{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Histograms"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook shows how to generate histograms with various settings."
   ]
  },
  {
   "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, hist, McStack, DataStack, Stack\n",
    "from freeforestml import toydata, example_style\n",
    "example_style()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load or generate toy dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = toydata.get()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define processes to plot as deparate colors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p_ztt = Process(r\"$Z\\rightarrow\\tau\\tau$\", range=(0, 0))\n",
    "p_sig = Process(r\"Signal\", range=(1, 1))\n",
    "\n",
    "p_asimov = Process(r\"Asimov\", selection=lambda d: d.fpid >= 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define colors and how to stack the processes. Data should not be stacked on top of the MC prediction."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "colors = [\"windows blue\", \"amber\", \"greyish\", \"faded green\", \"dusty purple\"]\n",
    "palette = sns.xkcd_palette(colors)\n",
    "\n",
    "s_bkg = McStack(p_ztt, p_sig, palette=palette)\n",
    "s_data = DataStack(p_asimov)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define the variable to use on the x-axis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "v_higgs_m = Variable(r\"$m^H$\", \"higgs_m\", \"GeV\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 20, [s_bkg, s_data], range=(0, 200), selection=None,\n",
    "     weight=\"weight\",  ratio_label=\"Data / SM\")\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 22, [s_bkg, s_data], range=(75, 130), selection=None,\n",
    "     weight=\"weight\",  ratio_label=\"Data / SM\", include_outside=True)\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 20, [s_bkg, s_data], range=(0, 200), selection=None,\n",
    "     weight=\"weight\",  ratio_label=\"Data / SM\", y_log=True, numerator=None)\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 20, [s_bkg, s_data], range=(0, 200), selection=None,\n",
    "     weight=\"weight\", ratio_label=\"MC / Data\", y_log=True, y_min=1e-1,\n",
    "     vlines=[80, {'x': 100, 'color': 'b'}])\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s_sig = McStack(p_sig, color=palette[1], histtype='step')\n",
    "s_ztt = McStack(p_ztt, color=palette[0], histtype='step')\n",
    "\n",
    "hist(df, v_higgs_m, 20, [s_bkg, s_data], range=(40, 120), selection=None,\n",
    "     weight=\"weight\", ratio_label=\"Signal / Bkg\", y_log=True, y_min=1e-1,\n",
    "     vlines=[80, {'x': 100, 'color': 'b'}], numerator=s_sig, denominator=s_ztt)\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 20, [s_bkg, s_data], range=(0, 200), selection=None,\n",
    "     weight=\"weight\", ratio_label=\"Data - Bkg\", y_log=True, y_min=1e-1, diff=True,\n",
    "     enlarge=1.5,\n",
    "     vlines=[80, {'x': 100, 'color': 'b'}], numerator=s_data, denominator=s_ztt)\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import freeforestml.plot as nnp\n",
    "nnp.INFO = \"$\\sqrt{s} = 13\\,\\mathrm{TeV}$, $140\\,\\mathrm{fb}^{-1}$\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 20, [s_bkg, s_data], range=(0, 200), selection=None,\n",
    "     weight=\"weight\",  ratio_label=\"Data / SM\")\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s_sig = McStack(p_sig, color=palette[1], histtype='step')\n",
    "s_ztt = McStack(p_ztt, color=palette[0], histtype='step')\n",
    "\n",
    "hist(df, v_higgs_m, 20, [s_sig, s_ztt], range=(0, 200), selection=None,\n",
    "     weight=\"weight\",  numerator=None, density=True)\n",
    "None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist(df, v_higgs_m, 30, [s_bkg, s_data], range=(25, 175),\n",
    "     selection=None, numerator=[s_ztt, s_sig], denominator=s_data,\n",
    "     weight=\"weight\",  ratio_label=\"Process / Asimov\")\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
}