{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "toc": true
   },
   "source": [
    "<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
    "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Chapter-Goals\" data-toc-modified-id=\"Chapter-Goals-1\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">1&nbsp;&nbsp;</span>Chapter Goals</a></span></li><li><span><a href=\"#Chapter-Outline\" data-toc-modified-id=\"Chapter-Outline-2\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">2&nbsp;&nbsp;</span>Chapter Outline</a></span></li><li><span><a href=\"#Algo-Evaluation-Motivation\" data-toc-modified-id=\"Algo-Evaluation-Motivation-3\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">3&nbsp;&nbsp;</span>Algo Evaluation Motivation</a></span><ul class=\"toc-item\"><li><span><a href=\"#Algorithm-Uncertainty-(AU)\" data-toc-modified-id=\"Algorithm-Uncertainty-(AU)-3.1\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">3.1&nbsp;&nbsp;</span>Algorithm Uncertainty (AU)</a></span></li><li><span><a href=\"#Model-Uncertainty-(MU)\" data-toc-modified-id=\"Model-Uncertainty-(MU)-3.2\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">3.2&nbsp;&nbsp;</span>Model Uncertainty (MU)</a></span></li></ul></li><li><span><a href=\"#Read-in-backtest-portfolio-equity-data.\" data-toc-modified-id=\"Read-in-backtest-portfolio-equity-data.-4\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">4&nbsp;&nbsp;</span>Read in backtest <em>portfolio equity</em> data.</a></span></li><li><span><a href=\"#Choose-the-Best-Algorithm-Among-4-Variants\" data-toc-modified-id=\"Choose-the-Best-Algorithm-Among-4-Variants-5\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">5&nbsp;&nbsp;</span>Choose the Best Algorithm Among 4 Variants</a></span></li><li><span><a href=\"#Choose-Best-Bayesian-Model-of-Algorithm-Returns\" data-toc-modified-id=\"Choose-Best-Bayesian-Model-of-Algorithm-Returns-6\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">6&nbsp;&nbsp;</span>Choose Best Bayesian Model of Algorithm Returns</a></span><ul class=\"toc-item\"><li><span><a href=\"#Model-Sampling-and-Comparison\" data-toc-modified-id=\"Model-Sampling-and-Comparison-6.1\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">6.1&nbsp;&nbsp;</span>Model Sampling and Comparison</a></span></li></ul></li><li><span><a href=\"#Comparing-Bayesian-Cones-for-all-Algos-and-all-Return-Models\" data-toc-modified-id=\"Comparing-Bayesian-Cones-for-all-Algos-and-all-Return-Models-7\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">7&nbsp;&nbsp;</span>Comparing Bayesian Cones for all Algos and all Return Models</a></span><ul class=\"toc-item\"><li><span><a href=\"#Some-observations:\" data-toc-modified-id=\"Some-observations:-7.1\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">7.1&nbsp;&nbsp;</span>Some observations:</a></span></li></ul></li><li><span><a href=\"#Compare-Best-Algo's-Predicted-Portfolio-Ending-Values\" data-toc-modified-id=\"Compare-Best-Algo's-Predicted-Portfolio-Ending-Values-8\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">8&nbsp;&nbsp;</span>Compare Best Algo's Predicted Portfolio Ending Values</a></span></li><li><span><a href=\"#Compare-Best-Algo-Predicted-CAGR-Distributions\" data-toc-modified-id=\"Compare-Best-Algo-Predicted-CAGR-Distributions-9\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">9&nbsp;&nbsp;</span>Compare Best Algo Predicted CAGR Distributions</a></span></li><li><span><a href=\"#Model-Averaging\" data-toc-modified-id=\"Model-Averaging-10\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">10&nbsp;&nbsp;</span>Model Averaging</a></span></li><li><span><a href=\"#Conclusions\" data-toc-modified-id=\"Conclusions-11\" data-vivaldi-spatnav-clickable=\"1\"><span class=\"toc-item-num\">11&nbsp;&nbsp;</span>Conclusions</a></span></li></ul></div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chapter Goals\n",
    "\n",
    "* Demonstrate how to extract algorithm portfolio equity from [Quantconnect](https://www.quantconnect.com/) backtest\n",
    "* Demonstrate how to predict future return paths using [bayesian cones](https://blog.quantopian.com/bayesian-cone/).\n",
    "* Demonstrate how to estimate distribution of algorithm CAGRs.\n",
    "* Demonstrate how to use model averaging to aid predictions."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chapter Outline\n",
    "\n",
    "1. Read in Algorithm Portfolio Equity\n",
    "2. Choose the Best Algorithm Among 4 Variants\n",
    "3. Choose Best Bayesian Model of Algorithm Returns\n",
    "4. Compare Bayesian Cones for all Algos and all Return Models\n",
    "5. Compare Best Algo Predicted Portfolio Ending Values\n",
    "6. Compare Best Algo Predicted CAGR Distributions\n",
    "7. Model Averaging\n",
    "8. Conclusion"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Algo Evaluation Motivation\n",
    "\n",
    "When evaluating our trading systems there are two major areas of uncertainty we have to address: `Algorithm Uncertainty`, `Model Uncertainty`. \n",
    "\n",
    "### Algorithm Uncertainty (AU)\n",
    "* trade sequencing\n",
    "* slippage/price impact\n",
    "* network errors\n",
    "* software errors\n",
    "* hardware errors\n",
    "\n",
    "### Model Uncertainty (MU)\n",
    "* model is misspecified\n",
    "* incorrect parameters\n",
    "* changing market environment/nonstationarity\n",
    "* missing variables\n",
    "* etc.\n",
    "\n",
    "What you will notice is that the `AU` examples given involve issues that can occur once our algorithm is live. What that also means is that some combination of those issues _did not happen_ in the past but some combination of them _could happen_ in the future. How can we estimate the impact of random exogenous shocks to our trading strategy's performance?\n",
    "\n",
    "In this chapter we will employ a Bayesian methodology which will allow us to reasonably estimate the variation in strategy performance across many different return paths in an attempt to account for the exogenous shocks. The flip side to this approach is that we will have to use a model and all of the requisite assumptions. \n",
    "\n",
    "That introduces the second area of importance `MU`. To incorporate our uncertainty about which model is \"best\" we will create `3` different models and compare them. Then we will combine their predictions before we make our final inference and prediction."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*NOTE: in this chapter I have abstracted away some of the boilerplate code used to create and format data in the imported script `ch5_utils.py`. Some other functions and processes I have chosen to leave in the notebook for easier reference due to its importance in the analysis.*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:34.508694Z",
     "start_time": "2018-11-11T04:09:28.948038Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2018-11-10T21:09:28-07:00\n",
      "\n",
      "CPython 3.6.6\n",
      "IPython 6.5.0\n",
      "\n",
      "compiler   : GCC 7.2.0\n",
      "system     : Linux\n",
      "release    : 4.15.0-38-generic\n",
      "machine    : x86_64\n",
      "processor  : x86_64\n",
      "CPU cores  : 12\n",
      "interpreter: 64bit\n",
      "\n",
      "pandas 0.23.4\n",
      "numpy 1.14.6\n",
      "pymc3 3.5\n",
      "theano 1.0.3\n",
      "sklearn 0.20.0\n",
      "statsmodels 0.9.0\n",
      "scipy 1.1.0\n",
      "ffn (0, 3, 3)\n",
      "matplotlib 3.0.0\n",
      "seaborn 0.9.0\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark\n",
    "\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "# import standard libs\n",
    "from IPython.display import display\n",
    "from IPython.core.debugger import set_trace as bp\n",
    "from pathlib import PurePath, Path\n",
    "import sys\n",
    "import time\n",
    "from collections import OrderedDict as od\n",
    "import re\n",
    "import os\n",
    "import json\n",
    "os.environ['THEANO_FLAGS'] = 'device=cpu,floatX=float32'\n",
    "\n",
    "# get project dir\n",
    "pp = PurePath(Path.cwd()).parts[:-1]\n",
    "pdir = PurePath(*pp)\n",
    "script_dir = pdir / 'scripts' \n",
    "viz_dir = pdir / 'visuals' / '05_Algorithm_Evaluation'\n",
    "log_dir = pdir / 'data' / 'quantconnect_data'\n",
    "sys.path.append(script_dir.as_posix())\n",
    "\n",
    "# import python scientific stack\n",
    "import pandas as pd\n",
    "pd.set_option('display.max_rows', 50)\n",
    "import numpy as np\n",
    "import scipy.stats as stats\n",
    "import math\n",
    "import pymc3 as pm\n",
    "from theano import shared, theano as tt\n",
    "import ffn\n",
    "\n",
    "# import visual tools\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "\n",
    "plt.style.use('seaborn-talk')\n",
    "plt.style.use('bmh')\n",
    "\n",
    "# import util libs\n",
    "from tqdm import tqdm\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "from utils import cprint\n",
    "from ch5_utils import pymc3_helper \n",
    "pmh = pymc3_helper()\n",
    "\n",
    "RANDOM_STATE = 777\n",
    "today = pd.to_datetime('today').date()\n",
    "\n",
    "print()# \n",
    "%watermark -p pandas,numpy,pymc3,theano,sklearn,statsmodels,scipy,ffn,matplotlib,seaborn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read in backtest *portfolio equity* data.\n",
    "\n",
    "To do this I have defined some useful convenience functions to clean up the raw dataset.\n",
    "\n",
    "    1. Read in raw json \n",
    "    2. Extract portfolio equity from json, rename columns, and parse time column\n",
    "    3. Rename df columns\n",
    "    4. Read in the properly formatted df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:34.824766Z",
     "start_time": "2018-11-11T04:10:34.511713Z"
    }
   },
   "outputs": [],
   "source": [
    "def read_bt_json(fp):\n",
    "    \"\"\"fn: read Quantconnect backtest json\"\"\"\n",
    "    with open(fp, encoding='utf-8') as f_in:\n",
    "        return(json.load(f_in))\n",
    "    \n",
    "    \n",
    "def extract_portfolio_equity(jdata):\n",
    "    \"\"\"fn: extract port equity timeseries from Quantconnect json\"\"\"\n",
    "    d = jdata['Charts']['Strategy Equity']['Series']['Equity']['Values']\n",
    "    equity = (pd.DataFrame(d)\n",
    "              .rename(columns=dict(x='time', y='equity'))\n",
    "              .assign(time=lambda df: pd.to_datetime(df.time, utc=True, unit='s'))\n",
    "              .set_index('time'))\n",
    "    return equity\n",
    "\n",
    "def _get_column_name(text):\n",
    "    \"\"\"fn: to get column name as first text group\"\"\"\n",
    "    #n = 4 # hardcoded based on fn structure\n",
    "    groups = text.split('.')\n",
    "    return '_'.join(groups[:-1])\n",
    "\n",
    "def read_port_equity(fn):\n",
    "    fp = PurePath(log_dir / fn)#.as_posix()\n",
    "    jdata = read_bt_json(fp) \n",
    "    \n",
    "    # get column name\n",
    "    col = _get_column_name(fn)\n",
    "    # extract equity data\n",
    "    equity = (extract_portfolio_equity(jdata)\n",
    "              .rename(columns=dict(equity=col)))\n",
    "    return equity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:35.543853Z",
     "start_time": "2018-11-11T04:10:34.826538Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-------------------------------------------------------------------------------\n",
      "dataframe information\n",
      "-------------------------------------------------------------------------------\n",
      "                           normal_2_thres_57_lev1_5x_rm\n",
      "time                                                   \n",
      "2018-11-07 21:00:00+00:00                   273236.9544\n",
      "2018-11-08 14:31:00+00:00                   272016.3744\n",
      "2018-11-08 21:00:00+00:00                   273236.9544\n",
      "2018-11-09 14:31:00+00:00                   273877.7244\n",
      "2018-11-09 21:00:00+00:00                   272953.9344\n",
      "--------------------------------------------------\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 5137 entries, 2008-09-01 04:00:00+00:00 to 2018-11-09 21:00:00+00:00\n",
      "Data columns (total 1 columns):\n",
      "normal_2_thres_57_lev1_5x_rm    5137 non-null float64\n",
      "dtypes: float64(1)\n",
      "memory usage: 80.3 KB\n",
      "None\n",
      "-------------------------------------------------------------------------------\n",
      "\n"
     ]
    }
   ],
   "source": [
    "\n",
    "#norm_2_cp_equity = read_port_equity('normal_2_thres_70cp.json')\n",
    "norm_2_cp_equity = read_port_equity('normal_2_thres_57_lev1_5x_rm.json')\n",
    "norm_2_60_equity = read_port_equity('normal_2_thres_60.json')\n",
    "norm_2_70_equity = read_port_equity('normal_2_thres_70.json')\n",
    "norm_2_80_equity = read_port_equity('normal_2_thres_80.json')\n",
    "cprint(norm_2_cp_equity)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Combine strategy dataframes into one df for easier analysis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:35.970056Z",
     "start_time": "2018-11-11T04:10:35.545844Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-------------------------------------------------------------------------------\n",
      "dataframe information\n",
      "-------------------------------------------------------------------------------\n",
      "                           normal_2_thres_57_lev1_5x_rm  normal_2_thres_60  \\\n",
      "time                                                                         \n",
      "2018-11-05 00:00:00+00:00                   272126.4094                NaN   \n",
      "2018-11-06 00:00:00+00:00                   272626.6644                NaN   \n",
      "2018-11-07 00:00:00+00:00                   272626.6644                NaN   \n",
      "2018-11-08 00:00:00+00:00                   272626.6644                NaN   \n",
      "2018-11-09 00:00:00+00:00                   273415.8294                NaN   \n",
      "\n",
      "                           normal_2_thres_70  normal_2_thres_80  \n",
      "time                                                             \n",
      "2018-11-05 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-06 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-07 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-08 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-09 00:00:00+00:00                NaN                NaN  \n",
      "--------------------------------------------------\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 2569 entries, 2008-09-01 to 2018-11-09\n",
      "Data columns (total 4 columns):\n",
      "normal_2_thres_57_lev1_5x_rm    2569 non-null float64\n",
      "normal_2_thres_60               2351 non-null float64\n",
      "normal_2_thres_70               2351 non-null float64\n",
      "normal_2_thres_80               2351 non-null float64\n",
      "dtypes: float64(4)\n",
      "memory usage: 100.4 KB\n",
      "None\n",
      "-------------------------------------------------------------------------------\n",
      "\n"
     ]
    }
   ],
   "source": [
    "list_of_dfs = [norm_2_cp_equity, norm_2_60_equity, norm_2_70_equity, norm_2_80_equity]\n",
    "dfs = (pd.concat(list_of_dfs, axis=1)\n",
    "       .resample('D') \n",
    "       .mean() # resample to average daily value\n",
    "       .dropna(how='all')) \n",
    "cprint(dfs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:36.490913Z",
     "start_time": "2018-11-11T04:10:35.971604Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-------------------------------------------------------------------------------\n",
      "dataframe information\n",
      "-------------------------------------------------------------------------------\n",
      "                           normal_2_thres_57_lev1_5x_rm  normal_2_thres_60  \\\n",
      "time                                                                         \n",
      "2018-11-05 00:00:00+00:00                     -0.003412                NaN   \n",
      "2018-11-06 00:00:00+00:00                      0.001837                NaN   \n",
      "2018-11-07 00:00:00+00:00                      0.000000                NaN   \n",
      "2018-11-08 00:00:00+00:00                      0.000000                NaN   \n",
      "2018-11-09 00:00:00+00:00                      0.002890                NaN   \n",
      "\n",
      "                           normal_2_thres_70  normal_2_thres_80  \n",
      "time                                                             \n",
      "2018-11-05 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-06 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-07 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-08 00:00:00+00:00                NaN                NaN  \n",
      "2018-11-09 00:00:00+00:00                NaN                NaN  \n",
      "--------------------------------------------------\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 2568 entries, 2008-09-02 to 2018-11-09\n",
      "Data columns (total 4 columns):\n",
      "normal_2_thres_57_lev1_5x_rm    2568 non-null float64\n",
      "normal_2_thres_60               2350 non-null float64\n",
      "normal_2_thres_70               2350 non-null float64\n",
      "normal_2_thres_80               2350 non-null float64\n",
      "dtypes: float64(4)\n",
      "memory usage: 100.3 KB\n",
      "None\n",
      "-------------------------------------------------------------------------------\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# portfolio equity returns \n",
    "R = ffn.to_log_returns(dfs).dropna(how='all')\n",
    "cprint(R)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Choose the Best Algorithm Among 4 Variants"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can use a useful package called [ffn](https://github.com/pmorissette/ffn) to compute an assortment of performance statistics we can use to compare the algorithm portfolios. We're going to choose the best algorithm using the following metrics:\n",
    "\n",
    "* Total Return\n",
    "* Daily Sharpe\n",
    "* CAGR\n",
    "* Calmar Ratio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:37.035660Z",
     "start_time": "2018-11-11T04:10:36.492584Z"
    }
   },
   "outputs": [],
   "source": [
    "perf = ffn.calc_stats(dfs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can view the portfolio cumulative returns indexed to 100 easily"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:37.826200Z",
     "start_time": "2018-11-11T04:10:37.037088Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "perf.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next we display the performance statistics."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:10:38.108639Z",
     "start_time": "2018-11-11T04:10:37.829116Z"
    },
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stat                 normal_2_thres_57_lev1_5x_rm    normal_2_thres_60    normal_2_thres_70    normal_2_thres_80\n",
      "-------------------  ------------------------------  -------------------  -------------------  -------------------\n",
      "Start                2008-09-01                      2008-09-01           2008-09-01           2008-09-01\n",
      "End                  2017-12-29                      2017-12-29           2017-12-29           2017-12-29\n",
      "Risk-free rate       0.00%                           0.00%                0.00%                0.00%\n",
      "\n",
      "Total Return         183.51%                         11.01%               20.51%               9.22%\n",
      "Daily Sharpe         0.93                            0.24                 0.43                 0.24\n",
      "Daily Sortino        1.24                            0.29                 0.48                 0.22\n",
      "CAGR                 11.82%                          1.13%                2.02%                0.95%\n",
      "Max Drawdown         -26.66%                         -15.83%              -13.01%              -11.08%\n",
      "Calmar Ratio         0.44                            0.07                 0.16                 0.09\n",
      "\n",
      "MTD                  2.55%                           0.23%                0.12%                0.30%\n",
      "3m                   7.45%                           0.38%                0.97%                1.48%\n",
      "6m                   12.64%                          1.24%                0.92%                1.48%\n",
      "YTD                  30.98%                          6.14%                4.11%                1.72%\n",
      "1Y                   31.00%                          6.16%                4.21%                1.72%\n",
      "3Y (ann.)            13.04%                          3.34%                3.87%                0.86%\n",
      "5Y (ann.)            11.07%                          1.21%                2.12%                -0.16%\n",
      "10Y (ann.)           11.82%                          1.13%                2.02%                0.95%\n",
      "Since Incep. (ann.)  11.82%                          1.13%                2.02%                0.95%\n",
      "\n",
      "Daily Sharpe         0.93                            0.24                 0.43                 0.24\n",
      "Daily Sortino        1.24                            0.29                 0.48                 0.22\n",
      "Daily Mean (ann.)    12.01%                          1.25%                2.12%                1.04%\n",
      "Daily Vol (ann.)     12.93%                          5.16%                4.99%                4.36%\n",
      "Daily Skew           -0.08                           -0.27                -0.63                -0.97\n",
      "Daily Kurt           5.09                            8.66                 12.41                20.09\n",
      "Best Day             5.18%                           2.31%                2.36%                2.36%\n",
      "Worst Day            -4.99%                          -2.21%               -2.65%               -2.65%\n",
      "\n",
      "Monthly Sharpe       0.97                            0.21                 0.38                 0.24\n",
      "Monthly Sortino      1.51                            0.32                 0.62                 0.30\n",
      "Monthly Mean (ann.)  12.65%                          1.22%                2.09%                1.05%\n",
      "Monthly Vol (ann.)   13.00%                          5.93%                5.52%                4.34%\n",
      "Monthly Skew         -0.16                           0.21                 0.40                 -0.19\n",
      "Monthly Kurt         0.48                            1.03                 1.74                 2.81\n",
      "Best Month           9.33%                           4.93%                5.62%                3.88%\n",
      "Worst Month          -10.34%                         -5.23%               -4.85%               -4.77%\n",
      "\n",
      "Yearly Sharpe        1.20                            0.33                 0.52                 0.48\n",
      "Yearly Sortino       -                               1.34                 3.93                 1.05\n",
      "Yearly Mean          13.87%                          1.93%                2.56%                1.43%\n",
      "Yearly Vol           11.57%                          5.79%                4.94%                2.96%\n",
      "Yearly Skew          0.81                            0.98                 1.37                 0.28\n",
      "Yearly Kurt          -0.58                           0.79                 1.95                 -0.29\n",
      "Best Year            32.90%                          13.60%               13.21%               6.53%\n",
      "Worst Year           0.89%                           -4.42%               -2.79%               -3.01%\n",
      "\n",
      "Avg. Drawdown        -2.09%                          -2.45%               -1.56%               -2.01%\n",
      "Avg. Drawdown Days   24.97                           175.05               102.22               156.38\n",
      "Avg. Up Month        3.45%                           1.29%                1.25%                1.02%\n",
      "Avg. Down Month      -2.34%                          -1.15%               -1.04%               -0.62%\n",
      "Win Year %           100.00%                         66.67%               77.78%               55.56%\n",
      "Win 12m %            95.05%                          58.42%               67.33%               53.47%\n"
     ]
    }
   ],
   "source": [
    "perf.display()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Among the four algorithms, according to the four metrics listed above the clear \"winner\" is the `normal_4` algo variant. This refers to the algorithm version that uses `4` mixture components and predicts the return distribution by sampling from the `normal` distribution.\n",
    "\n",
    "**Updated**: Best variant is the cherry picked version using a little bit of leverage and a long-term holding period."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Choose Best Bayesian Model of Algorithm Returns\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this section we address the dual issues of **algorithm uncertainty** and **model uncertainty**.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model Sampling and Comparison\n",
    "\n",
    "In this next section we model portfolio equity returns using 3 different distributions: `normal`, `laplace`, `student T`.\n",
    "Then we compare the models.\n",
    "\n",
    "$$ Y = \\mu + \\sigma $$\n",
    "\n",
    "Here's the `Normal` specification:\n",
    "\n",
    "$\\mu \\sim N(0,1)$\n",
    "\n",
    "$\\sigma \\sim HalfCauchy(1)$\n",
    "\n",
    "$Y \\sim N(\\mu, \\sigma)$\n",
    "\n",
    "Here's the `Laplace` specification:\n",
    "\n",
    "$\\mu \\sim N(0,1)$\n",
    "\n",
    "$\\sigma \\sim HalfCauchy(1)$\n",
    "\n",
    "$Y \\sim Laplace(\\mu, \\sigma)$\n",
    "\n",
    "Here's the `Student T` specification:\n",
    "\n",
    "$\\nu \\sim exp(.1)$\n",
    "\n",
    "$\\mu \\sim N(0,1)$\n",
    "\n",
    "$\\sigma \\sim HalfCauchy(1)$\n",
    "\n",
    "$Y \\sim StudentT(\\nu+2, \\mu, \\sigma)$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:11:36.401870Z",
     "start_time": "2018-11-11T04:11:36.099642Z"
    }
   },
   "outputs": [],
   "source": [
    "## Code adapted from: https://github.com/quantopian/pyfolio/blob/master/pyfolio/bayesian.py ##\n",
    "\n",
    "def normal_model(R, samples, name):\n",
    "    \"\"\"fn: sample normal model of strategy returns\n",
    "    \n",
    "    params\n",
    "    ------\n",
    "        R: pd.Series() simple returns ts\n",
    "        samples: int()\n",
    "        name: str(), model name\n",
    "        \n",
    "    returns\n",
    "    -------\n",
    "        model, trace\n",
    "    \"\"\"\n",
    "    with pm.Model(name=name) as model:\n",
    "        mu = pm.Normal('mean rets', mu=0, sd=.01, testval=R.mean())\n",
    "        sigma = pm.HalfCauchy('vol', beta=1, testval=R.std())\n",
    "        returns = pm.Normal('returns', mu=mu, sd=sigma, observed=R)\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'annual mean returns',\n",
    "            returns.distribution.mean * 252)\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'annual volatility',\n",
    "            returns.distribution.variance**.5 *\n",
    "            np.sqrt(252))\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'sharpe',\n",
    "            returns.distribution.mean /\n",
    "            returns.distribution.variance**.5*np.sqrt(252))\n",
    "\n",
    "        step = pm.NUTS()\n",
    "        trace = pm.sample(samples, tune=samples, step=step)   \n",
    "    return model, trace\n",
    "\n",
    "def laplace_model(R, samples, name):\n",
    "    \"\"\"fn: sample laplace model of strategy returns\n",
    "    \n",
    "    params\n",
    "    ------\n",
    "        R: pd.Series() simple returns ts\n",
    "        samples: int()\n",
    "        name: str(), model name\n",
    "        \n",
    "    returns\n",
    "    -------\n",
    "        model, trace\n",
    "    \"\"\"\n",
    "    with pm.Model(name=name) as model:\n",
    "        mu = pm.Normal('mean rets', mu=0, sd=.01, testval=R.mean())\n",
    "        sigma = pm.HalfCauchy('vol', beta=1, testval=R.std())\n",
    "        returns = pm.Laplace('returns', mu=mu, b=sigma, observed=R)\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'annual mean returns',\n",
    "            returns.distribution.mean * 252)\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'annual volatility',\n",
    "            returns.distribution.variance**.5 *\n",
    "            np.sqrt(252))\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'sharpe',\n",
    "            returns.distribution.mean /\n",
    "            returns.distribution.variance**.5*np.sqrt(252))\n",
    "\n",
    "        step = pm.NUTS(target_accept=.9)\n",
    "        trace = pm.sample(samples, tune=samples, step=step)\n",
    "    return model, trace \n",
    "\n",
    "def student_model(R, samples, name):\n",
    "    \"\"\"fn: sample student T model of strategy returns\n",
    "    \n",
    "    params\n",
    "    ------\n",
    "        R: pd.Series() simple returns ts\n",
    "        samples: int()\n",
    "        name: str(), model name\n",
    "        \n",
    "    returns\n",
    "    -------\n",
    "        model, trace\n",
    "    \"\"\"\n",
    "\n",
    "    with pm.Model(name=name) as model:\n",
    "        nu = pm.Exponential('nu_minus_two', 1. / 10., testval=3.)\n",
    "        mu = pm.Normal('mean rets', mu=0, sd=.01, testval=R.mean())\n",
    "        sigma = pm.HalfCauchy('vol', beta=1, testval=R.std())\n",
    "        returns = pm.StudentT('returns', nu=nu+2, mu=mu, sd=sigma, observed=R)\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'annual mean rets',\n",
    "            returns.distribution.mean * 252)\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'annual volatility',\n",
    "            returns.distribution.variance**.5*np.sqrt(252))\n",
    "\n",
    "        pm.Deterministic(\n",
    "            'sharpe',\n",
    "            returns.distribution.mean /\n",
    "            returns.distribution.variance**.5*np.sqrt(252))\n",
    "\n",
    "        step = pm.NUTS(target_accept=.9)\n",
    "        trace = pm.sample(samples, tune=samples, step=step)       \n",
    "    return model, trace\n",
    "\n",
    "def run_models_traces(r, samples=2_000):\n",
    "    \"\"\"fn: to run multiple models using algo returns\n",
    "    \n",
    "    params\n",
    "    ------\n",
    "        r: shared theano array\n",
    "            example: shared(R['normal_4'].values)\n",
    "            \n",
    "    returns\n",
    "    -------\n",
    "        models: ordereddict with model outputs\n",
    "        traces: ordereddict with trace outputs\n",
    "    \"\"\"\n",
    "\n",
    "    # get model, traces\n",
    "    norm_model, norm_trace = normal_model(r, samples, 'normal_model')\n",
    "    la_model, la_trace = laplace_model(r, samples, 'la_model')\n",
    "    t_model, t_trace = student_model(r, samples, 't_model')  \n",
    "    \n",
    "    # ordered dict is required to ensure insertion order\n",
    "    # python 3.7 dict will implement insertion order feature by default\n",
    "    models = od(norm_model=norm_model, la_model=la_model, t_model=t_model)    \n",
    "    traces = od(norm_trace=norm_trace, la_trace=la_trace, t_trace=t_trace)\n",
    "    \n",
    "    compareDict = {norm_model:norm_trace, la_model:la_trace, t_model:t_trace}\n",
    "    return models, traces, compareDict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For this portion of the analysis we will focus on the best algorithm variant `normal_4`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:15:06.613745Z",
     "start_time": "2018-11-11T04:11:36.403249Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [normal_model_vol, normal_model_mean rets]\n",
      "Sampling 4 chains: 100%|██████████| 16000/16000 [00:04<00:00, 3681.52draws/s]\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [la_model_vol, la_model_mean rets]\n",
      "Sampling 4 chains: 100%|██████████| 16000/16000 [00:04<00:00, 3225.34draws/s]\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [t_model_vol, t_model_mean rets, t_model_nu_minus_two]\n",
      "Sampling 4 chains: 100%|██████████| 16000/16000 [00:11<00:00, 1392.91draws/s]\n"
     ]
    }
   ],
   "source": [
    "best_algo_variant = 'normal_2_thres_57_lev1_5x_rm' #'normal_2_thres_70cp'\n",
    "r = R[best_algo_variant].values\n",
    "models, traces, compareDict = run_models_traces(r)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:15:21.099530Z",
     "start_time": "2018-11-11T04:15:06.616652Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>WAIC</th>\n",
       "      <th>pWAIC</th>\n",
       "      <th>dWAIC</th>\n",
       "      <th>weight</th>\n",
       "      <th>SE</th>\n",
       "      <th>dSE</th>\n",
       "      <th>var_warn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>t_model</th>\n",
       "      <td>-17905</td>\n",
       "      <td>2.92</td>\n",
       "      <td>0</td>\n",
       "      <td>0.51</td>\n",
       "      <td>104.14</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>la_model</th>\n",
       "      <td>-17902.6</td>\n",
       "      <td>2.22</td>\n",
       "      <td>2.39</td>\n",
       "      <td>0.49</td>\n",
       "      <td>104.47</td>\n",
       "      <td>13.78</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>normal_model</th>\n",
       "      <td>-17451.4</td>\n",
       "      <td>4.38</td>\n",
       "      <td>453.62</td>\n",
       "      <td>0</td>\n",
       "      <td>132.87</td>\n",
       "      <td>68.85</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 WAIC pWAIC   dWAIC weight      SE    dSE var_warn\n",
       "t_model        -17905  2.92       0   0.51  104.14      0        0\n",
       "la_model     -17902.6  2.22    2.39   0.49  104.47  13.78        0\n",
       "normal_model -17451.4  4.38  453.62      0  132.87  68.85        0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_comp_waic = (pm.compare(compareDict, method='stacking'))\n",
    "df_comp_waic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:15:21.561369Z",
     "start_time": "2018-11-11T04:15:21.101418Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots()\n",
    "pm.compareplot(df_comp_waic, ax=ax);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The best model is the `t_model` as it has the smallest deviance critierion. We can look at its traceplots below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:15:23.994977Z",
     "start_time": "2018-11-11T04:15:21.563768Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x604.8 with 12 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "rvs = pmh.get_model_varnames(models['t_model'])\n",
    "pmh.plot_traces_pymc(traces['t_trace'], varnames=rvs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Comparing Bayesian Cones for all Algos and all Return Models\n",
    "\n",
    "Even though we already know which model best describes the data, let's compare these algo variants and models a little more, in order to better understand how the model choices affect our algorithm performance predictions.\n",
    "\n",
    "To demonstrate this, in the next section we will sample from each of the 3 models for each of the 4 algorithm variants and output their predicted performance in the form of a [bayesian cone](https://blog.quantopian.com/bayesian-cone/). I first became aware of this concept via Thomas Wiecki at Quantopian. Simply put it is a Bayesian methodology to predict the probable return paths of the algorithm in question. Their primary use case was trying to determine if an algorithm was overfitted to its sample period by comparing its performance since going **live** vs its **backtest** performance. Once an algorithm is **live** if it severely underperforms the sampled bayesian credible intervals then it is likely overfitted.\n",
    "\n",
    "However in this use case we are going to adapt the methodology to simply predict the algo's likely return paths (aka future performance) and our uncertainty concerning the predicted performance.\n",
    "\n",
    "First we are going to make a prediction dictionary to hold the following information for each model:\n",
    "\n",
    "* `name`: this is the string name of the model and the dictionary key.\n",
    "* `ppc_samples`: this is the raw `pm.sample_ppc()` output.\n",
    "* `ppc`: this is a formatted df of the `ppc_samples` output.\n",
    "* `cuml_df`: this is a formatted df of *predicted* cumulative returns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T05:34:34.317406Z",
     "start_time": "2018-11-11T05:33:53.349122Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-----------------------------------------------------------------------------\n",
      "sampling algorithm variant: normal_2_thres_57_lev1_5x_rm\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [normal_model_vol, normal_model_mean rets]\n",
      "\n",
      "\n",
      "Sampling 4 chains:   0%|          | 0/16000 [00:00<?, ?draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   0%|          | 20/16000 [00:00<01:19, 199.98draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 89/16000 [00:00<01:03, 252.53draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 184/16000 [00:00<00:48, 323.77draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 307/16000 [00:00<00:37, 415.42draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 394/16000 [00:00<00:31, 492.39draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 468/16000 [00:00<00:42, 364.11draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   4%|▍         | 653/16000 [00:00<00:31, 479.61draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   6%|▌         | 987/16000 [00:01<00:23, 645.39draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   9%|▊         | 1376/16000 [00:01<00:16, 860.70draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  11%|█▏        | 1816/16000 [00:01<00:12, 1134.11draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  14%|█▎        | 2191/16000 [00:01<00:09, 1434.08draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  16%|█▌        | 2578/16000 [00:01<00:07, 1767.57draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  18%|█▊        | 2959/16000 [00:01<00:06, 2105.99draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  21%|██        | 3369/16000 [00:01<00:05, 2465.67draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  24%|██▎       | 3761/16000 [00:01<00:04, 2773.56draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  26%|██▌       | 4137/16000 [00:01<00:04, 2863.19draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  29%|██▊       | 4585/16000 [00:01<00:03, 3210.20draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  31%|███       | 4988/16000 [00:02<00:03, 3417.64draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  34%|███▍      | 5450/16000 [00:02<00:02, 3707.00draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  37%|███▋      | 5861/16000 [00:02<00:02, 3793.71draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  39%|███▉      | 6288/16000 [00:02<00:02, 3918.40draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  42%|████▏     | 6739/16000 [00:02<00:02, 4076.90draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  45%|████▍     | 7164/16000 [00:02<00:02, 4085.03draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  47%|████▋     | 7585/16000 [00:02<00:02, 4065.12draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  50%|█████     | 8070/16000 [00:02<00:01, 4271.33draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  54%|█████▎    | 8579/16000 [00:02<00:01, 4485.78draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  57%|█████▋    | 9100/16000 [00:02<00:01, 4678.34draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  60%|██████    | 9617/16000 [00:03<00:01, 4812.69draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  63%|██████▎   | 10151/16000 [00:03<00:01, 4958.12draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  67%|██████▋   | 10687/16000 [00:03<00:01, 5070.79draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  70%|██████▉   | 11199/16000 [00:03<00:00, 5062.17draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  73%|███████▎  | 11709/16000 [00:03<00:00, 5043.90draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  76%|███████▋  | 12230/16000 [00:03<00:00, 5090.37draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  80%|███████▉  | 12761/16000 [00:03<00:00, 5154.02draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  83%|████████▎ | 13278/16000 [00:03<00:00, 5014.90draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  86%|████████▌ | 13782/16000 [00:03<00:00, 4857.18draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  89%|████████▉ | 14283/16000 [00:03<00:00, 4899.78draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  92%|█████████▏| 14775/16000 [00:04<00:00, 4790.20draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  96%|█████████▌| 15308/16000 [00:04<00:00, 4938.11draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  99%|█████████▉| 15805/16000 [00:04<00:00, 4848.30draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains: 100%|██████████| 16000/16000 [00:04<00:00, 3620.96draws/s]\u001b[A\u001b[AMultiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [la_model_vol, la_model_mean rets]\n",
      "\n",
      "\n",
      "Sampling 4 chains:   0%|          | 0/16000 [00:00<?, ?draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 150/16000 [00:00<00:10, 1494.17draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 240/16000 [00:00<00:12, 1229.99draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 313/16000 [00:00<00:15, 1009.85draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 375/16000 [00:00<00:18, 830.87draws/s] \u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 436/16000 [00:00<00:32, 480.08draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 486/16000 [00:00<00:43, 359.04draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   4%|▍         | 632/16000 [00:00<00:33, 463.60draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   6%|▌         | 880/16000 [00:01<00:24, 613.03draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   7%|▋         | 1147/16000 [00:01<00:18, 797.30draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   9%|▉         | 1484/16000 [00:01<00:14, 1034.13draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  12%|█▏        | 1840/16000 [00:01<00:10, 1313.12draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  14%|█▍        | 2257/16000 [00:01<00:08, 1652.67draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  17%|█▋        | 2657/16000 [00:01<00:06, 2004.58draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  19%|█▉        | 3055/16000 [00:01<00:05, 2354.67draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  22%|██▏       | 3456/16000 [00:01<00:04, 2687.39draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  24%|██▍       | 3846/16000 [00:01<00:04, 2962.90draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  27%|██▋       | 4273/16000 [00:01<00:03, 3260.79draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  29%|██▉       | 4663/16000 [00:02<00:03, 3357.74draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  32%|███▏      | 5044/16000 [00:02<00:03, 3412.54draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  34%|███▍      | 5437/16000 [00:02<00:02, 3552.67draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  36%|███▋      | 5817/16000 [00:02<00:02, 3573.22draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  39%|███▊      | 6192/16000 [00:02<00:02, 3598.91draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  41%|████      | 6582/16000 [00:02<00:02, 3683.04draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  43%|████▎     | 6959/16000 [00:02<00:02, 3664.96draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  46%|████▌     | 7346/16000 [00:02<00:02, 3723.31draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  49%|████▊     | 7788/16000 [00:02<00:02, 3906.97draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  52%|█████▏    | 8242/16000 [00:03<00:01, 4076.80draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  54%|█████▍    | 8690/16000 [00:03<00:01, 4189.75draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  57%|█████▋    | 9114/16000 [00:03<00:01, 4022.54draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  60%|█████▉    | 9536/16000 [00:03<00:01, 4079.45draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  62%|██████▏   | 9948/16000 [00:03<00:01, 4075.41draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  65%|██████▍   | 10374/16000 [00:03<00:01, 4128.26draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  68%|██████▊   | 10830/16000 [00:03<00:01, 4247.81draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  70%|███████   | 11268/16000 [00:03<00:01, 4285.56draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  74%|███████▎  | 11776/16000 [00:03<00:00, 4493.81draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  76%|███████▋  | 12233/16000 [00:03<00:00, 4515.63draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  80%|███████▉  | 12721/16000 [00:04<00:00, 4619.02draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  83%|████████▎ | 13208/16000 [00:04<00:00, 4691.18draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  86%|████████▌ | 13694/16000 [00:04<00:00, 4739.68draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  89%|████████▊ | 14170/16000 [00:04<00:00, 4641.76draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  92%|█████████▏| 14653/16000 [00:04<00:00, 4696.05draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  95%|█████████▍| 15124/16000 [00:04<00:00, 4327.41draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  97%|█████████▋| 15564/16000 [00:04<00:00, 3121.07draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains: 100%|█████████▉| 15929/16000 [00:05<00:00, 2200.94draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains: 100%|██████████| 16000/16000 [00:05<00:00, 3106.22draws/s]\u001b[A\u001b[AMultiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [t_model_vol, t_model_mean rets, t_model_nu_minus_two]\n",
      "\n",
      "\n",
      "Sampling 4 chains:   0%|          | 0/16000 [00:00<?, ?draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   0%|          | 60/16000 [00:00<00:28, 553.08draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   0%|          | 77/16000 [00:00<00:49, 318.59draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 94/16000 [00:00<01:26, 184.47draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 109/16000 [00:00<01:42, 154.42draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 123/16000 [00:00<02:07, 124.41draws/s]\u001b[A\u001b[A\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains:   1%|          | 137/16000 [00:00<02:03, 128.29draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 150/16000 [00:00<02:09, 122.82draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 163/16000 [00:01<02:09, 122.67draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 179/16000 [00:01<02:00, 131.39draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|          | 198/16000 [00:01<01:49, 144.56draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|▏         | 215/16000 [00:01<01:49, 144.70draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   1%|▏         | 232/16000 [00:01<01:44, 151.09draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 248/16000 [00:01<01:42, 153.01draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 265/16000 [00:01<01:40, 157.26draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 281/16000 [00:01<01:42, 153.37draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 297/16000 [00:01<01:58, 132.61draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 313/16000 [00:02<01:56, 135.07draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 327/16000 [00:02<02:06, 124.04draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 343/16000 [00:02<01:57, 132.96draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 360/16000 [00:02<01:53, 137.59draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 375/16000 [00:02<01:57, 133.51draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   2%|▏         | 389/16000 [00:02<02:05, 124.30draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 402/16000 [00:02<02:09, 120.62draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 415/16000 [00:02<02:23, 108.52draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 427/16000 [00:03<02:47, 92.75draws/s] \u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 437/16000 [00:03<03:19, 77.88draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 446/16000 [00:03<03:16, 79.13draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 455/16000 [00:03<03:13, 80.32draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 465/16000 [00:03<03:04, 84.03draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 481/16000 [00:03<02:38, 97.66draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   3%|▎         | 522/16000 [00:03<02:02, 126.48draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   4%|▍         | 602/16000 [00:03<01:31, 169.18draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   4%|▍         | 714/16000 [00:03<01:07, 226.94draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   5%|▌         | 839/16000 [00:04<00:50, 300.75draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   6%|▌         | 978/16000 [00:04<00:38, 393.04draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   7%|▋         | 1118/16000 [00:04<00:29, 501.05draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   8%|▊         | 1271/16000 [00:04<00:23, 627.61draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:   9%|▉         | 1412/16000 [00:04<00:19, 751.72draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  10%|▉         | 1567/16000 [00:04<00:16, 888.61draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  11%|█         | 1752/16000 [00:04<00:13, 1052.50draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  12%|█▏        | 1945/16000 [00:04<00:11, 1218.26draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  13%|█▎        | 2126/16000 [00:04<00:10, 1350.05draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  14%|█▍        | 2310/16000 [00:04<00:09, 1464.91draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  16%|█▌        | 2506/16000 [00:05<00:08, 1581.27draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  17%|█▋        | 2702/16000 [00:05<00:07, 1677.33draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  18%|█▊        | 2920/16000 [00:05<00:07, 1796.47draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  20%|█▉        | 3125/16000 [00:05<00:06, 1865.09draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  21%|██        | 3322/16000 [00:05<00:06, 1893.64draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  22%|██▏       | 3549/16000 [00:05<00:06, 1991.83draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  24%|██▎       | 3772/16000 [00:05<00:05, 2057.56draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  25%|██▍       | 3983/16000 [00:05<00:05, 2040.98draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  26%|██▌       | 4191/16000 [00:05<00:05, 2048.05draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  28%|██▊       | 4403/16000 [00:05<00:05, 2067.66draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  29%|██▉       | 4613/16000 [00:06<00:05, 2076.68draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  30%|███       | 4827/16000 [00:06<00:05, 2093.28draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  31%|███▏      | 5039/16000 [00:06<00:05, 2100.19draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  33%|███▎      | 5250/16000 [00:06<00:05, 2092.66draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  34%|███▍      | 5460/16000 [00:06<00:05, 2008.65draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  35%|███▌      | 5669/16000 [00:06<00:05, 2030.69draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  37%|███▋      | 5891/16000 [00:06<00:04, 2083.90draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  38%|███▊      | 6114/16000 [00:06<00:04, 2125.38draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  40%|███▉      | 6332/16000 [00:06<00:04, 2139.99draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  41%|████      | 6547/16000 [00:06<00:04, 2105.67draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  42%|████▏     | 6771/16000 [00:07<00:04, 2143.77draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  44%|████▎     | 6986/16000 [00:07<00:04, 2067.51draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  45%|████▍     | 7194/16000 [00:07<00:04, 1982.87draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  46%|████▋     | 7410/16000 [00:07<00:04, 2029.95draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  48%|████▊     | 7634/16000 [00:07<00:04, 2083.23draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  49%|████▉     | 7865/16000 [00:07<00:03, 2144.92draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  51%|█████     | 8095/16000 [00:07<00:03, 2187.69draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  52%|█████▏    | 8321/16000 [00:07<00:03, 2207.75draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  53%|█████▎    | 8543/16000 [00:07<00:03, 2165.71draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  55%|█████▍    | 8769/16000 [00:08<00:03, 2192.99draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  56%|█████▋    | 9009/16000 [00:08<00:03, 2250.98draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  58%|█████▊    | 9250/16000 [00:08<00:02, 2295.65draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  59%|█████▉    | 9481/16000 [00:08<00:02, 2298.17draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  61%|██████    | 9712/16000 [00:08<00:02, 2226.78draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  62%|██████▏   | 9936/16000 [00:08<00:02, 2140.92draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  63%|██████▎   | 10152/16000 [00:08<00:02, 2121.06draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  65%|██████▍   | 10366/16000 [00:08<00:02, 2106.25draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  66%|██████▌   | 10578/16000 [00:08<00:02, 2091.18draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  68%|██████▊   | 10803/16000 [00:08<00:02, 2130.89draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  69%|██████▉   | 11032/16000 [00:09<00:02, 2176.10draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  70%|███████   | 11272/16000 [00:09<00:02, 2233.95draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  72%|███████▏  | 11512/16000 [00:09<00:01, 2280.25draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  73%|███████▎  | 11741/16000 [00:09<00:01, 2245.69draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  75%|███████▍  | 11967/16000 [00:09<00:01, 2193.24draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  76%|███████▌  | 12188/16000 [00:09<00:01, 2178.00draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  78%|███████▊  | 12417/16000 [00:09<00:01, 2209.45draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  79%|███████▉  | 12639/16000 [00:09<00:01, 2126.11draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  80%|████████  | 12864/16000 [00:09<00:01, 2156.78draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  82%|████████▏ | 13081/16000 [00:10<00:01, 2085.94draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  83%|████████▎ | 13306/16000 [00:10<00:01, 2131.10draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  85%|████████▍ | 13545/16000 [00:10<00:01, 2201.54draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  86%|████████▌ | 13782/16000 [00:10<00:00, 2248.47draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  88%|████████▊ | 14014/16000 [00:10<00:00, 2265.43draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  89%|████████▉ | 14252/16000 [00:10<00:00, 2293.82draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  91%|█████████ | 14483/16000 [00:10<00:00, 2290.54draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  92%|█████████▏| 14713/16000 [00:10<00:00, 2264.42draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  93%|█████████▎| 14940/16000 [00:10<00:00, 2232.01draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  95%|█████████▍| 15164/16000 [00:10<00:00, 2197.46draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  96%|█████████▌| 15385/16000 [00:11<00:00, 2150.58draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains:  98%|█████████▊| 15601/16000 [00:11<00:00, 1630.54draws/s]\u001b[A\u001b[A\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains:  99%|█████████▊| 15784/16000 [00:11<00:00, 1117.36draws/s]\u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains: 100%|█████████▉| 15931/16000 [00:11<00:00, 899.04draws/s] \u001b[A\u001b[A\n",
      "\n",
      "Sampling 4 chains: 100%|██████████| 16000/16000 [00:11<00:00, 1344.55draws/s]\u001b[A\u001b[A\n",
      "\n",
      "  0%|          | 0/504 [00:00<?, ?it/s]\u001b[A\u001b[A"
     ]
    },
    {
     "ename": "MemoryError",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mMemoryError\u001b[0m                               Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-20-c5fe94d775f5>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     13\u001b[0m                                     \u001b[0msamples\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m252\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     14\u001b[0m                                     \u001b[0mmodel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m                                     size=tmp_r.eval().shape[0])\n\u001b[0m\u001b[1;32m     16\u001b[0m         \u001b[0;31m#ppc_samples = pm.sample_posterior_predictive(trace,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     17\u001b[0m         \u001b[0;31m#                            samples=252*2,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/bcr/HDD/anaconda3/envs/bayes_dash/lib/python3.6/site-packages/pymc3/sampling.py\u001b[0m in \u001b[0;36msample_ppc\u001b[0;34m(trace, samples, model, vars, size, random_seed, progressbar)\u001b[0m\n\u001b[1;32m   1130\u001b[0m     \u001b[0mppc_trace\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdefaultdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlist\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1131\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mvarname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mvar_values\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1132\u001b[0;31m         \u001b[0mppc_trace\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mvarname\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mzeros\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msamples\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1133\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1134\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mMemoryError\u001b[0m: "
     ]
    }
   ],
   "source": [
    "preds = {}\n",
    "\n",
    "for algo_name in R.columns:\n",
    "    print('-'*77)\n",
    "    print(f'sampling algorithm variant: {algo_name}')\n",
    "    print()\n",
    "    tmp_dict = {}\n",
    "    tmp_r = shared(R[algo_name].dropna().values)\n",
    "    tmp_models, tmp_traces, tmp_compareDict = run_models_traces(tmp_r)\n",
    "    \n",
    "    for model, trace in tmp_compareDict.items():\n",
    "        ppc_samples = pm.sample_ppc(trace, \n",
    "                                    samples=252*2,\n",
    "                                    model=model,\n",
    "                                    size=tmp_r.eval().shape[0])\n",
    "        #ppc_samples = pm.sample_posterior_predictive(trace, \n",
    "        #                            samples=252*2,\n",
    "        #                            model=model,\n",
    "        #                            size=tmp_r.eval().shape[0])        \n",
    "        tmp_df = pd.DataFrame(ppc_samples[f'{model.name}_returns'])\n",
    "        tmp_df.index = pd.date_range(pd.to_datetime('today').date(),\n",
    "                                     periods=tmp_df.shape[0], freq='D')\n",
    "        ppc = pmh.make_ppc_df(tmp_df)\n",
    "        cuml_df = ppc.cumsum()\n",
    "        tmp_dict[model.name] = dict(ppc_samples=ppc_samples,\n",
    "                                    ppc=ppc,\n",
    "                                    cuml_df=cuml_df)\n",
    "    preds[algo_name] = tmp_dict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this section we are adapting the [bayesian cone](https://github.com/quantopian/pyfolio/blob/master/pyfolio/bayesian.py) code from [pyfolio](https://github.com/quantopian/pyfolio) for our use case below. \n",
    "\n",
    "1. The first function `make_train_test()` is creating the train and test splits needed for the bayesian cone plot. In the original use case this is a little simpler because we would simply be splitting the algorithm return series at the date when the algorithm is **live**. In this custom implementation we are using *all* of the algorithm's *cumulative returns + 1*, as the **train** set. The **test** set is the *predicted mean* of the sampled cumulative returns scaled by the last return of the train set.\n",
    "\n",
    "2. The function `compute_bayes_cone()` is calculating the percentile scores, or returns at the specified percentiles.\n",
    "\n",
    "3. The function `plot_bayes_cone()` plots a single algorithm's predicted performance along with credible intervals we computed `compute_bayes_cone()`\n",
    "\n",
    "4. The function `plot_bayes_cone_grid()` is simply a wrapper function to plot each of the `4` algorithm variants with each of the `3` models for easy comparison"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.625833Z",
     "start_time": "2018-11-11T04:11:36.112Z"
    }
   },
   "outputs": [],
   "source": [
    "## Code adapted from: https://github.com/quantopian/pyfolio/blob/master/pyfolio/bayesian.py ##\n",
    "\n",
    "def make_train_test(returns, cuml_df):\n",
    "    \"\"\"fn: to make train test dfs\n",
    "    \n",
    "    Params\n",
    "    ------\n",
    "        returns: pd.Series()\n",
    "        cuml_df: df of simulated cuml returns\n",
    "    \n",
    "    Returns\n",
    "    -------\n",
    "        train, test: pd.Series(), pd.DataFrame()\n",
    "    \"\"\"\n",
    "    t = returns.cumsum().add(1)\n",
    "    t_test = cuml_df['mean_sim_path'].add(1) * t.iloc[-1]\n",
    "    t_test.index = t_test.index.tz_localize('utc')\n",
    "    return t, t_test\n",
    "\n",
    "def compute_bayes_cone(preds, starting_value=1.):\n",
    "    \"\"\"\n",
    "    Compute 5, 25, 75 and 95 percentiles of cumulative returns, used\n",
    "    for the Bayesian cone.\n",
    "    \n",
    "    Params\n",
    "    ------\n",
    "    preds : numpy.array\n",
    "        Multiple (simulated) cumulative returns.\n",
    "    starting_value : int (optional)\n",
    "        Have cumulative returns start around this value.\n",
    "        Default = 1.\n",
    "        \n",
    "    Returns\n",
    "    -------\n",
    "    dict of percentiles over time\n",
    "        Dictionary mapping percentiles (5, 25, 75, 95) to a\n",
    "        timeseries.\n",
    "    \"\"\"\n",
    "\n",
    "    def scoreatpercentile(cum_preds, p):\n",
    "        return [stats.scoreatpercentile(\n",
    "            c, p) for c in cum_preds.T]\n",
    "\n",
    "    cum_preds = np.cumprod(preds + 1, 1) * starting_value\n",
    "    perc = {p: scoreatpercentile(cum_preds, p) for p in (5, 25, 75, 95)}\n",
    "\n",
    "    return perc\n",
    "\n",
    "def plot_bayes_cone(train, test, algo_name, model_name, percentiles, ax=None):\n",
    "    \"\"\"fn: plot bayes cone using train 'test' split\"\"\"\n",
    "    if ax is None: ax = plt.gca()\n",
    "        \n",
    "    t = train\n",
    "    t_rel = test\n",
    "    t.loc[t_rel.index[0]] = t_rel.iloc[0]\n",
    "\n",
    "    t.plot(ax=ax, color='g', label='in-sample')\n",
    "    t_rel.plot(ax=ax, color='r', label='future estimate')\n",
    "\n",
    "    ax.fill_between(t_rel.index, percentiles[5], percentiles[95], alpha=.3)\n",
    "    ax.fill_between(t_rel.index, percentiles[25], percentiles[75], alpha=.6)\n",
    "    ax.legend(loc='upper left', frameon=True, framealpha=0.5)\n",
    "    ax.set_title(f'{algo_name}::{model_name}')\n",
    "    ax.set_xlabel('')\n",
    "    ax.set_ylabel('Cumulative returns')\n",
    "\n",
    "    ax.set_xlim(t.index[0], t_rel.index[-1])\n",
    "\n",
    "\n",
    "def plot_bayes_cone_grid(preds, R, model_labels):\n",
    "\n",
    "    algo_names = R.columns\n",
    "    \n",
    "    n = len(model_labels)\n",
    "    m = len(algo_names)\n",
    "    \n",
    "    fig, axes = plt.subplots(m,n, figsize=(15,15))\n",
    "\n",
    "    for i, algo_name in enumerate(algo_names):    \n",
    "        for j, model_label in enumerate(model_labels):\n",
    "\n",
    "            r = R[algo_name]\n",
    "            tmp_c_df = preds[algo_name][model_label]['cuml_df']\n",
    "            train, test = make_train_test(r, tmp_c_df)\n",
    "\n",
    "            tmp_ppc_samples = preds[algo_name][model_label]['ppc_samples']\n",
    "            \n",
    "            # extract subsample before computing cone\n",
    "            df_t = (pd.DataFrame(tmp_ppc_samples[f'{model_label}_returns'])\n",
    "                    .sample(len(tmp_ppc_samples[f'{model_label}_returns']),\n",
    "                            axis=1)\n",
    "                    .values)\n",
    "            perc = compute_bayes_cone(df_t, starting_value=train.iloc[-1])\n",
    "\n",
    "            ax = axes[i,j]\n",
    "            plot_bayes_cone(train, test, algo_name, model_label, perc, ax=ax)\n",
    "        plt.suptitle('Bayesian cone || algo_name::model_name', \n",
    "                     fontsize=14, fontweight='medium',)\n",
    "    plt.tight_layout()    \n",
    "    fig.subplots_adjust(top=.92)\n",
    "    today=pd.to_datetime('today').date()\n",
    "    save_pth = PurePath(viz_dir/f'bayesian_cones_comparison_{today}.png').as_posix()\n",
    "    fig.savefig(save_pth, dpi=300, bbox_inches='tight')    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's examine the results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.626626Z",
     "start_time": "2018-11-11T04:11:36.114Z"
    }
   },
   "outputs": [],
   "source": [
    "model_labels = ['normal_model', 'la_model', 't_model']\n",
    "## plot\n",
    "plot_bayes_cone_grid(preds, R, model_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Some observations:\n",
    "\n",
    "* If we look at the last column which features all 4 algo variants paired with the `t_model` we can see that compared to the other columns the `t_model` consistently has the widest dispersion of predicted return paths. This is somewhat expected given that the Student T model is supposed to incorporate wider tails. \n",
    "\n",
    "* Looking at the `la_model` column we can see that it consistently estimates the predicted return path to hover very close to zero on average no matter what the performance of the of the algorithm was. This is also expected because the `Laplace` distribution is made by double exponential functions that concentrate the mass of the distribution around 0. The `la_model` also seems to have the smallest range in the cone compared to the others.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compare Best Algo's Predicted Portfolio Ending Values\n",
    "## Compare Best Algo Predicted CAGR Distributions\n",
    "\n",
    "In the next section we will quantify our observations about the bayesian cone widths. We will again disregard all the other algorithm variants and use our `best_algo_variant` which is the `normal_4` algo to compare each of the `3` models and the width's of their bayesian cones at the **end** of the prediction period. To do this we will be using the distribution of the simulated portfolio ending values and comparing their `5, 50, 95` percentile values. \n",
    "\n",
    "This analysis will also allow us to compare estimated CAGRs of the `best_algo_variant` for each of the `3` return models."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First let's look at a quick sample of the predicted cumulative return paths of our best algorithm with the \"best\" model of returns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.627394Z",
     "start_time": "2018-11-11T04:11:36.116Z"
    },
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "ex_cuml_df = preds[best_algo_variant]['t_model']['cuml_df']\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(15,5))\n",
    "ex_cuml_df.sample(150, axis=1).plot(legend=False, ax=ax, x_compat=True)\n",
    "xmin, xmax = ex_cuml_df.index.min(), ex_cuml_df.index.max()\n",
    "ax.set_xlim((xmin, xmax))\n",
    "save_pth=PurePath(viz_dir/f'best_algo_t_model_simulated_paths_sample_{today}.png').as_posix()\n",
    "fig.savefig(save_pth, dpi=300)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this section we are going to extract the simulated portfolio ending values using the best algo variant `normal_2_thres_70cp` and for each return model and we're going to compare the ending value distributions.\n",
    "\n",
    "We will also compute **CAGR's** for each simulated return path and summarize the distribution of expected CAGRs using the `5, 50, 95` percentiles. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.628236Z",
     "start_time": "2018-11-11T04:11:36.119Z"
    },
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "n_cols = 5000\n",
    "quantiles = [0.05,.5,.95]\n",
    "\n",
    "for model in model_labels:\n",
    "    ## get ppc, paths and end vals \n",
    "    tmp_ppc = preds[best_algo_variant][model]['ppc']\n",
    "    sim_path_df = pmh.get_paths(tmp_ppc, n_cols)\n",
    "    sim_end_val = pmh.get_end_vals(sim_path_df)\n",
    "    \n",
    "    ## plot sim port end vals\n",
    "    fig, axes = plt.subplots(1,2, figsize=(15,3))\n",
    "    pmh.plot_port_end_dist(sim_end_val, axes,\n",
    "                           model_name=model)\n",
    "    save_pth = PurePath(viz_dir/f'best_algo_{model}_simulated_ending_values_dist_{today}.png').as_posix()\n",
    "    fig.savefig(save_pth, dpi=300)\n",
    "    ## plot cagr bar\n",
    "    cagr = ffn.calc_cagr(sim_path_df)\n",
    "    step = .01\n",
    "    pcts = np.arange(0,1+step,step)\n",
    "    pcts = np.round(pd.Index(pcts),2)\n",
    "    ser = cagr.quantile(pcts)    \n",
    "\n",
    "    fig, ax = plt.subplots(figsize=(15,3))\n",
    "    pmh.plot_cagr_bar(ser, quantiles,\n",
    "                      ax, model_name=model)\n",
    "    save_pth = PurePath(viz_dir/f'best_algo_{model}_simulated_cagr_perc_{today}.png').as_posix()\n",
    "    fig.savefig(save_pth, dpi=300)    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Averaging\n",
    "\n",
    "So now we have `3` return models. Our previous `WAIC` based decision criterion told us that the `t_model` does the best job of modeling the algorithm returns. But as we can see there are other potentially credible models that hold information that could help improve our predictions. How can we incorporate other useful models in our predictions?\n",
    "\n",
    "Lucky for us `pymc3` has made the process straightforward. In section `3` we compared our `3` models using `pm.compare()`. The output dataframe has a column of `weights` which we can *\"vaguely interpret as the probability that each model will make the correct predictions on future data.\"*\n",
    "\n",
    "Next we can use the function `pm.sample_ppc_w()` to incorporate those weights. Make sure the weights are ordered identically to the traces and models we constructed above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.629369Z",
     "start_time": "2018-11-11T04:11:36.121Z"
    }
   },
   "outputs": [],
   "source": [
    "df_comp_waic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.631370Z",
     "start_time": "2018-11-11T04:11:36.122Z"
    },
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "def make_stacked_model_df(traces, models, weights, samples=500, seed=0):\n",
    "    \"\"\"fn: sample wtd ppc\n",
    "    \n",
    "    Params\n",
    "    ------\n",
    "        traces: list of traces\n",
    "        models: list of models\n",
    "        weights: pd.Series of weights\n",
    "    \n",
    "    Returns\n",
    "    -------\n",
    "        ppc_df: df of wtd ppc samples\n",
    "    \"\"\"\n",
    "    cols = []\n",
    "    for i in tqdm(range(samples)):\n",
    "        ppc_w = pm.sample_ppc_w(traces=traces, samples=252*2, \n",
    "                                models=models, \n",
    "                                weights=weights,\n",
    "                                random_seed=seed+i, # reproducible                               \n",
    "                                progressbar=False)\n",
    "        ppc_w_data = (ppc_w[k] for k in list(ppc_w.keys()))\n",
    "        col = pd.Series(np.hstack(ppc_w_data))\n",
    "        cols.append(col)\n",
    "    ppc_df = (pd.concat(cols,axis=1)) \n",
    "    ppc_df.index = pd.date_range(pd.to_datetime('today').date(),\n",
    "                              periods=ppc_df.shape[0], freq='D')\n",
    "\n",
    "    ppc_df = ppc_df.assign(mean_sim_port=lambda df: df.mean(1))\n",
    "    return ppc_df\n",
    "\n",
    "\n",
    "traces = list(compareDict.values())\n",
    "models = list(compareDict.keys())\n",
    "weights = df_comp_waic.weight.sort_values(ascending=True)\n",
    "\n",
    "ppc_df = make_stacked_model_df(traces, models, weights)\n",
    "cprint(ppc_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.632716Z",
     "start_time": "2018-11-11T04:11:36.124Z"
    }
   },
   "outputs": [],
   "source": [
    "n_cols = 500\n",
    "quantiles = [0.05,.5,.95]\n",
    "\n",
    "## get ppc, paths and end vals \n",
    "sim_path_df = pmh.get_paths(ppc_df, n_cols)\n",
    "sim_end_val = pmh.get_end_vals(sim_path_df)\n",
    "\n",
    "## plot sim port end vals\n",
    "fig, axes = plt.subplots(1,2, figsize=(15,3))\n",
    "pmh.plot_port_end_dist(sim_end_val, axes,\n",
    "                       model_name='stacked_model')\n",
    "save_pth = PurePath(viz_dir/f'stacked_model_simulated_ending_values_dist_{today}.png').as_posix()\n",
    "fig.savefig(save_pth, dpi=300)\n",
    "\n",
    "## plot cagr bar\n",
    "cagr = ffn.calc_cagr(sim_path_df)\n",
    "step = .01\n",
    "pcts = np.arange(0,1+step,step)\n",
    "pcts = np.round(pd.Index(pcts),2)\n",
    "ser = cagr.quantile(pcts)    \n",
    "\n",
    "fig, ax = plt.subplots(figsize=(15,3))\n",
    "pmh.plot_cagr_bar(ser, quantiles,\n",
    "                  ax, model_name='stacked_model')\n",
    "save_pth = PurePath(viz_dir/f'stacked_model_simulated_cagr_perc_{today}.png').as_posix()\n",
    "fig.savefig(save_pth, dpi=300)  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "What if we try our own arbitrary weights?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.634534Z",
     "start_time": "2018-11-11T04:11:36.126Z"
    }
   },
   "outputs": [],
   "source": [
    "new_weights = [0.32, 0.34, 0.34]\n",
    "\n",
    "new_ppc_dfs = make_stacked_model_df(traces, models, new_weights)\n",
    "cprint(new_ppc_dfs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-11-11T04:16:07.636885Z",
     "start_time": "2018-11-11T04:11:36.128Z"
    }
   },
   "outputs": [],
   "source": [
    "n_cols = 500\n",
    "quantiles = [0.05,.5,.95]\n",
    "\n",
    "## get ppc, paths and end vals \n",
    "sim_path_df = pmh.get_paths(new_ppc_dfs, n_cols)\n",
    "sim_end_val = pmh.get_end_vals(sim_path_df)\n",
    "\n",
    "## plot sim port end vals\n",
    "fig, axes = plt.subplots(1,2, figsize=(15,3))\n",
    "pmh.plot_port_end_dist(sim_end_val, axes,\n",
    "                       model_name='alt_stacked_model')\n",
    "save_pth = PurePath(viz_dir/f'alt_stacked_model_simulated_ending_values_dist_{today}.png').as_posix()\n",
    "fig.savefig(save_pth, dpi=300)\n",
    "\n",
    "## plot cagr bar\n",
    "cagr = ffn.calc_cagr(sim_path_df)\n",
    "step = .01\n",
    "pcts = np.arange(0,1+step,step)\n",
    "pcts = np.round(pd.Index(pcts),2)\n",
    "ser = cagr.quantile(pcts)    \n",
    "\n",
    "fig, ax = plt.subplots(figsize=(15,3))\n",
    "pmh.plot_cagr_bar(ser, quantiles,\n",
    "                  ax, model_name='alt_stacked_model')\n",
    "save_pth = PurePath(viz_dir/f'alt_stacked_model_simulated_cagr_perc_{today}.png').as_posix()\n",
    "fig.savefig(save_pth, dpi=300)  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conclusions\n",
    "\n",
    "Using our `stacked_model` with the original pymc3 generated weights we can interpret the results as so; Trading the `normal_2_thres_70cp` algorithm variant, we would expect over the next `504 trading days` or approximately `2 years` that our portfolio equity will be between `~$92K` and `~$114K` with an expected value of `~$103K`. The predicted CAGR is estimated to be between `-5%` and `+10%` with an expected value of `2.0%`. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:bayes_dash]",
   "language": "python",
   "name": "conda-env-bayes_dash-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.6"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "339px"
   },
   "toc_section_display": true,
   "toc_window_display": true
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}