🧠 Machine Learning & Deep Learning Portfolio

A comprehensive Python portfolio demonstrating foundational Machine Learning algorithms, Data Preprocessing techniques, and Deep Learning models.

Demonstrating hands-on implementations of regression, classification, clustering, and computer vision using popular data science libraries.

---

✨ Features

• Python Fundamentals: Object-Oriented Programming (Single, Multi-level, Hierarchical, Multiple Inheritance), Dictionary manipulations, and Numpy Vector operations.
• Data Wrangling: Filtering, slicing, and summary statistics using Pandas.
• Regression Analysis: Linear Regression and Polynomial Regression (up to Degree 10) for continuous predictions.
• Clustering: Unsupervised learning using K-Means Clustering, evaluated with the Elbow Method.
• Classification: Predicting categories using K-Nearest Neighbors (KNN), Gaussian Naive Bayes, and Logistic Regression.
• Computer Vision: A Convolutional Neural Network (CNN) built with Keras for MNIST handwritten digit classification.
• Evaluation Metrics: Implementation of K-Fold Cross Validation, Confusion Matrices, and Accuracy Scoring.

---

🛠️ Tech Stack & Architecture

This project utilizes standard Python data science and machine learning libraries:

Core Python	Data Manipulation	Visualization	Machine Learning	Deep Learning
Python 3.8+	Pandas	Matplotlib	Scikit-Learn	TensorFlow
NumPy	SciPy	Seaborn		Keras

---

📂 Project Modules

The repository is broken down into standalone scripts for easy execution.

Script	Description
01_pandas_filtering.py	Data exploration, statistical summaries, and conditional filtering.
02_regression_models.py	Predicts outputs using Linear and Polynomial regression models.
03_kmeans_clustering.py	Segments customer data into clusters based on spending habits.
04_classification_models.py	Compares KNN, Naive Bayes, and Logistic Regression accuracies.
05_mnist_cnn.py	Trains a CNN model to recognize image data with high accuracy.
06_python_basics.py	Demonstrates Python fundamentals like Object-Oriented Programming, Dictionaries, and Vector math.

---

⚙️ Quick Start & Installation

Click to view installation instructions

1. Clone the repository

   git clone [https://github.com/yeshagevariya/machine-learning-experiments.git](https://github.com/yeshagevariya/machine-learning-experiments.git)

2. Navigate to the project directory

   cd machine-learning-experiments

3. Install dependencies

   pip install -r requirements.txt

4. Run any script

   python 04_classification_models.py

---

🗂️ Project Structure

    machine-learning-experiments/
    │
    ├── datasets/
    │   ├── Air_Traffic.csv
    │   ├── car_data.csv
    │   ├── data.csv
    │   ├── diabetes.csv
    │   ├── glass.csv
    │   ├── Iris.csv
    │   ├── Mall_Customers.csv
    │   ├── play_data.csv
    │   ├── Salaries.csv
    │   ├── Salary_Data.csv
    │   ├── Social_Network_Ads.csv
    │   ├── tech_sup_data.csv
    │   ├── titanic.csv
    │   └── weight-height.csv
    │
    ├── .gitignore
    ├── requirements.txt
    ├── README.md
    │
    ├── 01_pandas_filtering.py
    ├── 02_regression_models.py
    ├── 03_kmeans_clustering.py
    ├── 04_classification_models.py
    ├── 05_mnist_cnn.py
    └── 06_python_basics.py

---

👩‍💻 Author

Yesha Gevariya

Frontend Engineer building modern web applications and AI-powered products.

Specialized in: React.js Next.js TypeScript JavaScript Node.js REST APIs AI Integration RAG LLM Applications

🔗 Connect With Me

📄 License

This project was created for educational and professional development purposes.