Inspiration
To classify text messages as spam or ham using machine learning and natural language processing.
What it does
The model detects whether a given text message is spam or not, using NLP techniques and classification algorithms.
How I built it
I used Python, Pandas, NumPy, scikit-learn, and Streamlit. The dataset was processed using TF-IDF vectorization and a classification model was trained.
Challenges I ran into
Cleaning and preprocessing noisy text data. Choosing the right vectorization technique. Tuning hyperparameters to get better model performance.
Accomplishments that I'm proud of
Successfully deployed a working spam-ham detection model. Learned end-to-end NLP workflow. Completed full deployment using Streamlit.
What I learned
Applied NLP techniques for real-world text classification. Learned to use TF-IDF vectorization for feature extraction. Understood how to train, evaluate, and fine-tune classification models. Practiced deploying ML models using Streamlit. Improved my Python, scikit-learn, and data preprocessing skills. Gained confidence in building end-to-end AI/ML projects.
What's next for Spam Ham Detection
Improve model accuracy with deep learning. Deploy using cloud services. Build a proper UI for real-world users.
Built With
- natural-language-processing
- numpy
- pandas
- python
- scikit-learn
- streamlit
- tf-idf
