https://github.com/AVoss84/pdf_extract

Text classification based on PDF inputs
https://github.com/AVoss84/pdf_extract

classification fastapi nlp python streamlit

Last synced: about 2 months ago
JSON representation

Text classification based on PDF inputs

• Host: GitHub
• URL: https://github.com/AVoss84/pdf_extract
• Owner: AVoss84
• Created: 2022-12-27T12:41:00.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-04-30T13:31:21.000Z (over 1 year ago)
• Last Synced: 2024-04-17T00:19:52.110Z (5 months ago)
• Topics: classification, fastapi, nlp, python, streamlit
• Language: Jupyter Notebook
• Homepage:
• Size: 886 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Text classification based on PDF input data

## Package structure

```

.

├── environment.yml

├── logs

├── main.py

├── README.md

├── requirements.txt

├── src

│   ├── __init__.py

│   ├── notebooks

│   │   ├── fasttext_classifier.ipynb

│   │   └── naivebayes_classifier.ipynb

│   ├── pdf_extract

│   │   ├── config

│   │   ├── data

│   │   ├── resources

│   │   ├── services

│   │   └── utils

│   ├── setup.py

│   └── templates

└── stream_app.py

```

## Package installation

Create conda virtual environment with required packages 

```bash

conda env create -f environment.yml 

conda activate env_pdf

```

Install your package

```bash

python -m spacy download en_core_web_lg

python -m spacy download de_core_news_lg      # install large word embeddings

pip install -e src

``` 

Start REST API locally:

```bash

uvicorn main:app --reload --port 5000         # checkout Swagger docs: http://127.0.0.1:5000/docs 

``` 

Start streamlit app locally:

```bash

streamlit run stream_app.py     

```