X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=list_utils.py;h=182e2bc5c104908f39a15e4675021e6ed8a7c338;hb=fa4298fa508e00759565c246aef423ba28fedf31;hp=993ca8af9ca9f9a633c02162e0f155fd3b3cab74;hpb=709370b2198e09f1dbe195fe8813602a3125b7f6;p=python_utils.git

diff --git a/list_utils.py b/list_utils.py
index 993ca8a..182e2bc 100644
--- a/list_utils.py
+++ b/list_utils.py
@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
 
+from collections import Counter
 from itertools import islice
-from typing import Any, Iterator, List
+from typing import Any, Iterator, List, Mapping, Sequence
 
 
 def shard(lst: List[Any], size: int) -> Iterator[Any]:
@@ -47,6 +48,68 @@ def prepend(item: Any, lst: List[Any]) -> List[Any]:
     return lst
 
 
+def population_counts(lst: List[Any]) -> Mapping[Any, int]:
+    """
+    Return a population count mapping for the list (i.e. the keys are
+    list items and the values are the number of occurrances of that
+    list item in the original list.
+
+    >>> population_counts([1, 1, 1, 2, 2, 3, 3, 3, 4])
+    Counter({1: 3, 3: 3, 2: 2, 4: 1})
+
+    """
+    return Counter(lst)
+
+
+def most_common_item(lst: List[Any]) -> Any:
+
+    """
+    Return the most common item in the list.  In the case of ties,
+    which most common item is returned will be random.
+
+    >>> most_common_item([1, 1, 1, 2, 2, 3, 3, 3, 3, 4, 4])
+    3
+
+    """
+    return population_counts(lst).most_common(1)[0][0]
+
+
+def least_common_item(lst: List[Any]) -> Any:
+    """
+    Return the least common item in the list.  In the case of
+    ties, which least common item is returned will be random.
+
+    >>> least_common_item([1, 1, 1, 2, 2, 3, 3, 3, 4])
+    4
+
+    """
+    return population_counts(lst).most_common()[-1][0]
+
+
+def dedup_list(lst: List[Any]) -> List[Any]:
+    """
+    Remove duplicates from the list performantly.
+
+    >>> dedup_list([1, 2, 1, 3, 3, 4, 2, 3, 4, 5, 1])
+    [1, 2, 3, 4, 5]
+
+    """
+    return list(set(lst))
+
+
+def uniq(lst: List[Any]) -> List[Any]:
+    """
+    Alias for dedup_list.
+
+    """
+    return dedup_list(lst)
+
+
+def ngrams(lst: Sequence[Any], n):
+    for i in range(len(lst) - n + 1):
+        yield lst[i:i + n]
+
+
 if __name__ == '__main__':
     import doctest
     doctest.testmod()