There are 3 phases in this project.

Required Libraries Download following libraries:

1. pip install flask
2. pip install numpy
3. pip install nltk
4. pip install scipy
5. pip install sklearn
6. pip install Flask-Images
7. pip install image
8. pip --default-timeout=60 install "tensorflow-gpu>=1.19,<2"

Steps to run and deploy in localhost

1. Install flask in your environment.
2. Download this repo to a folder
3. Navigate upto the 'app' directory
4. from a console run the app.py file by the command python app.py
5. Hit localhost:5000 in browser.

Main.py can be used to run the two pythons files. One is for tf-idf and other is for classification. Keep the pickle files with the main folder to get the fast results

Clone the repository : $ git clone --bare https://github.com/ruchirchugh/Data-Mining.git

References:

https://nlp.stanford.edu/IR-book/pdf/13bayes.pdf https://gist.github.com/adolfoguimaraes/91fbef8beceabafdcef2b407639290d4 https://www.geeksforgeeks.org/python-lemmatization-with-nltk/