ml-finance-python

03_dirichlet_distribution.ipynb

(4797B)

 {
  "cells": [
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "# Dirichlet Distribution"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
     }
    },
    "source": [
     "## Imports"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2018-11-30T18:32:41.753600Z",
      "start_time": "2018-11-30T18:32:41.741408Z"
     },
     "slideshow": {
      "slide_type": "fragment"
     }
    },
    "outputs": [],
    "source": [
     "import warnings\n",
     "from collections import OrderedDict\n",
     "from pathlib import Path\n",
     "\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "\n",
     "# Visualization\n",
     "from ipywidgets import interact, FloatSlider\n",
     "import matplotlib.pyplot as plt\n",
     "import seaborn as sns"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2018-11-30T18:32:57.047779Z",
      "start_time": "2018-11-30T18:32:57.038865Z"
     }
    },
    "outputs": [],
    "source": [
     "%matplotlib inline\n",
     "plt.style.use('ggplot')\n",
     "plt.rcParams['figure.figsize'] = (14.0, 8.7)\n",
     "warnings.filterwarnings('ignore')\n",
     "pd.options.display.float_format = '{:,.2f}'.format"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
     }
    },
    "source": [
     "## Simulate Dirichlet Distribution"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "The Dirichlet distribution produces probability vectors that can be used with discrete distributions. That is, it randomly generates a given number of values that are positive and sum to one. It has a parameter 𝜶  of positive real value that controls the concentration of the probabilities. Values closer to zero mean that only a few values will be positive and receive most probability mass. \n",
     "\n",
     "The following simulation let's you interactively explore how different parameter values affect the resulting probability distributions."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2018-11-30T18:32:58.986986Z",
      "start_time": "2018-11-30T18:32:58.197387Z"
     },
     "hide_input": false,
     "scrolled": false,
     "slideshow": {
      "slide_type": "fragment"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
        "model_id": "1f076c57d1ff4decaae28960325cc703",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
        "interactive(children=(FloatSlider(value=1.0, continuous_update=False, description='Alpha', min=0.01, step=0.01…"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
     }
    ],
    "source": [
     "f=FloatSlider(value=1, min=1e-2, max=1e2, step=1e-2, continuous_update=False, description='Alpha')\n",
     "@interact(alpha=f)\n",
     "def sample_dirichlet(alpha):\n",
     "    topics = 10\n",
     "    draws= 9\n",
     "    alphas = np.full(shape=topics, fill_value=alpha)\n",
     "    samples = np.random.dirichlet(alpha=alphas, size=draws)\n",
     "    \n",
     "    fig, axes = plt.subplots(nrows=3, ncols=3, sharex=True, sharey=True)\n",
     "    axes = axes.flatten()\n",
     "    plt.setp(axes, ylim=(0, 1))\n",
     "    for i, sample in enumerate(samples):\n",
     "        axes[i].bar(x=list(range(10)), height=sample, color=sns.color_palette(\"Set2\", 10))\n",
     "    fig.suptitle('Dirichlet Allocation | 10 Topics, 9 Samples')\n",
     "    fig.tight_layout()\n",
     "    plt.subplots_adjust(top=.95)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": []
   }
  ],
  "metadata": {
   "celltoolbar": "Slideshow",
   "hide_input": false,
   "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": "3.6.8"
   },
   "name": "_merged",
   "toc": {
    "base_numbering": 1,
    "nav_menu": {},
    "number_sections": true,
    "sideBar": true,
    "skip_h1_title": false,
    "title_cell": "Table of Contents",
    "title_sidebar": "Contents",
    "toc_cell": false,
    "toc_position": {
     "height": "100px",
     "left": "85.9915px",
     "right": "1064px",
     "top": "66.3352px",
     "width": "241.562px"
    },
    "toc_section_display": true,
    "toc_window_display": true
   }
  },
  "nbformat": 4,
  "nbformat_minor": 2
 }