save_trans_data = aux;
+ free (save_trans_data->ws->predvars);
+ free (save_trans_data->ws->residvars);
+
+ casereader_destroy (save_trans_data->ws->reader);
+ free (save_trans_data->ws);
+ free (save_trans_data);
+ return true;
+}
+
static int
-transX (void *aux, struct ccase **c, casenumber x UNUSED)
+save_trans_func (void *aux, struct ccase **c, casenumber x UNUSED)
{
- struct thing *thing = aux;
- struct regression_workspace *ws = thing->ws;
- const struct ccase *in = casereader_read (ws->reader);
+ struct save_trans_data *save_trans_data = aux;
+ struct regression_workspace *ws = save_trans_data->ws;
+ struct ccase *in = casereader_read (ws->reader);
if (in)
{
int k;
*c = case_unshare (*c);
- for (k = 0; k < thing->n_dep_vars; ++k)
+ for (k = 0; k < save_trans_data->n_dep_vars; ++k)
{
if (ws->pred_idx != -1)
{
case_data_rw (*c, ws->residvars[k])->f = resid;
}
}
+ case_unref (in);
}
return TRNS_CONTINUE;
int
cmd_regression (struct lexer *lexer, struct dataset *ds)
{
- int n_splits = 0;
struct regression_workspace workspace;
struct regression regression;
const struct dictionary *dict = dataset_dict (ds);
bool save;
- workspace.psw = NULL;
memset (®ression, 0, sizeof (struct regression));
- regression.anova = true;
- regression.coeff = true;
- regression.r = true;
-
+ regression.stats = STATS_DEFAULT;
regression.pred = false;
regression.resid = false;
if (!lex_force_match (lexer, T_EQUALS))
goto error;
+ free (regression.dep_vars);
+ regression.n_dep_vars = 0;
+
if (!parse_variables_const (lexer, dict,
®ression.dep_vars,
®ression.n_dep_vars,
{
if (lex_match (lexer, T_ALL))
{
+ regression.stats = ~0;
}
else if (lex_match_id (lexer, "DEFAULTS"))
{
+ regression.stats |= STATS_DEFAULT;
}
else if (lex_match_id (lexer, "R"))
{
+ regression.stats |= STATS_R;
}
else if (lex_match_id (lexer, "COEFF"))
{
+ regression.stats |= STATS_COEFF;
}
else if (lex_match_id (lexer, "ANOVA"))
{
+ regression.stats |= STATS_ANOVA;
}
else if (lex_match_id (lexer, "BCOV"))
{
+ regression.stats |= STATS_BCOV;
+ }
+ else if (lex_match_id (lexer, "CI"))
+ {
+ regression.stats |= STATS_CI;
+
+ if (lex_match (lexer, T_LPAREN))
+ {
+ lex_number (lexer);
+ lex_get (lexer);
+ lex_force_match (lexer, T_RPAREN);
+ }
}
else
{
"Temporary transformations will be made permanent."));
workspace.writer = autopaging_writer_create (proto);
+ caseproto_unref (proto);
}
- n_splits = 0;
{
struct casegrouper *grouper;
struct casereader *group;
while (casegrouper_get_next_group (grouper, &group))
{
- workspace.psw = xrealloc (workspace.psw, ++n_splits * sizeof (*workspace.psw));
-
- run_regression (®ression, &workspace.psw[n_splits - 1],
+ run_regression (®ression,
&workspace,
group);
ok = proc_commit (ds) && ok;
}
+ if (workspace.writer)
{
- if (workspace.writer)
- {
- struct thing *thing = xmalloc (sizeof *thing);
- struct casereader *r = casewriter_make_reader (workspace.writer);
- workspace.writer = NULL;
- workspace.reader = r;
- thing->ws = xmalloc (sizeof (workspace));
- memcpy (thing->ws, &workspace, sizeof (workspace));
- thing->n_dep_vars = regression.n_dep_vars;
+ struct save_trans_data *save_trans_data = xmalloc (sizeof *save_trans_data);
+ struct casereader *r = casewriter_make_reader (workspace.writer);
+ workspace.writer = NULL;
+ workspace.reader = r;
+ save_trans_data->ws = xmalloc (sizeof (workspace));
+ memcpy (save_trans_data->ws, &workspace, sizeof (workspace));
+ save_trans_data->n_dep_vars = regression.n_dep_vars;
- add_transformation (ds, transX, NULL, thing);
- }
+ add_transformation (ds, save_trans_func, save_trans_free, save_trans_data);
}
return CMD_FAILURE;
}
-
+/* Return the size of the union of dependent and independent variables */
static size_t
get_n_all_vars (const struct regression *cmd)
{
return result;
}
+/* Fill VARS with the union of dependent and independent variables */
static void
fill_all_vars (const struct variable **vars, const struct regression *cmd)
{
+ size_t x = 0;
size_t i;
- size_t j;
- bool absent;
-
for (i = 0; i < cmd->n_vars; i++)
{
vars[i] = cmd->vars[i];
}
+
for (i = 0; i < cmd->n_dep_vars; i++)
{
- absent = true;
+ size_t j;
+ bool absent = true;
for (j = 0; j < cmd->n_vars; j++)
{
if (cmd->dep_vars[i] == cmd->vars[j])
}
if (absent)
{
- vars[i + cmd->n_vars] = cmd->dep_vars[i];
+ vars[cmd->n_vars + x++] = cmd->dep_vars[i];
}
}
}
*/
msg (SW,
gettext
- ("The dependent variable is equal to the independent variable."
- "The least squares line is therefore Y=X."
+ ("The dependent variable is equal to the independent variable. "
+ "The least squares line is therefore Y=X. "
"Standard errors and related statistics may be meaningless."));
n_indep_vars = 1;
indep_vars[0] = cmd->vars[0];
const gsl_matrix *ssize_matrix;
double result = 0.0;
- gsl_matrix *cm = covariance_calculate_unnormalized (all_cov);
+ const gsl_matrix *cm = covariance_calculate_unnormalized (all_cov);
if (cm == NULL)
return 0;
gsl_matrix_set (cov, cov->size1 - 1, cov->size1 - 1,
gsl_matrix_get (cm, dep_subscript, dep_subscript));
free (rows);
- gsl_matrix_free (cm);
return result;
}
+\f
/*
STATISTICS subcommand output functions.
*/
-static void reg_stats_r (linreg *, void *, const struct variable *);
-static void reg_stats_coeff (linreg *, void *, const struct variable *);
-static void reg_stats_anova (linreg *, void *, const struct variable *);
-static void reg_stats_bcov (linreg *, void *, const struct variable *);
-
-static void
-statistics_keyword_output (void (*)
- (linreg *, void *, const struct variable *), bool,
- linreg *, void *, const struct variable *);
-
+static void reg_stats_r (const linreg *, const struct variable *);
+static void reg_stats_coeff (const linreg *, const gsl_matrix *, const struct variable *);
+static void reg_stats_anova (const linreg *, const struct variable *);
+static void reg_stats_bcov (const linreg *, const struct variable *);
static void
-subcommand_statistics (const struct regression *cmd, linreg * c, void *aux,
+subcommand_statistics (const struct regression *cmd, const linreg * c, const gsl_matrix * cm,
const struct variable *var)
{
- statistics_keyword_output (reg_stats_r, cmd->r, c, aux, var);
- statistics_keyword_output (reg_stats_anova, cmd->anova, c, aux, var);
- statistics_keyword_output (reg_stats_coeff, cmd->coeff, c, aux, var);
- statistics_keyword_output (reg_stats_bcov, cmd->bcov, c, aux, var);
+ if (cmd->stats & STATS_R)
+ reg_stats_r (c, var);
+
+ if (cmd->stats & STATS_ANOVA)
+ reg_stats_anova (c, var);
+
+ if (cmd->stats & STATS_COEFF)
+ reg_stats_coeff (c, cm, var);
+
+ if (cmd->stats & STATS_BCOV)
+ reg_stats_bcov (c, var);
}
static void
run_regression (const struct regression *cmd,
- struct per_split_ws *psw,
struct regression_workspace *ws,
struct casereader *input)
{
size_t i;
+ linreg **models;
int k;
struct ccase *c;
casereader_destroy (r);
}
- psw->models = xcalloc (cmd->n_dep_vars, sizeof (*psw->models));
+ models = xcalloc (cmd->n_dep_vars, sizeof (*models));
for (k = 0; k < cmd->n_dep_vars; k++)
{
-
const struct variable **vars = xnmalloc (cmd->n_vars, sizeof (*vars));
const struct variable *dep_var = cmd->dep_vars[k];
int n_indep = identify_indep_vars (cmd, vars, dep_var);
gsl_matrix *this_cm = gsl_matrix_alloc (n_indep + 1, n_indep + 1);
double n_data = fill_covariance (this_cm, cov, vars, n_indep,
dep_var, all_vars, n_all_vars, means);
- psw->models[k] = linreg_alloc (dep_var, vars, n_data, n_indep);
- psw->models[k]->depvar = dep_var;
+ models[k] = linreg_alloc (dep_var, vars, n_data, n_indep);
+ models[k]->depvar = dep_var;
for (i = 0; i < n_indep; i++)
{
- linreg_set_indep_variable_mean (psw->models[k], i, means[i]);
+ linreg_set_indep_variable_mean (models[k], i, means[i]);
}
- linreg_set_depvar_mean (psw->models[k], means[i]);
+ linreg_set_depvar_mean (models[k], means[i]);
/*
For large data sets, use QR decomposition.
*/
if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
{
- psw->models[k]->method = LINREG_QR;
+ models[k]->method = LINREG_QR;
}
if (n_data > 0)
/*
Find the least-squares estimates and other statistics.
*/
- linreg_fit (this_cm, psw->models[k]);
+ linreg_fit (this_cm, models[k]);
if (!taint_has_tainted_successor (casereader_get_taint (input)))
{
- subcommand_statistics (cmd, psw->models[k], this_cm, dep_var);
+ subcommand_statistics (cmd, models[k], this_cm, dep_var);
}
}
else
if (cmd->pred)
{
- double pred = linreg_predict (psw->models[k], vals, n_indep);
+ double pred = linreg_predict (models[k], vals, n_indep);
case_data_rw_idx (outc, k * ws->extras + ws->pred_idx)->f = pred;
}
if (cmd->resid)
{
- double obs = case_data (c, psw->models[k]->depvar)->f;
- double res = linreg_residual (psw->models[k], obs, vals, n_indep);
+ double obs = case_data (c, models[k]->depvar)->f;
+ double res = linreg_residual (models[k], obs, vals, n_indep);
case_data_rw_idx (outc, k * ws->extras + ws->res_idx)->f = res;
}
+ free (vals);
+ free (vars);
}
casewriter_write (ws->writer, outc);
}
casereader_destroy (reader);
+ for (k = 0; k < cmd->n_dep_vars; k++)
+ {
+ linreg_unref (models[k]);
+ }
+ free (models);
free (all_vars);
free (means);
casereader_destroy (input);
covariance_destroy (cov);
}
-\f
-
+\f
static void
-reg_stats_r (linreg * c, void *aux UNUSED, const struct variable *var)
+reg_stats_r (const linreg * c, const struct variable *var)
{
struct tab_table *t;
int n_rows = 2;
Table showing estimated regression coefficients.
*/
static void
-reg_stats_coeff (linreg * c, void *aux_, const struct variable *var)
+reg_stats_coeff (const linreg * c, const gsl_matrix *cov, const struct variable *var)
{
size_t j;
int n_cols = 7;
const struct variable *v;
struct tab_table *t;
- gsl_matrix *cov = aux_;
assert (c != NULL);
n_rows = linreg_n_coeffs (c) + 3;
tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Std. Error"));
tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Beta"));
tab_text (t, 5, 0, TAB_CENTER | TAT_TITLE, _("t"));
- tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Significance"));
+ tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Sig."));
tab_text (t, 1, 1, TAB_LEFT | TAT_TITLE, _("(Constant)"));
tab_double (t, 2, 1, 0, linreg_intercept (c), NULL);
std_err = sqrt (gsl_matrix_get (linreg_cov (c), 0, 0));
Display the ANOVA table.
*/
static void
-reg_stats_anova (linreg * c, void *aux UNUSED, const struct variable *var)
+reg_stats_anova (const linreg * c, const struct variable *var)
{
int n_cols = 7;
int n_rows = 4;
tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("df"));
tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Mean Square"));
tab_text (t, 5, 0, TAB_CENTER | TAT_TITLE, _("F"));
- tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Significance"));
+ tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Sig."));
tab_text (t, 1, 1, TAB_LEFT | TAT_TITLE, _("Regression"));
tab_text (t, 1, 2, TAB_LEFT | TAT_TITLE, _("Residual"));
static void
-reg_stats_bcov (linreg * c, void *aux UNUSED, const struct variable *var)
+reg_stats_bcov (const linreg * c, const struct variable *var)
{
int n_cols;
int n_rows;
tab_submit (t);
}
-static void
-statistics_keyword_output (void (*function)
- (linreg *, void *, const struct variable * var),
- bool keyword, linreg * c, void *aux,
- const struct variable *var)
-{
- if (keyword)
- {
- (*function) (c, aux, var);
- }
-}