{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import datetime\n",
    "import exploration.dispersion as disp\n",
    "import matplotlib.pyplot as plt\n",
    "import statsmodels.formula.api as smf\n",
    "\n",
    "from analytics.basket_index import MarkitBasketIndex\n",
    "from analytics import on_the_run\n",
    "from statsmodels.graphics.regressionplots import plot_fit\n",
    "from pygam import LinearGAM, s, f, GAM\n",
    "from utils.db import dbengine\n",
    "\n",
    "serenitas_engine = dbengine('serenitasdb')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "value_date = (datetime.datetime.today() - pd.offsets.BDay(1)).date()\n",
    "start_date = datetime.date(2019,9,27)\n",
    "end_date = datetime.date(2020,1,30)\n",
    "index_type = 'HY'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Get Gini factor\n",
    "date_range = pd.bdate_range(end=value_date, freq='1B',periods=52*4)\n",
    "risk = disp.get_tranche_data(index_type, serenitas_engine)\n",
    "risk = risk[risk.index.get_level_values(0).isin(date_range)]\n",
    "gini_model, gini_calc = disp.create_models(risk, use_gini=True, use_log=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "to_plot_gini = gini_calc.xs(0, level='attach').groupby(['date', 'series']).nth(-1)\n",
    "to_plot_gini['dispersion'].unstack().plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "today = gini_calc.xs([value_date,33], level=['date','series'])\n",
    "today[['exp_percentage', 'predict_N', 'predict_preN', 'mispricing']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "to_plot = gini_calc.xs(0, level='attach')['mispricing']\n",
    "to_plot.reset_index(['index','tenor'], drop=True).unstack().plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_fit(gini_model[0], 'np.log(index_duration)')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Run a particular gini scenario\n",
    "scenario = gini_calc.loc(axis=0)[value_date,33,'HY','5yr',0]\n",
    "scenario['dispersion'] = .6\n",
    "scenario_disp = np.exp(gini_model[0].predict(scenario))\n",
    "mispricing = (scenario['exp_percentage'] - scenario_disp) * \\\n",
    "             scenario['index_expected_loss'] / \\\n",
    "             (scenario['detach_adj'] - scenario['attach_adj']) / \\\n",
    "             scenario['indexfactor'] * 10000\n",
    "mispricing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Let's use a GAM model instead?\n",
    "#only use the 5yr point for modeling\n",
    "equity = gini_calc.loc(axis=0)[:,:,[25,27,29,31,33],'5yr',0]\n",
    "X = np.array(equity[['gini_spread', 'duration', 'moneyness']])\n",
    "y = np.array(equity['exp_percentage'])\n",
    "\n",
    "#Fit for Lamda\n",
    "gam_model = GAM(s(0, n_splines=5) +\n",
    "                  s(1, n_splines=5) +\n",
    "                  s(2, n_splines=5))\n",
    "lam = np.logspace(-3, 5, 5, base=3)\n",
    "lams = [lam] * 3\n",
    "gam_model.gridsearch(X, y, lam=lams)\n",
    "\n",
    "gam_model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## plotting\n",
    "fig, axs = plt.subplots(1,3);\n",
    "\n",
    "titles = ['gini_spread', 'duration', 'moneyness']\n",
    "for i, ax in enumerate(axs):\n",
    "    XX = gam_model.generate_X_grid(term=i)\n",
    "    ax.plot(XX[:, i], gam_model.partial_dependence(term=i, X=XX))\n",
    "    ax.plot(XX[:, i], gam_model.partial_dependence(term=i, X=XX, width=.95)[1], c='r', ls='--')\n",
    "    if i == 0:\n",
    "        ax.set_ylim(-30,30)\n",
    "    ax.set_title(titles[i]);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.scatter(y, gam_model.predict(X))\n",
    "plt.xlabel('actual correlation')\n",
    "plt.ylabel('predicted correlation')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "today = gini_calc.loc(axis=0)[value_date,'HY',33,'5yr',0]\n",
    "predict_HY33 = gam_model.predict(np.array(today[['gini_spread', 'duration', 'moneyness']]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "today, predict_HY33"
   ]
  }
 ],
 "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": "3.8.1-final"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}