Skip to content

Auto-ML

Upload a CSV, pick a target column — Auto-ML trains 5 models and picks the best one. Powered by scikit-learn running in your browser via Pyodide.

Features

  • Auto-detection — determines classification vs regression from target column
  • 5 algorithms compared:
    • Classification: Logistic Regression, Random Forest, Gradient Boosting, KNN, SVM
    • Regression: Linear Regression, Random Forest, Gradient Boosting, SVR, KNN
  • Results table — accuracy, precision, recall, F1 (or R², MAE, MSE)
  • Feature importance — bar chart from tree-based models
  • Test predictions — enter values, predict with best model
  • Export — download best model as pickle

How it works

  1. Drop a CSV file
  2. Select target column
  3. Select feature columns (auto-excludes non-numeric)
  4. Click "Run Auto-ML"
  5. Wait ~30-120 seconds while 5 models train
  6. See comparison table with best model highlighted
  7. Test predictions and export

Technical details

  • Runs full CPython via Pyodide (WebAssembly)
  • scikit-learn, pandas, numpy loaded in-browser
  • First load downloads ~15 MB of packages (cached after)
  • Handles up to ~100K rows comfortably