ML-Practice

Welcome to my personal Machine Learning and Deep Learning hub.

This repository is not intended as a tutorial or a course. This is just a learning playground, where I implement and experiment with ML concepts, and occasionally try Deep Learning architectures.

---

Topics:

Data Analysis and Preprocessing

• Basic Data Pre-processing
• Explanatory Data Analysis
• Feature Engineering

Machine Learning

• Linear Regression
• Logistic Regression
• K-Nearest-Neighbours
• Decision Trees
• Random Forest
• K-Means Clustering
• Support Vector Machines
• Gradient Boosting Algorithms
• Hyperparameter Tuning
• Model Evaluation
• Data Imbalance Handling
• Pipelines

Deep Learning

• Neural Networks (Perceptrons)
• Convolutional Neural Networks (CNN)
• Recurrent Neural Networks (RNN)
• Gated Recurrent Units (GRU)
• Long Short-term Memory (LSTM)
• Transformers

Long-term Plan

• Natural Language Processing
• Computer Vision

---

Dataset Index

Dataset	Source	Used In
Titanic Dataset	Kaggle	Day-02, Day-18
Student Scores	Kaggle	Day-03, Day-12
Breast Cancer Dataset	Kaggle	Day-04, Day-09, Day-13
Diabetes Dataset	GitHub	Day-05, Day-10, Day-17
Iris Dataset	UCI	Day-06
MNIST	HuggingFace	Day-01, Day-07, Day-14
Wine Quality (Red)	UCI	Day-08, Day-13
Ames Housing Dataset	Kaggle	Day-12
Credit Card Fraud Dataset	Kaggle	Day-11
Tiny Shakespeare	GitHub	Day-15, Day-16
Surname Nationality	Kaggle	Day-20

---

Structure

Each Day-XX-* directory represents a concept/topic. Inside, you’ll find:

• .py scripts implementing the concept.
• Output plots or visualizations (when applicable)
• Sample datasets (if required)
• A requirements.txt file, to install the required dependencies.
• A per-topic README.md that gives a quick summary.

Environment

If you want to try out any implementation in this repository, you can,

• Clone the repository,

  git clone https://github.com/IshaqJunejo/ML-Practice.git

• Navigate to your concerned implementation, and make sure you have installed dependencies using pip install -r requirements.txt, preferably in a virtual environment.
• And run the code.

Note: Each Day-XX-* directory may use different Python packages. Refer to the imports in the individual scripts.

Notes

• This is mostly self-supervised learning from multiple sources (YouTube, and ChatGPT suggestions).
• .py scripts are used instead of .ipynb notebooks due to personal preferences.
• The number of Days seen in the directory naming may be misleading. Some "Day"s took longer than a day, and some came after a lazy break.

License

This is a personal practice laboratory, so feel free to use for your own learning.