{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Interactive Accumulator Models with `Evidently`\n",
    "\n",
    "This notebook contains interactive visualisations for a number of evidence models\n",
    "created using the [evidently](https://github.com/EoinTravers/Evidently) package for python.\n",
    "\n",
    "If you're running this notebook on [mybinder.org](https://mybinder.org/),\n",
    "and find things to be a little slow,\n",
    "you can run the code on your own machine instead by downloading the \n",
    "[GitHub repository](https://github.com/EoinTravers/Evidently).\n",
    "\n",
    "If you're unfamiliar with [Jupyter notebooks](https://jupyter.org/),\n",
    "you can:\n",
    "- Run each code cell by clicking on it to select it,\n",
    "  then clicking the \n",
    "  [<i class=\"fa-step-forward fa\"></i> Run]\n",
    "  button in the toolbar above.\n",
    "- Run everything by clicking [Cell] → [Run All]\n",
    "\n",
    "Either way, some of the cells below will generate interactive plots with sliders attached.\n",
    "Go ahead and play with the sliders, and see what happens!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import evidently\n",
    "\n",
    "from ipywidgets import interact, FloatSlider\n",
    "def fs(v, low, high, step, desc=''):\n",
    "    return FloatSlider(value=v, min=low, max=high, step=step, description=desc, continuous_update=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Simple Wald Model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(evidently.Wald.__doc__) # Print the documentation for this model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def wald_simulation_plot(t0=1., v=.5, z=0, a=1., c=1.):\n",
    "    model = evidently.Wald(pars=[t0, v, z, a, c], max_time=5)\n",
    "    evidently.viz.visualise_model(model, model_type='wald', measure='raw')\n",
    "    title = 'Start time = %.1f, Drift = %.1f, Start = %.1f, Threshold = %.1f' % (t0, v, z, a)\n",
    "    plt.suptitle(title, y=1.01)\n",
    "    plt.show()\n",
    "\n",
    "interact(wald_simulation_plot,\n",
    "         t0  = fs(1., 0, 5., .1,   'Start time'),\n",
    "         v   = fs(.5, 0, 2., .1,   'Drift'),\n",
    "         z   = fs(0, 0, .5, .1,   'Starting point'),\n",
    "         a   = fs(.5, 0., 2., .1,   'Threshold'),\n",
    "         c   = fs(.1, 0., 2., .1,   'Noise SD'));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Simple Drift Diffusion Model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(evidently.Diffusion.__doc__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def ddm_simulation_plot(t0=1., v=.5, z=0., a=.5, c=.1):\n",
    "    model = evidently.Diffusion(pars=[t0, v, z, a, c])\n",
    "    evidently.viz.visualise_model(model)\n",
    "    title = 't0 = %.1f, Drift = %.1f, Bias = %.1f, Threshold = %.1f' % (t0, v, z, a)\n",
    "    plt.suptitle(title, y=1.01)\n",
    "    plt.show()\n",
    "\n",
    "interact(ddm_simulation_plot,\n",
    "         t0  = fs(1., 0, 2., .1,   't0'),\n",
    "         v   = fs(.5, 0, 2., .1,   'Drift'),\n",
    "         z   = fs(-.5, -1., 1., .1,  'Bias'),\n",
    "         a     = fs(.5, 0., 2., .1,   'Threshold'),\n",
    "         c   = fs(.2, 0., 1., .1,   'Noise SD'));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hierarchical Drift Diffusion Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(evidently.HDiffusion.__doc__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def hddm_simulation_plot(m_t0=1., m_v=.5, m_z=0., m_a=.5,\n",
    "                         s_t0=.1, s_v=.1, s_z=.1, s_a=.1, c=.1):\n",
    "    model = evidently.HDiffusion(pars=[m_t0, m_v, m_z, m_a, s_t0, s_v, s_z, s_a, c])\n",
    "    evidently.viz.visualise_model(model, measure='means', threshold=m_a)\n",
    "    title = 't0 = %.1f (%.1f), Drift = %.1f (%.1f), Bias = %.1f (%.1f), Threshold = %.1f (%.1f), Noise = %.1f' % (\n",
    "        m_t0, s_t0, m_v, s_v, m_z, s_z, m_a, s_a, c)\n",
    "    plt.suptitle(title, y=1.05)\n",
    "    plt.show()\n",
    "\n",
    "interact(hddm_simulation_plot,\n",
    "    m_t0 = fs(1., 0., 1., .1, 'T0'),\n",
    "    m_v  = fs(.5, -1., 1., .1, 'Drift'),\n",
    "    m_z  = fs(-.5, -1., 1., .1, 'Bias'),\n",
    "    m_a  = fs(1., 0., 2., .1, 'Threshold'),\n",
    "    s_t0 = fs(.1, 0., 1., .1, 'SD T0'),\n",
    "    s_v  = fs(.5, 0., 1., .1, 'SD Drift'),\n",
    "    s_z  = fs(.1, 0., 1., .1, 'SD Bias'),\n",
    "    s_a  = fs(.1, 0., 1., .1, 'SD Threshold'),\n",
    "    c    = fs(.1, 0., 1., .1, 'Noise'));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Race"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(evidently.Race.__doc__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def race_simulation_plot(t1, v1, z1, c1, t2, v2, z2, c2, a):\n",
    "    model = evidently.Race(pars=[t1, v1, z1, c1, t2, v2, z2, c2, a])\n",
    "    evidently.viz.visualise_model(model, model_type='race', measure='means')\n",
    "    title = 'Option #1: t0 = %.1f, Drift = %.1f, Bias = %.1f, Noise = %.1f' % (t1, v1, z1, c1)\n",
    "    title += '\\nOption #2: t0 = %.1f, Drift = %.1f, Bias = %.1f, Noise = %.1f' % (t2, v2, z2, c2)\n",
    "    title += '\\nThreshold: %.1f' % a    \n",
    "    plt.suptitle(title, y=1.2)\n",
    "    plt.show()\n",
    "\n",
    "interact(race_simulation_plot,\n",
    "         t1   = fs(1., 0, 2., .1,   '#1: t0'),\n",
    "         v1   = fs(.5, 0, 2., .1,   '#1: Drift'),\n",
    "         z1   = fs(0., 0, 1., .1,  '#1: Bias'),\n",
    "         c1   = fs(.1, 0., 1., .1,   '#1: Noise SD'),\n",
    "         t2   = fs(2., 0, 2., .1,   '#2: t0'),\n",
    "         v2   = fs(.75, 0, 2., .1,   '#2: Drift'),\n",
    "         z2   = fs(.2, 0., 1., .1,  '#2: Bias'),\n",
    "         c2   = fs(.2, 0., 1., .1,   '#2: Noise SD'),\n",
    "         a     = fs(.5, 0., 2., .1,  'Threshold'));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Schurger Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(evidently.models.Schurger.__doc__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def schurger_simulation_plot(t0=0., v=.5, k=.6, z=0., a=1., c=1.):\n",
    "    model = evidently.models.Schurger(pars=[t0, v, k, z, a, c], max_time=20.)\n",
    "    evidently.viz.visualise_schurger(model, rp_duration=3)\n",
    "    title = 'Start time = %.1f, Input = %.1f, Decay = %.1f, Start = %.1f, Threshold = %.1f, Noise = %.1f' % (\n",
    "        t0, v, k, z, a, c)\n",
    "    plt.suptitle(title, y=1.05)\n",
    "    plt.show()\n",
    "\n",
    "interact(schurger_simulation_plot,\n",
    "         t0  = fs(0., 0, 5., .1,   'Start time'),\n",
    "         v   = fs(.5, 0, 2., .1,   'Drift'),\n",
    "         k   = fs(.6, 0, 2., .1,   'Decay'),\n",
    "         z   = fs(0, 0, 1., .1,   'Starting point'),\n",
    "         a   = fs(1., 0., 2., .1,   'Threshold'),\n",
    "         c   = fs(.1, 0., 1., .1,   'Noise SD'));"
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}