[MRG] scikit-learn#6581 n_samples of utils.resample can be more when replace is True

* scikit-learn#6581 n_samples can be more when replace is True

* more compact code

Author: facaiy

sklearn/utils/__init__.py

@@ -133,6 +133,8 @@ def resample(*arrays, **options):
     n_samples : int, None by default
         Number of samples to generate. If left to None this is
         automatically set to the first dimension of the arrays.
+        If replace is False it should not be larger than the length of
+        arrays.
 
     random_state : int or RandomState instance
         Control the shuffling for reproducible behavior.
@@ -194,10 +196,10 @@ def resample(*arrays, **options):
 
     if max_n_samples is None:
         max_n_samples = n_samples
-
-    if max_n_samples > n_samples:
-        raise ValueError("Cannot sample %d out of arrays with dim %d" % (
-            max_n_samples, n_samples))
+    elif (max_n_samples > n_samples) and (not replace):
+        raise ValueError("Cannot sample %d out of arrays with dim %d"
+                         "when replace is False" % (max_n_samples,
+                                                    n_samples))
 
     check_consistent_length(*arrays)
 

sklearn/utils/tests/test_utils.py

@@ -42,11 +42,6 @@ def test_make_rng():
     assert_raises(ValueError, check_random_state, "some invalid seed")
 
 
-def test_resample_noarg():
-    # Border case not worth mentioning in doctests
-    assert_true(resample() is None)
-
-
 def test_deprecated():
     # Test whether the deprecated decorator issues appropriate warnings
     # Copied almost verbatim from http://docs.python.org/library/warnings.html
@@ -84,11 +79,17 @@ class Ham(object):
         assert_true("deprecated" in str(w[0].message).lower())
 
 
-def test_resample_value_errors():
+def test_resample():
+    # Border case not worth mentioning in doctests
+    assert_true(resample() is None)
+
     # Check that invalid arguments yield ValueError
     assert_raises(ValueError, resample, [0], [0, 1])
-    assert_raises(ValueError, resample, [0, 1], [0, 1], n_samples=3)
+    assert_raises(ValueError, resample, [0, 1], [0, 1],
+                  replace=False, n_samples=3)
     assert_raises(ValueError, resample, [0, 1], [0, 1], meaning_of_life=42)
+    # Issue:6581, n_samples can be more when replace is True (default).
+    assert_equal(len(resample([1, 2], n_samples=5)), 5)
 
 
 def test_safe_mask():