X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=list_utils.py;h=05512b564c2303372ff81660840bfd29dcba942b;hb=7e6972bc7c8e891dc669645fa5969ed76fe38314;hp=182e2bc5c104908f39a15e4675021e6ed8a7c338;hpb=986d5f7ada15e56019518db43d07b76f94468e1a;p=python_utils.git diff --git a/list_utils.py b/list_utils.py index 182e2bc..05512b5 100644 --- a/list_utils.py +++ b/list_utils.py @@ -48,6 +48,23 @@ 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 @@ -61,29 +78,39 @@ def population_counts(lst: List[Any]) -> Mapping[Any, int]: return Counter(lst) -def most_common_item(lst: List[Any]) -> Any: +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_item([1, 1, 1, 2, 2, 3, 3, 3, 3, 4, 4]) + >>> 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] + """ - return population_counts(lst).most_common(1)[0][0] + p = population_counts(lst) + return remove_list_if_one_element([_[0] for _ in p.most_common()[0:count]]) -def least_common_item(lst: List[Any]) -> Any: +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_item([1, 1, 1, 2, 2, 3, 3, 3, 4]) + >>> 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] + """ - return population_counts(lst).most_common()[-1][0] + 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]: @@ -100,12 +127,75 @@ def dedup_list(lst: List[Any]) -> List[Any]: 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]