🤖 Modular AutoML Framework
A lightweight, modular Automated Machine Learning (AutoML) system built in Python. This project automates the end-to-end machine learning lifecycle—from data preprocessing and feature engineering to model training and hyperparameter optimization—while retaining the flexibility for manual control.

🚀 Key Features
Dual Execution Modes:

Full Auto: One-click pipeline execution (Preprocess → Train → Report).

Manual Control: Step-by-step execution to inspect data state at every stage.

Intelligent Preprocessing: Automatically detects data types, handles missing values (imputation), scales numeric features, and one-hot encodes categorical variables.

Multi-Model Optimization: simultaneously trains and tunes multiple algorithms:

Logistic Regression

Random Forest

Decision Trees

XGBoost

Modular Architecture: Clean separation of concerns (model_zoo, optimizer, preprocessing) making it easy to add new models or logic.