mirror of
https://github.com/CodedotAl/gpt-code-clippy.git
synced 2024-09-17 10:27:14 +03:00
125 lines
4.6 KiB
Python
125 lines
4.6 KiB
Python
# Copyright 2017 Google Inc. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
# ==============================================================================
|
|
# Took the following from CodeXGlue Repository - https://github.com/microsoft/CodeXGLUE/blob/main/Code-Code/code-to-code-trans/evaluator/CodeBLEU/bleu.py
|
|
|
|
|
|
"""Python implementation of BLEU and smooth-BLEU.
|
|
|
|
This module provides a Python implementation of BLEU and smooth-BLEU.
|
|
Smooth BLEU is computed following the method outlined in the paper:
|
|
Chin-Yew Lin, Franz Josef Och. ORANGE: a method for evaluating automatic
|
|
evaluation metrics for machine translation. COLING 2004.
|
|
"""
|
|
|
|
import collections
|
|
import math
|
|
|
|
|
|
def _get_ngrams(segment, max_order):
|
|
"""Extracts all n-grams upto a given maximum order from an input segment.
|
|
|
|
Args:
|
|
segment: text segment from which n-grams will be extracted.
|
|
max_order: maximum length in tokens of the n-grams returned by this
|
|
methods.
|
|
|
|
Returns:
|
|
The Counter containing all n-grams upto max_order in segment
|
|
with a count of how many times each n-gram occurred.
|
|
"""
|
|
ngram_counts = collections.Counter()
|
|
for order in range(1, max_order + 1):
|
|
for i in range(0, len(segment) - order + 1):
|
|
ngram = tuple(segment[i:i+order])
|
|
ngram_counts[ngram] += 1
|
|
return ngram_counts
|
|
|
|
|
|
def compute_bleu(reference_corpus, translation_corpus, max_order=4,
|
|
smooth=True):
|
|
"""Computes BLEU score of translated segments against one or more references.
|
|
|
|
Args:
|
|
reference_corpus: list of lists of references for each translation. Each
|
|
reference should be tokenized into a list of tokens.
|
|
translation_corpus: list of translations to score. Each translation
|
|
should be tokenized into a list of tokens.
|
|
max_order: Maximum n-gram order to use when computing BLEU score.
|
|
smooth: Whether or not to apply Lin et al. 2004 smoothing.
|
|
|
|
Returns:
|
|
3-Tuple with the BLEU score, n-gram precisions, geometric mean of n-gram
|
|
precisions and brevity penalty.
|
|
"""
|
|
matches_by_order = [0] * max_order
|
|
possible_matches_by_order = [0] * max_order
|
|
reference_length = 0
|
|
translation_length = 0
|
|
for (references, translation) in zip(reference_corpus,
|
|
translation_corpus):
|
|
reference_length += min(len(r) for r in references)
|
|
translation_length += len(translation)
|
|
|
|
merged_ref_ngram_counts = collections.Counter()
|
|
for reference in references:
|
|
merged_ref_ngram_counts |= _get_ngrams(reference, max_order)
|
|
translation_ngram_counts = _get_ngrams(translation, max_order)
|
|
overlap = translation_ngram_counts & merged_ref_ngram_counts
|
|
for ngram in overlap:
|
|
matches_by_order[len(ngram)-1] += overlap[ngram]
|
|
for order in range(1, max_order+1):
|
|
possible_matches = len(translation) - order + 1
|
|
if possible_matches > 0:
|
|
possible_matches_by_order[order-1] += possible_matches
|
|
|
|
precisions = [0] * max_order
|
|
for i in range(0, max_order):
|
|
if smooth:
|
|
precisions[i] = ((matches_by_order[i] + 1.) /
|
|
(possible_matches_by_order[i] + 1.))
|
|
else:
|
|
if possible_matches_by_order[i] > 0:
|
|
precisions[i] = (float(matches_by_order[i]) /
|
|
possible_matches_by_order[i])
|
|
else:
|
|
precisions[i] = 0.0
|
|
|
|
if min(precisions) > 0:
|
|
p_log_sum = sum((1. / max_order) * math.log(p) for p in precisions)
|
|
geo_mean = math.exp(p_log_sum)
|
|
else:
|
|
geo_mean = 0
|
|
|
|
ratio = float(translation_length) / reference_length
|
|
|
|
if ratio > 1.0:
|
|
bp = 1.
|
|
else:
|
|
bp = math.exp(1 - 1. / ratio)
|
|
bleu = geo_mean * bp
|
|
print(geo_mean)
|
|
bleu_score_dict = {"bleu":bleu,"precision":precisions,"bp":bp,"ratio":ratio,"trans_len":translation_length,"ref_len":reference_length}
|
|
return bleu_score_dict#(bleu, precisions, bp, ratio, translation_length, reference_length)
|
|
|
|
def bleu_test_case():
|
|
"""A simple functionality test case to evaluate BLEU"""
|
|
generated = [[["a","=","b","\n","y","=","a","+","1"]]]
|
|
reference = [["a","=","b","\n","print","a"]]
|
|
score_dict = compute_bleu(generated,reference,smooth=False)
|
|
return score_dict
|
|
|
|
if __name__ == "__main__":
|
|
score_dict = bleu_test_case()
|
|
print(score_dict) |