📊 Predict apartment rental prices in Tel Aviv using machine learning models, featuring Elastic Net and Decision Trees for accurate forecasting.

A HDF5-based pickle-like library for object serialization.

📘 dict subclass with keylist/keypath support, built-in I/O operations (base64, csv, html, ini, json, pickle, plist, query-string, toml, xls, xml, yaml), s3 support and many utilities.

A Gherkin/Pickle linter written in javascript

Caching and distributed locks in your applications with just one or two lines. Easy to learn. Fast to code.

Simple text classifier

This system is a machine learning-based web application built with Python, Scikit-learn, and Flask that predicts the calorie expenditure based on various features such as Weight, Height, Body Temperature, and Heart Rate.

A production-ready microservice that exposes a Machine Learning model (serialized via Pickle) as a REST API for predicting income based on key professional features. The Flask API is served using Gunicorn and deployed to a public cloud environment (Render), allowing for global consumption via HTTP endpoints.

Python library for serializing any arbitrary object graph into JSON. It can take almost any Python object and turn the object into JSON. Additionally, it can reconstitute the object back into Python.

Drop-in pickle replacement with transparent compression - smaller files, same API

💬 An AI-powered medical chatbot that supports English, Hindi, Marathi, and Bengali. It uses semantic search, language detection, and confidence scoring to deliver accurate health-related answers. Developed by Manish Kumar Rajak

MoneyLion DS Assessment

A simple and elegant task manager built with PySide6 (Qt for Python) featuring a modern dark theme and persistent storage.

Early Risk Signals: Credit Card Delinquency Watch - AI-powered predictive analytics for proactive credit risk management. Machine learning models (Random Forest & Gradient Boosting) analyze behavioral patterns to identify at-risk customers before default, enabling 30-40% reduction in losses.

churn classification model using random forest and xgboost , prediction and deployment using streamlit

FastAPI model machine learning yang memprediksi apakah seseorang memiliki kesempatan lebih besar untuk berlangganan atau tidak (target y bernilai binary “yes”/”no” ).

Persistent, stale-free, local and cross-machine caching for Python functions.

Simple extensive tar-like archive format with indexing

A simple immutable dictionary for Python