How mohammedghennai/spam-emails-classification-approaches works
This repository is a collection of notebook-based approaches to spam email classification. A user’s broad workflow is to explore a notebook implementing an approach; filenames identify several model families, but the README does not describe notebook execution, data flow, or how the CSV files are used. With no source excerpts, those relationships are left unspecified.
Main entry points: LSTM_1.ipynb LSTM experiment · RiadLSTM.ipynb Riad LSTM · mail_spam_RNN.ipynb Mail spam RNN · XGboost_implementation.ipynb XGBoost approach
Components 10
Recurrent models
- LSTM experiment
LSTM_1.ipynb - Riad LSTM
RiadLSTM.ipynb - Mail spam RNN
mail_spam_RNN.ipynb
Other approaches
- XGBoost approach
XGboost_implementation.ipynb - BERT classification
bert_nlp_classification.ipynb - Riad models
RiadModels.ipynb - Spam ham classifier
spam-mail-classifier.ipynb
CSV files
- Spam ham dataset
spam_ham_dataset.csv - Additional CSV
xx.csv
Other components
- Explorer
Connections 7
- Explorer → LSTM experiment: explores
README.md - Explorer → Riad LSTM: explores
README.md - Explorer → Mail spam RNN: explores
README.md - Explorer → XGBoost approach: explores
README.md - Explorer → BERT classification: explores
README.md - Explorer → Riad models: explores
README.md - Explorer → Spam ham classifier: explores
README.md