{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Confusion Matrix"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook illustrates how to create a confusion matrix plot directly from a dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "\n",
    "from freeforestml import Variable, Process, Cut, confusion_matrix, HistogramFactory\n",
    "from freeforestml import toydata, example_style\n",
    "example_style()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = toydata.get()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p_sig = Process(r\"Signal\", range=(1, 1))\n",
    "p_ztt = Process(r\"$Z\\rightarrow\\tau\\tau$\", range=(0, 0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c_low = Cut(lambda d: d.m_jj  < 350, label=\"Low $m^{jj}$\")\n",
    "c_mid = Cut(lambda d: (d.m_jj >= 350) & (d.m_jj  < 600), label=\"Mid $m^{jj}$\")\n",
    "c_high = Cut(lambda d: d.m_jj  > 600, label=\"High $m^{jj}$\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Normalized columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "confusion_matrix(df, [p_sig, p_ztt], [c_low, c_mid, c_high],\n",
    "                 y_label=\"Region\", x_label=\"Truth Signal\", annot=True, weight=\"weight\")\n",
    "None"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Normalized rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "confusion_matrix(df, [p_sig, p_ztt], [c_low, c_mid, c_high], normalize_rows=True,\n",
    "                 y_label=\"Region\", x_label=\"Truth Signal\", annot=True, weight=\"weight\")\n",
    "None"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}