- Demo
- Overview
- Motivation
- Technical Aspect
- Installation
- Directory Tree
- Technologies Used
- Team
- Credits
Link: https://spamnlpdemo.herokuapp.com/
This is an simple NLP project in which the model is able to predict the incoming mail whether it is spam or not spam(ham). As we seen in gmail automatically the mail is classified and stored in spam or inbox so this project is prototype.
As a Data Science enthusiast I am utilizing the lockdown period with implementing various machine learning and deep learning projects and try to do end to end projects,also writing blogs on my data science projects on medium (Link: https://medium.com/analytics-vidhya/implementing-lstm-for-stock-price-prediction-time-series-4c0c65bb493d/)
This project is divided into two part:
- Training a machine learning model.
- Building and hosting a Flask web app on Heroku.
- Used WordLammitizer and Stopwords.
- We can also perform Hyperparammeter tunning but using NaiveBayes the accuracy is all other parameter are having high rate
The Code is written in Python 3.7. If you don't have Python installed you can find it here. If you are using a lower version of Python you can upgrade using the pip package, ensuring you have the latest version of pip. To install the required packages and libraries, run this command in the project directory after cloning the repository:
pip install -r requirements.txt
├── static
│ ├── style.css
├── templates
│ ├── home.html
| ├── result.html
├── requirements.txt
├── Procfile
├── README.md
├── SMSSpamCollection.csv
├── app.py
├── nlp model.pkl
├── nlts.txt
├── transform.pkl
├── SpamClassifier.ipynb
Mayank Yogi