Added select functions (was quasi_random_indices in FRL)

bob/bio/base/test/test_utils.py

@@ -2,6 +2,7 @@ import bob.bio.base
 import bob.learn.linear
 import pkg_resources
 import os
+import numpy
 
 import bob.io.base.test_utils
 
@@ -59,3 +60,24 @@ def test_io():
     # cleanup
     if os.path.exists(filename):
       os.remove(filename)
+
+def test_sampling():
+  # test selection of elements
+  indices = bob.bio.base.selected_indices(100, 10)
+  assert indices == range(5, 100, 10)
+
+  indices = bob.bio.base.selected_indices(100, 300)
+  assert indices == range(100)
+
+  indices = bob.bio.base.selected_indices(100, None)
+  assert indices == range(100)
+
+  array = numpy.arange(100)
+  elements = bob.bio.base.selected_elements(array, 10)
+  assert (elements - numpy.arange(5, 100, 10) == 0.).all()
+
+  elements = bob.bio.base.selected_elements(array, 200)
+  assert (elements - numpy.arange(100) == 0.).all()
+
+  elements = bob.bio.base.selected_elements(array, None)
+  assert (elements - numpy.arange(100) == 0.).all()

bob/bio/base/utils/__init__.py

@@ -31,3 +31,23 @@ def score_fusion_strategy(strategy_name = 'avarage'):
   except KeyError:
 #    warn("score fusion strategy '%s' is unknown" % strategy_name)
     return None
+
+
+def selected_indices(total_number_of_indices, desired_number_of_indices = None):
+  """Returns a list of indices that will contain exactly the number of desired indices (or the number of total items in the list, if this is smaller).
+  These indices are selected such that they are evenly spread over the whole sequence."""
+  if desired_number_of_indices is None or desired_number_of_indices >= total_number_of_indices or desired_number_of_indices < 0:
+    return range(total_number_of_indices)
+  increase = float(total_number_of_indices)/float(desired_number_of_indices)
+  # generate a regular quasi-random index list
+  return [int((i +.5)*increase) for i in range(desired_number_of_indices)]
+
+
+def selected_elements(list_of_elements, desired_number_of_elements = None):
+  """Returns a list of elements that are sub-selected from the given list (or the list itself, if its length is smaller).
+  These elements are selected such that they are evenly spread over the whole list."""
+  total_number_of_elements = len(list_of_elements)
+  if desired_number_of_elements is None or desired_number_of_elements >= total_number_of_elements or desired_number_of_elements < 0:
+    return list_of_elements
+  # sub-select
+  return [list_of_elements[i] for i in selected_indices(total_number_of_elements, desired_number_of_elements)]