Unofficial pip/hf compatible `CodeBLEU` implementation
Project description
CodeBLEU
Unofficial CodeBLEU
implementation with Linux and MacOS supports available with PyPI and HF HUB.
Based on original CodeXGLUE/CodeBLEU code -- refactored, build for macos, tested and fixed multiple crutches to make it more usable.
Metric Description
An ideal evaluation metric should consider the grammatical correctness and the logic correctness. We propose weighted n-gram match and syntactic AST match to measure grammatical correctness, and introduce semantic data-flow match to calculate logic correctness.
(from CodeXGLUE repo)
In a nutshell, CodeBLEU
is a weighted combination of n-gram match (BLEU)
, weighted n-gram match (BLEU-weighted)
, AST match
and data-flow match
scores.
The metric has shown higher correlation with human evaluation than BLEU
and accuracy
metrics.
Usage
from codebleu import calc_codebleu
prediction = "def add ( a , b ) :\n return a + b"
reference = "def sum ( first , second ) :\n return second + first"
result = calc_codebleu([reference], [prediction], lang="python", weights=(0.25, 0.25, 0.25, 0.25), tokenizer=None)
print(result)
# {
# 'codebleu': 0.5537,
# 'ngram_match_score': 0.1041,
# 'weighted_ngram_match_score': 0.1109,
# 'syntax_match_score': 1.0,
# 'dataflow_match_score': 1.0
# }
where calc_codebleu takes the following arguments:
refarences
(list[str]
orlist[list[str]]
): reference codepredictions
(list[str]
) predicted codelang
(str
): code language, seecodebleu.AVAILABLE_LANGS
for available languages (python, c_sharp, java at the moment)weights
(tuple[float,float,float,float]): weights of thengram_match
,weighted_ngram_match
,syntax_match
, anddataflow_match
respectively, defaults to(0.25, 0.25, 0.25, 0.25)
tokenizer
(callable
): to split code string to tokens, defaults tos.split()
and outputs the dict[str, float]
with following fields:
codebleu
: the finalCodeBLEU
scorengram_match_score
:ngram_match
score (BLEU)weighted_ngram_match_score
:weighted_ngram_match
score (BLEU-weighted)syntax_match_score
:syntax_match
score (AST match)dataflow_match_score
:dataflow_match
score
Alternatively, you can use k4black/codebleu
from HuggingFace Spaces:
import evaluate
metric = evaluate.load("dvitel/codebleu")
result = metric.compute([reference], [prediction], lang="python", weights=(0.25, 0.25, 0.25, 0.25))
Feel free to check the HF Space with online example: k4black/codebleu
Installation
Requires Python 3.8+
The metrics can be installed with pip and used as indicated above:
pip install codebleu
alternatively the metric is available as k4black/codebleu in evaluate
(lib installation required):
import evaluate
metric = evaluate.load("dvitel/codebleu")
Citation
Official CodeBLEU paper can be cited as follows:
@misc{ren2020codebleu,
title={CodeBLEU: a Method for Automatic Evaluation of Code Synthesis},
author={Shuo Ren and Daya Guo and Shuai Lu and Long Zhou and Shujie Liu and Duyu Tang and Neel Sundaresan and Ming Zhou and Ambrosio Blanco and Shuai Ma},
year={2020},
eprint={2009.10297},
archivePrefix={arXiv},
primaryClass={cs.SE}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Hashes for codebleu-0.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dfc5b50f6f3149780a32b9bfcdf8e0e347f94eea776c442103bbea53948ffe63 |
|
MD5 | 4ddf724d280f9ae226cad0f14d776a81 |
|
BLAKE2b-256 | c032affa806fd2337bb301a4ff05a93d869b47c048a56bbbfbf48201e4037c0a |
Hashes for codebleu-0.1.5-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0f6834e912ae9cce5a4d2a3a268e1354a74ff720a2f648355681097aa812fcaf |
|
MD5 | e314d04e6d4378cc6480d8e166956a0d |
|
BLAKE2b-256 | bf5619d6a2c9d3554d4e29656357d5b5b51a2c6b8ae365894d8613e93c7b71ce |
Hashes for codebleu-0.1.5-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f63ba6ea07971936f3f5ab26c8de35b4e00b6baa00c00fe4bf7cd67937d860b2 |
|
MD5 | 598e0cf63787f2e2b6d09734e8219d8c |
|
BLAKE2b-256 | 116c9f1350caf9e0cc30ac8be7166916082ece533e9dcbbc42338ed4feba8708 |
Hashes for codebleu-0.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e919f62e9287777b3123c8563dc025bfa4935423cc2c1e992c77627fa57f7c6b |
|
MD5 | 9d0bbaf56ecf7e42248144e575ea0ada |
|
BLAKE2b-256 | 82203bc13020fffb33e6920c0a29cb8b9882b3e18f36e81f77b38cd585661f58 |
Hashes for codebleu-0.1.5-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 283ad2a30e613019250af6a26be38d133247c6cae6abee730ff7d5de7786eb36 |
|
MD5 | 7b3d63aa1ffe123b2322a42906629872 |
|
BLAKE2b-256 | 06915276d09ae09909ea1b3cdc4a20b6681dc5edb41ed02e37721e318699644f |
Hashes for codebleu-0.1.5-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 16cd91e57e92d9ac336f7ed3e37f960aa8790c5d936600d76912a83bf90ec338 |
|
MD5 | d2f09dc2a675913d319954149a7c4096 |
|
BLAKE2b-256 | 9dacfcb9e6338b6945704264dc337023edb11eecb8db4e0431dc67dae93bcfe4 |
Hashes for codebleu-0.1.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e57e0ddfcccd34fd48490f188991329adc9fedc9226941cabe851854e12eb34f |
|
MD5 | 8715bf1ae8ba8e56fd955cae92ca1230 |
|
BLAKE2b-256 | aa706c52752d60d13706ccfd29292d2e0335f4283ea860fe52b0ea4f67ab1243 |
Hashes for codebleu-0.1.5-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4d35f8aec7a67e261f8ddd4f7e866a4a20e85664bcfdb82828ba0e749d00ae8b |
|
MD5 | 1dd73ee779eeb7f9181c6a6a587bb3dc |
|
BLAKE2b-256 | 6f5c3689d0335c9b3f62aa9e4666ad50279c8ffe2607a32f3747957e3bae1e54 |
Hashes for codebleu-0.1.5-cp39-cp39-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1299042429422f723ab40ef85301c618a37d215f675607528d7b70ba22210248 |
|
MD5 | d03c140a08261a07197d12a0a5725d45 |
|
BLAKE2b-256 | 5b7e18bd069c6c7dc4df85984edfc0cccb1f622124f3b6f46d81f0444bc13f8c |
Hashes for codebleu-0.1.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e0394f661eaf74432f07132ddd940175fe5487f17d4151048c0d90903ea4746f |
|
MD5 | e8be8485e90ff9aa2edcb3a9e17830e2 |
|
BLAKE2b-256 | 63eb2073b2a785d0411f20d886b917c0a43d0db95be7ffdf1c1dcd31266c34c5 |
Hashes for codebleu-0.1.5-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 568a53a45f62a5754625c27b3cb69c21368066ff7e6e2db0694576bb36b2a19a |
|
MD5 | f80ec9a10c2a746e0d38fab6e3a98dca |
|
BLAKE2b-256 | df5c47957904c6519d90efc35ebe6c1f8d46c2436b09a104801a37c23e9996c7 |
Hashes for codebleu-0.1.5-cp38-cp38-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8d8f40b2d17a621d66bfe3c259cc94979b26afc6276f3bb8b2a27da97af5be7f |
|
MD5 | 278436ffa61bb5b40a1531e87af03f7d |
|
BLAKE2b-256 | 383e51edcef5e54e25142e85a8347afb487237413ea7084d83253d6aeeb7e806 |