CSV

Practical tasks on Deep Learning (DL) and Neural Networks (NN). 🤖

A production-oriented Machine Learning pipeline that predicts whether an active user session will result in a purchase.

Model: XGBoost Classifier optimized for class imbalance.

Performance: ROC AUC 0.936 | F1-score 0.71 (at 0.30 threshold).

Key Features: Reproducible environment (uv), modular CLI for training/inference, leakage-free preprocessing, and SHAP interpretability analysis.

Data: UCI Online Shoppers Purchasing Intention Dataset.

Tech Stack: Python, XGBoost, Scikit-learn, Pandas, SHAP.

The EDA (exploratory data analysis) repository consist of all the EDA related projects based on the real world datasets.

This repo will have all resources, labs, data which I use/d on Kaggle Network

Repository displaying the results of measurements of various Institute of Solar-Terrestrial Physics (ISTP) SB RAS instruments for the May 2024 geomagnetic storm

Performed Exploratory Data Analysis (EDA) on the Google Play Store dataset using Python. Leveraged pandas for data cleaning and matplotlib for visualizations to analyze categories, ratings, installs, pricing, and update frequency. Created clear charts and dashboard-style visuals to uncover trends driving app popularity and user satisfaction.

Data projects for WGU

An advanced Streamlit dashboard providing real-time and historical analytics for PayPal USD (PYUSD) on the Ethereum blockchain. This version (v2.1) is powered by Google Cloud Platform (GCP) Blockchain RPC, MongoDB for data caching, persistence, and search, a Google Gemini AI assistant, and a NewsAPI feed. It offers extensive event tracking (Transfers, Mint, Burn, Approvals), network graph visualization, historical analysis, address tagging, a MongoDB-backed watchlist, and a conceptual simulation of bio-implant payments.

This project explores the use of big data analytics and machine learning techniques to predict the likelihood of ICU admission among COVID-19 patients. It includes data cleansing, exploratory analysis, classification models, and clustering, implemented using Python (Pandas, Scikit-learn, Imbalanced-learn) and PySpark for distributed processing.

Official inference library for Mistral models

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

Extract-Metadata permet l'extraction de métadonnées à partir de bases de données tabulaires (au format .csv) et d’imagerie (au format DICOM). Les métadonnées extraites sont stockées au format JSON.

Predicting customer spending in international supermarket chain for loyalty program

Optimizing listing prices of houses by predicting home sale price given its characteristics

Using Python & SQL to analyze dataset containing every game from 2018-2019 English Premier League Soccer season

A comprehensive repository documenting my study work on Big Data Analytics, Machine Learning, and Python, as part of my coursework at IBA Karachi. This repository includes detailed notes, code snippets, and project files, providing insights into essential concepts and techniques for data analysis, modeling, and big data processing.

This project predicts house prices using machine learning models based on the King County House Sales dataset. It explores Simple Linear, Multiple Linear, Polynomial, and Ridge Regression models, comparing their performance in terms of accuracy. The best model identified is Polynomial Regression, achieving an R² score of 0.75.

This project aims to develop a robust and interpretable machine learning model for early detection of cyberattacks within network systems. By analyzing network traffic data and identifying patterns associated with malicious activities, the model strives to improve network security and prevent potential cyber threats.