#!/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]:
- """Yield successive size-sized shards from lst."""
+ """
+ Yield successive size-sized shards from lst.
+
+ >>> for sublist in shard([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], 3):
+ ... [_ for _ in sublist]
+ [1, 2, 3]
+ [4, 5, 6]
+ [7, 8, 9]
+ [10, 11, 12]
+
+ """
for x in range(0, len(lst), size):
yield islice(lst, x, x + size)
def flatten(lst: List[Any]) -> List[Any]:
- """Flatten out a list:
+ """
+ Flatten out a list:
- >>> flatten([ 1, [2, 3, 4, [5], 6], 7, [8, [9]]])
- [1, 2, 3, 4, 5, 6, 7, 8, 9]
+ >>> flatten([ 1, [2, 3, 4, [5], 6], 7, [8, [9]]])
+ [1, 2, 3, 4, 5, 6, 7, 8, 9]
"""
if len(lst) == 0:
if isinstance(lst[0], list):
return flatten(lst[0]) + flatten(lst[1:])
return lst[:1] + flatten(lst[1:])
+
+
+def prepend(item: Any, lst: List[Any]) -> List[Any]:
+ """
+ Prepend an item to a list.
+
+ >>> prepend('foo', ['bar', 'baz'])
+ ['foo', 'bar', 'baz']
+
+ """
+ lst.insert(0, item)
+ 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()