Measure Investor Risk

RiskMeasure.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "import matplotlib.ticker as mticker\n",
    "plt.xkcd()\n",
    "import pandas as pd\n",
    "import ipywidgets as widgets\n",
    "from IPython.display import display\n",
    "from IPython.display import clear_output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Drawer:\n",
    "    def __init__(self):\n",
    "        self.reset()\n",
    "    def reset(self):\n",
    "        s, p, u = self.roll()\n",
    "        self.s = s\n",
    "        self.p = p\n",
    "        self.u = u\n",
    "    def roll(self):\n",
    "        u = np.around(np.random.uniform(0, 0.2), 2)\n",
    "        p = np.random.choice(np.linspace(0.05, 0.95, 19))\n",
    "        s = p*u+(1-p)*(-u)\n",
    "        return s, p, u\n",
    "    def draw(self):\n",
    "        s = self.s\n",
    "        p = self.p\n",
    "        u = self.u\n",
    "        f = plt.figure()#figsize=(10, 10))\n",
    "        plt.bar(['Win', 'Loss', 'Safe'], height=[100*u, -100*u, 100*s], width=[p, 1-p, 1], color=['#9bc53d', '#e55934', '#5bc0eb'])\n",
    "        plt.gca().text('Win', 100*u/2, str(np.around(100*u, 2)) + '%\\n'+'mit Wkt\\n' +str(np.around(100*p, 2)) + '%', ha='center')\n",
    "        plt.gca().text('Loss', -100*u/2, str(np.around(100*-u, 2)) + '%\\n'+'mit Wkt\\n' + str(np.around(100*(1-p), 2)) + '%', ha='center')\n",
    "        plt.gca().text('Safe', 100*s/2, str(np.around(100*s, 2)) + '%\\n'+'sicher', ha='center')\n",
    "        plt.ylabel('Rendite (%)')\n",
    "        plt.ylim((-25, 25))\n",
    "        display(f)\n",
    "    def save(self, r=-1):\n",
    "        f = open('log.txt', 'a+', encoding='utf-8')\n",
    "        f.write(str(self.s) + ';' + str(self.p) + ';' + str(self.u) + ';' + str(r) + '\\n')\n",
    "        f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "09c675d1d82e4e869521aca0f739b26a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "624c60d6d2974d9e8ec19b285e214fbe",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Button(description='Risiko', style=ButtonStyle())"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "edd5128fcebc4de0a6ce93c5f3e7978f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Button(description='Sicher', style=ButtonStyle())"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "49f1d59e99b749379ceb47165221f59f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Button(description='Next', style=ButtonStyle())"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "yes = widgets.Button(description=\"Risiko\")\n",
    "no = widgets.Button(description=\"Sicher\")\n",
    "nextbtn = widgets.Button(description=\"Next\")\n",
    "\n",
    "output = widgets.Output()\n",
    "display(output, yes, no, nextbtn)\n",
    "\n",
    "d = Drawer()\n",
    "\n",
    "def on_yes_button_clicked(b):\n",
    "    with output:\n",
    "        clear_output(wait=True)\n",
    "        d.save(1)\n",
    "        d.reset()\n",
    "        d.draw()\n",
    "        \n",
    "yes.on_click(on_yes_button_clicked)\n",
    "def on_no_button_clicked(b):\n",
    "    with output:\n",
    "        clear_output(wait=True)\n",
    "        d.save(0)\n",
    "        d.reset()\n",
    "        d.draw()\n",
    "        \n",
    "no.on_click(on_no_button_clicked)\n",
    "def on_next_button_clicked(b):\n",
    "    with output:\n",
    "        clear_output(wait=True)\n",
    "        d.reset()\n",
    "        d.draw()\n",
    "        \n",
    "nextbtn.on_click(on_next_button_clicked)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('log.txt', sep=';', header=-1)\n",
    "df.columns = ['s', 'p', 'u', 'r']\n",
    "df['color'] = df['r'].apply(lambda x: 'red' if x == 1 else 'blue')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Mean')"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['u'], df['s'], color=df['color'])\n",
    "plt.xlabel('Std')\n",
    "plt.ylabel('Mean')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}