Wesamalnabki-bsc commited on
Commit
b0ea028
Β·
verified Β·
1 Parent(s): 6522b7b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -76
README.md CHANGED
@@ -1,76 +1,12 @@
1
- # Text Classification Benchmark Leaderboard
2
-
3
- This project provides a **leaderboard** for evaluating **Text Classification** models. Users can upload their model predictions in a CSV format, compare performance metrics against ground truth datasets, and track submissions over time.
4
-
5
- ## Features
6
- - **Dataset Selection:** Users can choose a dataset from predefined test sets.
7
- - **Submission Upload:** Supports CSV files with `file_name` and `label` columns.
8
- - **Automated Evaluation:** Calculates **Accuracy, Precision, Recall, and F1-score**.
9
- - **Leaderboard Tracking:** Stores and displays past experiments.
10
- - **Gradio Interface:** Simple and interactive web interface.
11
-
12
- ## Requirements
13
- Ensure you have the following installed before running the project:
14
-
15
- ```bash
16
- pip install gradio pandas sqlalchemy scikit-learn
17
- ```
18
-
19
- ## Setup & Usage
20
-
21
- 1. **Clone the repository:**
22
- ```bash
23
- git clone https://github.com/nlp4bia-bsc/text-classification-leaderboard.git
24
- cd text-classification-leaderboard
25
- ```
26
-
27
- 2. **Run the application:**
28
- ```bash
29
- python app.py
30
- ```
31
-
32
- 3. **Access the interface:**
33
- The application runs locally. Open your browser and go to:
34
- ```
35
- http://127.0.0.1:7860/
36
- ```
37
-
38
- ## Submission Format
39
- Your submission file must be a **CSV** containing the following columns:
40
-
41
- | file_name | label |
42
- |-----------|--------|
43
- | doc1.txt | spam |
44
- | doc2.txt | ham |
45
- | doc3.txt | spam |
46
-
47
- ### Evaluation Metrics
48
- The system calculates:
49
- - **Accuracy**
50
- - **Precision (weighted)**
51
- - **Recall (weighted)**
52
- - **F1-score (weighted)**
53
-
54
- ## Directory Structure
55
- ```
56
- text-classification-leaderboard/
57
- │── testsets/ # Folder containing test datasets
58
- │── submissions.db # SQLite database for storing results
59
- │── app.py # Main application script
60
- │── README.md # Project documentation
61
- ```
62
-
63
- ## Future Improvements
64
- - Add support for multi-label classification.
65
- - Expand dataset compatibility with more formats.
66
-
67
- ## License
68
- This project is licensed under the **MIT License**. Feel free to contribute and enhance it!
69
-
70
- ## Contributing
71
- Pull requests are welcome! If you have suggestions or find issues, please open an issue on the repository.
72
-
73
- ---
74
- **Author:** Wesam Alnabki
75
- **GitHub:** [wesamalnabki](https://github.com/wesamalnabki)
76
-
 
1
+ ---
2
+ title: Text Classification Leaderboard
3
+ emoji: 🌍
4
+ colorFrom: yellow
5
+ colorTo: indigo
6
+ sdk: gradio
7
+ sdk_version: 5.18.0
8
+ app_file: app.py
9
+ pinned: false
10
+ ---
11
+
12
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference