This repository contains my work from the Data Analytics & Machine Learning module, focusing on practical applications of machine learning, deep learning, and natural language processing (NLP) using Python and Google Colab.
Throughout the course, I learned how to clean real-world datasets, build ML and DL models, perform NLP preprocessing, evaluate performance metrics, and apply AI techniques to solve meaningful problems.
- Classification models (Decision Tree, Logistic Regression, etc.)
- Handling imbalanced datasets
- Model evaluation (Accuracy, Precision, Recall, F1, ROC–AUC)
- Recurrent Neural Networks (RNN)
- LSTM-based sequence models
- Embedding layers, regularization, dropout
- Overfitting control (EarlyStopping, ReduceLROnPlateau)
- Text cleaning & tokenization
- Stopword removal
- Padding / truncation
- Sequence modelling for text classification
- Python, Google Colab
- Pandas, NumPy
- TensorFlow / Keras
- scikit-learn
- NLTK
- Matplotlib / Seaborn
A text-classification project that predicts Normal vs Depressed statements using:
- Decision Tree (ML)
- RNN/LSTM (Deep Learning)
📁 Folder: /Mental Health Sentiment Analysis/
Contains the exam-based ML/NLP tasks, dataset, and Colab notebook.
📁 Folder: /Exam/
✨ Thank you for visiting this DAML project repository!