A python jupyter notebook which will train machine learning models to detect Spam messages.The project is hosted at streamlit app on the web.
- Data cleaning.
- Data preprocessing.
- Extensive data analysis.
- Text vectorization using Bag of words , Tf-idf , Word2Vec encoding.
- 8 classification model training using pipeline.
- Above 95% accurate and precise.
- Hosting using Streamlit.
You need python installed in your system to run this repository.
Install the dependencies from the requirements.txt.
pip install -r requirements.txtTo host the project locally , run app.py with the help of streamlit.
streamlit run app.pyThe project has some drawbacks.
- Does not have 100% accuracy and percision.
- Model building requires lot of memory (1.5GB).
- Longer training period.
- Might throw exceptions.
- Email : pratham20442@gamil.com
- github : https://github.com/pratham-ak2004
- linkedin : https://www.linkedin.com/in/pratham-a-kadekar-8397a7249/