Safetensors weights for seeds 42, 1337, 2024; model card, config, inference code
Browse files- .gitattributes +3 -0
- README.md +183 -0
- commit_intent.py +162 -0
- config.json +21 -0
- model_attention_1337.safetensors +3 -0
- model_attention_2024.safetensors +3 -0
- model_attention_42.safetensors +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model_attention_1337.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
model_attention_2024.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
model_attention_42.safetensors filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language: en
|
| 4 |
+
library_name: pytorch
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
base_model: microsoft/codebert-base
|
| 7 |
+
tags:
|
| 8 |
+
- code
|
| 9 |
+
- commit-classification
|
| 10 |
+
- maintenance-activities
|
| 11 |
+
- software-engineering
|
| 12 |
+
- mining-software-repositories
|
| 13 |
+
- codebert
|
| 14 |
+
- java
|
| 15 |
+
metrics:
|
| 16 |
+
- accuracy
|
| 17 |
+
model-index:
|
| 18 |
+
- name: codebert-commit-intent
|
| 19 |
+
results:
|
| 20 |
+
- task:
|
| 21 |
+
type: text-classification
|
| 22 |
+
name: Commit maintenance-activity classification
|
| 23 |
+
dataset:
|
| 24 |
+
type: levin-yehudai-commits
|
| 25 |
+
name: Levin & Yehudai labelled commits (173-commit test split)
|
| 26 |
+
metrics:
|
| 27 |
+
- type: accuracy
|
| 28 |
+
value: 86.7
|
| 29 |
+
name: Accuracy, mean of 3 seeds
|
| 30 |
+
- type: cohen_kappa
|
| 31 |
+
value: 0.791
|
| 32 |
+
name: Cohen's kappa, mean of 3 seeds
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
# CodeBERT commit-intent classifier
|
| 36 |
+
|
| 37 |
+
Classifies a commit as **corrective** (fixing a fault), **adaptive** (adding a feature) or
|
| 38 |
+
**perfective** (improving the code or its design), Swanson's maintenance categories, from its
|
| 39 |
+
message and its diff.
|
| 40 |
+
|
| 41 |
+
It is [CodeBERT](https://huggingface.co/microsoft/codebert-base) fine-tuned on the 1,151 commits
|
| 42 |
+
Levin & Yehudai labelled by hand. Where their method reads 48 counts of AST change types extracted
|
| 43 |
+
by ChangeDistiller, this model reads the diff itself, so it runs on modern Java that ChangeDistiller
|
| 44 |
+
cannot parse. On the same 173 held-out commits it reaches **86.7% accuracy and Cohen's κ 0.791**,
|
| 45 |
+
against 75.7% and 0.621 for a reproduction of their best model.
|
| 46 |
+
|
| 47 |
+
| | |
|
| 48 |
+
|---|---|
|
| 49 |
+
| Training code and evaluation | [github.com/Binamra00/commit-intent-and-refactoring-levels](https://github.com/Binamra00/commit-intent-and-refactoring-levels) |
|
| 50 |
+
| Data, stage outputs and 34,609 classified commits | [10.5281/zenodo.24295072](https://doi.org/10.5281/zenodo.24295072) |
|
| 51 |
+
| Base model | [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) |
|
| 52 |
+
|
| 53 |
+
## Files
|
| 54 |
+
|
| 55 |
+
| file | |
|
| 56 |
+
|---|---|
|
| 57 |
+
| `model_attention_2024.safetensors` | the default model, seed 2024 |
|
| 58 |
+
| `model_attention_42.safetensors`, `model_attention_1337.safetensors` | the other two seeds; the reported scores are the mean of all three |
|
| 59 |
+
| `config.json` | labels, input limits, calibration temperature and thresholds |
|
| 60 |
+
| `commit_intent.py` | the architecture and an inference wrapper; the weights load into it unchanged |
|
| 61 |
+
|
| 62 |
+
## Usage
|
| 63 |
+
|
| 64 |
+
```bash
|
| 65 |
+
pip install torch transformers safetensors huggingface_hub
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
```python
|
| 69 |
+
from huggingface_hub import hf_hub_download
|
| 70 |
+
import importlib.util
|
| 71 |
+
|
| 72 |
+
path = hf_hub_download("Binamra00/codebert-commit-intent", "commit_intent.py")
|
| 73 |
+
spec = importlib.util.spec_from_file_location("commit_intent", path)
|
| 74 |
+
ci = importlib.util.module_from_spec(spec); spec.loader.exec_module(ci)
|
| 75 |
+
|
| 76 |
+
clf = ci.CommitIntent.from_pretrained("Binamra00/codebert-commit-intent") # seed=42 / 1337 for the others
|
| 77 |
+
|
| 78 |
+
patch = """@@ -10,7 +10,9 @@ public Config load(Path file) {
|
| 79 |
+
- return parse(Files.readString(file));
|
| 80 |
+
+ String text = Files.readString(file);
|
| 81 |
+
+ if (text.isBlank()) return Config.empty();
|
| 82 |
+
+ return parse(text);
|
| 83 |
+
"""
|
| 84 |
+
clf.predict("Fix NPE when the config file is empty", {"src/main/java/Config.java": patch})
|
| 85 |
+
# {'label': ..., 'predicted': ..., 'probabilities': {...}, 'margin': ...}
|
| 86 |
+
```
|
| 87 |
+
|
| 88 |
+
**Input.** The full commit message, and for each changed file its unified-diff patch, as GitHub's
|
| 89 |
+
API returns it in the `patch` field or as one file's section of `git diff`. Context lines are
|
| 90 |
+
ignored. The model was trained on Java projects.
|
| 91 |
+
|
| 92 |
+
**Output.**
|
| 93 |
+
|
| 94 |
+
- `probabilities`: calibrated with temperature scaling (T = 2.86).
|
| 95 |
+
- `margin`: the top probability minus the runner-up.
|
| 96 |
+
- `predicted`: the most likely class.
|
| 97 |
+
- `label`: the same class, or `unclassified` when the margin is below 0.47. Pass `threshold=` to
|
| 98 |
+
change that cut, or read `predicted` to always get one of the three classes.
|
| 99 |
+
|
| 100 |
+
## How it works
|
| 101 |
+
|
| 102 |
+
Each commit is split into pieces: one for the message, and one per changed file, holding that
|
| 103 |
+
file's removed and added lines. Each piece is encoded by CodeBERT, in 512-token windows when it is
|
| 104 |
+
longer. Windows are averaged within a piece, and a learned attention score weights the pieces into
|
| 105 |
+
one commit vector. A linear layer then predicts the three classes. A commit is never truncated: up
|
| 106 |
+
to 256 pieces are kept, and no commit in the training data had more.
|
| 107 |
+
|
| 108 |
+
## Training
|
| 109 |
+
|
| 110 |
+
| | |
|
| 111 |
+
|---|---|
|
| 112 |
+
| Data | Levin & Yehudai's 1,151 labelled commits from 11 Java projects ([10.5281/zenodo.835534](https://doi.org/10.5281/zenodo.835534)), with diffs fetched from the GitHub API; 1,150 used, one excluded because the API truncated it or it changed no Java file |
|
| 113 |
+
| Split | their protocol: 85/15 stratified, 977 training / 173 test commits |
|
| 114 |
+
| Model selection | attention vs transformer pooling, by 5-fold cross-validation repeated twice on the training commits |
|
| 115 |
+
| Optimiser | AdamW, learning rate 2e-5 for the encoder and 1e-3 for the head, linear warmup over 10% of steps then linear decay, weight decay 0.01, gradient clipping at 1.0 |
|
| 116 |
+
| Loss | cross-entropy weighted by inverse class frequency |
|
| 117 |
+
| Epochs | up to 10, early stopping after 3 without a better validation κ, on 10% of the training commits |
|
| 118 |
+
| Seeds | 42, 1337, 2024 |
|
| 119 |
+
| Hardware | one NVIDIA A100 80 GB, bfloat16 autocast |
|
| 120 |
+
|
| 121 |
+
## Evaluation
|
| 122 |
+
|
| 123 |
+
On the 173 test commits, which were opened once, after training:
|
| 124 |
+
|
| 125 |
+
| seed | accuracy | κ | macro F1 |
|
| 126 |
+
|---|---|---|---|
|
| 127 |
+
| 42 | 85.5% | 0.771 | 83.4 |
|
| 128 |
+
| 1337 | 86.7% | 0.792 | 85.3 |
|
| 129 |
+
| 2024 | 87.9% | 0.810 | 86.5 |
|
| 130 |
+
| **mean** | **86.7% ± 1.2** | **0.791 ± 0.020** | **85.1** |
|
| 131 |
+
|
| 132 |
+
For comparison, on the same commits:
|
| 133 |
+
|
| 134 |
+
| model | accuracy | κ |
|
| 135 |
+
|---|---|---|
|
| 136 |
+
| Levin & Yehudai, as published | 76.7% | 0.635 |
|
| 137 |
+
| Our reproduction of their model | 75.7% | 0.621 |
|
| 138 |
+
| Best reproduced feature-based model | 78.0% | 0.654 |
|
| 139 |
+
|
| 140 |
+
Temperature scaling, fitted on the test commits, took expected calibration error from 0.109 to
|
| 141 |
+
0.025.
|
| 142 |
+
|
| 143 |
+
## Limitations
|
| 144 |
+
|
| 145 |
+
- **Small test set.** 173 commits. Seed 2024 is the default because it scored best of the three
|
| 146 |
+
on them, so its own scores are optimistic; quote the mean.
|
| 147 |
+
- **Clean training data.** Levin & Yehudai dropped commits they could not classify confidently,
|
| 148 |
+
so the model has never seen an ambiguous commit and will still name a class for one. The
|
| 149 |
+
`unclassified` threshold helps, but it was set on that clean data and is probably too
|
| 150 |
+
permissive elsewhere.
|
| 151 |
+
- **Java only.** All training commits come from 11 Java projects.
|
| 152 |
+
- **Weak outside check.** Applied to 34,609 commits from five other Java projects, its predictions
|
| 153 |
+
agreed with the class implied by maintainers' issue labels 58.3% of the time, rising from 37%
|
| 154 |
+
for the least confident commits to 78% for the most. Those labels are themselves noisy.
|
| 155 |
+
|
| 156 |
+
## Intended use
|
| 157 |
+
|
| 158 |
+
Research on software maintenance: labelling commits at scale by the kind of work they do, as a
|
| 159 |
+
feature or a stratifier. It is not meant for judging individual developers' work.
|
| 160 |
+
|
| 161 |
+
## Citation
|
| 162 |
+
|
| 163 |
+
If you use this model, please cite the repository (its `CITATION.cff`) and the work it builds on:
|
| 164 |
+
|
| 165 |
+
```bibtex
|
| 166 |
+
@inproceedings{levin2017boosting,
|
| 167 |
+
author = {Levin, Stanislav and Yehudai, Amiram},
|
| 168 |
+
title = {Boosting Automatic Commit Classification Into Maintenance Activities By
|
| 169 |
+
Utilizing Source Code Changes},
|
| 170 |
+
booktitle = {Proceedings of the 13th International Conference on Predictive Models and
|
| 171 |
+
Data Analytics in Software Engineering (PROMISE)},
|
| 172 |
+
pages = {97--106},
|
| 173 |
+
year = {2017},
|
| 174 |
+
doi = {10.1145/3127005.3127016}
|
| 175 |
+
}
|
| 176 |
+
|
| 177 |
+
@inproceedings{feng2020codebert,
|
| 178 |
+
author = {Feng, Zhangyin and others},
|
| 179 |
+
title = {{CodeBERT}: A Pre-Trained Model for Programming and Natural Languages},
|
| 180 |
+
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020},
|
| 181 |
+
year = {2020}
|
| 182 |
+
}
|
| 183 |
+
```
|
commit_intent.py
ADDED
|
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Commit-intent classifier: is a commit corrective, adaptive or perfective?
|
| 3 |
+
|
| 4 |
+
CodeBERT fine-tuned on Levin & Yehudai's 1,151 labelled commits. It reads the commit message and
|
| 5 |
+
the per-file diff, encodes each piece separately, and attention-pools the pieces into one commit
|
| 6 |
+
vector. This module rebuilds exactly the architecture that was trained, so the published weights
|
| 7 |
+
load into it unchanged.
|
| 8 |
+
|
| 9 |
+
from commit_intent import CommitIntent
|
| 10 |
+
clf = CommitIntent.from_pretrained("Binamra00/codebert-commit-intent")
|
| 11 |
+
clf.predict("Fix NPE when the config file is empty",
|
| 12 |
+
{"src/main/java/Config.java": patch_text})
|
| 13 |
+
|
| 14 |
+
Training code and evaluation: github.com/Binamra00/commit-intent-and-refactoring-levels
|
| 15 |
+
"""
|
| 16 |
+
|
| 17 |
+
import json
|
| 18 |
+
import re
|
| 19 |
+
from pathlib import Path
|
| 20 |
+
|
| 21 |
+
import torch
|
| 22 |
+
import torch.nn as nn
|
| 23 |
+
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
| 24 |
+
|
| 25 |
+
DEFAULT_REPO = "Binamra00/codebert-commit-intent"
|
| 26 |
+
HUNK = re.compile(r"^@@ .*? @@")
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
class CommitClassifier(nn.Module):
|
| 30 |
+
"""The trained network. Parameter names match the published state dicts."""
|
| 31 |
+
|
| 32 |
+
def __init__(self, base_model, n_labels=3, dropout=0.2):
|
| 33 |
+
super().__init__()
|
| 34 |
+
# Built from the config alone: the fine-tuned encoder weights come from the state dict.
|
| 35 |
+
self.enc = AutoModel.from_config(AutoConfig.from_pretrained(base_model))
|
| 36 |
+
hid = self.enc.config.hidden_size
|
| 37 |
+
self.score = nn.Linear(hid, 1) # attention score per piece
|
| 38 |
+
self.drop = nn.Dropout(dropout)
|
| 39 |
+
self.out = nn.Linear(hid, n_labels)
|
| 40 |
+
|
| 41 |
+
def forward_pieces(self, window_cls, owner):
|
| 42 |
+
"""window_cls: (windows, hid) [CLS] vectors; owner: piece index of each window."""
|
| 43 |
+
n = int(owner.max()) + 1
|
| 44 |
+
pv = torch.zeros(n, window_cls.size(1), device=window_cls.device, dtype=window_cls.dtype)
|
| 45 |
+
pv.index_add_(0, owner, window_cls)
|
| 46 |
+
cnt = torch.bincount(owner, minlength=n).to(window_cls.dtype).unsqueeze(1)
|
| 47 |
+
pv = pv / cnt # windows mean-pooled within a piece
|
| 48 |
+
a = self.score(pv).softmax(0) # pieces attention-pooled into a commit
|
| 49 |
+
return self.out(self.drop((pv * a).sum(0)))
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def pieces_from_patches(message, files):
|
| 53 |
+
"""
|
| 54 |
+
Render a commit the way the model was trained on it.
|
| 55 |
+
|
| 56 |
+
message : the full commit message, as git records it
|
| 57 |
+
files : {path: unified-diff patch} for each changed file -- GitHub's API `patch` field or one
|
| 58 |
+
file's section of `git diff`. Header and hunk lines are dropped; '+' lines become
|
| 59 |
+
ADDED, '-' lines REMOVED. Context lines are ignored.
|
| 60 |
+
|
| 61 |
+
Returns the message piece followed by one piece per file, largest first.
|
| 62 |
+
"""
|
| 63 |
+
pieces = [f"<COMMIT_MESSAGE>{(message or '').strip()}</COMMIT_MESSAGE>"]
|
| 64 |
+
rendered = []
|
| 65 |
+
for path, patch in dict(files or {}).items():
|
| 66 |
+
added, removed = [], []
|
| 67 |
+
for ln in (patch or "").split("\n"):
|
| 68 |
+
if HUNK.match(ln) or ln.startswith(("--- ", "+++ ")):
|
| 69 |
+
continue
|
| 70 |
+
if ln.startswith("+"):
|
| 71 |
+
added.append(ln[1:])
|
| 72 |
+
elif ln.startswith("-"):
|
| 73 |
+
removed.append(ln[1:])
|
| 74 |
+
part = [f"<FILE>{path}</FILE>"]
|
| 75 |
+
if removed:
|
| 76 |
+
part.append("<REMOVED>" + "\n".join(removed) + "</REMOVED>")
|
| 77 |
+
if added:
|
| 78 |
+
part.append("<ADDED>" + "\n".join(added) + "</ADDED>")
|
| 79 |
+
rendered.append("\n".join(part))
|
| 80 |
+
rendered.sort(key=len, reverse=True)
|
| 81 |
+
return pieces + rendered
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
class CommitIntent:
|
| 85 |
+
"""Calibrated predictions from a commit's message and diff."""
|
| 86 |
+
|
| 87 |
+
def __init__(self, model, tokenizer, config, device):
|
| 88 |
+
self.model, self.tok, self.cfg, self.device = model, tokenizer, config, device
|
| 89 |
+
self.labels = config["labels"]
|
| 90 |
+
|
| 91 |
+
@classmethod
|
| 92 |
+
def from_pretrained(cls, repo_or_dir=DEFAULT_REPO, seed=None, device=None):
|
| 93 |
+
"""Load from a Hugging Face repo id or a local folder holding config.json and the weights."""
|
| 94 |
+
from safetensors.torch import load_file
|
| 95 |
+
local = Path(repo_or_dir)
|
| 96 |
+
if local.is_dir():
|
| 97 |
+
fetch = lambda name: str(local / name)
|
| 98 |
+
else:
|
| 99 |
+
from huggingface_hub import hf_hub_download
|
| 100 |
+
fetch = lambda name: hf_hub_download(repo_or_dir, name)
|
| 101 |
+
config = json.load(open(fetch("config.json"), encoding="utf-8"))
|
| 102 |
+
seed = str(seed or config["default_seed"])
|
| 103 |
+
device = device or ("cuda" if torch.cuda.is_available() else "cpu")
|
| 104 |
+
|
| 105 |
+
model = CommitClassifier(config["base_model"], len(config["labels"]), config["dropout"])
|
| 106 |
+
state = load_file(fetch(config["weights"][seed]))
|
| 107 |
+
missing, unexpected = model.load_state_dict(state, strict=False)
|
| 108 |
+
# Older transformers versions also save a position_ids buffer; nothing else may differ.
|
| 109 |
+
stray = [k for k in missing + unexpected if not k.endswith("position_ids")]
|
| 110 |
+
if stray:
|
| 111 |
+
raise RuntimeError(f"weights do not match the architecture: {stray[:5]}")
|
| 112 |
+
model.to(device).eval()
|
| 113 |
+
return cls(model, AutoTokenizer.from_pretrained(config["base_model"]), config, device)
|
| 114 |
+
|
| 115 |
+
def _windows(self, text):
|
| 116 |
+
ids = self.tok.encode(text, add_special_tokens=False, truncation=False)
|
| 117 |
+
body = self.cfg["max_length"] - 2
|
| 118 |
+
return [ids[i:i + body] for i in range(0, max(len(ids), 1), body)] or [[]]
|
| 119 |
+
|
| 120 |
+
@torch.no_grad()
|
| 121 |
+
def logits(self, pieces, batch=64):
|
| 122 |
+
"""Raw logits for one commit given its rendered pieces."""
|
| 123 |
+
pieces = pieces[: self.cfg["max_pieces"]]
|
| 124 |
+
wins, owner = [], []
|
| 125 |
+
for pi, p in enumerate(pieces):
|
| 126 |
+
for w in self._windows(p):
|
| 127 |
+
wins.append(w)
|
| 128 |
+
owner.append(pi)
|
| 129 |
+
cls_vecs = []
|
| 130 |
+
for s in range(0, len(wins), batch):
|
| 131 |
+
chunk = wins[s:s + batch]
|
| 132 |
+
L = max(len(w) for w in chunk) + 2
|
| 133 |
+
ids = torch.full((len(chunk), L), self.tok.pad_token_id, dtype=torch.long)
|
| 134 |
+
att = torch.zeros((len(chunk), L), dtype=torch.long)
|
| 135 |
+
for j, w in enumerate(chunk):
|
| 136 |
+
seq = [self.tok.cls_token_id] + w + [self.tok.sep_token_id]
|
| 137 |
+
ids[j, :len(seq)] = torch.tensor(seq)
|
| 138 |
+
att[j, :len(seq)] = 1
|
| 139 |
+
h = self.model.enc(input_ids=ids.to(self.device),
|
| 140 |
+
attention_mask=att.to(self.device)).last_hidden_state[:, 0]
|
| 141 |
+
cls_vecs.append(h)
|
| 142 |
+
return self.model.forward_pieces(torch.cat(cls_vecs),
|
| 143 |
+
torch.tensor(owner, device=self.device)).cpu()
|
| 144 |
+
|
| 145 |
+
def predict(self, message, files, threshold=None):
|
| 146 |
+
"""
|
| 147 |
+
Predicted class with calibrated probabilities.
|
| 148 |
+
|
| 149 |
+
Probabilities use the temperature fitted on held-out commits. `margin` is the top
|
| 150 |
+
probability minus the runner-up; below `threshold` (default 0.47) the commit is reported
|
| 151 |
+
as 'unclassified' rather than forced into a class.
|
| 152 |
+
"""
|
| 153 |
+
z = self.logits(pieces_from_patches(message, files)) / self.cfg["temperature"]
|
| 154 |
+
p = z.softmax(-1)
|
| 155 |
+
top2 = p.topk(2).values
|
| 156 |
+
margin = float(top2[0] - top2[1])
|
| 157 |
+
threshold = self.cfg["margin_threshold"] if threshold is None else threshold
|
| 158 |
+
label = self.labels[int(p.argmax())]
|
| 159 |
+
return {"label": label if margin >= threshold else "unclassified",
|
| 160 |
+
"predicted": label,
|
| 161 |
+
"probabilities": {l: round(float(v), 4) for l, v in zip(self.labels, p)},
|
| 162 |
+
"margin": round(margin, 4)}
|
config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "CommitClassifier",
|
| 3 |
+
"base_model": "microsoft/codebert-base",
|
| 4 |
+
"labels": ["adaptive", "corrective", "perfective"],
|
| 5 |
+
"pooling": "attention",
|
| 6 |
+
"max_length": 512,
|
| 7 |
+
"window_overlap": 0,
|
| 8 |
+
"max_pieces": 256,
|
| 9 |
+
"dropout": 0.2,
|
| 10 |
+
"temperature": 2.86,
|
| 11 |
+
"margin_threshold": 0.47,
|
| 12 |
+
"sensitivity_margin_threshold": 0.34,
|
| 13 |
+
"default_seed": 2024,
|
| 14 |
+
"weights": {
|
| 15 |
+
"42": "model_attention_42.safetensors",
|
| 16 |
+
"1337": "model_attention_1337.safetensors",
|
| 17 |
+
"2024": "model_attention_2024.safetensors"
|
| 18 |
+
},
|
| 19 |
+
"training_code": "https://github.com/Binamra00/commit-intent-and-refactoring-levels",
|
| 20 |
+
"data": "https://doi.org/10.5281/zenodo.24295072"
|
| 21 |
+
}
|
model_attention_1337.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84a7e71878176c1e4c0d7f6d5875ea6c37e81849be4584bce3a87ebd90dac84f
|
| 3 |
+
size 498618432
|
model_attention_2024.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0996bcdf063d9fa71702eeeabb461f40d0550a77c0d8eaa5afe0e0ac7c975f73
|
| 3 |
+
size 498618432
|
model_attention_42.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebc1f5f522aea6bc393d5c29650979de807b96b7b3a8782d07fdbe411b26d758
|
| 3 |
+
size 498618424
|