docs: describe project and installation instructions
Browse files
README.md
CHANGED
|
@@ -8,7 +8,49 @@ sdk_version: 1.41.1
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
license: mit
|
| 11 |
-
short_description: BERTimbau finetuned for
|
| 12 |
---
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
license: mit
|
| 11 |
+
short_description: BERTimbau finetuned for Sentiment Analysis of Glassdoor reviews
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# Bertimbau Finetuned Glassdoor Reviews
|
| 15 |
+
|
| 16 |
+
This project provides a Streamlit web application for classifying Glassdoor reviews into sentiment categories using a fine-tuned BERT model. The model is based on the pre-trained BERT model from [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) and fine-tuned on Glassdoor review data.
|
| 17 |
+
|
| 18 |
+
## Model
|
| 19 |
+
|
| 20 |
+
The model architecture and training process can be found at [glassdoor-reviews-analysis-nlp](https://github.com/stevillis/glassdoor-reviews-analysis-nlp).
|
| 21 |
+
|
| 22 |
+
## Installation
|
| 23 |
+
|
| 24 |
+
To run this project locally, follow these steps:
|
| 25 |
+
|
| 26 |
+
1. Download the [pytorch_model.bin](https://huggingface.co/stevillis/bertimbau-finetuned-glassdoor-reviews/blob/main/pytorch_model.bin) from `stevillis/bertimbau-finetuned-glassdoor-reviews`.
|
| 27 |
+
|
| 28 |
+
2. Clone the repository:
|
| 29 |
+
```sh
|
| 30 |
+
git clone https://github.com/your-username/bertimbau-finetuned-glassdoor-reviews.git
|
| 31 |
+
cd bertimbau-finetuned-glassdoor-reviews
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
3. Create a virtual environment and activate it:
|
| 35 |
+
```sh
|
| 36 |
+
python -m venv venv
|
| 37 |
+
source venv/bin/activate # On Windows, use `venv\Scripts\activate`
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
4. Install the required dependencies:
|
| 41 |
+
```sh
|
| 42 |
+
pip install -r requirements.txt
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
5. Move the **pytorch_model.bin** to `bertimbau-finetuned-glassdoor-reviews` directory.
|
| 46 |
+
|
| 47 |
+
6. Run the Streamlit application:
|
| 48 |
+
```sh
|
| 49 |
+
streamlit run app.py
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
## Usage
|
| 53 |
+
|
| 54 |
+
1. Open your web browser and go to `http://localhost:8501`.
|
| 55 |
+
2. Enter a Glassdoor review text in the input box.
|
| 56 |
+
3. The application will display the predicted sentiment and its corresponding score.
|