Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,55 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
# Code Qualiy Evaluation Dataset
|
5 |
+
Welcome to the repository for our research paper: T. Wang and Z. Chen, "Analyzing Code Text Strings for Code Evaluation," 2023 IEEE International Conference on Big Data (BigData), Sorrento, Italy, 2023, pp. 5619-5628, doi: 10.1109/BigData59044.2023.10386406.
|
6 |
+
|
7 |
+
## Contents
|
8 |
+
This repository contains the following:
|
9 |
+
- License
|
10 |
+
- Dataset
|
11 |
+
- Fine-tuned Model
|
12 |
+
|
13 |
+
## Model Info
|
14 |
+
There are three BERT models, each fine-tuned on a dataset of 70,000 Python 3 solutions submitted by users for problems #1 through #100 on LeetCode:
|
15 |
+
- `bert_lc100_hp25`: This model classifies code based on the 25th percentile as its threshold. It is designed for identifying lower quartile code solutions in terms of quality or performance.
|
16 |
+
- `bert_lc100_hp50`: Operating with a median-based approach, this model uses the 50th percentile as its classification threshold. It is suitable for general assessments, providing a balanced view of code quality.
|
17 |
+
- `bert_lc100_regression`: Unlike the others, this is a regression model. It provides a nuanced prediction of the overall code quality score, offering a more detailed evaluation compared to the binary classification approach.
|
18 |
+
|
19 |
+
## Model Usage
|
20 |
+
**Installation**
|
21 |
+
First, ensure you have the latest version of the tf-models-official package. You can install it using the following command:```
|
22 |
+
pip install -q tf-models-official
|
23 |
+
```
|
24 |
+
|
25 |
+
**Loading the Model**
|
26 |
+
To utilize the bert_lc100_regression model within TensorFlow, follow these steps:
|
27 |
+
|
28 |
+
```
|
29 |
+
import tensorflow as tf
|
30 |
+
import tensorflow_text as text
|
31 |
+
model = tf.keras.models.load_model('saved_model/bert_lc100_regression/', compile=False)
|
32 |
+
|
33 |
+
```
|
34 |
+
|
35 |
+
**Making Predictions**
|
36 |
+
To assess the quality of code, given that `X_test` contains a list of code strings, use the model to predict as follows:
|
37 |
+
```
|
38 |
+
y_pred = model.predict(X_test)
|
39 |
+
```
|
40 |
+
|
41 |
+
## Reference
|
42 |
+
If you found the dataset useful in your research or applications, please cite using the following BibTeX:
|
43 |
+
```
|
44 |
+
@INPROCEEDINGS{10386406,
|
45 |
+
author={Wang, Tianyu and Chen, Zhixiong},
|
46 |
+
booktitle={2023 IEEE International Conference on Big Data (BigData)},
|
47 |
+
title={Analyzing Code Text Strings for Code Evaluation},
|
48 |
+
year={2023},
|
49 |
+
volume={},
|
50 |
+
number={},
|
51 |
+
pages={5619-5628},
|
52 |
+
keywords={Measurement;Deep learning;Codes;Bidirectional control;Organizations;Transformers;Software;code assessment;code annotation;deep learning;nature language processing;software assurance;code security},
|
53 |
+
doi={10.1109/BigData59044.2023.10386406}
|
54 |
+
}
|
55 |
+
```
|