This project implements a Neural Network Classifier for Spam Classification, achieving 98% accuracy and deployed on AWS. It covers the complete lifecycle of an ML project from data collection to deployment.
This project focuses on building and deploying a machine learning model for spam email classification using a Neural Network. Key phases of the project include:
- Data Collection: Utilized a dataset of spam and non-spam emails for training the classifier.
- Data Preprocessing: Cleaned and prepared the dataset for model training.
- Model Training: Developed a Neural Network model using TensorFlow/Keras to classify emails.
- Model Evaluation: Evaluated the model's performance using metrics like accuracy, precision, recall, and F1-score.
- Model Deployment: Deployed the trained model on AWS using Streamlit for interactive web application deployment.
The motivation behind this project is to demonstrate the end-to-end process of deploying a machine learning model, emphasizing the importance of deployment skills for aspiring Data Scientists and ML engineers.
- Python: Programming language used for data preprocessing, model training, and deployment.
- TensorFlow/Keras: Deep learning framework used to build and train the Neural Network model.
- Streamlit: Used for building and deploying the web application for model inference.
- AWS (Amazon Web Services): Cloud platform used for model deployment.
- Joblib: Library used for saving and loading models.
- Scikit-learn: Used for various machine learning utilities including metrics calculation and data preprocessing.
- NLTK and WordCloud: Used for natural language processing and visualization tasks.
For any issues or questions related to this project, feel free to reach out through the following channels:
- Kaggle: Kaggle Notebook 📊
- LinkedIn: LinkedIn Profile 👔
- Medium: Medium Blog ✍️
Your feedback and contributions are greatly appreciated!
By N Sai Harshith Varma