ezyml 1.2.1

A lightweight tool to train, evaluate, and export ML models in one line.

📦 ezyml 🚀

From raw data to a trained model — in just one line of code.

---

🌟 Why ezyml?

ezyml is a lightweight, high-level Python library and CLI tool that automates the most tedious parts of your ML pipeline — so you can focus on what matters. Whether you're building a classifier, a regressor, or just exploring data, ezyml does the heavy lifting.

✅ Key Features

• 🪄 Auto-Pilot Mode – Detects task type (classification, regression, etc.) automatically.
• 🧹 Smart Preprocessing – Handles missing values, encodes categories, and scales features out of the box.
• 🧰 20+ Models – Pre-integrated models from scikit-learn and xgboost.
• 💾 One-Line Export – Save your model as .pkl and performance report as .json.
• 📉 Dimensionality Reduction – Easily visualize data using PCA or t-SNE.
• 🧪 Dual Interface – Use as a Python package or from the command line.

---

📦 Installation

Install via pip:

pip install ezyml

---

🚀 CLI Quickstart

🧠 Train a Classifier

ezyml train \
  --data titanic.csv \
  --target Survived \
  --model extra_trees \
  --output titanic_model.pkl

📈 Train a Regressor

ezyml train \
  --data housing.csv \
  --target price \
  --model ridge \
  --output house_price_model.pkl

📉 Run PCA

ezyml reduce \
  --data features.csv \
  --model pca \
  --components 2 \
  --output pca_data.csv

---

🧪 Python API Example

▶️ Classification

from ezyml import EZTrainer

# 1. Initialize
trainer = EZTrainer(data='heart.csv', target='label', model='naive_bayes')

# 2. Train
trainer.train()

# 3. Save Results
trainer.save_model('heart_model.pkl')
trainer.save_report('heart_report.json')

🔍 Dimensionality Reduction (PCA)

from ezyml import EZTrainer

pca_trainer = EZTrainer(
    data='high_dim.csv',
    model='pca',
    task='dim_reduction',
    n_components=2
)

pca_trainer.train()
pca_trainer.save_transformed('pca_output.csv')

---

🧰 Supported Models

Task	Models
Classification	logistic_regression, random_forest, xgboost, svm, naive_bayes, gradient_boosting, extra_trees, knn
Regression	linear_regression, ridge, lasso, elasticnet, random_forest, xgboost, svr, gradient_boosting
Clustering	kmeans, dbscan, agglo (Agglomerative Clustering)
Dimensionality Reduction	pca, tsne

---

📜 License

MIT License – View License

---

👨‍💻 Author

Built with ❤️ by Raktim Kalita

---