Spam message detection using Keras

By ADIL SHAIKH

This project is used for detecting if a message is spam provided there are certain words present in the message using RNN(Recurrent Neural Networks) through the Keras framework.

This can be used to detect spam messages after a person has received them and automatically classify them and decide if they should be read.

This project uses the following libraries:

REQUIREMENTS:

1. TensorFlow 

2. Python 

3. Keras 

4. pandas

 

USAGE :

You must have Jupyter notebook installed in your pc.

There are 2 ways to use the given zip file:

1) Directly use the Keras model saved 'spam_predict.h5' in your own personal prediction model. This is present in the zip folder

2) Train using your own dataset by changing the dataset file location at "df = pd.read_csv("/home/adil/python3_dir/spam_detection/dataset/spam_or_not_spam.csv" to suit your purpose. This will also help you visualize the data present in your own dataset. Run the file "spam_detection.ipynb. The code has been explained inside the file.

 

NOTE: IF TRAINING ON YOUR OWN DATASET DONT FORGET TO CHANGE THE FILE PATH

"df = pd.read_csv("/home/adil/python3_dir/spam_detection/dataset/spam_or_not_spam.csv"