create det_dedupe(), which deterministically deduplicates a list

tests/util/test_list.py

@@ -1,12 +1,13 @@
 """ Test list utilities
 
 :Author: Jonathan Karr <karr@mssm.edu>
+:Author: Arthur Goldberg <Arthur.Goldberg@mssm.edu>
 :Date: 2016-11-30
 :Copyright: 2016, Karr Lab
 :License: MIT
 """
 
-from wc_utils.util.list import is_sorted, transpose, difference
+from wc_utils.util.list import is_sorted, transpose, difference, det_dedupe
 import unittest
 
 
@@ -28,9 +29,16 @@ def test_transpose(self):
         self.assertEqual(transpose(lst), t_lst)
 
     def test_difference(self):
-        l = list([0, 1, 2, 3, 4])
-        m = list([1, 2, 3])
+        l = [0, 1, 2, 3, 4]
+        m = [1, 2, 3]
         self.assertEqual(difference(l, m), [0, 4])
         self.assertEqual(difference(m, l), [])
         with self.assertRaises(TypeError):
             self.assertEqual(difference([], [[1]]), [])
+
+    def test_det_dedupe(self):
+        l = [0, 1, 2, 0, 1, 0, 7, 1]
+        expected = [0, 1, 2, 7]
+        self.assertEqual(det_dedupe(l), expected)
+        with self.assertRaises(TypeError):
+            det_dedupe([[]])

wc_utils/util/list.py

@@ -57,7 +57,32 @@ def difference(list_1, list_2):
         :obj:`list`: a set-like difference between `list_1` and `list_2`
 
     Raises:
-        `TypeError` if  `list_1` or `list_2` contains an unhashable (mutable) type
+        `TypeError` if `list_1` or `list_2` contains an unhashable (mutable) type
     """
     list_2_set = set(list_2)
     return list(filter(lambda item:not item in list_2_set, list_1))
+
+
+def det_dedupe(l):
+    """ Deterministically deduplicate a list
+
+    Returns a deduplicated copy of `l`. That is, returns a new list that contains one instance of
+    each element in `l` and orders these instances by their first occurrence in `l`.
+    Costs O(n), where n is the length of `l`.
+
+    Args:
+        l (:obj:`list`): a list with hashable elements
+
+    Returns:
+        :obj:`list`: a deterministically deduplicated copy of `l`
+
+    Raises:
+        `TypeError` if `l` contains an unhashable (mutable) type
+    """
+    s = set()
+    t = []
+    for e in l:
+        if e not in s:
+            t.append(e)
+            s.add(e)
+    return t