In this repo i have created a SMS Spam Prediction project in machine learning using NLP, and i am using nltk Library for NLP. Deployment on Heroku app.
- Day by day people get a lot of sms, In those sms include are spam and helpful message. In today's runaway life we don't have enough time to recognize these sms whether it is spam or not, so i have develop a machine learning programme using kaggle dataset which will split the sms. Hope this programme are helpful for you.
1). Run all command manually
- Clone github repository in your local system
git clone https://github.com/yogeshnile/spam-sms-detector.git
- Move in spam-sms-detector repository
cd spam-sms-detector
- Create new virtual python environment
python3 -m venv venv
- Activate virtual python environment
source venv/bin/activate
- Install all the libraries mentioned in requirements.txt using
pip install -r requirements.txt
- Run FlaskApp file
python app.py
- Go to your browser and type http://127.0.0.1:5000/ in the address bar.
- Hurray! That's it.
2). Run Shell Script
- Clone github repository in your local system
git clone https://github.com/yogeshnile/unix.git
- Give execute permission to spam-sms-detector.sh file via
chmod +x spam-sms-detector.sh
- Run spam-sms-detector.sh file using
./spam-sms-detector.sh
- Go to your browser and type http://127.0.0.1:5000/ in the address bar.
- Finished...
.
├── app.py
├── corpus.pkl
├── Images
│ ├── 1.png
│ ├── 2.png
│ └── 3.png
├── LICENSE
├── model_creation.py
├── nltk.txt
├── Procfile
├── README.md
├── requirements.txt
├── Spam SMS Collection
├── Spam_sms_prediction.pkl
├── static
│ ├── css
│ │ └── main.css
│ ├── icon
│ │ └── icon.ico
│ ├── js
│ │ └── global.js
│ └── vendor
│ └── jquery
│ ├── jquery.js
│ └── jquery.min.js
└── templates
└── index.html
8 directories, 19 files
If you find a bug (the website couldn't handle the query and / or gave undesired results), kindly open an issue here by including your search query and the expected result.
If you'd like to request a new function, feel free to do so by opening an issue here. Please include sample queries and their corresponding results.
Known on internet as Yogesh Nile