From eed8476f7d184d8ca1515a489698784e174fa693 Mon Sep 17 00:00:00 2001 From: purificant Date: Sun, 17 Dec 2023 15:16:48 +0000 Subject: [PATCH 1/2] upgrade pre-commit --- .pre-commit-config.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index ac8f07feef..ffbed25851 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,6 +1,6 @@ repos: - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v4.0.1 + rev: v4.5.0 hooks: - id: fix-byte-order-marker - id: trailing-whitespace @@ -8,7 +8,7 @@ repos: - id: requirements-txt-fixer - id: check-yaml - repo: https://github.com/asottile/pyupgrade - rev: v3.1.0 + rev: v3.15.0 hooks: - id: pyupgrade args: ["--py37-plus"] @@ -27,4 +27,4 @@ repos: types_or: [cython, pyi, python] args: ['--filter-files'] minimum_pre_commit_version: '2.9.2' - additional_dependencies: ['isort==5.10.1'] + additional_dependencies: ['isort==5.13.2'] From f5f439ecab8de683d923c64e4bc2984399ee8a7a Mon Sep 17 00:00:00 2001 From: purificant Date: Sun, 17 Dec 2023 15:17:07 +0000 Subject: [PATCH 2/2] apply pyupgrade v3.1.0 -> v3.15.0 changes to the codebase --- nltk/classify/naivebayes.py | 2 +- nltk/translate/chrf_score.py | 2 +- nltk/translate/ibm1.py | 2 +- nltk/translate/ibm2.py | 6 +++--- nltk/translate/ibm3.py | 4 ++-- nltk/translate/ibm4.py | 8 ++++---- nltk/translate/ibm5.py | 10 ++++------ nltk/translate/ibm_model.py | 8 ++++---- 8 files changed, 20 insertions(+), 22 deletions(-) diff --git a/nltk/classify/naivebayes.py b/nltk/classify/naivebayes.py index 0cda42fe38..ca2bc44f19 100644 --- a/nltk/classify/naivebayes.py +++ b/nltk/classify/naivebayes.py @@ -168,7 +168,7 @@ def most_informative_features(self, n=100): features = set() # The max & min probability associated w/ each (fname, fval) # pair. Maps (fname,fval) -> float. - maxprob = defaultdict(lambda: 0.0) + maxprob = defaultdict(float) minprob = defaultdict(lambda: 1.0) for (label, fname), probdist in self._feature_probdist.items(): diff --git a/nltk/translate/chrf_score.py b/nltk/translate/chrf_score.py index ca816969f2..f312d7e7dd 100644 --- a/nltk/translate/chrf_score.py +++ b/nltk/translate/chrf_score.py @@ -194,7 +194,7 @@ def corpus_chrf( num_sents = len(hypotheses) # Keep f-scores for each n-gram order separate - ngram_fscores = defaultdict(lambda: list()) + ngram_fscores = defaultdict(list) # Iterate through each hypothesis and their corresponding references. for reference, hypothesis in zip(references, hypotheses): diff --git a/nltk/translate/ibm1.py b/nltk/translate/ibm1.py index 2ee7c0eb51..c278f04d67 100644 --- a/nltk/translate/ibm1.py +++ b/nltk/translate/ibm1.py @@ -187,7 +187,7 @@ def prob_all_alignments(self, src_sentence, trg_sentence): :return: Probability of t for all s in ``src_sentence`` :rtype: dict(str): float """ - alignment_prob_for_t = defaultdict(lambda: 0.0) + alignment_prob_for_t = defaultdict(float) for t in trg_sentence: for s in src_sentence: alignment_prob_for_t[t] += self.prob_alignment_point(s, t) diff --git a/nltk/translate/ibm2.py b/nltk/translate/ibm2.py index 4067f35804..e85586e796 100644 --- a/nltk/translate/ibm2.py +++ b/nltk/translate/ibm2.py @@ -209,7 +209,7 @@ def prob_all_alignments(self, src_sentence, trg_sentence): :return: Probability of t for all s in ``src_sentence`` :rtype: dict(str): float """ - alignment_prob_for_t = defaultdict(lambda: 0.0) + alignment_prob_for_t = defaultdict(float) for j in range(1, len(trg_sentence)): t = trg_sentence[j] for i in range(0, len(src_sentence)): @@ -304,10 +304,10 @@ class Model2Counts(Counts): def __init__(self): super().__init__() self.alignment = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0.0))) + lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(float))) ) self.alignment_for_any_i = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: 0.0)) + lambda: defaultdict(lambda: defaultdict(float)) ) def update_lexical_translation(self, count, s, t): diff --git a/nltk/translate/ibm3.py b/nltk/translate/ibm3.py index d3c159c922..3adaabfa3e 100644 --- a/nltk/translate/ibm3.py +++ b/nltk/translate/ibm3.py @@ -334,10 +334,10 @@ class Model3Counts(Counts): def __init__(self): super().__init__() self.distortion = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0.0))) + lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(float))) ) self.distortion_for_any_j = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: 0.0)) + lambda: defaultdict(lambda: defaultdict(float)) ) def update_distortion(self, count, alignment_info, j, l, m): diff --git a/nltk/translate/ibm4.py b/nltk/translate/ibm4.py index 665520e41e..8c1b3c6887 100644 --- a/nltk/translate/ibm4.py +++ b/nltk/translate/ibm4.py @@ -457,11 +457,11 @@ class Model4Counts(Counts): def __init__(self): super().__init__() self.head_distortion = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: 0.0)) + lambda: defaultdict(lambda: defaultdict(float)) ) - self.head_distortion_for_any_dj = defaultdict(lambda: defaultdict(lambda: 0.0)) - self.non_head_distortion = defaultdict(lambda: defaultdict(lambda: 0.0)) - self.non_head_distortion_for_any_dj = defaultdict(lambda: 0.0) + self.head_distortion_for_any_dj = defaultdict(lambda: defaultdict(float)) + self.non_head_distortion = defaultdict(lambda: defaultdict(float)) + self.non_head_distortion_for_any_dj = defaultdict(float) def update_distortion(self, count, alignment_info, j, src_classes, trg_classes): i = alignment_info.alignment[j] diff --git a/nltk/translate/ibm5.py b/nltk/translate/ibm5.py index b4591df77b..a80ff238bc 100644 --- a/nltk/translate/ibm5.py +++ b/nltk/translate/ibm5.py @@ -581,14 +581,12 @@ class Model5Counts(Counts): def __init__(self): super().__init__() - self.head_vacancy = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: 0.0)) - ) - self.head_vacancy_for_any_dv = defaultdict(lambda: defaultdict(lambda: 0.0)) + self.head_vacancy = defaultdict(lambda: defaultdict(lambda: defaultdict(float))) + self.head_vacancy_for_any_dv = defaultdict(lambda: defaultdict(float)) self.non_head_vacancy = defaultdict( - lambda: defaultdict(lambda: defaultdict(lambda: 0.0)) + lambda: defaultdict(lambda: defaultdict(float)) ) - self.non_head_vacancy_for_any_dv = defaultdict(lambda: defaultdict(lambda: 0.0)) + self.non_head_vacancy_for_any_dv = defaultdict(lambda: defaultdict(float)) def update_vacancy(self, count, alignment_info, i, trg_classes, slots): """ diff --git a/nltk/translate/ibm_model.py b/nltk/translate/ibm_model.py index e2b3760350..adc6bb99e7 100644 --- a/nltk/translate/ibm_model.py +++ b/nltk/translate/ibm_model.py @@ -521,12 +521,12 @@ class Counts: """ def __init__(self): - self.t_given_s = defaultdict(lambda: defaultdict(lambda: 0.0)) - self.any_t_given_s = defaultdict(lambda: 0.0) + self.t_given_s = defaultdict(lambda: defaultdict(float)) + self.any_t_given_s = defaultdict(float) self.p0 = 0.0 self.p1 = 0.0 - self.fertility = defaultdict(lambda: defaultdict(lambda: 0.0)) - self.fertility_for_any_phi = defaultdict(lambda: 0.0) + self.fertility = defaultdict(lambda: defaultdict(float)) + self.fertility_for_any_phi = defaultdict(float) def update_lexical_translation(self, count, alignment_info, j): i = alignment_info.alignment[j]