X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Flogistic.c;h=b3cf843400f6460b077de5b396e2e7c10cada8d1;hb=c91f650b47f33cfbd4b7ed45dbfa7eb012c7e6fb;hp=7171563032e396b37ec2a83df8bf94fd6c15a347;hpb=e26b8dc756df6631193e87250b4ceeec0866d5ec;p=pspp diff --git a/src/language/stats/logistic.c b/src/language/stats/logistic.c index 7171563032..b3cf843400 100644 --- a/src/language/stats/logistic.c +++ b/src/language/stats/logistic.c @@ -135,7 +135,8 @@ struct lr_spec /* What results should be presented */ unsigned int print; - double cut_point; + /* Inverse logit of the cut point */ + double ilogit_cut_point; }; @@ -172,6 +173,10 @@ struct lr_result /* The estimates of the predictor coefficients */ gsl_vector *beta_hat; + + /* The predicted classifications: + True Negative, True Positive, False Negative, False Positive */ + double tn, tp, fn, fp; }; @@ -197,6 +202,7 @@ map_dependent_var (const struct lr_spec *cmd, const struct lr_result *res, const return SYSMIS; } +static void output_classification_table (const struct lr_spec *cmd, const struct lr_result *res); static void output_categories (const struct lr_spec *cmd, const struct lr_result *res); @@ -328,7 +334,9 @@ hessian (const struct lr_spec *cmd, y is the vector of observed independent variables pi is the vector of estimates for y - As a side effect, the likelihood is stored in LIKELIHOOD + Side effects: + the likelihood is stored in LIKELIHOOD; + the predicted values are placed in the respective tn, fn, tp fp values in RES */ static gsl_vector * xt_times_y_pi (const struct lr_spec *cmd, @@ -336,16 +344,18 @@ xt_times_y_pi (const struct lr_spec *cmd, struct casereader *input, const struct variable **x, size_t n_x, const struct variable *y_var, - double *likelihood) + double *llikelihood) { struct casereader *reader; struct ccase *c; gsl_vector *output = gsl_vector_calloc (res->beta_hat->size); - *likelihood = 1.0; + *llikelihood = 0.0; + res->tn = res->tp = res->fn = res->fp = 0; for (reader = casereader_clone (input); (c = casereader_read (reader)) != NULL; case_unref (c)) { + double pred_y = 0; int v0; double pi = pi_hat (cmd, res, x, n_x, c); double weight = dict_get_case_weight (cmd->dict, c, &res->warn_bad_weight); @@ -353,13 +363,31 @@ xt_times_y_pi (const struct lr_spec *cmd, double y = map_dependent_var (cmd, res, case_data (c, y_var)); - *likelihood *= pow (pi, weight * y) * pow (1 - pi, weight * (1 - y)); + *llikelihood += (weight * y) * log (pi) + log (1 - pi) * weight * (1 - y); for (v0 = 0; v0 < res->beta_hat->size; ++v0) { double in0 = predictor_value (c, x, n_x, res->cats, v0); double *o = gsl_vector_ptr (output, v0); *o += in0 * (y - pi) * weight; + pred_y += gsl_vector_get (res->beta_hat, v0) * in0; + } + + /* Count the number of cases which would be correctly/incorrectly classified by this + estimated model */ + if (pred_y <= cmd->ilogit_cut_point) + { + if (y == 0) + res->tn += weight; + else + res->fn += weight; + } + else + { + if (y == 0) + res->fp += weight; + else + res->tp += weight; } } @@ -450,6 +478,11 @@ initial_pass (const struct lr_spec *cmd, struct lr_result *res, struct casereade double weight = dict_get_case_weight (cmd->dict, c, &res->warn_bad_weight); const union value *depval = case_data (c, cmd->dep_var); + if (var_is_value_missing (cmd->dep_var, depval, cmd->exclude)) + { + missing = true; + } + else for (v = 0; v < cmd->n_indep_vars; ++v) { const union value *val = case_data (c, cmd->indep_vars[v]); @@ -550,10 +583,10 @@ run_lr (const struct lr_spec *cmd, struct casereader *input, bool converged = false; - /* Set the likelihoods to a negative sentinel value */ - double likelihood = -1; - double prev_likelihood = -1; - double initial_likelihood = -1; + /* Set the log likelihoods to a sentinel value */ + double log_likelihood = SYSMIS; + double prev_log_likelihood = SYSMIS; + double initial_log_likelihood = SYSMIS; struct lr_result work; work.n_missing = 0; @@ -561,11 +594,12 @@ run_lr (const struct lr_spec *cmd, struct casereader *input, work.warn_bad_weight = true; work.cats = NULL; work.beta_hat = NULL; + work.hessian = NULL; /* Get the initial estimates of \beta and their standard errors. And perform other auxilliary initialisation. */ if (! initial_pass (cmd, &work, input)) - return false; + goto error; for (i = 0; i < cmd->n_cat_predictors; ++i) { @@ -579,7 +613,7 @@ run_lr (const struct lr_spec *cmd, struct casereader *input, msg (ME, _("Category %s does not have at least two distinct values. Logistic regression will not be run."), ds_cstr(&str)); ds_destroy (&str); - return false; + goto error; } } @@ -595,6 +629,12 @@ run_lr (const struct lr_spec *cmd, struct casereader *input, NULL, NULL); + input = casereader_create_filter_missing (input, + &cmd->dep_var, + 1, + cmd->exclude, + NULL, + NULL); work.hessian = gsl_matrix_calloc (work.beta_hat->size, work.beta_hat->size); @@ -615,7 +655,7 @@ run_lr (const struct lr_spec *cmd, struct casereader *input, v = xt_times_y_pi (cmd, &work, input, cmd->predictor_vars, cmd->n_predictor_vars, cmd->dep_var, - &likelihood); + &log_likelihood); { /* delta = M.v */ @@ -638,41 +678,50 @@ run_lr (const struct lr_spec *cmd, struct casereader *input, gsl_vector_free (delta); } - if ( prev_likelihood >= 0) + if (i > 0) { - if (-log (likelihood) > -(1.0 - cmd->lcon) * log (prev_likelihood)) + if (-log_likelihood > -(1.0 - cmd->lcon) * prev_log_likelihood) { msg (MN, _("Estimation terminated at iteration number %d because Log Likelihood decreased by less than %g%%"), i + 1, 100 * cmd->lcon); converged = true; } } if (i == 0) - initial_likelihood = likelihood; - prev_likelihood = likelihood; + initial_log_likelihood = log_likelihood; + prev_log_likelihood = log_likelihood; if (converged) break; } - casereader_destroy (input); - assert (initial_likelihood >= 0); + + if ( ! converged) msg (MW, _("Estimation terminated at iteration number %d because maximum iterations has been reached"), i ); - output_model_summary (&work, initial_likelihood, likelihood); + output_model_summary (&work, initial_log_likelihood, log_likelihood); if (work.cats) output_categories (cmd, &work); + output_classification_table (cmd, &work); output_variables (cmd, &work); + casereader_destroy (input); gsl_matrix_free (work.hessian); gsl_vector_free (work.beta_hat); - categoricals_destroy (work.cats); return true; + + error: + casereader_destroy (input); + gsl_matrix_free (work.hessian); + gsl_vector_free (work.beta_hat); + categoricals_destroy (work.cats); + + return false; } struct variable_node @@ -701,10 +750,12 @@ lookup_variable (const struct hmap *map, const struct variable *var, unsigned in int cmd_logistic (struct lexer *lexer, struct dataset *ds) { + int i; /* Temporary location for the predictor variables. These may or may not include the categorical predictors */ const struct variable **pred_vars; size_t n_pred_vars; + double cp = 0.5; int v, x; struct lr_spec lr; @@ -717,7 +768,6 @@ cmd_logistic (struct lexer *lexer, struct dataset *ds) lr.lcon = 0.0000; lr.bcon = 0.001; lr.min_epsilon = 0.00000001; - lr.cut_point = 0.5; lr.constant = true; lr.confidence = 95; lr.print = PRINT_DEFAULT; @@ -928,6 +978,30 @@ cmd_logistic (struct lexer *lexer, struct dataset *ds) } } } + else if (lex_match_id (lexer, "CUT")) + { + if (lex_force_match (lexer, T_LPAREN)) + { + if (! lex_force_num (lexer)) + { + lex_error (lexer, NULL); + goto error; + } + cp = lex_number (lexer); + + if (cp < 0 || cp > 1.0) + { + msg (ME, _("Cut point value must be in the range [0,1]")); + goto error; + } + lex_get (lexer); + if ( ! lex_force_match (lexer, T_RPAREN)) + { + lex_error (lexer, NULL); + goto error; + } + } + } else { lex_error (lexer, NULL); @@ -942,11 +1016,13 @@ cmd_logistic (struct lexer *lexer, struct dataset *ds) } } + lr.ilogit_cut_point = - log (1/cp - 1); + + /* Copy the predictor variables from the temporary location into the final one, dropping any categorical variables which appear there. FIXME: This is O(NxM). */ - { struct variable_node *vn, *next; struct hmap allvars; @@ -1026,6 +1102,10 @@ cmd_logistic (struct lexer *lexer, struct dataset *ds) ok = proc_commit (ds) && ok; } + for (i = 0 ; i < lr.n_cat_predictors; ++i) + { + interaction_destroy (lr.cat_predictors[i]); + } free (lr.predictor_vars); free (lr.cat_predictors); free (lr.indep_vars); @@ -1034,6 +1114,10 @@ cmd_logistic (struct lexer *lexer, struct dataset *ds) error: + for (i = 0 ; i < lr.n_cat_predictors; ++i) + { + interaction_destroy (lr.cat_predictors[i]); + } free (lr.predictor_vars); free (lr.cat_predictors); free (lr.indep_vars); @@ -1234,10 +1318,14 @@ output_variables (const struct lr_spec *cmd, if (cmd->print & PRINT_CI) { + int last_ci = nr; double wc = gsl_cdf_ugaussian_Pinv (0.5 + cmd->confidence / 200.0); wc *= sqrt (sigma2); - if (idx < cmd->n_predictor_vars) + if (cmd->constant) + last_ci--; + + if (row < last_ci) { tab_double (t, 8, row, 0, exp (b - wc), 0); tab_double (t, 9, row, 0, exp (b + wc), 0); @@ -1252,7 +1340,7 @@ output_variables (const struct lr_spec *cmd, /* Show the model summary box */ static void output_model_summary (const struct lr_result *res, - double initial_likelihood, double likelihood) + double initial_log_likelihood, double log_likelihood) { const int heading_columns = 0; const int heading_rows = 1; @@ -1274,15 +1362,15 @@ output_model_summary (const struct lr_result *res, tab_text (t, 0, 0, TAB_LEFT | TAT_TITLE, _("Step 1")); tab_text (t, 1, 0, TAB_CENTER | TAT_TITLE, _("-2 Log likelihood")); - tab_double (t, 1, 1, 0, -2 * log (likelihood), 0); + tab_double (t, 1, 1, 0, -2 * log_likelihood, 0); tab_text (t, 2, 0, TAB_CENTER | TAT_TITLE, _("Cox & Snell R Square")); - cox = 1.0 - pow (initial_likelihood /likelihood, 2 / res->cc); + cox = 1.0 - exp((initial_log_likelihood - log_likelihood) * (2 / res->cc)); tab_double (t, 2, 1, 0, cox, 0); tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Nagelkerke R Square")); - tab_double (t, 3, 1, 0, cox / ( 1.0 - pow (initial_likelihood, 2 / res->cc)), 0); + tab_double (t, 3, 1, 0, cox / ( 1.0 - exp(initial_log_likelihood * (2 / res->cc))), 0); tab_submit (t); @@ -1436,3 +1524,86 @@ output_categories (const struct lr_spec *cmd, const struct lr_result *res) tab_submit (t); } + + +static void +output_classification_table (const struct lr_spec *cmd, const struct lr_result *res) +{ + const struct fmt_spec *wfmt = + cmd->wv ? var_get_print_format (cmd->wv) : &F_8_0; + + const int heading_columns = 3; + const int heading_rows = 3; + + struct string sv0, sv1; + + const int nc = heading_columns + 3; + const int nr = heading_rows + 3; + + struct tab_table *t = tab_create (nc, nr); + + ds_init_empty (&sv0); + ds_init_empty (&sv1); + + tab_title (t, _("Classification Table")); + + tab_headers (t, heading_columns, 0, heading_rows, 0); + + tab_box (t, TAL_2, TAL_2, -1, -1, 0, 0, nc - 1, nr - 1); + tab_box (t, -1, -1, -1, TAL_1, heading_columns, 0, nc - 1, nr - 1); + + tab_hline (t, TAL_2, 0, nc - 1, heading_rows); + tab_vline (t, TAL_2, heading_columns, 0, nr - 1); + + tab_text (t, 0, heading_rows, TAB_CENTER | TAT_TITLE, _("Step 1")); + + + tab_joint_text (t, heading_columns, 0, nc - 1, 0, + TAB_CENTER | TAT_TITLE, _("Predicted")); + + tab_joint_text (t, heading_columns, 1, heading_columns + 1, 1, + 0, var_to_string (cmd->dep_var) ); + + tab_joint_text (t, 1, 2, 2, 2, + TAB_LEFT | TAT_TITLE, _("Observed")); + + tab_text (t, 1, 3, TAB_LEFT, var_to_string (cmd->dep_var) ); + + + tab_joint_text (t, nc - 1, 1, nc - 1, 2, + TAB_CENTER | TAT_TITLE, _("Percentage\nCorrect")); + + + tab_joint_text (t, 1, nr - 1, 2, nr - 1, + TAB_LEFT | TAT_TITLE, _("Overall Percentage")); + + + tab_hline (t, TAL_1, 1, nc - 1, nr - 1); + + var_append_value_name (cmd->dep_var, &res->y0, &sv0); + var_append_value_name (cmd->dep_var, &res->y1, &sv1); + + tab_text (t, 2, heading_rows, TAB_LEFT, ds_cstr (&sv0)); + tab_text (t, 2, heading_rows + 1, TAB_LEFT, ds_cstr (&sv1)); + + tab_text (t, heading_columns, 2, 0, ds_cstr (&sv0)); + tab_text (t, heading_columns + 1, 2, 0, ds_cstr (&sv1)); + + ds_destroy (&sv0); + ds_destroy (&sv1); + + tab_double (t, heading_columns, 3, 0, res->tn, wfmt); + tab_double (t, heading_columns + 1, 4, 0, res->tp, wfmt); + + tab_double (t, heading_columns + 1, 3, 0, res->fp, wfmt); + tab_double (t, heading_columns, 4, 0, res->fn, wfmt); + + tab_double (t, heading_columns + 2, 3, 0, 100 * res->tn / (res->tn + res->fp), 0); + tab_double (t, heading_columns + 2, 4, 0, 100 * res->tp / (res->tp + res->fn), 0); + + tab_double (t, heading_columns + 2, 5, 0, + 100 * (res->tp + res->tn) / (res->tp + res->tn + res->fp + res->fn), 0); + + + tab_submit (t); +}