static struct cmd_regression cmd;
/* Linear regression models. */
-pspp_linreg_cache **models = NULL;
+static pspp_linreg_cache **models = NULL;
/*
Transformations for saving predicted values
File where the model will be saved if the EXPORT subcommand
is given.
*/
-struct file_handle *model_file;
+static struct file_handle *model_file;
/*
Return value for the procedure.
*/
-int pspp_reg_rc = CMD_SUCCESS;
+static int pspp_reg_rc = CMD_SUCCESS;
static bool run_regression (const struct ccase *,
- const struct casefile *, void *);
+ const struct casefile *, void *,
+ const struct dataset *);
/*
STATISTICS subcommand output functions.
label = var_to_string (v);
/* Do not overwrite the variable's name. */
strncpy (tmp, label, MAX_STRING);
- if (v->type == ALPHA)
+ if (var_is_alpha (v))
{
/*
Append the value associated with this coefficient.
Gets the predicted values.
*/
static int
-regression_trns_pred_proc (void *t_, struct ccase *c,
- casenum_t case_idx UNUSED)
+regression_trns_pred_proc (void *t_, struct ccase *c,
+ casenumber case_idx UNUSED)
{
size_t i;
size_t n_vals;
Gets the residuals.
*/
static int
-regression_trns_resid_proc (void *t_, struct ccase *c,
- casenum_t case_idx UNUSED)
+regression_trns_resid_proc (void *t_, struct ccase *c,
+ casenumber case_idx UNUSED)
{
size_t i;
size_t n_vals;
}
/*
- Returns 0 if NAME is a duplicate of any existing variable name.
+ Returns false if NAME is a duplicate of any existing variable name.
*/
-static int
-try_name (char *name)
+static bool
+try_name (const struct dictionary *dict, const char *name)
{
- if (dict_lookup_var (default_dict, name) != NULL)
- return 0;
+ if (dict_lookup_var (dict, name) != NULL)
+ return false;
- return 1;
+ return true;
}
+
static void
-reg_get_name (char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN])
+reg_get_name (const struct dictionary *dict, char name[LONG_NAME_LEN], const char prefix[LONG_NAME_LEN])
{
int i = 1;
snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i);
- while (!try_name (name))
+ while (!try_name (dict, name))
{
i++;
snprintf (name, LONG_NAME_LEN, "%s%d", prefix, i);
}
}
+
static void
-reg_save_var (const char *prefix, trns_proc_func * f,
+reg_save_var (struct dataset *ds, const char *prefix, trns_proc_func * f,
pspp_linreg_cache * c, struct variable **v, int n_trns)
{
+ struct dictionary *dict = dataset_dict (ds);
static int trns_index = 1;
char name[LONG_NAME_LEN];
struct variable *new_var;
t->trns_id = trns_index;
t->n_trns = n_trns;
t->c = c;
- reg_get_name (name, prefix);
- new_var = dict_create_var (default_dict, name, 0);
+ reg_get_name (dict, name, prefix);
+ new_var = dict_create_var (dict, name, 0);
assert (new_var != NULL);
*v = new_var;
- add_transformation (f, regression_trns_free, t);
+ add_transformation (ds, f, regression_trns_free, t);
trns_index++;
}
+
static void
-subcommand_save (int save, pspp_linreg_cache ** models)
+subcommand_save (struct dataset *ds, int save, pspp_linreg_cache ** models)
{
pspp_linreg_cache **lc;
int n_trns = 0;
assert ((*lc)->depvar != NULL);
if (cmd.a_save[REGRESSION_SV_RESID])
{
- reg_save_var ("RES", regression_trns_resid_proc, *lc,
+ reg_save_var (ds, "RES", regression_trns_resid_proc, *lc,
&(*lc)->resid, n_trns);
}
if (cmd.a_save[REGRESSION_SV_PRED])
{
- reg_save_var ("PRED", regression_trns_pred_proc, *lc,
+ reg_save_var (ds, "PRED", regression_trns_pred_proc, *lc,
&(*lc)->pred, n_trns);
}
}
}
}
}
+
static int
reg_inserted (const struct variable *v, struct variable **varlist, int n_vars)
{
}
return 0;
}
+
static void
reg_print_categorical_encoding (FILE * fp, pspp_linreg_cache * c)
{
{
coeff = c->coeff[i];
v = pspp_coeff_get_var (coeff, 0);
- if (v->type == ALPHA)
+ if (var_is_alpha (v))
{
if (!reg_inserted (v, varlist, n_vars))
{
fprintf (fp, "struct pspp_reg_categorical_variable %s;\n\t",
- v->name);
+ var_get_name (v));
varlist[n_vars] = (struct variable *) v;
n_vars++;
}
n_vars);
for (i = 0; i < n_vars - 1; i++)
{
- fprintf (fp, "&%s,\n\t\t", varlist[i]->name);
+ fprintf (fp, "&%s,\n\t\t", var_get_name (varlist[i]));
}
- fprintf (fp, "&%s};\n\t", varlist[i]->name);
+ fprintf (fp, "&%s};\n\t", var_get_name (varlist[i]));
for (i = 0; i < n_vars; i++)
{
coeff = c->coeff[i];
- fprintf (fp, "%s.name = \"%s\";\n\t", varlist[i]->name,
- varlist[i]->name);
- fprintf (fp, "%s.n_vals = %d;\n\t", varlist[i]->name,
+ fprintf (fp, "%s.name = \"%s\";\n\t",
+ var_get_name (varlist[i]),
+ var_get_name (varlist[i]));
+ fprintf (fp, "%s.n_vals = %d;\n\t",
+ var_get_name (varlist[i]),
varlist[i]->obs_vals->n_categories);
for (j = 0; j < varlist[i]->obs_vals->n_categories; j++)
{
val = cat_subscript_to_value ((const size_t) j, varlist[i]);
- fprintf (fp, "%s.values[%d] = \"%s\";\n\t", varlist[i]->name, j,
+ fprintf (fp, "%s.values[%d] = \"%s\";\n\t",
+ var_get_name (varlist[i]), j,
value_to_string (val, varlist[i]));
}
}
{
coeff = c->coeff[i];
v = pspp_coeff_get_var (coeff, 0);
- fprintf (fp, "\"%s\",\n\t\t", v->name);
+ fprintf (fp, "\"%s\",\n\t\t", var_get_name (v));
}
coeff = c->coeff[i];
v = pspp_coeff_get_var (coeff, 0);
- fprintf (fp, "\"%s\"};\n\t", v->name);
+ fprintf (fp, "\"%s\"};\n\t", var_get_name (v));
}
static void
reg_print_getvar (FILE * fp, pspp_linreg_cache * c)
for (i = 1; i < c->n_coeffs; i++)
{
v = pspp_coeff_get_var (c->coeff[i], 0);
- if (v->type == ALPHA)
- {
- return 1;
- }
+ if (var_is_alpha (v))
+ return 1;
}
return 0;
}
size_t i;
size_t j;
int n_quantiles = 100;
- double increment;
double tmp;
struct pspp_coeff *coeff;
reg_print_categorical_encoding (fp, c);
}
fprintf (fp, "%s", reg_export_t_quantiles_1);
- increment = 0.5 / (double) increment;
for (i = 0; i < n_quantiles - 1; i++)
{
tmp = 0.5 + 0.005 * (double) i;
fclose (fp);
}
}
+
static int
-regression_custom_export (struct cmd_regression *cmd UNUSED, void *aux UNUSED)
+regression_custom_export (struct lexer *lexer, struct dataset *ds UNUSED, struct cmd_regression *cmd UNUSED, void *aux UNUSED)
{
/* 0 on failure, 1 on success, 2 on failure that should result in syntax error */
- if (!lex_force_match ('('))
+ if (!lex_force_match (lexer, '('))
return 0;
- if (lex_match ('*'))
+ if (lex_match (lexer, '*'))
model_file = NULL;
else
{
- model_file = fh_parse (FH_REF_FILE);
+ model_file = fh_parse (lexer, FH_REF_FILE);
if (model_file == NULL)
return 0;
}
- if (!lex_force_match (')'))
+ if (!lex_force_match (lexer, ')'))
return 0;
return 1;
}
int
-cmd_regression (void)
+cmd_regression (struct lexer *lexer, struct dataset *ds)
{
- if (!parse_regression (&cmd, NULL))
+ if (!parse_regression (lexer, ds, &cmd, NULL))
return CMD_FAILURE;
models = xnmalloc (cmd.n_dependent, sizeof *models);
- if (!multipass_procedure_with_splits (run_regression, &cmd))
+ if (!multipass_procedure_with_splits (ds, run_regression, &cmd))
return CMD_CASCADING_FAILURE;
- subcommand_save (cmd.sbc_save, models);
+ subcommand_save (ds, cmd.sbc_save, models);
free (v_variables);
free (models);
return pspp_reg_rc;
size_t row;
const union value *val;
- for (r = casefile_get_reader (cf);
+ for (r = casefile_get_reader (cf, NULL);
casereader_read (r, &c); case_destroy (&c))
{
row = casereader_cnum (r) - 1;
val = case_data (&c, v->fv);
cat_value_update (v, val);
- if (mv_is_value_missing (&v->miss, val))
+ if (var_is_value_missing (v, val))
{
if (!is_missing_case[row])
{
/* Parser for the variables sub command */
static int
-regression_custom_variables (struct cmd_regression *cmd UNUSED,
- void *aux UNUSED)
+regression_custom_variables (struct lexer *lexer, struct dataset *ds,
+ struct cmd_regression *cmd UNUSED,
+ void *aux UNUSED)
{
+ const struct dictionary *dict = dataset_dict (ds);
- lex_match ('=');
+ lex_match (lexer, '=');
- if ((token != T_ID || dict_lookup_var (default_dict, tokid) == NULL)
- && token != T_ALL)
+ if ((lex_token (lexer) != T_ID || dict_lookup_var (dict, lex_tokid (lexer)) == NULL)
+ && lex_token (lexer) != T_ALL)
return 2;
- if (!parse_variables (default_dict, &v_variables, &n_variables, PV_NONE))
+ if (!parse_variables (lexer, dict, &v_variables, &n_variables, PV_NONE))
{
free (v_variables);
return 0;
{
indep_vars[j] = v_variables[i];
j++;
- if (v_variables[i]->type == ALPHA)
+ if (var_is_alpha (v_variables[i]))
{
/* Make a place to hold the binary vectors
corresponding to this variable's values. */
return n_data;
}
static void
-coeff_init (pspp_linreg_cache *c, struct design_matrix *dm)
+coeff_init (pspp_linreg_cache * c, struct design_matrix *dm)
{
c->coeff = xnmalloc (dm->m->size2 + 1, sizeof (*c->coeff));
- c->coeff[0] = xmalloc (sizeof (*(c->coeff[0]))); /* The first coefficient is the intercept. */
+ c->coeff[0] = xmalloc (sizeof (*(c->coeff[0]))); /* The first coefficient is the intercept. */
c->coeff[0]->v_info = NULL; /* Intercept has no associated variable. */
pspp_coeff_init (c->coeff + 1, dm);
}
+
static bool
run_regression (const struct ccase *first,
- const struct casefile *cf, void *cmd_ UNUSED)
+ const struct casefile *cf, void *cmd_ UNUSED, const struct dataset *ds)
{
size_t i;
size_t n_data = 0; /* Number of valide cases. */
assert (models != NULL);
- output_split_file_values (first);
+ output_split_file_values (ds, first);
if (!v_variables)
{
- dict_get_vars (default_dict, &v_variables, &n_variables,
+ dict_get_vars (dataset_dict (ds), &v_variables, &n_variables,
1u << DC_SYSTEM);
}
for (i = 0; i < cmd.n_dependent; i++)
{
- if (cmd.v_dependent[i]->type != NUMERIC)
+ if (!var_is_numeric (cmd.v_dependent[i]))
{
msg (SE, gettext ("Dependent variable must be numeric."));
pspp_reg_rc = CMD_FAILURE;
The second pass fills the design matrix.
*/
row = 0;
- for (r = casefile_get_reader (cf); casereader_read (r, &c);
+ for (r = casefile_get_reader (cf, NULL); casereader_read (r, &c);
case_destroy (&c))
/* Iterate over the cases. */
{
*/
if (!is_depvar (i, cmd.v_dependent[k]))
{
- if (v_variables[i]->type == ALPHA)
+ if (var_is_alpha (v_variables[i]))
{
design_matrix_set_categorical (X, row,
v_variables[i], val);
}
- else if (v_variables[i]->type == NUMERIC)
+ else
{
design_matrix_set_numeric (X, row, v_variables[i],
val);
coefficients.
*/
coeff_init (models[k], X);
-
+
/*
Find the least-squares estimates and other statistics.
*/
projects / pspp-builds.git / blobdiff