This project focuses on building a machine learning model to classify emails as spam or not spam using a Support Vector Machine (SVM) classifier. The dataset contains features extracted from email text content, and the model is trained to effectively distinguish between spam and legitimate emails.
├── Email Spam Detection - Vector machines.ipynb
├── README.md
├── data/
│ └── spam_dataset.csv (or relevant dataset)
├── models/
│ └── svm_model.pkl-
Python
-
Jupyter Notebook
-
Scikit-learn
-
NumPy
-
Pandas
-
Matplotlib / Seaborn (for visualization)
-
The dataset includes features derived from email contents such as:
-
Frequency of specific keywords
-
Capital letter usage
-
Special character frequency
-
Each email is labeled as:
-
1 → Spam
-
0 → Not Spam
-
- Clone the Repository
git clone https://github.com/RAVINDRAN-S/Email_Spam_Detection_using_vector_machines
cd email-spam-detection-svm- Install Dependencies
pip install -r requirements.txt
Run the Notebook- Open Email Spam Detection - Vector machines.ipynb in Jupyter Notebook and run all cells.
-
Algorithm: Support Vector Machine (SVM)
-
Kernel Used: Linear
-
Evaluation Metrics:
-
Accuracy : 99%
-
Precision : 0.99
-
Recall : 1.00
-
F1-Score : 1.00
-
The SVM model achieved high accuracy in detecting spam emails.
-
Confusion matrix and classification report are used to interpret model performance.
-
How to preprocess and clean text data for ML tasks.
-
Implementing SVM for binary classification.
-
Evaluating model using various performance metrics.
-
Visualizing results for better interpretation.
-
Use more advanced NLP techniques (e.g., TF-IDF, Word2Vec).
-
Test with other classifiers (e.g., Naive Bayes, Random Forest).
-
Build a web interface for real-time email classification.
Developer • ML Enthusiast • Neovim Customizer • Linux Power User
Hi! I'm Ravindran S, an engineering student passionate about:
- Linux & System Engineering
- AIML (Artificial Intelligence & Machine Learning)
- Full-stack Web Development
- Hackathon-grade project development
You can reach me here: