KDE with StatsModels

kde_statsmodels.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from ipywidgets import interact\n",
    "import ipywidgets as widgets\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy import stats\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.distributions.mixture_rvs import mixture_rvs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "dist1_loc, dist1_scale, weight1 = 100 , 100, 0.5\n",
    "dist2_loc, dist2_scale, weight2 = 300 , 40, 0.5\n",
    "\n",
    "X = mixture_rvs(prob=[weight1, weight2], size=250,\n",
    "                        dist=[stats.norm, stats.norm],\n",
    "                        kwargs = (dict(loc=dist1_loc, scale=dist1_scale),\n",
    "                                  dict(loc=dist2_loc, scale=dist2_scale)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6580698853e1422ca04c436e08d33c26",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(IntSlider(value=30, description='bw', max=50, step=5), Dropdown(description='Kernel', in…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dd = widgets.Dropdown(\n",
    "    options=['biw', 'cos', 'epa', 'gau', 'tri', 'triw', 'uni'],\n",
    "    value='gau',\n",
    "    description='Kernel',\n",
    "    disabled=False,\n",
    ")\n",
    "\n",
    "@interact(bw=(0, 50, 5), kernel=dd)\n",
    "def plot_kde(bw=30, kernel='gau'):\n",
    "    kde = sm.nonparametric.KDEUnivariate(X)\n",
    "    kde.fit(kernel=kernel, bw=bw, fft=False)\n",
    "\n",
    "    fig = plt.figure(figsize=(12, 5))\n",
    "    ax = fig.add_subplot(111)\n",
    "    ax.set_xlim((-300, 500))\n",
    "    ax.set_ylim((0, 0.008))\n",
    "\n",
    "    # Plot the histrogram\n",
    "    ax.hist(X, bins=20, density=True, label='Histogram from samples',\n",
    "            zorder=5, edgecolor='k', alpha=0.5)\n",
    "\n",
    "    # Plot the KDE as fitted using the default arguments\n",
    "    ax.plot(kde.support, kde.density, lw=3, label='KDE from samples', zorder=10)\n",
    "\n",
    "    # Plot the true distribution\n",
    "    true_values = (stats.norm.pdf(loc=100, scale=100, x=kde.support)*0.5\n",
    "                  + stats.norm.pdf(loc=300, scale=40, x=kde.support)*0.5)\n",
    "    ax.plot(kde.support, true_values, lw=3, label='True distribution', zorder=15)\n",
    "\n",
    "    ax.legend(loc='best')\n",
    "    ax.grid(True, zorder=-5)"
   ]
  }
 ],
 "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
}