Machine Learning Portfolio

This portfolio showcases various machine learning projects and techniques implemented during my studies. The projects demonstrate proficiency in different areas of machine learning, from basic classification to advanced techniques, big data processing, and deployment.

Project Structure

1. Machine Learning Techniques

This directory contains assignments demonstrating various machine learning algorithms and techniques:

• Perceptron_Adaline_Classification_Assn_1.ipynb

  • Implementation of Perceptron and Adaline algorithms
  • Binary classification on the Iris dataset
  • Includes data preprocessing and visualization

• Logistic_Regression_Network_Intrusion_Assn_2.ipynb

  • Network intrusion detection using Logistic Regression
  • Handling imbalanced data
  • Feature engineering and preprocessing

• SVM_Network_Intrusion_Assn_3.ipynb

  • Support Vector Machine implementation
  • Advanced classification techniques
  • Performance comparison with previous models

• Advanced_ML_Techniques_Assn_4.ipynb

  • Advanced machine learning techniques
  • Model evaluation and optimization
  • Complex classification problems

2. Spark Big Data

• Spark.ipynb
  • Apache Spark implementation
  • Big data processing and analysis
  • Distributed computing concepts
  • Data manipulation with PySpark

3. Docker Deployment

• preprocessing_predict.py

  • Production-ready preprocessing pipeline
  • Model prediction implementation
  • Clean, modular code structure

• Dockerfile.txt

  • Containerization configuration
  • Environment setup
  • Deployment specifications

Technologies Used

• Python
• Scikit-learn
• PySpark
• Docker
• Jupyter Notebooks
• Pandas
• NumPy
• Matplotlib/Seaborn

Getting Started

1. Clone the repository
2. Install required dependencies (see requirements.txt)
3. Navigate to specific project directories for detailed instructions