Data Science

React Tailwind CSS Framer Motion Plotly.js

Full-stack music streaming platform with ML-powered song recommendations, real-time chat, and comprehensive music library management.

🤖

LangChain Tutorial

LangChain LangChain OpenAI LangChain Core OpenAI GPT-3.5-turbo

Comprehensive tutorial on LangChain framework for building LLM applications, featuring OpenAI integration, prompt templates, chains, and LangSmith tracing.

❤️

Heart Disease Data Preprocessing

Pandas NumPy Scikit-learn Pipeline

Comprehensive data preprocessing project for Heart Disease UCI dataset with type-specific pipelines, EDA, and scikit-learn preprocessing workflows.

🩺

Heart Disease KNN Modeling

Scikit-learn KNeighborsClassifier GridSearchCV RandomizedSearchCV

k-NN classifiers on Heart Disease UCI dataset: baseline preprocessed data vs KNN-imputed data, with GridSearchCV/RandomizedSearchCV tuning and full evaluation.

🧪

Heart Disease Modeling (ML3)

Scikit-learn SVC/LinearSVC LDA GridSearchCV

Heart disease classification with KNN-imputed preprocessing, SVM (LinearSVC/SVC), and LDA tuned via GridSearchCV/RandomizedSearchCV.

📈

Heart Disease Naive Bayes & Logistic Regression

GaussianNB CategoricalNB MixedNB LogisticRegression

Comprehensive ML project comparing Naive Bayes variants (Gaussian, Categorical, Mixed) and Logistic Regression for heart disease prediction with extensive hyperparameter tuning.

🐦

Twitter Text Preprocessing & Prediction

NLTK spaCy Naive Bayes Logistic Regression

Comprehensive NLP project for Twitter text data, focusing on preprocessing, feature extraction, and prediction models for text classification or sentiment analysis.

💎

Twitter Classification & Diamond Price Prediction

RandomForestClassifier Regression Models MinMaxScaler OrdinalEncoder

Dual-task ML project combining Twitter text classification using Random Forest and diamond price prediction using regression models, with comprehensive feature engineering and evaluation.

✈️

Airline Data Analysis - Multi-Task ML

GaussianNB CategoricalNB LinearSVC LogisticRegression

Comprehensive ML project analyzing airline data with binary classification, multi-class classification, and regression tasks, comparing multiple algorithms with extensive evaluation and model selection.

🌍

Country Anthems Clustering & Analysis

NLTK Unidecode Regular Expressions KMeans

Unsupervised learning project analyzing 190 country anthems using text clustering techniques with advanced NLP preprocessing, TF-IDF vectorization, and multiple clustering algorithms.

🎵

Audio Extraction & Speech Transcription

MoviePy PyDub FFmpeg Speech Recognition

Audio processing and speech-to-text transcription project that extracts audio from video sources, converts between formats, and transcribes speech using Google Speech Recognition API.

📊

Fatal Police Shootings Data Analysis

Pandas NumPy xlrd Matplotlib

Comprehensive data analysis study of fatal interactions between law enforcement and citizens in the USA (2015-2024), including statistical analysis, geographic visualization, and temporal trends.

PyTorch TensorFlow Transformers GPT

🎷

Jazz Music Generation with GPT and GAN

2025

Deep learning project exploring two approaches to jazz music generation: GPT-based sequence models and Generative Adversarial Networks (GANs), working with jazz MIDI files to generate new compositions.

MLflow Prefect Great Expectations FastAPI

⚙️

MLOps - Machine Learning Lifecycle Management

2025

Complete MLOps pipeline integrating Great Expectations for data validation, Prefect for workflow orchestration, and MLflow for experiment tracking and model management.

🎌

Anime Recommendation System

Comprehensive recommendation system for anime using MyAnimeList data, implementing collaborative filtering, content-based filtering, and user similarity approaches with multiple algorithms and evaluation metrics.

Surprise KNN SVD SVD++

🤖

Deep Learning - Sign Language Classification

TensorFlow Keras CNN VGG16

Comprehensive deep learning project for sign language alphabet recognition using Sign Language MNIST dataset, implementing custom CNN architectures, VGG16 transfer learning, data augmentation, and hyperparameter optimization.

🔍

Qdrant Vector Database

Qdrant Docker Python 3.11+ Poetry

Comprehensive project demonstrating the setup and usage of Qdrant, a high-performance vector database for applications working with embeddings, including local Docker deployment, collection management, and similarity search operations.

🔍

EasySearch - Local RAG

LangChain LangChain Community LangChain HuggingFace LangChain Qdrant

Local Retrieval Augmented Generation (RAG) application for querying documents using natural language, with fully local processing ensuring data privacy and confidentiality.