{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quickstart\n",
    "This notebook demonstrates the simplest workflow: load models, create an ExplainToolkit, compute an explanation, and plot it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import skexplain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "estimators = skexplain.load_models()\n",
    "X, y = skexplain.load_data()\n",
    "\n",
    "print(estimators)\n",
    "print(f'X Shape : {X.shape}')\n",
    "print(f'y Skew : {y.mean()*100:.1f}%')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explainer = skexplain.ExplainToolkit(estimators=estimators, X=X, y=y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compute Permutation Importance\n",
    "The simplest explanation method — how much does model performance drop when a feature is shuffled?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "perm_imp = explainer.permutation_importance(n_vars=10, evaluation_fn='norm_aupdc')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explainer.plot_importance(data=perm_imp, panels=[('multipass', 'Random Forest')])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compute ALE Curves\n",
    "Accumulated Local Effects show how each feature affects predictions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ale = explainer.ale(features=['sfc_temp', 'temp2m', 'dwpt2m', 'sat_irbt'], n_bins=20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explainer.plot_ale(ale=ale)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Next Steps\n",
    "Explore the other notebooks for deeper dives into each method."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}