{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Portfolio simulation summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "from simple_back_test import *\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "ff = \"../../data/portfolio_simulations.pickle\"\n",
    "runs_per_cap = pickle.load( open(ff, 'rb'))\n",
    "all_summaries = convert_to_summary_df(runs_per_cap)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_summaries.head()\n",
    "all_summaries['cc'] = all_summaries['capital'].astype('category')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "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>average_positions</th>\n",
       "      <th>average_position_size</th>\n",
       "      <th>average_portfolio_return</th>\n",
       "      <th>portfolio_std</th>\n",
       "      <th>cumulative_return</th>\n",
       "      <th>max_drawdown</th>\n",
       "      <th>sharpe</th>\n",
       "      <th>annualised_ret</th>\n",
       "      <th>annual_volatility</th>\n",
       "      <th>sortino</th>\n",
       "      <th>downside_risk</th>\n",
       "      <th>tail_risk</th>\n",
       "      <th>capital</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>11.227572</td>\n",
       "      <td>76261.179200</td>\n",
       "      <td>0.003186</td>\n",
       "      <td>0.029285</td>\n",
       "      <td>2.923035</td>\n",
       "      <td>-0.112575</td>\n",
       "      <td>1.738981</td>\n",
       "      <td>1.067099</td>\n",
       "      <td>0.464886</td>\n",
       "      <td>12.285392</td>\n",
       "      <td>0.087883</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.387138</td>\n",
       "      <td>16357.811663</td>\n",
       "      <td>0.000859</td>\n",
       "      <td>0.005941</td>\n",
       "      <td>1.334308</td>\n",
       "      <td>0.054738</td>\n",
       "      <td>0.424342</td>\n",
       "      <td>0.390467</td>\n",
       "      <td>0.094315</td>\n",
       "      <td>9.728410</td>\n",
       "      <td>0.037878</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>6.881720</td>\n",
       "      <td>46324.010802</td>\n",
       "      <td>0.000388</td>\n",
       "      <td>0.017816</td>\n",
       "      <td>0.090291</td>\n",
       "      <td>-0.279671</td>\n",
       "      <td>0.310099</td>\n",
       "      <td>0.047962</td>\n",
       "      <td>0.282812</td>\n",
       "      <td>0.459498</td>\n",
       "      <td>0.017895</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>9.677419</td>\n",
       "      <td>64819.824511</td>\n",
       "      <td>0.002654</td>\n",
       "      <td>0.025122</td>\n",
       "      <td>1.935018</td>\n",
       "      <td>-0.142298</td>\n",
       "      <td>1.478694</td>\n",
       "      <td>0.792317</td>\n",
       "      <td>0.398802</td>\n",
       "      <td>6.436859</td>\n",
       "      <td>0.062798</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>10.967742</td>\n",
       "      <td>74948.548828</td>\n",
       "      <td>0.003254</td>\n",
       "      <td>0.028624</td>\n",
       "      <td>2.854072</td>\n",
       "      <td>-0.109124</td>\n",
       "      <td>1.740068</td>\n",
       "      <td>1.077449</td>\n",
       "      <td>0.454388</td>\n",
       "      <td>10.405729</td>\n",
       "      <td>0.083313</td>\n",
       "      <td>NaN</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>12.903226</td>\n",
       "      <td>86202.950005</td>\n",
       "      <td>0.003707</td>\n",
       "      <td>0.031923</td>\n",
       "      <td>3.601407</td>\n",
       "      <td>-0.071364</td>\n",
       "      <td>2.003689</td>\n",
       "      <td>1.286883</td>\n",
       "      <td>0.506764</td>\n",
       "      <td>15.333557</td>\n",
       "      <td>0.111164</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>17.204301</td>\n",
       "      <td>119485.022168</td>\n",
       "      <td>0.005179</td>\n",
       "      <td>0.049274</td>\n",
       "      <td>6.619313</td>\n",
       "      <td>-0.018933</td>\n",
       "      <td>3.038153</td>\n",
       "      <td>2.005671</td>\n",
       "      <td>0.782194</td>\n",
       "      <td>72.937218</td>\n",
       "      <td>0.212767</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       average_positions  average_position_size  average_portfolio_return  \\\n",
       "count         100.000000             100.000000                100.000000   \n",
       "mean           11.227572           76261.179200                  0.003186   \n",
       "std             2.387138           16357.811663                  0.000859   \n",
       "min             6.881720           46324.010802                  0.000388   \n",
       "25%             9.677419           64819.824511                  0.002654   \n",
       "50%            10.967742           74948.548828                  0.003254   \n",
       "75%            12.903226           86202.950005                  0.003707   \n",
       "max            17.204301          119485.022168                  0.005179   \n",
       "\n",
       "       portfolio_std  cumulative_return  max_drawdown      sharpe  \\\n",
       "count     100.000000         100.000000    100.000000  100.000000   \n",
       "mean        0.029285           2.923035     -0.112575    1.738981   \n",
       "std         0.005941           1.334308      0.054738    0.424342   \n",
       "min         0.017816           0.090291     -0.279671    0.310099   \n",
       "25%         0.025122           1.935018     -0.142298    1.478694   \n",
       "50%         0.028624           2.854072     -0.109124    1.740068   \n",
       "75%         0.031923           3.601407     -0.071364    2.003689   \n",
       "max         0.049274           6.619313     -0.018933    3.038153   \n",
       "\n",
       "       annualised_ret  annual_volatility     sortino  downside_risk  \\\n",
       "count      100.000000         100.000000  100.000000     100.000000   \n",
       "mean         1.067099           0.464886   12.285392       0.087883   \n",
       "std          0.390467           0.094315    9.728410       0.037878   \n",
       "min          0.047962           0.282812    0.459498       0.017895   \n",
       "25%          0.792317           0.398802    6.436859       0.062798   \n",
       "50%          1.077449           0.454388   10.405729       0.083313   \n",
       "75%          1.286883           0.506764   15.333557       0.111164   \n",
       "max          2.005671           0.782194   72.937218       0.212767   \n",
       "\n",
       "       tail_risk  capital  \n",
       "count   7.000000    100.0  \n",
       "mean         inf  50000.0  \n",
       "std          NaN      0.0  \n",
       "min          inf  50000.0  \n",
       "25%          inf  50000.0  \n",
       "50%          NaN  50000.0  \n",
       "75%          inf  50000.0  \n",
       "max          inf  50000.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>average_positions</th>\n",
       "      <th>average_position_size</th>\n",
       "      <th>average_portfolio_return</th>\n",
       "      <th>portfolio_std</th>\n",
       "      <th>cumulative_return</th>\n",
       "      <th>max_drawdown</th>\n",
       "      <th>sharpe</th>\n",
       "      <th>annualised_ret</th>\n",
       "      <th>annual_volatility</th>\n",
       "      <th>sortino</th>\n",
       "      <th>downside_risk</th>\n",
       "      <th>tail_risk</th>\n",
       "      <th>capital</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>11.227572</td>\n",
       "      <td>76261.179200</td>\n",
       "      <td>0.003186</td>\n",
       "      <td>0.029285</td>\n",
       "      <td>2.923035</td>\n",
       "      <td>-0.112575</td>\n",
       "      <td>1.738981</td>\n",
       "      <td>1.067099</td>\n",
       "      <td>0.464886</td>\n",
       "      <td>12.285392</td>\n",
       "      <td>0.087883</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.387138</td>\n",
       "      <td>16357.811663</td>\n",
       "      <td>0.000859</td>\n",
       "      <td>0.005941</td>\n",
       "      <td>1.334308</td>\n",
       "      <td>0.054738</td>\n",
       "      <td>0.424342</td>\n",
       "      <td>0.390467</td>\n",
       "      <td>0.094315</td>\n",
       "      <td>9.728410</td>\n",
       "      <td>0.037878</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>6.881720</td>\n",
       "      <td>46324.010802</td>\n",
       "      <td>0.000388</td>\n",
       "      <td>0.017816</td>\n",
       "      <td>0.090291</td>\n",
       "      <td>-0.279671</td>\n",
       "      <td>0.310099</td>\n",
       "      <td>0.047962</td>\n",
       "      <td>0.282812</td>\n",
       "      <td>0.459498</td>\n",
       "      <td>0.017895</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>9.677419</td>\n",
       "      <td>64819.824511</td>\n",
       "      <td>0.002654</td>\n",
       "      <td>0.025122</td>\n",
       "      <td>1.935018</td>\n",
       "      <td>-0.142298</td>\n",
       "      <td>1.478694</td>\n",
       "      <td>0.792317</td>\n",
       "      <td>0.398802</td>\n",
       "      <td>6.436859</td>\n",
       "      <td>0.062798</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>10.967742</td>\n",
       "      <td>74948.548828</td>\n",
       "      <td>0.003254</td>\n",
       "      <td>0.028624</td>\n",
       "      <td>2.854072</td>\n",
       "      <td>-0.109124</td>\n",
       "      <td>1.740068</td>\n",
       "      <td>1.077449</td>\n",
       "      <td>0.454388</td>\n",
       "      <td>10.405729</td>\n",
       "      <td>0.083313</td>\n",
       "      <td>NaN</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>12.903226</td>\n",
       "      <td>86202.950005</td>\n",
       "      <td>0.003707</td>\n",
       "      <td>0.031923</td>\n",
       "      <td>3.601407</td>\n",
       "      <td>-0.071364</td>\n",
       "      <td>2.003689</td>\n",
       "      <td>1.286883</td>\n",
       "      <td>0.506764</td>\n",
       "      <td>15.333557</td>\n",
       "      <td>0.111164</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>17.204301</td>\n",
       "      <td>119485.022168</td>\n",
       "      <td>0.005179</td>\n",
       "      <td>0.049274</td>\n",
       "      <td>6.619313</td>\n",
       "      <td>-0.018933</td>\n",
       "      <td>3.038153</td>\n",
       "      <td>2.005671</td>\n",
       "      <td>0.782194</td>\n",
       "      <td>72.937218</td>\n",
       "      <td>0.212767</td>\n",
       "      <td>inf</td>\n",
       "      <td>50000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       average_positions  average_position_size  average_portfolio_return  \\\n",
       "count         100.000000             100.000000                100.000000   \n",
       "mean           11.227572           76261.179200                  0.003186   \n",
       "std             2.387138           16357.811663                  0.000859   \n",
       "min             6.881720           46324.010802                  0.000388   \n",
       "25%             9.677419           64819.824511                  0.002654   \n",
       "50%            10.967742           74948.548828                  0.003254   \n",
       "75%            12.903226           86202.950005                  0.003707   \n",
       "max            17.204301          119485.022168                  0.005179   \n",
       "\n",
       "       portfolio_std  cumulative_return  max_drawdown      sharpe  \\\n",
       "count     100.000000         100.000000    100.000000  100.000000   \n",
       "mean        0.029285           2.923035     -0.112575    1.738981   \n",
       "std         0.005941           1.334308      0.054738    0.424342   \n",
       "min         0.017816           0.090291     -0.279671    0.310099   \n",
       "25%         0.025122           1.935018     -0.142298    1.478694   \n",
       "50%         0.028624           2.854072     -0.109124    1.740068   \n",
       "75%         0.031923           3.601407     -0.071364    2.003689   \n",
       "max         0.049274           6.619313     -0.018933    3.038153   \n",
       "\n",
       "       annualised_ret  annual_volatility     sortino  downside_risk  \\\n",
       "count      100.000000         100.000000  100.000000     100.000000   \n",
       "mean         1.067099           0.464886   12.285392       0.087883   \n",
       "std          0.390467           0.094315    9.728410       0.037878   \n",
       "min          0.047962           0.282812    0.459498       0.017895   \n",
       "25%          0.792317           0.398802    6.436859       0.062798   \n",
       "50%          1.077449           0.454388   10.405729       0.083313   \n",
       "75%          1.286883           0.506764   15.333557       0.111164   \n",
       "max          2.005671           0.782194   72.937218       0.212767   \n",
       "\n",
       "       tail_risk  capital  \n",
       "count   7.000000    100.0  \n",
       "mean         inf  50000.0  \n",
       "std          NaN      0.0  \n",
       "min          inf  50000.0  \n",
       "25%          inf  50000.0  \n",
       "50%          NaN  50000.0  \n",
       "75%          inf  50000.0  \n",
       "max          inf  50000.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>average_positions</th>\n",
       "      <th>average_position_size</th>\n",
       "      <th>average_portfolio_return</th>\n",
       "      <th>portfolio_std</th>\n",
       "      <th>cumulative_return</th>\n",
       "      <th>max_drawdown</th>\n",
       "      <th>sharpe</th>\n",
       "      <th>annualised_ret</th>\n",
       "      <th>annual_volatility</th>\n",
       "      <th>sortino</th>\n",
       "      <th>downside_risk</th>\n",
       "      <th>tail_risk</th>\n",
       "      <th>capital</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>85.000000</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>22.095755</td>\n",
       "      <td>152105.583576</td>\n",
       "      <td>0.003102</td>\n",
       "      <td>0.020401</td>\n",
       "      <td>2.997059</td>\n",
       "      <td>-0.075536</td>\n",
       "      <td>2.438061</td>\n",
       "      <td>1.099897</td>\n",
       "      <td>0.323859</td>\n",
       "      <td>17.271529</td>\n",
       "      <td>0.060525</td>\n",
       "      <td>inf</td>\n",
       "      <td>100000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>4.202118</td>\n",
       "      <td>29768.122340</td>\n",
       "      <td>0.000614</td>\n",
       "      <td>0.003056</td>\n",
       "      <td>1.099452</td>\n",
       "      <td>0.055530</td>\n",
       "      <td>0.470058</td>\n",
       "      <td>0.312612</td>\n",
       "      <td>0.048510</td>\n",
       "      <td>11.947575</td>\n",
       "      <td>0.028424</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10.967742</td>\n",
       "      <td>75796.184773</td>\n",
       "      <td>0.001644</td>\n",
       "      <td>0.014937</td>\n",
       "      <td>0.913678</td>\n",
       "      <td>-0.344750</td>\n",
       "      <td>1.117171</td>\n",
       "      <td>0.421526</td>\n",
       "      <td>0.237123</td>\n",
       "      <td>2.690172</td>\n",
       "      <td>0.015151</td>\n",
       "      <td>inf</td>\n",
       "      <td>100000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>19.386123</td>\n",
       "      <td>133127.178638</td>\n",
       "      <td>0.002590</td>\n",
       "      <td>0.018518</td>\n",
       "      <td>2.066658</td>\n",
       "      <td>-0.094928</td>\n",
       "      <td>2.085404</td>\n",
       "      <td>0.835444</td>\n",
       "      <td>0.293967</td>\n",
       "      <td>9.897639</td>\n",
       "      <td>0.042804</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>21.935484</td>\n",
       "      <td>151008.499414</td>\n",
       "      <td>0.003170</td>\n",
       "      <td>0.020063</td>\n",
       "      <td>2.992918</td>\n",
       "      <td>-0.060960</td>\n",
       "      <td>2.457380</td>\n",
       "      <td>1.117651</td>\n",
       "      <td>0.318490</td>\n",
       "      <td>13.571511</td>\n",
       "      <td>0.059796</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>24.354839</td>\n",
       "      <td>169166.858804</td>\n",
       "      <td>0.003417</td>\n",
       "      <td>0.021696</td>\n",
       "      <td>3.471873</td>\n",
       "      <td>-0.042117</td>\n",
       "      <td>2.789298</td>\n",
       "      <td>1.251763</td>\n",
       "      <td>0.344417</td>\n",
       "      <td>21.010622</td>\n",
       "      <td>0.071644</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>34.838710</td>\n",
       "      <td>243069.963378</td>\n",
       "      <td>0.004669</td>\n",
       "      <td>0.032978</td>\n",
       "      <td>6.175693</td>\n",
       "      <td>-0.015566</td>\n",
       "      <td>3.491875</td>\n",
       "      <td>1.909531</td>\n",
       "      <td>0.523504</td>\n",
       "      <td>61.634420</td>\n",
       "      <td>0.169604</td>\n",
       "      <td>inf</td>\n",
       "      <td>100000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       average_positions  average_position_size  average_portfolio_return  \\\n",
       "count         100.000000             100.000000                100.000000   \n",
       "mean           22.095755          152105.583576                  0.003102   \n",
       "std             4.202118           29768.122340                  0.000614   \n",
       "min            10.967742           75796.184773                  0.001644   \n",
       "25%            19.386123          133127.178638                  0.002590   \n",
       "50%            21.935484          151008.499414                  0.003170   \n",
       "75%            24.354839          169166.858804                  0.003417   \n",
       "max            34.838710          243069.963378                  0.004669   \n",
       "\n",
       "       portfolio_std  cumulative_return  max_drawdown      sharpe  \\\n",
       "count     100.000000         100.000000    100.000000  100.000000   \n",
       "mean        0.020401           2.997059     -0.075536    2.438061   \n",
       "std         0.003056           1.099452      0.055530    0.470058   \n",
       "min         0.014937           0.913678     -0.344750    1.117171   \n",
       "25%         0.018518           2.066658     -0.094928    2.085404   \n",
       "50%         0.020063           2.992918     -0.060960    2.457380   \n",
       "75%         0.021696           3.471873     -0.042117    2.789298   \n",
       "max         0.032978           6.175693     -0.015566    3.491875   \n",
       "\n",
       "       annualised_ret  annual_volatility     sortino  downside_risk  \\\n",
       "count      100.000000         100.000000  100.000000     100.000000   \n",
       "mean         1.099897           0.323859   17.271529       0.060525   \n",
       "std          0.312612           0.048510   11.947575       0.028424   \n",
       "min          0.421526           0.237123    2.690172       0.015151   \n",
       "25%          0.835444           0.293967    9.897639       0.042804   \n",
       "50%          1.117651           0.318490   13.571511       0.059796   \n",
       "75%          1.251763           0.344417   21.010622       0.071644   \n",
       "max          1.909531           0.523504   61.634420       0.169604   \n",
       "\n",
       "       tail_risk   capital  \n",
       "count  85.000000     100.0  \n",
       "mean         inf  100000.0  \n",
       "std          NaN       0.0  \n",
       "min          inf  100000.0  \n",
       "25%          NaN  100000.0  \n",
       "50%          NaN  100000.0  \n",
       "75%          NaN  100000.0  \n",
       "max          inf  100000.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>average_positions</th>\n",
       "      <th>average_position_size</th>\n",
       "      <th>average_portfolio_return</th>\n",
       "      <th>portfolio_std</th>\n",
       "      <th>cumulative_return</th>\n",
       "      <th>max_drawdown</th>\n",
       "      <th>sharpe</th>\n",
       "      <th>annualised_ret</th>\n",
       "      <th>annual_volatility</th>\n",
       "      <th>sortino</th>\n",
       "      <th>downside_risk</th>\n",
       "      <th>tail_risk</th>\n",
       "      <th>capital</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>1.000000e+02</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>57.014906</td>\n",
       "      <td>397606.320751</td>\n",
       "      <td>0.003110</td>\n",
       "      <td>0.012709</td>\n",
       "      <td>3.125492</td>\n",
       "      <td>-0.037299</td>\n",
       "      <td>3.894212</td>\n",
       "      <td>1.149219</td>\n",
       "      <td>0.201744</td>\n",
       "      <td>23.192545</td>\n",
       "      <td>0.037259</td>\n",
       "      <td>inf</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.076068</td>\n",
       "      <td>42456.304857</td>\n",
       "      <td>0.000352</td>\n",
       "      <td>0.000990</td>\n",
       "      <td>0.660183</td>\n",
       "      <td>0.017999</td>\n",
       "      <td>0.423458</td>\n",
       "      <td>0.186585</td>\n",
       "      <td>0.015720</td>\n",
       "      <td>8.662841</td>\n",
       "      <td>0.010520</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>39.784946</td>\n",
       "      <td>280732.172990</td>\n",
       "      <td>0.002077</td>\n",
       "      <td>0.010466</td>\n",
       "      <td>1.530757</td>\n",
       "      <td>-0.122648</td>\n",
       "      <td>2.636441</td>\n",
       "      <td>0.654001</td>\n",
       "      <td>0.166145</td>\n",
       "      <td>8.166482</td>\n",
       "      <td>0.017061</td>\n",
       "      <td>6.247094e+00</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>53.118280</td>\n",
       "      <td>370699.642483</td>\n",
       "      <td>0.002867</td>\n",
       "      <td>0.012096</td>\n",
       "      <td>2.637426</td>\n",
       "      <td>-0.044308</td>\n",
       "      <td>3.607025</td>\n",
       "      <td>1.013326</td>\n",
       "      <td>0.192012</td>\n",
       "      <td>16.905889</td>\n",
       "      <td>0.030618</td>\n",
       "      <td>7.239463e+01</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>56.881720</td>\n",
       "      <td>397630.079189</td>\n",
       "      <td>0.003123</td>\n",
       "      <td>0.012659</td>\n",
       "      <td>3.091242</td>\n",
       "      <td>-0.032778</td>\n",
       "      <td>3.877471</td>\n",
       "      <td>1.145784</td>\n",
       "      <td>0.200956</td>\n",
       "      <td>22.243098</td>\n",
       "      <td>0.035643</td>\n",
       "      <td>1.149488e+14</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>60.752688</td>\n",
       "      <td>424563.055292</td>\n",
       "      <td>0.003352</td>\n",
       "      <td>0.013125</td>\n",
       "      <td>3.550711</td>\n",
       "      <td>-0.026424</td>\n",
       "      <td>4.179165</td>\n",
       "      <td>1.273194</td>\n",
       "      <td>0.208349</td>\n",
       "      <td>27.362399</td>\n",
       "      <td>0.043842</td>\n",
       "      <td>2.340766e+14</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>69.462366</td>\n",
       "      <td>484395.413443</td>\n",
       "      <td>0.003892</td>\n",
       "      <td>0.016192</td>\n",
       "      <td>4.841764</td>\n",
       "      <td>-0.010759</td>\n",
       "      <td>4.760423</td>\n",
       "      <td>1.602660</td>\n",
       "      <td>0.257042</td>\n",
       "      <td>54.078001</td>\n",
       "      <td>0.067758</td>\n",
       "      <td>inf</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       average_positions  average_position_size  average_portfolio_return  \\\n",
       "count         100.000000             100.000000                100.000000   \n",
       "mean           57.014906          397606.320751                  0.003110   \n",
       "std             6.076068           42456.304857                  0.000352   \n",
       "min            39.784946          280732.172990                  0.002077   \n",
       "25%            53.118280          370699.642483                  0.002867   \n",
       "50%            56.881720          397630.079189                  0.003123   \n",
       "75%            60.752688          424563.055292                  0.003352   \n",
       "max            69.462366          484395.413443                  0.003892   \n",
       "\n",
       "       portfolio_std  cumulative_return  max_drawdown      sharpe  \\\n",
       "count     100.000000         100.000000    100.000000  100.000000   \n",
       "mean        0.012709           3.125492     -0.037299    3.894212   \n",
       "std         0.000990           0.660183      0.017999    0.423458   \n",
       "min         0.010466           1.530757     -0.122648    2.636441   \n",
       "25%         0.012096           2.637426     -0.044308    3.607025   \n",
       "50%         0.012659           3.091242     -0.032778    3.877471   \n",
       "75%         0.013125           3.550711     -0.026424    4.179165   \n",
       "max         0.016192           4.841764     -0.010759    4.760423   \n",
       "\n",
       "       annualised_ret  annual_volatility     sortino  downside_risk  \\\n",
       "count      100.000000         100.000000  100.000000     100.000000   \n",
       "mean         1.149219           0.201744   23.192545       0.037259   \n",
       "std          0.186585           0.015720    8.662841       0.010520   \n",
       "min          0.654001           0.166145    8.166482       0.017061   \n",
       "25%          1.013326           0.192012   16.905889       0.030618   \n",
       "50%          1.145784           0.200956   22.243098       0.035643   \n",
       "75%          1.273194           0.208349   27.362399       0.043842   \n",
       "max          1.602660           0.257042   54.078001       0.067758   \n",
       "\n",
       "          tail_risk   capital  \n",
       "count  1.000000e+02     100.0  \n",
       "mean            inf  250000.0  \n",
       "std             NaN       0.0  \n",
       "min    6.247094e+00  250000.0  \n",
       "25%    7.239463e+01  250000.0  \n",
       "50%    1.149488e+14  250000.0  \n",
       "75%    2.340766e+14  250000.0  \n",
       "max             inf  250000.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>average_positions</th>\n",
       "      <th>average_position_size</th>\n",
       "      <th>average_portfolio_return</th>\n",
       "      <th>portfolio_std</th>\n",
       "      <th>cumulative_return</th>\n",
       "      <th>max_drawdown</th>\n",
       "      <th>sharpe</th>\n",
       "      <th>annualised_ret</th>\n",
       "      <th>annual_volatility</th>\n",
       "      <th>sortino</th>\n",
       "      <th>downside_risk</th>\n",
       "      <th>tail_risk</th>\n",
       "      <th>capital</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>108.142173</td>\n",
       "      <td>757858.917202</td>\n",
       "      <td>0.003004</td>\n",
       "      <td>0.008665</td>\n",
       "      <td>2.974238</td>\n",
       "      <td>-0.024289</td>\n",
       "      <td>5.517803</td>\n",
       "      <td>1.109975</td>\n",
       "      <td>0.137545</td>\n",
       "      <td>29.262258</td>\n",
       "      <td>0.027377</td>\n",
       "      <td>8.434089</td>\n",
       "      <td>500000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>5.975605</td>\n",
       "      <td>42080.579071</td>\n",
       "      <td>0.000225</td>\n",
       "      <td>0.000540</td>\n",
       "      <td>0.414133</td>\n",
       "      <td>0.009613</td>\n",
       "      <td>0.447654</td>\n",
       "      <td>0.118912</td>\n",
       "      <td>0.008571</td>\n",
       "      <td>8.139811</td>\n",
       "      <td>0.005945</td>\n",
       "      <td>3.278267</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>94.838710</td>\n",
       "      <td>657017.077313</td>\n",
       "      <td>0.002479</td>\n",
       "      <td>0.007387</td>\n",
       "      <td>2.106593</td>\n",
       "      <td>-0.067696</td>\n",
       "      <td>4.318615</td>\n",
       "      <td>0.848359</td>\n",
       "      <td>0.117259</td>\n",
       "      <td>14.526830</td>\n",
       "      <td>0.014125</td>\n",
       "      <td>4.174481</td>\n",
       "      <td>500000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>104.731183</td>\n",
       "      <td>733825.599755</td>\n",
       "      <td>0.002865</td>\n",
       "      <td>0.008225</td>\n",
       "      <td>2.718569</td>\n",
       "      <td>-0.027682</td>\n",
       "      <td>5.259526</td>\n",
       "      <td>1.037539</td>\n",
       "      <td>0.130569</td>\n",
       "      <td>23.953173</td>\n",
       "      <td>0.023157</td>\n",
       "      <td>6.215086</td>\n",
       "      <td>500000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>107.982749</td>\n",
       "      <td>757549.169910</td>\n",
       "      <td>0.003017</td>\n",
       "      <td>0.008654</td>\n",
       "      <td>2.971819</td>\n",
       "      <td>-0.022286</td>\n",
       "      <td>5.522452</td>\n",
       "      <td>1.114192</td>\n",
       "      <td>0.137384</td>\n",
       "      <td>27.795763</td>\n",
       "      <td>0.027407</td>\n",
       "      <td>7.598986</td>\n",
       "      <td>500000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>112.365591</td>\n",
       "      <td>784202.891142</td>\n",
       "      <td>0.003140</td>\n",
       "      <td>0.009025</td>\n",
       "      <td>3.212689</td>\n",
       "      <td>-0.018426</td>\n",
       "      <td>5.836667</td>\n",
       "      <td>1.180731</td>\n",
       "      <td>0.143268</td>\n",
       "      <td>34.350296</td>\n",
       "      <td>0.030205</td>\n",
       "      <td>9.980531</td>\n",
       "      <td>500000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>123.870968</td>\n",
       "      <td>878138.554750</td>\n",
       "      <td>0.003627</td>\n",
       "      <td>0.010137</td>\n",
       "      <td>4.252630</td>\n",
       "      <td>-0.010073</td>\n",
       "      <td>6.492623</td>\n",
       "      <td>1.461723</td>\n",
       "      <td>0.160922</td>\n",
       "      <td>62.807220</td>\n",
       "      <td>0.048422</td>\n",
       "      <td>25.779303</td>\n",
       "      <td>500000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       average_positions  average_position_size  average_portfolio_return  \\\n",
       "count         100.000000             100.000000                100.000000   \n",
       "mean          108.142173          757858.917202                  0.003004   \n",
       "std             5.975605           42080.579071                  0.000225   \n",
       "min            94.838710          657017.077313                  0.002479   \n",
       "25%           104.731183          733825.599755                  0.002865   \n",
       "50%           107.982749          757549.169910                  0.003017   \n",
       "75%           112.365591          784202.891142                  0.003140   \n",
       "max           123.870968          878138.554750                  0.003627   \n",
       "\n",
       "       portfolio_std  cumulative_return  max_drawdown      sharpe  \\\n",
       "count     100.000000         100.000000    100.000000  100.000000   \n",
       "mean        0.008665           2.974238     -0.024289    5.517803   \n",
       "std         0.000540           0.414133      0.009613    0.447654   \n",
       "min         0.007387           2.106593     -0.067696    4.318615   \n",
       "25%         0.008225           2.718569     -0.027682    5.259526   \n",
       "50%         0.008654           2.971819     -0.022286    5.522452   \n",
       "75%         0.009025           3.212689     -0.018426    5.836667   \n",
       "max         0.010137           4.252630     -0.010073    6.492623   \n",
       "\n",
       "       annualised_ret  annual_volatility     sortino  downside_risk  \\\n",
       "count      100.000000         100.000000  100.000000     100.000000   \n",
       "mean         1.109975           0.137545   29.262258       0.027377   \n",
       "std          0.118912           0.008571    8.139811       0.005945   \n",
       "min          0.848359           0.117259   14.526830       0.014125   \n",
       "25%          1.037539           0.130569   23.953173       0.023157   \n",
       "50%          1.114192           0.137384   27.795763       0.027407   \n",
       "75%          1.180731           0.143268   34.350296       0.030205   \n",
       "max          1.461723           0.160922   62.807220       0.048422   \n",
       "\n",
       "        tail_risk   capital  \n",
       "count  100.000000     100.0  \n",
       "mean     8.434089  500000.0  \n",
       "std      3.278267       0.0  \n",
       "min      4.174481  500000.0  \n",
       "25%      6.215086  500000.0  \n",
       "50%      7.598986  500000.0  \n",
       "75%      9.980531  500000.0  \n",
       "max     25.779303  500000.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: []\n",
       "Index: []"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_summaries.groupby('cc').apply( lambda x: display(x.describe()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from plotnine import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/plotnine/utils.py:281: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  ndistinct = ids.apply(len_unique, axis=0).as_matrix()\n",
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/pandas/core/generic.py:4384: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  object.__getattribute__(self, name)\n",
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/pandas/core/generic.py:4385: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  return object.__setattr__(self, name, value)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (8747888107882)>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ggplot(all_summaries, aes('annualised_ret')) + geom_density(aes(color = 'cc'), alpha = 0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/plotnine/utils.py:281: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  ndistinct = ids.apply(len_unique, axis=0).as_matrix()\n",
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/plotnine/stats/stat_bin.py:90: UserWarning: 'stat_bin()' using 'bins = 27'. Pick better value with 'binwidth'.\n",
      "  warn(msg.format(params['bins']))\n",
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/pandas/core/generic.py:4384: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  object.__getattribute__(self, name)\n",
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/pandas/core/generic.py:4385: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  return object.__setattr__(self, name, value)\n",
      "/home/sergiusz/anaconda3/envs/whitelist/lib/python3.6/site-packages/plotnine/positions/position.py:188: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  intervals = data[xminmax].drop_duplicates().as_matrix().flatten()\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (-9223363289036985933)>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ggplot(all_summaries, aes('annualised_ret')) + geom_histogram(aes(fill = 'cc')) + facet_wrap('~cc')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:whitelist]",
   "language": "python",
   "name": "conda-env-whitelist-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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}