Metadata-Version: 2.1
Name: lazytrainer
Version: 0.1.0
Summary: lazyml: Because training ML models shouldn’t need more energy than your morning coffee.
Author: Mr. Phantom
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Requires-Python: >=3.7
Description-Content-Type: text/markdown

# LazyTrainer

**Train your regression models with zero drama.**  
LazyTrainer helps you get started with machine learning model training in the simplest way possible — no unnecessary complications.

---

## Why LazyTrainer?

This project was created by **MrFayntom** with a clear goal in mind:

> "I made LazyTrainer for beginners who want to train machine learning models but feel overwhelmed by all the complexity.  
> LazyTrainer wraps it up into a clean, lazy workflow so you can focus on *what matters* — learning and iterating."

---

## What it Does

- Automatically preprocesses your data
- Handles categorical encoding and scaling
- Trains a regression model (SGD for now)
- Evaluates performance (MAE, R², Accuracy)
- Plots predictions
- Saves the model, scaler, and encoders

---

## Installation

```bash
pip install lazyml
```
---

# LazyML – Quick Start Guide

For full details, visit the official GitHub repository:  
: [https://github.com/mrfayntom/LazyML](https://github.com/mrfayntom/LazyML)

---

## Minimal Workflow Example

```python
from lazyml.trainer import LazyTrainer

# Initialize the trainer
trainer = LazyTrainer(
    data_path="path/to/your/data.csv",          # Path to your CSV file
    target_col="TargetColumn",                  # Column name you want to predict
    features=["Feature1", "Feature2", "Feature3"],  # List of input feature column names
    categorical_cols=["Feature3"]               # List of categorical feature names (if any)
)

# Train the model
trainer.train()

# Evaluate the model
trainer.evaluate()

# Plot prediction summary
trainer.plot_summary()

# Save model, scaler and encoders
trainer.save()
trainer.save_scaler()
trainer.save_encoders()
```
— **Mr. Phantom**


