X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=list_utils.py;h=05512b564c2303372ff81660840bfd29dcba942b;hb=e5da1fa6bab9ea6bf4394facbb29f13cdc3daf9a;hp=993ca8af9ca9f9a633c02162e0f155fd3b3cab74;hpb=709370b2198e09f1dbe195fe8813602a3125b7f6;p=python_utils.git

diff --git a/list_utils.py b/list_utils.py
index 993ca8a..05512b5 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 +48,158 @@ def prepend(item: Any, lst: List[Any]) -> List[Any]:
     return lst
 
 
+def remove_list_if_one_element(lst: List[Any]) -> Any:
+    """
+    Remove the list and return the 0th element iff its length is one.
+
+    >>> remove_list_if_one_element([1234])
+    1234
+
+    >>> remove_list_if_one_element([1, 2, 3, 4])
+    [1, 2, 3, 4]
+
+    """
+    if len(lst) == 1:
+        return lst[0]
+    else:
+        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(lst: List[Any], *, count=1) -> 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([1, 1, 1, 2, 2, 3, 3, 3, 3, 4, 4])
+    3
+
+    >>> most_common([1, 1, 1, 2, 2, 3, 3, 3, 3, 4, 4], count=2)
+    [3, 1]
+
+    """
+    p = population_counts(lst)
+    return remove_list_if_one_element([_[0] for _ in p.most_common()[0:count]])
+
+
+def least_common(lst: List[Any], *, count=1) -> 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([1, 1, 1, 2, 2, 3, 3, 3, 4])
+    4
+
+    >>> least_common([1, 1, 1, 2, 2, 3, 3, 3, 4], count=2)
+    [4, 2]
+
+    """
+    p = population_counts(lst)
+    mc = p.most_common()[-count:]
+    mc.reverse()
+    return remove_list_if_one_element([_[0] for _ in mc])
+
+
+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 contains_duplicates(lst: List[Any]) -> bool:
+    """
+    Does the list contian duplicate elements or not?
+
+    >>> lst = [1, 2, 1, 3, 3, 4, 4, 5, 6, 1, 3, 4]
+    >>> contains_duplicates(lst)
+    True
+
+    >>> contains_duplicates(dedup_list(lst))
+    False
+
+    """
+    seen = set()
+    for _ in lst:
+        if _ in seen:
+            return True
+        seen.add(_)
+    return False
+
+
+def all_unique(lst: List[Any]) -> bool:
+    """
+    Inverted alias for contains_duplicates.
+    """
+    return not contains_duplicates(lst)
+
+
+def transpose(lst: List[Any]) -> List[Any]:
+    """
+    Transpose a list of lists.
+
+    >>> lst = [[1, 2], [3, 4], [5, 6]]
+    >>> transpose(lst)
+    [[1, 3, 5], [2, 4, 6]]
+
+    """
+    transposed = zip(*lst)
+    return [list(_) for _ in transposed]
+
+
+def ngrams(lst: Sequence[Any], n):
+    """
+    Return the ngrams in the sequence.
+
+    >>> seq = 'encyclopedia'
+    >>> for _ in ngrams(seq, 3):
+    ...     _
+    'enc'
+    'ncy'
+    'cyc'
+    'ycl'
+    'clo'
+    'lop'
+    'ope'
+    'ped'
+    'edi'
+    'dia'
+
+    >>> seq = ['this', 'is', 'an', 'awesome', 'test']
+    >>> for _ in ngrams(seq, 3):
+    ...     _
+    ['this', 'is', 'an']
+    ['is', 'an', 'awesome']
+    ['an', 'awesome', 'test']
+    """
+    for i in range(len(lst) - n + 1):
+        yield lst[i:i + n]
+
+
 if __name__ == '__main__':
     import doctest
     doctest.testmod()