Move set_params back to fit_grid_point

AlexanderFabisch · AlexanderFabisch · commit 30c86ea2ddcc · 2014-01-11T00:32:19.000+01:00
diff --git a/sklearn/cross_validation.py b/sklearn/cross_validation.py
@@ -25,7 +25,7 @@
 from .utils import check_arrays, check_random_state, safe_mask
 from .utils.validation import _num_samples
 from .utils.fixes import unique
-from .externals.joblib import Parallel, delayed, logger
+from .externals.joblib import Parallel, delayed
 from .externals.six import string_types, with_metaclass
 from .metrics.scorer import _deprecate_loss_and_score_funcs
 
@@ -1096,18 +1096,14 @@ def cross_val_score(estimator, X, y=None, scoring=None, cv=None, n_jobs=1,
                         pre_dispatch=pre_dispatch)
     scores = parallel(
         delayed(_cross_val_score)(clone(estimator), X, y, scorer, train, test,
-                                  parameters=None, verbose=verbose,
-                                  fit_params=fit_params,
-                                  log_label="cross_val_score")
+                                  verbose=verbose, fit_params=fit_params)
         for train, test in cv)
     return np.array(scores)[:, 0]
 
 
-def _cross_val_score(estimator, X, y, scorer, train, test, parameters,
-                     verbose, fit_params, log_label):
+def _cross_val_score(estimator, X, y, scorer, train, test,
+                     verbose, fit_params):
     """Inner loop for cross validation"""
-    if parameters is not None:
-        estimator.set_params(**parameters)
     n_samples = _num_samples(X)
     fit_params = fit_params if fit_params is not None else {}
     fit_params = dict([(k, np.asarray(v)[train]
@@ -1116,25 +1112,12 @@ def _cross_val_score(estimator, X, y, scorer, train, test, parameters,
 
     start_time = time.time()
 
-    if verbose > 1:
-        if parameters is None:
-            msg = ""
-        else:
-            msg = '%s' % (', '.join('%s=%s' % (k, v)
-                          for k, v in parameters.items()))
-        print("[%s] %s %s" % (log_label, msg, (64 - len(msg)) * '.'))
-
     X_train, y_train = _split(estimator, X, y, train)
     X_test, y_test = _split(estimator, X, y, test, train)
     _fit(estimator.fit, X_train, y_train, **fit_params)
     score = _score(estimator, X_test, y_test, scorer)
 
     scoring_time = time.time() - start_time
-    if verbose > 2:
-        msg += ", score=%f" % score
-    if verbose > 1:
-        end_msg = "%s -%s" % (msg, logger.short_format_time(scoring_time))
-        print("[%s] %s %s" % (log_label, (64 - len(end_msg)) * '.', end_msg))
 
     return score, _num_samples(X_test), scoring_time
 
diff --git a/sklearn/grid_search.py b/sklearn/grid_search.py
@@ -24,7 +24,7 @@
 from .base import MetaEstimatorMixin
 from .cross_validation import _check_cv as check_cv
 from .cross_validation import _check_scorable, _cross_val_score
-from .externals.joblib import Parallel, delayed
+from .externals.joblib import Parallel, delayed, logger
 from .externals import six
 from .utils import safe_mask, check_random_state
 from .utils.validation import _num_samples, check_arrays
@@ -229,10 +229,21 @@ def fit_grid_point(X, y, estimator, parameters, train, test, scorer,
     n_samples_test : int
         Number of test samples in this split.
     """
-    score, n_samples_test, _ = _cross_val_score(estimator, X, y, scorer,
-                                                train, test, parameters,
-                                                verbose, fit_params,
-                                                log_label="GridSearchCV")
+    if verbose > 1:
+        msg = '%s' % (', '.join('%s=%s' % (k, v)
+                      for k, v in parameters.items()))
+        print("[GridSearchCV] %s %s" % (msg, (64 - len(msg)) * '.'))
+
+    estimator.set_params(**parameters)
+    score, n_samples_test, scoring_time = _cross_val_score(
+        estimator, X, y, scorer, train, test, verbose, fit_params)
+
+    if verbose > 2:
+        msg += ", score=%f" % score
+    if verbose > 1:
+        end_msg = "%s -%s" % (msg, logger.short_format_time(scoring_time))
+        print("[GridSearchCV] %s %s" % ((64 - len(end_msg)) * '.', end_msg))
+
     return score, parameters, n_samples_test
 
 
