DifferentialRegression.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/differential-machine-learning/notebooks/blob/master/DifferentialRegression.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "hk92RcHiLru-"
   },
   "source": [
    "# Differential Regression\n",
    "\n",
    "---\n",
    "Brian Huge & Antoine Savine, May 2021\n",
    "---\n",
    "\n",
    "This notebook presents an implementation of <b> differential regression</b>, one of the algorithms introduced in our Risk article <b> Axes that matter: PCA with a difference. </b> The Risk article is published in the October 2021 issue of [Risk Magazine](https://www.risk.net/risk-magazine). It is also available on [Risk.net](https://www.risk.net/cutting-edge/banking/7877231/axes-that-matter-pca-with-a-difference), behind Risk paywall. \n",
    "\n",
    "The article is also presented in a recording publicly available on [YouTube](https://www.youtube.com/watch?v=eHZZa6fpL20), with closed-captions:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/eHZZa6fpL20\"     title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer;     autoplay; clipboard-write; encrypted-media; gyroscope;     picture-in-picture\" allowfullscreen></iframe>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "from IPython.display import HTML\n",
    "\n",
    "# Youtube\n",
    "HTML('<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/eHZZa6fpL20\" \\\n",
    "    title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; \\\n",
    "    autoplay; clipboard-write; encrypted-media; gyroscope; \\\n",
    "    picture-in-picture\" allowfullscreen></iframe>')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Differential regression implements <b> differential machine learning </b> in the simple context of linear regression. Linear regression is not the most powerful or novel corner of differential ML but it gives us a chance to illustrate and implement the main notions in a very simple context. Differential ML was introduced in our October 2020 Risk article [Differential Machine Learning: the Shape of Things to Come](https://www.risk.net/cutting-edge/banking/7688441/differential-machine-learning-the-shape-of-things-to-come). Its main promise is the design of novel, more effective, ML algorithms based on the availability of <b> differential labels </b>. Classic datasets in machine learning include inputs $X\\in\\mathbb{R}^n$ and labels $Y \\in \\mathbb{R}$. Differential labels are defined as the gradients of labels $Y$ wrt inputs $X$:\n",
    "    \n",
    "        \n",
    "$$Z^{\\left(i\\right)} \\equiv \\frac{\\partial Y^{\\left(i\\right)}}{\\partial X^{\\left(i\\right)}} \\in \\mathbb{R}^n$$\n",
    "    \n",
    "Differential labels are easily and efficiently computed with [algorithmic adjoint differentiation (AAD)](https://sites.google.com/view/antoinesavine-aad) in some situations, like simulated datasets in finance.\n",
    "\n",
    "Probably the simplest application of differential ML is a differential variant of linear regression. Recall that linear regression works with a fixed collection of basis functions of $X$:\n",
    "\n",
    "$$\\phi \\left( X \\right)\\equiv \\left[\\phi_1\\left(X\\right), ..., \\phi_K\\left(X\\right)\\right]$$\n",
    "    \n",
    "This notebook implements polynomial regression, where the basis functions are all the polynomials of $X=\\left[X_1, ..., X_n \\right]$ with degree up to $p$. The method is extended to arbitrary choices of basis functions in a straightforward manner. Note that the number $K$ of basis functions grows exponentially with dimension $n$, which is also generally true with other choices of basis functions. For this reason, linear regression is ineffective in high dimension and limited in practice to dimension lower than around $10$. More sophisticated ML models like neural networks are necessary in higher dimension, unless dimension is effectively reduced by adequate data pre-processing.\n",
    "\n",
    "Linear regression approximates the target $Y$ with a linear combination of the basis functions $\\phi$:\n",
    "\n",
    "$$\n",
    "    Y \\approx \\beta \\cdot \\phi\\left(X\\right)\n",
    "$$\n",
    "\n",
    "with weights $\\beta$ found by minimization of the mean squared error: \n",
    "\n",
    "$$MSE = E\\left\\{\\left[Y-\\beta \\cdot \\phi\\left(X\\right)\\right]^2\\right\\}$$ \n",
    "\n",
    "Zeroing the gradient of the MSE wrt weights we find the well-known normal equation:\n",
    "\n",
    "$$\n",
    "    \\beta = \\left(C_{\\phi\\phi}\\right)^{-1} C_{\\phi y}\n",
    "$$\n",
    "\n",
    "where $C_{\\phi\\phi} = E\\left[\\phi\\left(X\\right) \\phi\\left(X\\right)^T\\right] \\in \\mathbb{R}^{K \\times K}$ and $C_{\\phi y} = E\\left[\\phi\\left(X\\right) y\\right] \\in \\mathbb{R}^K$ are estimated on the training set.\n",
    "\n",
    "A more stable and effective form of regression is obtained by Tikhonov regularization, which penalizes large weights to mitigate overfitting, so as to minimize the modified cost function:\n",
    "\n",
    "$$\n",
    "    \\min \\left\\{ MSE + \\alpha \\left\\Vert \\beta \\right \\Vert ^2 \\right\\}\n",
    "$$\n",
    "\n",
    "leading to the modified normal equation:\n",
    "\n",
    "$$\n",
    "    \\beta = \\left(C_{\\phi\\phi} + \\alpha I_K\\right)^{-1} C_{\\phi y}\n",
    "$$\n",
    "\n",
    "Tikhonov regularization (also called ridge regression) is known to effectively regularize linear regression but considerably depend on regularization strength $\\alpha$. Ridge regression reverts to standard regression with small $\\alpha$, hence failing to mitigate overfitting, and converges to a horizontal line with large $\\alpha$, a phenomenon known as underfitting. Because Tikhonov regularization trades variance for bias, a sweet spot must be found, generally by cross-validation. Therefore, ridge regression is not a simple, zero-cost drop-in replacement for linear regression.\n",
    "\n",
    "Given the availability of differential labels $Z$, <b> differential regression </b> minimizes a combination of value and derivatives errors:\n",
    "    \n",
    "$$\n",
    "    \\min \\left\\{ MSE + \\sum_{j=1}^n \\alpha_j   E\\left\\{\\left[Z_j-\\beta \\cdot \\delta \\phi_j\\left(X\\right)\\right]^2\\right\\} \\right\\}\n",
    "$$\n",
    "\n",
    "where $\\delta \\phi_j\\left(X\\right) = \\left[\\frac{\\partial \\phi_1\\left(X\\right)}{\\partial X_j}, ...,  \\frac{\\partial \\phi_K\\left(X\\right)}{\\partial X_j}\\right] \\in \\mathbb{R}^K$ is the vector of partial derivatives of the basis functions wrt the j-th input $X_j$, and $Z_j$ is the j-th differential label.\n",
    "\n",
    "Zeroing the gradient of the differential objective wrt weights $\\beta$, we obtain the differential normal equation:\n",
    "\n",
    "$$\n",
    "    \\beta = \\left( C_{\\phi\\phi} + \\sum_{j=1}^n \\alpha_j C_{jj}^\\phi \\right)^{-1} \\left( C_{\\phi y} + \\sum_{j=1}^n \\alpha_j C_{j}^{\\phi z} \\right)\n",
    "$$\n",
    "\n",
    "where $C_{jj}^\\phi = E\\left[\\delta \\phi_j\\left(X\\right) \\delta \\phi_j\\left(X\\right)^T\\right] \\in \\mathbb{R}^{K \\times K}$ and $C_{j}^{\\phi z} = E\\left[\\delta \\phi_j\\left(X\\right) z_j \\right] \\in \\mathbb{R}^K$.\n",
    "\n",
    "Similarly to ridge regression, the hyperparameters $\\alpha_j$ control the relative importance of derivatives correctness in the minimization objective. Contrarily to ridge regression, however, differential regularization does not introduce bias. It follows that it has little risk of underfitting. A reasonable default is given by:\n",
    "\n",
    "$$\n",
    "    \\alpha_j = \\frac{E\\left[Y^2\\right]}{E\\left[Z_j^2\\right]}\n",
    "$$\n",
    "\n",
    "and doesn't generally require manual tinkering or cross-validation. It follows that, in addition to being much more effective as we will see, differential regression is a simple drop-in replacement for classic regression. Its effectiveness hinges on differential labels, which may or may not be cheaply available in a given situation. In the context of computed or simulated datasets, differential labels are always efficiently computed with AAD. \n",
    "\n",
    "Differential regression, however, doesn't provide a silver bullet against the curse of dimensionality. Like classic or ridge regression, it is limited to low dimension. For high-dimensional problems, unless dimension is reducible by adequate pre-processing, the differential neural networks presented in our 2020 article offer a robust alternative."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "ndQ6wgh_Rsec"
   },
   "source": [
    "# Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "u9v32SMlUsMn"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>.container { width:100% !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style>.output_result { max-width:100% !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Not running on CoLab\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>.container { width:100% !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style>.output_result { max-width:100% !important; }</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "if 'google.colab' in str(get_ipython()):\n",
    "    colab = True\n",
    "    print('Running on CoLab')\n",
    "else:\n",
    "    colab = False\n",
    "    # enable full width for wide figures\n",
    "    from IPython.core.display import display, HTML\n",
    "    display(HTML(\"<style>.container { width:100% !important; }</style>\"))\n",
    "    display(HTML(\"<style>.output_result { max-width:100% !important; }</style>\"))\n",
    "    print('Not running on CoLab')\n",
    "\n",
    "if colab:\n",
    "  %matplotlib inline\n",
    "else:\n",
    "  %matplotlib notebook\n",
    "\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.animation import FuncAnimation, PillowWriter\n",
    "mpl.rc('axes', labelsize=14)\n",
    "mpl.rc('xtick', labelsize=12)\n",
    "mpl.rc('ytick', labelsize=12)\n",
    "if colab == True: mpl.rc('animation', html='jshtml')\n",
    "\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.linear_model import LinearRegression, Ridge, RidgeCV  \n",
    "from sklearn.preprocessing import PolynomialFeatures \n",
    "from sklearn.pipeline import make_pipeline\n",
    "\n",
    "from scipy.stats import norm # cumulative normal distribution\n",
    "\n",
    "# enable full width for wide figures\n",
    "from IPython.core.display import display, HTML\n",
    "display(HTML(\"<style>.container { width:100% !important; }</style>\"))\n",
    "display(HTML(\"<style>.output_result { max-width:100% !important; }</style>\"))\n",
    "\n",
    "# constants\n",
    "epsilon = 1.0e-08"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Implementation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Classic polynomial regression is trivially implemented by piping polynomial features with linear regression in scikit-learn."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_polynomial(degree=5):\n",
    "    return make_pipeline(PolynomialFeatures(degree=degree), LinearRegression(normalize=True))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A factory function for ridge regression is implemented in an identical manner. Conveniently, scikit-learn has a variant with cross-validation built-in."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# ridge regression with builtin cross-validation\n",
    "def make_ridge(degree=5, alpha=1.0): \n",
    "    return make_pipeline(PolynomialFeatures(degree=degree), Ridge(alpha=alpha, normalize=True))\n",
    "\n",
    "# ridge regression with builtin cross-validation\n",
    "def make_ridge_cv(degree=5, min_alpha=1e-05, max_alpha=1e02, num_alphas=100): \n",
    "    alphas = np.exp(np.linspace(np.log(min_alpha), np.log(max_alpha), num_alphas))\n",
    "    return make_pipeline(PolynomialFeatures(degree=degree), RidgeCV(alphas=alphas, normalize=True))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Differential regression requires a custom implementation of the equations given in the introduction. The code may be hard to read at first sight because the equations are efficiently implemented with numpy's vectorized primitives. This implementation otherwise directly reflects the equations. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "class DifferentialRegression:\n",
    "    \n",
    "    def __init__(self, degree=5, alpha=1.0):\n",
    "        self.degree = degree\n",
    "        self.polynomial_features = PolynomialFeatures(degree=degree, include_bias=True)\n",
    "        self.alpha = alpha\n",
    "    \n",
    "    def fit(self, x, y, z):     \n",
    "        self.phi_ = self.polynomial_features.fit_transform(x)\n",
    "        self.powers_ = self.polynomial_features.powers_\n",
    "        \n",
    "        self.dphi_ = self.phi_[:, :, np.newaxis] * self.powers_[np.newaxis, :, :] / (x[:, np.newaxis, :] + epsilon)\n",
    "                \n",
    "        self.lamj_ = ((y ** 2).mean(axis=0) / (z ** 2).mean(axis=0)).reshape(1,1,-1)\n",
    "        self.dphiw_ = self.dphi_ * self.lamj_\n",
    "        \n",
    "        phiTphi = np.tensordot(self.dphiw_, self.dphi_, axes=([0,2],[0,2]))\n",
    "        phiTz = np.tensordot(self.dphiw_, z, axes=([0,2],[0,1])).reshape(-1,1)\n",
    "        \n",
    "        # note we use np.linalg.pinv (as opposed to np.linalg.inv) to perform safe (SVD) inversion, resilient to near singularities\n",
    "        inv = np.linalg.pinv(self.phi_.T @ self.phi_ + self.alpha * phiTphi, hermitian=True)\n",
    "        self.beta_ = (inv @ (self.phi_.T @ y + self.alpha * phiTz)).reshape(-1, 1)\n",
    "        \n",
    "    def predict(self, x, predict_derivs=False):\n",
    "        phi = self.polynomial_features.transform(x)\n",
    "        y_pred = phi @ self.beta_\n",
    "        \n",
    "        if predict_derivs:\n",
    "            dphi = phi[:, :, np.newaxis] * self.powers_[np.newaxis, :, :] / (x[:, np.newaxis, :] + epsilon)\n",
    "            z_pred = np.tensordot(dphi, self.beta_, (1, 0)).reshape(dphi.shape[0], -1)\n",
    "            return y_pred, z_pred\n",
    "        else:\n",
    "            return y_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Black & Scholes dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We illustrate the performance of differential regression with two simulated datasets: the one-dimensional European call in the lognormal Black & Scholes model, and the multi-dimensional basket option in the Gaussian Bachelier model. In both cases, we learn the pricing function $v\\left(X\\right)$ from examples of initial states $X$ labeled by simulated payoffs $Y$ and pathwise differentials $Z$ and compare to known ground truth on independent test sets.  \n",
    "\n",
    "Note that prices are not learned from examples of prices but from examples of payoffs, whereby each training example consists in one payoff sampled with the simulation model. The computational cost of one example is therefore the cost of simulating one Monte-Carlo path, so the entire dataset is generated for a cost similar to one pricing by Monte-Carlo. The pathwise differentials are easily computed by instrumenting the path simulation with AAD. In the simple examples presented here, pathwise differentials are computed analytically.\n",
    "\n",
    "The pricing formula is only implemented for reference, so we easily measure the out-of-sample performance of the fit."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def BlackScholes(S, K, sigma, T):\n",
    "    d1 = (np.log(S/K) + 0.5 * sigma * sigma * T) / sigma / np.sqrt(T)\n",
    "    d2 = d1 - sigma * np.sqrt(T)\n",
    "    return S * norm.cdf(d1) - K * norm.cdf(d2)\n",
    "\n",
    "def BlackScholesDelta(S, K, sigma, T):\n",
    "    d1 = (np.log(S/K) + 0.5 * sigma * sigma * T) / sigma / np.sqrt(T)\n",
    "    return norm.cdf(d1)\n",
    "\n",
    "class BlackScholesSimulator():\n",
    "    def __init__(self, sigma, K, T, lower=10, upper=200):\n",
    "        self.sigma = sigma\n",
    "        self.sigma2 = sigma * sigma\n",
    "        self.K = K\n",
    "        self.T = T\n",
    "        self.sqrtT = np.sqrt(T)\n",
    "        self.lower = lower\n",
    "        self.upper = upper\n",
    "        \n",
    "    def trainSet(self, m, seed=0):\n",
    "        s0 = np.linspace(self.lower, self.upper, m)\n",
    "        \n",
    "        np.random.seed(seed)\n",
    "        wT = np.random.normal(size=m)\n",
    "        sT = s0 * np.exp(-0.5 * self.sigma2 * self.T + self.sigma * self.sqrtT * wT)\n",
    "        pay = np.maximum(0, sT - self.K)\n",
    "        deriv = np.where(sT > self.K, sT / s0, 0)\n",
    "        \n",
    "        return s0.reshape(-1, 1), pay.reshape(-1, 1), deriv.reshape(-1, 1)\n",
    "    \n",
    "    def testSet(self, m):\n",
    "        s0 = np.linspace(self.lower, self.upper, m)\n",
    "        val = BlackScholes(s0, self.K, self.sigma, self.T)\n",
    "        delta = BlackScholesDelta(s0, self.K, self.sigma, self.T)\n",
    "        return s0.reshape(-1, 1), val.reshape(-1, 1), delta.reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We learn Black & Scholes pricing by regression over 200 evenly spaced examples. We purposely train on a small dataset to highlight overfitting and dependency on noise. Readers can easily increase the size of the dataset (variable m below) to confim convergence."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "using seed 1598\n"
     ]
    }
   ],
   "source": [
    "# parameters and constants\n",
    "\n",
    "sigma = 0.2\n",
    "K = 110\n",
    "T = 2\n",
    "\n",
    "m = 200       # size of train set\n",
    "M = 5000      # size of test set\n",
    "lower = 10\n",
    "upper = 200\n",
    "\n",
    "seed = np.random.randint(8192)\n",
    "print(\"using seed\", seed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# simulate dataset\n",
    "\n",
    "bs = BlackScholesSimulator(sigma, K, T, lower, upper)\n",
    "x_train, y_train, z_train = bs.trainSet(m, seed=seed)\n",
    "x_test, y_test, z_test = bs.testSet(M)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# learn and predict\n",
    "\n",
    "linreg = make_polynomial()\n",
    "linreg.fit(x_train, y_train)\n",
    "linpred = linreg.predict(x_test)\n",
    "\n",
    "ridgereg = make_ridge_cv()\n",
    "ridgereg.fit(x_train, y_train)\n",
    "ridgepred = ridgereg.predict(x_test)\n",
    "alpha = ridgereg['ridgecv'].alpha_\n",
    "\n",
    "diffreg = DifferentialRegression()\n",
    "diffreg.fit(x_train, y_train, z_train)\n",
    "diffpred = diffreg.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ridge regression alpha = 0.1748\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "/* Put everything inside the global mpl namespace */\n",
       "/* global mpl */\n",
       "window.mpl = {};\n",
       "\n",
       "mpl.get_websocket_type = function () {\n",
       "    if (typeof WebSocket !== 'undefined') {\n",
       "        return WebSocket;\n",
       "    } else if (typeof MozWebSocket !== 'undefined') {\n",
       "        return MozWebSocket;\n",
       "    } else {\n",
       "        alert(\n",
       "            'Your browser does not have WebSocket support. ' +\n",
       "                'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
       "                'Firefox 4 and 5 are also supported but you ' +\n",
       "                'have to enable WebSockets in about:config.'\n",
       "        );\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n",
       "    this.id = figure_id;\n",
       "\n",
       "    this.ws = websocket;\n",
       "\n",
       "    this.supports_binary = this.ws.binaryType !== undefined;\n",
       "\n",
       "    if (!this.supports_binary) {\n",
       "        var warnings = document.getElementById('mpl-warnings');\n",
       "        if (warnings) {\n",
       "            warnings.style.display = 'block';\n",
       "            warnings.textContent =\n",
       "                'This browser does not support binary websocket messages. ' +\n",
       "                'Performance may be slow.';\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.imageObj = new Image();\n",
       "\n",
       "    this.context = undefined;\n",
       "    this.message = undefined;\n",
       "    this.canvas = undefined;\n",
       "    this.rubberband_canvas = undefined;\n",
       "    this.rubberband_context = undefined;\n",
       "    this.format_dropdown = undefined;\n",
       "\n",
       "    this.image_mode = 'full';\n",
       "\n",
       "    this.root = document.createElement('div');\n",
       "    this.root.setAttribute('style', 'display: inline-block');\n",
       "    this._root_extra_style(this.root);\n",
       "\n",
       "    parent_element.appendChild(this.root);\n",
       "\n",
       "    this._init_header(this);\n",
       "    this._init_canvas(this);\n",
       "    this._init_toolbar(this);\n",
       "\n",
       "    var fig = this;\n",
       "\n",
       "    this.waiting = false;\n",
       "\n",
       "    this.ws.onopen = function () {\n",
       "        fig.send_message('supports_binary', { value: fig.supports_binary });\n",
       "        fig.send_message('send_image_mode', {});\n",
       "        if (fig.ratio !== 1) {\n",
       "            fig.send_message('set_dpi_ratio', { dpi_ratio: fig.ratio });\n",
       "        }\n",
       "        fig.send_message('refresh', {});\n",
       "    };\n",
       "\n",
       "    this.imageObj.onload = function () {\n",
       "        if (fig.image_mode === 'full') {\n",
       "            // Full images could contain transparency (where diff images\n",
       "            // almost always do), so we need to clear the canvas so that\n",
       "            // there is no ghosting.\n",
       "            fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
       "        }\n",
       "        fig.context.drawImage(fig.imageObj, 0, 0);\n",
       "    };\n",
       "\n",
       "    this.imageObj.onunload = function () {\n",
       "        fig.ws.close();\n",
       "    };\n",
       "\n",
       "    this.ws.onmessage = this._make_on_message_function(this);\n",
       "\n",
       "    this.ondownload = ondownload;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_header = function () {\n",
       "    var titlebar = document.createElement('div');\n",
       "    titlebar.classList =\n",
       "        'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n",
       "    var titletext = document.createElement('div');\n",
       "    titletext.classList = 'ui-dialog-title';\n",
       "    titletext.setAttribute(\n",
       "        'style',\n",
       "        'width: 100%; text-align: center; padding: 3px;'\n",
       "    );\n",
       "    titlebar.appendChild(titletext);\n",
       "    this.root.appendChild(titlebar);\n",
       "    this.header = titletext;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._init_canvas = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var canvas_div = (this.canvas_div = document.createElement('div'));\n",
       "    canvas_div.setAttribute(\n",
       "        'style',\n",
       "        'border: 1px solid #ddd;' +\n",
       "            'box-sizing: content-box;' +\n",
       "            'clear: both;' +\n",
       "            'min-height: 1px;' +\n",
       "            'min-width: 1px;' +\n",
       "            'outline: 0;' +\n",
       "            'overflow: hidden;' +\n",
       "            'position: relative;' +\n",
       "            'resize: both;'\n",
       "    );\n",
       "\n",
       "    function on_keyboard_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.key_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    canvas_div.addEventListener(\n",
       "        'keydown',\n",
       "        on_keyboard_event_closure('key_press')\n",
       "    );\n",
       "    canvas_div.addEventListener(\n",
       "        'keyup',\n",
       "        on_keyboard_event_closure('key_release')\n",
       "    );\n",
       "\n",
       "    this._canvas_extra_style(canvas_div);\n",
       "    this.root.appendChild(canvas_div);\n",
       "\n",
       "    var canvas = (this.canvas = document.createElement('canvas'));\n",
       "    canvas.classList.add('mpl-canvas');\n",
       "    canvas.setAttribute('style', 'box-sizing: content-box;');\n",
       "\n",
       "    this.context = canvas.getContext('2d');\n",
       "\n",
       "    var backingStore =\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        this.context.webkitBackingStorePixelRatio ||\n",
       "        this.context.mozBackingStorePixelRatio ||\n",
       "        this.context.msBackingStorePixelRatio ||\n",
       "        this.context.oBackingStorePixelRatio ||\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        1;\n",
       "\n",
       "    this.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
       "\n",
       "    var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n",
       "        'canvas'\n",
       "    ));\n",
       "    rubberband_canvas.setAttribute(\n",
       "        'style',\n",
       "        'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n",
       "    );\n",
       "\n",
       "    // Apply a ponyfill if ResizeObserver is not implemented by browser.\n",
       "    if (this.ResizeObserver === undefined) {\n",
       "        if (window.ResizeObserver !== undefined) {\n",
       "            this.ResizeObserver = window.ResizeObserver;\n",
       "        } else {\n",
       "            var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n",
       "            this.ResizeObserver = obs.ResizeObserver;\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n",
       "        var nentries = entries.length;\n",
       "        for (var i = 0; i < nentries; i++) {\n",
       "            var entry = entries[i];\n",
       "            var width, height;\n",
       "            if (entry.contentBoxSize) {\n",
       "                if (entry.contentBoxSize instanceof Array) {\n",
       "                    // Chrome 84 implements new version of spec.\n",
       "                    width = entry.contentBoxSize[0].inlineSize;\n",
       "                    height = entry.contentBoxSize[0].blockSize;\n",
       "                } else {\n",
       "                    // Firefox implements old version of spec.\n",
       "                    width = entry.contentBoxSize.inlineSize;\n",
       "                    height = entry.contentBoxSize.blockSize;\n",
       "                }\n",
       "            } else {\n",
       "                // Chrome <84 implements even older version of spec.\n",
       "                width = entry.contentRect.width;\n",
       "                height = entry.contentRect.height;\n",
       "            }\n",
       "\n",
       "            // Keep the size of the canvas and rubber band canvas in sync with\n",
       "            // the canvas container.\n",
       "            if (entry.devicePixelContentBoxSize) {\n",
       "                // Chrome 84 implements new version of spec.\n",
       "                canvas.setAttribute(\n",
       "                    'width',\n",
       "                    entry.devicePixelContentBoxSize[0].inlineSize\n",
       "                );\n",
       "                canvas.setAttribute(\n",
       "                    'height',\n",
       "                    entry.devicePixelContentBoxSize[0].blockSize\n",
       "                );\n",
       "            } else {\n",
       "                canvas.setAttribute('width', width * fig.ratio);\n",
       "                canvas.setAttribute('height', height * fig.ratio);\n",
       "            }\n",
       "            canvas.setAttribute(\n",
       "                'style',\n",
       "                'width: ' + width + 'px; height: ' + height + 'px;'\n",
       "            );\n",
       "\n",
       "            rubberband_canvas.setAttribute('width', width);\n",
       "            rubberband_canvas.setAttribute('height', height);\n",
       "\n",
       "            // And update the size in Python. We ignore the initial 0/0 size\n",
       "            // that occurs as the element is placed into the DOM, which should\n",
       "            // otherwise not happen due to the minimum size styling.\n",
       "            if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n",
       "                fig.request_resize(width, height);\n",
       "            }\n",
       "        }\n",
       "    });\n",
       "    this.resizeObserverInstance.observe(canvas_div);\n",
       "\n",
       "    function on_mouse_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.mouse_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousedown',\n",
       "        on_mouse_event_closure('button_press')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseup',\n",
       "        on_mouse_event_closure('button_release')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'dblclick',\n",
       "        on_mouse_event_closure('dblclick')\n",
       "    );\n",
       "    // Throttle sequential mouse events to 1 every 20ms.\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousemove',\n",
       "        on_mouse_event_closure('motion_notify')\n",
       "    );\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseenter',\n",
       "        on_mouse_event_closure('figure_enter')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseleave',\n",
       "        on_mouse_event_closure('figure_leave')\n",
       "    );\n",
       "\n",
       "    canvas_div.addEventListener('wheel', function (event) {\n",
       "        if (event.deltaY < 0) {\n",
       "            event.step = 1;\n",
       "        } else {\n",
       "            event.step = -1;\n",
       "        }\n",
       "        on_mouse_event_closure('scroll')(event);\n",
       "    });\n",
       "\n",
       "    canvas_div.appendChild(canvas);\n",
       "    canvas_div.appendChild(rubberband_canvas);\n",
       "\n",
       "    this.rubberband_context = rubberband_canvas.getContext('2d');\n",
       "    this.rubberband_context.strokeStyle = '#000000';\n",
       "\n",
       "    this._resize_canvas = function (width, height, forward) {\n",
       "        if (forward) {\n",
       "            canvas_div.style.width = width + 'px';\n",
       "            canvas_div.style.height = height + 'px';\n",
       "        }\n",
       "    };\n",
       "\n",
       "    // Disable right mouse context menu.\n",
       "    this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n",
       "        event.preventDefault();\n",
       "        return false;\n",
       "    });\n",
       "\n",
       "    function set_focus() {\n",
       "        canvas.focus();\n",
       "        canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    window.setTimeout(set_focus, 100);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'mpl-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'mpl-button-group';\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'mpl-button-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        var button = (fig.buttons[name] = document.createElement('button'));\n",
       "        button.classList = 'mpl-widget';\n",
       "        button.setAttribute('role', 'button');\n",
       "        button.setAttribute('aria-disabled', 'false');\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "\n",
       "        var icon_img = document.createElement('img');\n",
       "        icon_img.src = '_images/' + image + '.png';\n",
       "        icon_img.srcset = '_images/' + image + '_large.png 2x';\n",
       "        icon_img.alt = tooltip;\n",
       "        button.appendChild(icon_img);\n",
       "\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    var fmt_picker = document.createElement('select');\n",
       "    fmt_picker.classList = 'mpl-widget';\n",
       "    toolbar.appendChild(fmt_picker);\n",
       "    this.format_dropdown = fmt_picker;\n",
       "\n",
       "    for (var ind in mpl.extensions) {\n",
       "        var fmt = mpl.extensions[ind];\n",
       "        var option = document.createElement('option');\n",
       "        option.selected = fmt === mpl.default_extension;\n",
       "        option.innerHTML = fmt;\n",
       "        fmt_picker.appendChild(option);\n",
       "    }\n",
       "\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n",
       "    // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
       "    // which will in turn request a refresh of the image.\n",
       "    this.send_message('resize', { width: x_pixels, height: y_pixels });\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_message = function (type, properties) {\n",
       "    properties['type'] = type;\n",
       "    properties['figure_id'] = this.id;\n",
       "    this.ws.send(JSON.stringify(properties));\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_draw_message = function () {\n",
       "    if (!this.waiting) {\n",
       "        this.waiting = true;\n",
       "        this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    var format_dropdown = fig.format_dropdown;\n",
       "    var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
       "    fig.ondownload(fig, format);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_resize = function (fig, msg) {\n",
       "    var size = msg['size'];\n",
       "    if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n",
       "        fig._resize_canvas(size[0], size[1], msg['forward']);\n",
       "        fig.send_message('refresh', {});\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_rubberband = function (fig, msg) {\n",
       "    var x0 = msg['x0'] / fig.ratio;\n",
       "    var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n",
       "    var x1 = msg['x1'] / fig.ratio;\n",
       "    var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n",
       "    x0 = Math.floor(x0) + 0.5;\n",
       "    y0 = Math.floor(y0) + 0.5;\n",
       "    x1 = Math.floor(x1) + 0.5;\n",
       "    y1 = Math.floor(y1) + 0.5;\n",
       "    var min_x = Math.min(x0, x1);\n",
       "    var min_y = Math.min(y0, y1);\n",
       "    var width = Math.abs(x1 - x0);\n",
       "    var height = Math.abs(y1 - y0);\n",
       "\n",
       "    fig.rubberband_context.clearRect(\n",
       "        0,\n",
       "        0,\n",
       "        fig.canvas.width / fig.ratio,\n",
       "        fig.canvas.height / fig.ratio\n",
       "    );\n",
       "\n",
       "    fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_figure_label = function (fig, msg) {\n",
       "    // Updates the figure title.\n",
       "    fig.header.textContent = msg['label'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_cursor = function (fig, msg) {\n",
       "    var cursor = msg['cursor'];\n",
       "    switch (cursor) {\n",
       "        case 0:\n",
       "            cursor = 'pointer';\n",
       "            break;\n",
       "        case 1:\n",
       "            cursor = 'default';\n",
       "            break;\n",
       "        case 2:\n",
       "            cursor = 'crosshair';\n",
       "            break;\n",
       "        case 3:\n",
       "            cursor = 'move';\n",
       "            break;\n",
       "    }\n",
       "    fig.rubberband_canvas.style.cursor = cursor;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_message = function (fig, msg) {\n",
       "    fig.message.textContent = msg['message'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_draw = function (fig, _msg) {\n",
       "    // Request the server to send over a new figure.\n",
       "    fig.send_draw_message();\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_image_mode = function (fig, msg) {\n",
       "    fig.image_mode = msg['mode'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n",
       "    for (var key in msg) {\n",
       "        if (!(key in fig.buttons)) {\n",
       "            continue;\n",
       "        }\n",
       "        fig.buttons[key].disabled = !msg[key];\n",
       "        fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n",
       "    if (msg['mode'] === 'PAN') {\n",
       "        fig.buttons['Pan'].classList.add('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    } else if (msg['mode'] === 'ZOOM') {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.add('active');\n",
       "    } else {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Called whenever the canvas gets updated.\n",
       "    this.send_message('ack', {});\n",
       "};\n",
       "\n",
       "// A function to construct a web socket function for onmessage handling.\n",
       "// Called in the figure constructor.\n",
       "mpl.figure.prototype._make_on_message_function = function (fig) {\n",
       "    return function socket_on_message(evt) {\n",
       "        if (evt.data instanceof Blob) {\n",
       "            var img = evt.data;\n",
       "            if (img.type !== 'image/png') {\n",
       "                /* FIXME: We get \"Resource interpreted as Image but\n",
       "                 * transferred with MIME type text/plain:\" errors on\n",
       "                 * Chrome.  But how to set the MIME type?  It doesn't seem\n",
       "                 * to be part of the websocket stream */\n",
       "                img.type = 'image/png';\n",
       "            }\n",
       "\n",
       "            /* Free the memory for the previous frames */\n",
       "            if (fig.imageObj.src) {\n",
       "                (window.URL || window.webkitURL).revokeObjectURL(\n",
       "                    fig.imageObj.src\n",
       "                );\n",
       "            }\n",
       "\n",
       "            fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
       "                img\n",
       "            );\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        } else if (\n",
       "            typeof evt.data === 'string' &&\n",
       "            evt.data.slice(0, 21) === 'data:image/png;base64'\n",
       "        ) {\n",
       "            fig.imageObj.src = evt.data;\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        var msg = JSON.parse(evt.data);\n",
       "        var msg_type = msg['type'];\n",
       "\n",
       "        // Call the  \"handle_{type}\" callback, which takes\n",
       "        // the figure and JSON message as its only arguments.\n",
       "        try {\n",
       "            var callback = fig['handle_' + msg_type];\n",
       "        } catch (e) {\n",
       "            console.log(\n",
       "                \"No handler for the '\" + msg_type + \"' message type: \",\n",
       "                msg\n",
       "            );\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        if (callback) {\n",
       "            try {\n",
       "                // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
       "                callback(fig, msg);\n",
       "            } catch (e) {\n",
       "                console.log(\n",
       "                    \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n",
       "                    e,\n",
       "                    e.stack,\n",
       "                    msg\n",
       "                );\n",
       "            }\n",
       "        }\n",
       "    };\n",
       "};\n",
       "\n",
       "// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
       "mpl.findpos = function (e) {\n",
       "    //this section is from http://www.quirksmode.org/js/events_properties.html\n",
       "    var targ;\n",
       "    if (!e) {\n",
       "        e = window.event;\n",
       "    }\n",
       "    if (e.target) {\n",
       "        targ = e.target;\n",
       "    } else if (e.srcElement) {\n",
       "        targ = e.srcElement;\n",
       "    }\n",
       "    if (targ.nodeType === 3) {\n",
       "        // defeat Safari bug\n",
       "        targ = targ.parentNode;\n",
       "    }\n",
       "\n",
       "    // pageX,Y are the mouse positions relative to the document\n",
       "    var boundingRect = targ.getBoundingClientRect();\n",
       "    var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n",
       "    var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n",
       "\n",
       "    return { x: x, y: y };\n",
       "};\n",
       "\n",
       "/*\n",
       " * return a copy of an object with only non-object keys\n",
       " * we need this to avoid circular references\n",
       " * http://stackoverflow.com/a/24161582/3208463\n",
       " */\n",
       "function simpleKeys(original) {\n",
       "    return Object.keys(original).reduce(function (obj, key) {\n",
       "        if (typeof original[key] !== 'object') {\n",
       "            obj[key] = original[key];\n",
       "        }\n",
       "        return obj;\n",
       "    }, {});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.mouse_event = function (event, name) {\n",
       "    var canvas_pos = mpl.findpos(event);\n",
       "\n",
       "    if (name === 'button_press') {\n",
       "        this.canvas.focus();\n",
       "        this.canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    var x = canvas_pos.x * this.ratio;\n",
       "    var y = canvas_pos.y * this.ratio;\n",
       "\n",
       "    this.send_message(name, {\n",
       "        x: x,\n",
       "        y: y,\n",
       "        button: event.button,\n",
       "        step: event.step,\n",
       "        guiEvent: simpleKeys(event),\n",
       "    });\n",
       "\n",
       "    /* This prevents the web browser from automatically changing to\n",
       "     * the text insertion cursor when the button is pressed.  We want\n",
       "     * to control all of the cursor setting manually through the\n",
       "     * 'cursor' event from matplotlib */\n",
       "    event.preventDefault();\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (_event, _name) {\n",
       "    // Handle any extra behaviour associated with a key event\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.key_event = function (event, name) {\n",
       "    // Prevent repeat events\n",
       "    if (name === 'key_press') {\n",
       "        if (event.key === this._key) {\n",
       "            return;\n",
       "        } else {\n",
       "            this._key = event.key;\n",
       "        }\n",
       "    }\n",
       "    if (name === 'key_release') {\n",
       "        this._key = null;\n",
       "    }\n",
       "\n",
       "    var value = '';\n",
       "    if (event.ctrlKey && event.key !== 'Control') {\n",
       "        value += 'ctrl+';\n",
       "    }\n",
       "    else if (event.altKey && event.key !== 'Alt') {\n",
       "        value += 'alt+';\n",
       "    }\n",
       "    else if (event.shiftKey && event.key !== 'Shift') {\n",
       "        value += 'shift+';\n",
       "    }\n",
       "\n",
       "    value += 'k' + event.key;\n",
       "\n",
       "    this._key_event_extra(event, name);\n",
       "\n",
       "    this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onclick = function (name) {\n",
       "    if (name === 'download') {\n",
       "        this.handle_save(this, null);\n",
       "    } else {\n",
       "        this.send_message('toolbar_button', { name: name });\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n",
       "    this.message.textContent = tooltip;\n",
       "};\n",
       "\n",
       "///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n",
       "// prettier-ignore\n",
       "var _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\n",
       "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
       "\n",
       "mpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
       "\n",
       "mpl.default_extension = \"png\";/* global mpl */\n",
       "\n",
       "var comm_websocket_adapter = function (comm) {\n",
       "    // Create a \"websocket\"-like object which calls the given IPython comm\n",
       "    // object with the appropriate methods. Currently this is a non binary\n",
       "    // socket, so there is still some room for performance tuning.\n",
       "    var ws = {};\n",
       "\n",
       "    ws.binaryType = comm.kernel.ws.binaryType;\n",
       "    ws.readyState = comm.kernel.ws.readyState;\n",
       "    function updateReadyState(_event) {\n",
       "        if (comm.kernel.ws) {\n",
       "            ws.readyState = comm.kernel.ws.readyState;\n",
       "        } else {\n",
       "            ws.readyState = 3; // Closed state.\n",
       "        }\n",
       "    }\n",
       "    comm.kernel.ws.addEventListener('open', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('close', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('error', updateReadyState);\n",
       "\n",
       "    ws.close = function () {\n",
       "        comm.close();\n",
       "    };\n",
       "    ws.send = function (m) {\n",
       "        //console.log('sending', m);\n",
       "        comm.send(m);\n",
       "    };\n",
       "    // Register the callback with on_msg.\n",
       "    comm.on_msg(function (msg) {\n",
       "        //console.log('receiving', msg['content']['data'], msg);\n",
       "        var data = msg['content']['data'];\n",
       "        if (data['blob'] !== undefined) {\n",
       "            data = {\n",
       "                data: new Blob(msg['buffers'], { type: data['blob'] }),\n",
       "            };\n",
       "        }\n",
       "        // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
       "        ws.onmessage(data);\n",
       "    });\n",
       "    return ws;\n",
       "};\n",
       "\n",
       "mpl.mpl_figure_comm = function (comm, msg) {\n",
       "    // This is the function which gets called when the mpl process\n",
       "    // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
       "\n",
       "    var id = msg.content.data.id;\n",
       "    // Get hold of the div created by the display call when the Comm\n",
       "    // socket was opened in Python.\n",
       "    var element = document.getElementById(id);\n",
       "    var ws_proxy = comm_websocket_adapter(comm);\n",
       "\n",
       "    function ondownload(figure, _format) {\n",
       "        window.open(figure.canvas.toDataURL());\n",
       "    }\n",
       "\n",
       "    var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n",
       "\n",
       "    // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
       "    // web socket which is closed, not our websocket->open comm proxy.\n",
       "    ws_proxy.onopen();\n",
       "\n",
       "    fig.parent_element = element;\n",
       "    fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
       "    if (!fig.cell_info) {\n",
       "        console.error('Failed to find cell for figure', id, fig);\n",
       "        return;\n",
       "    }\n",
       "    fig.cell_info[0].output_area.element.on(\n",
       "        'cleared',\n",
       "        { fig: fig },\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_close = function (fig, msg) {\n",
       "    var width = fig.canvas.width / fig.ratio;\n",
       "    fig.cell_info[0].output_area.element.off(\n",
       "        'cleared',\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "    fig.resizeObserverInstance.unobserve(fig.canvas_div);\n",
       "\n",
       "    // Update the output cell to use the data from the current canvas.\n",
       "    fig.push_to_output();\n",
       "    var dataURL = fig.canvas.toDataURL();\n",
       "    // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
       "    // the notebook keyboard shortcuts fail.\n",
       "    IPython.keyboard_manager.enable();\n",
       "    fig.parent_element.innerHTML =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "    fig.close_ws(fig, msg);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.close_ws = function (fig, msg) {\n",
       "    fig.send_message('closing', msg);\n",
       "    // fig.ws.close()\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.push_to_output = function (_remove_interactive) {\n",
       "    // Turn the data on the canvas into data in the output cell.\n",
       "    var width = this.canvas.width / this.ratio;\n",
       "    var dataURL = this.canvas.toDataURL();\n",
       "    this.cell_info[1]['text/html'] =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Tell IPython that the notebook contents must change.\n",
       "    IPython.notebook.set_dirty(true);\n",
       "    this.send_message('ack', {});\n",
       "    var fig = this;\n",
       "    // Wait a second, then push the new image to the DOM so\n",
       "    // that it is saved nicely (might be nice to debounce this).\n",
       "    setTimeout(function () {\n",
       "        fig.push_to_output();\n",
       "    }, 1000);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'btn-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'btn-group';\n",
       "    var button;\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'btn-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        button = fig.buttons[name] = document.createElement('button');\n",
       "        button.classList = 'btn btn-default';\n",
       "        button.href = '#';\n",
       "        button.title = name;\n",
       "        button.innerHTML = '<i class=\"fa ' + image + ' fa-lg\"></i>';\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    // Add the status bar.\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message pull-right';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "\n",
       "    // Add the close button to the window.\n",
       "    var buttongrp = document.createElement('div');\n",
       "    buttongrp.classList = 'btn-group inline pull-right';\n",
       "    button = document.createElement('button');\n",
       "    button.classList = 'btn btn-mini btn-primary';\n",
       "    button.href = '#';\n",
       "    button.title = 'Stop Interaction';\n",
       "    button.innerHTML = '<i class=\"fa fa-power-off icon-remove icon-large\"></i>';\n",
       "    button.addEventListener('click', function (_evt) {\n",
       "        fig.handle_close(fig, {});\n",
       "    });\n",
       "    button.addEventListener(\n",
       "        'mouseover',\n",
       "        on_mouseover_closure('Stop Interaction')\n",
       "    );\n",
       "    buttongrp.appendChild(button);\n",
       "    var titlebar = this.root.querySelector('.ui-dialog-titlebar');\n",
       "    titlebar.insertBefore(buttongrp, titlebar.firstChild);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._remove_fig_handler = function (event) {\n",
       "    var fig = event.data.fig;\n",
       "    if (event.target !== this) {\n",
       "        // Ignore bubbled events from children.\n",
       "        return;\n",
       "    }\n",
       "    fig.close_ws(fig, {});\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (el) {\n",
       "    el.style.boxSizing = 'content-box'; // override notebook setting of border-box.\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (el) {\n",
       "    // this is important to make the div 'focusable\n",
       "    el.setAttribute('tabindex', 0);\n",
       "    // reach out to IPython and tell the keyboard manager to turn it's self\n",
       "    // off when our div gets focus\n",
       "\n",
       "    // location in version 3\n",
       "    if (IPython.notebook.keyboard_manager) {\n",
       "        IPython.notebook.keyboard_manager.register_events(el);\n",
       "    } else {\n",
       "        // location in version 2\n",
       "        IPython.keyboard_manager.register_events(el);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (event, _name) {\n",
       "    var manager = IPython.notebook.keyboard_manager;\n",
       "    if (!manager) {\n",
       "        manager = IPython.keyboard_manager;\n",
       "    }\n",
       "\n",
       "    // Check for shift+enter\n",
       "    if (event.shiftKey && event.which === 13) {\n",
       "        this.canvas_div.blur();\n",
       "        // select the cell after this one\n",
       "        var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
       "        IPython.notebook.select(index + 1);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    fig.ondownload(fig, null);\n",
       "};\n",
       "\n",
       "mpl.find_output_cell = function (html_output) {\n",
       "    // Return the cell and output element which can be found *uniquely* in the notebook.\n",
       "    // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
       "    // IPython event is triggered only after the cells have been serialised, which for\n",
       "    // our purposes (turning an active figure into a static one), is too late.\n",
       "    var cells = IPython.notebook.get_cells();\n",
       "    var ncells = cells.length;\n",
       "    for (var i = 0; i < ncells; i++) {\n",
       "        var cell = cells[i];\n",
       "        if (cell.cell_type === 'code') {\n",
       "            for (var j = 0; j < cell.output_area.outputs.length; j++) {\n",
       "                var data = cell.output_area.outputs[j];\n",
       "                if (data.data) {\n",
       "                    // IPython >= 3 moved mimebundle to data attribute of output\n",
       "                    data = data.data;\n",
       "                }\n",
       "                if (data['text/html'] === html_output) {\n",
       "                    return [cell, data, j];\n",
       "                }\n",
       "            }\n",
       "        }\n",
       "    }\n",
       "};\n",
       "\n",
       "// Register the function which deals with the matplotlib target/channel.\n",
       "// The kernel may be null if the page has been refreshed.\n",
       "if (IPython.notebook.kernel !== null) {\n",
       "    IPython.notebook.kernel.comm_manager.register_target(\n",
       "        'matplotlib',\n",
       "        mpl.mpl_figure_comm\n",
       "    );\n",
       "}\n"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<img src=\"data:image/png;base64,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\" width=\"1500\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot results\n",
    "\n",
    "def plot_one(ax, x_train, y_train, x_test, y_test, pred):\n",
    "    ax.set_xlim(0, 225)\n",
    "    ax.set_ylim(-20, 100)\n",
    "    samples, = ax.plot(x_train, y_train, 'co', markersize=5, markerfacecolor=\"white\", label=\"samples\")\n",
    "    predict, = ax.plot(x_test, pred, 'b-', label=\"predict\")\n",
    "    correct, = ax.plot(x_test, y_test, 'r-', label=\"correct\")\n",
    "    return samples, predict, correct\n",
    "\n",
    "def plot_multi(x_train, y_train, x_test, y_test, titles, preds):\n",
    "    nplots = len(preds)\n",
    "    nrows = (nplots - 1) // 3 + 1\n",
    "    ncols = min(nplots, 3)\n",
    "    \n",
    "    fig, axs = plt.subplots(nrows, ncols, squeeze=False)\n",
    "    fig.set_size_inches(ncols * 5, nrows * 5)\n",
    "\n",
    "    lines = []\n",
    "    for i, ax in enumerate(axs.flatten()):\n",
    "        if i < nplots:\n",
    "            samples, predict, correct = plot_one(ax, x_train, y_train, x_test, y_test, preds[i])\n",
    "            lines.extend([samples, predict, correct])\n",
    "            ax.legend()\n",
    "            ax.set_title(titles[i])\n",
    "    \n",
    "    return fig, lines\n",
    "            \n",
    "print(\"Ridge regression alpha = %.4f\" % alpha)\n",
    "fig, lines = plot_multi(x_train, y_train, x_test, y_test, \n",
    "           [\"linear regression\", \"ridge regression\", \"differential regression\"],\n",
    "           [linpred, ridgepred, diffpred])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To better appreciate overfitting and stabilization by ridge or differentials, we repeatedly learn from independently simulated datasets and animate. <b> This cell may take about 10 seconds to render the animation on Google colab </b>."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "/* Put everything inside the global mpl namespace */\n",
       "/* global mpl */\n",
       "window.mpl = {};\n",
       "\n",
       "mpl.get_websocket_type = function () {\n",
       "    if (typeof WebSocket !== 'undefined') {\n",
       "        return WebSocket;\n",
       "    } else if (typeof MozWebSocket !== 'undefined') {\n",
       "        return MozWebSocket;\n",
       "    } else {\n",
       "        alert(\n",
       "            'Your browser does not have WebSocket support. ' +\n",
       "                'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
       "                'Firefox 4 and 5 are also supported but you ' +\n",
       "                'have to enable WebSockets in about:config.'\n",
       "        );\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n",
       "    this.id = figure_id;\n",
       "\n",
       "    this.ws = websocket;\n",
       "\n",
       "    this.supports_binary = this.ws.binaryType !== undefined;\n",
       "\n",
       "    if (!this.supports_binary) {\n",
       "        var warnings = document.getElementById('mpl-warnings');\n",
       "        if (warnings) {\n",
       "            warnings.style.display = 'block';\n",
       "            warnings.textContent =\n",
       "                'This browser does not support binary websocket messages. ' +\n",
       "                'Performance may be slow.';\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.imageObj = new Image();\n",
       "\n",
       "    this.context = undefined;\n",
       "    this.message = undefined;\n",
       "    this.canvas = undefined;\n",
       "    this.rubberband_canvas = undefined;\n",
       "    this.rubberband_context = undefined;\n",
       "    this.format_dropdown = undefined;\n",
       "\n",
       "    this.image_mode = 'full';\n",
       "\n",
       "    this.root = document.createElement('div');\n",
       "    this.root.setAttribute('style', 'display: inline-block');\n",
       "    this._root_extra_style(this.root);\n",
       "\n",
       "    parent_element.appendChild(this.root);\n",
       "\n",
       "    this._init_header(this);\n",
       "    this._init_canvas(this);\n",
       "    this._init_toolbar(this);\n",
       "\n",
       "    var fig = this;\n",
       "\n",
       "    this.waiting = false;\n",
       "\n",
       "    this.ws.onopen = function () {\n",
       "        fig.send_message('supports_binary', { value: fig.supports_binary });\n",
       "        fig.send_message('send_image_mode', {});\n",
       "        if (fig.ratio !== 1) {\n",
       "            fig.send_message('set_dpi_ratio', { dpi_ratio: fig.ratio });\n",
       "        }\n",
       "        fig.send_message('refresh', {});\n",
       "    };\n",
       "\n",
       "    this.imageObj.onload = function () {\n",
       "        if (fig.image_mode === 'full') {\n",
       "            // Full images could contain transparency (where diff images\n",
       "            // almost always do), so we need to clear the canvas so that\n",
       "            // there is no ghosting.\n",
       "            fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
       "        }\n",
       "        fig.context.drawImage(fig.imageObj, 0, 0);\n",
       "    };\n",
       "\n",
       "    this.imageObj.onunload = function () {\n",
       "        fig.ws.close();\n",
       "    };\n",
       "\n",
       "    this.ws.onmessage = this._make_on_message_function(this);\n",
       "\n",
       "    this.ondownload = ondownload;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_header = function () {\n",
       "    var titlebar = document.createElement('div');\n",
       "    titlebar.classList =\n",
       "        'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n",
       "    var titletext = document.createElement('div');\n",
       "    titletext.classList = 'ui-dialog-title';\n",
       "    titletext.setAttribute(\n",
       "        'style',\n",
       "        'width: 100%; text-align: center; padding: 3px;'\n",
       "    );\n",
       "    titlebar.appendChild(titletext);\n",
       "    this.root.appendChild(titlebar);\n",
       "    this.header = titletext;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._init_canvas = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var canvas_div = (this.canvas_div = document.createElement('div'));\n",
       "    canvas_div.setAttribute(\n",
       "        'style',\n",
       "        'border: 1px solid #ddd;' +\n",
       "            'box-sizing: content-box;' +\n",
       "            'clear: both;' +\n",
       "            'min-height: 1px;' +\n",
       "            'min-width: 1px;' +\n",
       "            'outline: 0;' +\n",
       "            'overflow: hidden;' +\n",
       "            'position: relative;' +\n",
       "            'resize: both;'\n",
       "    );\n",
       "\n",
       "    function on_keyboard_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.key_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    canvas_div.addEventListener(\n",
       "        'keydown',\n",
       "        on_keyboard_event_closure('key_press')\n",
       "    );\n",
       "    canvas_div.addEventListener(\n",
       "        'keyup',\n",
       "        on_keyboard_event_closure('key_release')\n",
       "    );\n",
       "\n",
       "    this._canvas_extra_style(canvas_div);\n",
       "    this.root.appendChild(canvas_div);\n",
       "\n",
       "    var canvas = (this.canvas = document.createElement('canvas'));\n",
       "    canvas.classList.add('mpl-canvas');\n",
       "    canvas.setAttribute('style', 'box-sizing: content-box;');\n",
       "\n",
       "    this.context = canvas.getContext('2d');\n",
       "\n",
       "    var backingStore =\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        this.context.webkitBackingStorePixelRatio ||\n",
       "        this.context.mozBackingStorePixelRatio ||\n",
       "        this.context.msBackingStorePixelRatio ||\n",
       "        this.context.oBackingStorePixelRatio ||\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        1;\n",
       "\n",
       "    this.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
       "\n",
       "    var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n",
       "        'canvas'\n",
       "    ));\n",
       "    rubberband_canvas.setAttribute(\n",
       "        'style',\n",
       "        'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n",
       "    );\n",
       "\n",
       "    // Apply a ponyfill if ResizeObserver is not implemented by browser.\n",
       "    if (this.ResizeObserver === undefined) {\n",
       "        if (window.ResizeObserver !== undefined) {\n",
       "            this.ResizeObserver = window.ResizeObserver;\n",
       "        } else {\n",
       "            var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n",
       "            this.ResizeObserver = obs.ResizeObserver;\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n",
       "        var nentries = entries.length;\n",
       "        for (var i = 0; i < nentries; i++) {\n",
       "            var entry = entries[i];\n",
       "            var width, height;\n",
       "            if (entry.contentBoxSize) {\n",
       "                if (entry.contentBoxSize instanceof Array) {\n",
       "                    // Chrome 84 implements new version of spec.\n",
       "                    width = entry.contentBoxSize[0].inlineSize;\n",
       "                    height = entry.contentBoxSize[0].blockSize;\n",
       "                } else {\n",
       "                    // Firefox implements old version of spec.\n",
       "                    width = entry.contentBoxSize.inlineSize;\n",
       "                    height = entry.contentBoxSize.blockSize;\n",
       "                }\n",
       "            } else {\n",
       "                // Chrome <84 implements even older version of spec.\n",
       "                width = entry.contentRect.width;\n",
       "                height = entry.contentRect.height;\n",
       "            }\n",
       "\n",
       "            // Keep the size of the canvas and rubber band canvas in sync with\n",
       "            // the canvas container.\n",
       "            if (entry.devicePixelContentBoxSize) {\n",
       "                // Chrome 84 implements new version of spec.\n",
       "                canvas.setAttribute(\n",
       "                    'width',\n",
       "                    entry.devicePixelContentBoxSize[0].inlineSize\n",
       "                );\n",
       "                canvas.setAttribute(\n",
       "                    'height',\n",
       "                    entry.devicePixelContentBoxSize[0].blockSize\n",
       "                );\n",
       "            } else {\n",
       "                canvas.setAttribute('width', width * fig.ratio);\n",
       "                canvas.setAttribute('height', height * fig.ratio);\n",
       "            }\n",
       "            canvas.setAttribute(\n",
       "                'style',\n",
       "                'width: ' + width + 'px; height: ' + height + 'px;'\n",
       "            );\n",
       "\n",
       "            rubberband_canvas.setAttribute('width', width);\n",
       "            rubberband_canvas.setAttribute('height', height);\n",
       "\n",
       "            // And update the size in Python. We ignore the initial 0/0 size\n",
       "            // that occurs as the element is placed into the DOM, which should\n",
       "            // otherwise not happen due to the minimum size styling.\n",
       "            if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n",
       "                fig.request_resize(width, height);\n",
       "            }\n",
       "        }\n",
       "    });\n",
       "    this.resizeObserverInstance.observe(canvas_div);\n",
       "\n",
       "    function on_mouse_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.mouse_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousedown',\n",
       "        on_mouse_event_closure('button_press')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseup',\n",
       "        on_mouse_event_closure('button_release')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'dblclick',\n",
       "        on_mouse_event_closure('dblclick')\n",
       "    );\n",
       "    // Throttle sequential mouse events to 1 every 20ms.\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousemove',\n",
       "        on_mouse_event_closure('motion_notify')\n",
       "    );\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseenter',\n",
       "        on_mouse_event_closure('figure_enter')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseleave',\n",
       "        on_mouse_event_closure('figure_leave')\n",
       "    );\n",
       "\n",
       "    canvas_div.addEventListener('wheel', function (event) {\n",
       "        if (event.deltaY < 0) {\n",
       "            event.step = 1;\n",
       "        } else {\n",
       "            event.step = -1;\n",
       "        }\n",
       "        on_mouse_event_closure('scroll')(event);\n",
       "    });\n",
       "\n",
       "    canvas_div.appendChild(canvas);\n",
       "    canvas_div.appendChild(rubberband_canvas);\n",
       "\n",
       "    this.rubberband_context = rubberband_canvas.getContext('2d');\n",
       "    this.rubberband_context.strokeStyle = '#000000';\n",
       "\n",
       "    this._resize_canvas = function (width, height, forward) {\n",
       "        if (forward) {\n",
       "            canvas_div.style.width = width + 'px';\n",
       "            canvas_div.style.height = height + 'px';\n",
       "        }\n",
       "    };\n",
       "\n",
       "    // Disable right mouse context menu.\n",
       "    this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n",
       "        event.preventDefault();\n",
       "        return false;\n",
       "    });\n",
       "\n",
       "    function set_focus() {\n",
       "        canvas.focus();\n",
       "        canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    window.setTimeout(set_focus, 100);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'mpl-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'mpl-button-group';\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'mpl-button-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        var button = (fig.buttons[name] = document.createElement('button'));\n",
       "        button.classList = 'mpl-widget';\n",
       "        button.setAttribute('role', 'button');\n",
       "        button.setAttribute('aria-disabled', 'false');\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "\n",
       "        var icon_img = document.createElement('img');\n",
       "        icon_img.src = '_images/' + image + '.png';\n",
       "        icon_img.srcset = '_images/' + image + '_large.png 2x';\n",
       "        icon_img.alt = tooltip;\n",
       "        button.appendChild(icon_img);\n",
       "\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    var fmt_picker = document.createElement('select');\n",
       "    fmt_picker.classList = 'mpl-widget';\n",
       "    toolbar.appendChild(fmt_picker);\n",
       "    this.format_dropdown = fmt_picker;\n",
       "\n",
       "    for (var ind in mpl.extensions) {\n",
       "        var fmt = mpl.extensions[ind];\n",
       "        var option = document.createElement('option');\n",
       "        option.selected = fmt === mpl.default_extension;\n",
       "        option.innerHTML = fmt;\n",
       "        fmt_picker.appendChild(option);\n",
       "    }\n",
       "\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n",
       "    // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
       "    // which will in turn request a refresh of the image.\n",
       "    this.send_message('resize', { width: x_pixels, height: y_pixels });\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_message = function (type, properties) {\n",
       "    properties['type'] = type;\n",
       "    properties['figure_id'] = this.id;\n",
       "    this.ws.send(JSON.stringify(properties));\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_draw_message = function () {\n",
       "    if (!this.waiting) {\n",
       "        this.waiting = true;\n",
       "        this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    var format_dropdown = fig.format_dropdown;\n",
       "    var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
       "    fig.ondownload(fig, format);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_resize = function (fig, msg) {\n",
       "    var size = msg['size'];\n",
       "    if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n",
       "        fig._resize_canvas(size[0], size[1], msg['forward']);\n",
       "        fig.send_message('refresh', {});\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_rubberband = function (fig, msg) {\n",
       "    var x0 = msg['x0'] / fig.ratio;\n",
       "    var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n",
       "    var x1 = msg['x1'] / fig.ratio;\n",
       "    var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n",
       "    x0 = Math.floor(x0) + 0.5;\n",
       "    y0 = Math.floor(y0) + 0.5;\n",
       "    x1 = Math.floor(x1) + 0.5;\n",
       "    y1 = Math.floor(y1) + 0.5;\n",
       "    var min_x = Math.min(x0, x1);\n",
       "    var min_y = Math.min(y0, y1);\n",
       "    var width = Math.abs(x1 - x0);\n",
       "    var height = Math.abs(y1 - y0);\n",
       "\n",
       "    fig.rubberband_context.clearRect(\n",
       "        0,\n",
       "        0,\n",
       "        fig.canvas.width / fig.ratio,\n",
       "        fig.canvas.height / fig.ratio\n",
       "    );\n",
       "\n",
       "    fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_figure_label = function (fig, msg) {\n",
       "    // Updates the figure title.\n",
       "    fig.header.textContent = msg['label'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_cursor = function (fig, msg) {\n",
       "    var cursor = msg['cursor'];\n",
       "    switch (cursor) {\n",
       "        case 0:\n",
       "            cursor = 'pointer';\n",
       "            break;\n",
       "        case 1:\n",
       "            cursor = 'default';\n",
       "            break;\n",
       "        case 2:\n",
       "            cursor = 'crosshair';\n",
       "            break;\n",
       "        case 3:\n",
       "            cursor = 'move';\n",
       "            break;\n",
       "    }\n",
       "    fig.rubberband_canvas.style.cursor = cursor;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_message = function (fig, msg) {\n",
       "    fig.message.textContent = msg['message'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_draw = function (fig, _msg) {\n",
       "    // Request the server to send over a new figure.\n",
       "    fig.send_draw_message();\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_image_mode = function (fig, msg) {\n",
       "    fig.image_mode = msg['mode'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n",
       "    for (var key in msg) {\n",
       "        if (!(key in fig.buttons)) {\n",
       "            continue;\n",
       "        }\n",
       "        fig.buttons[key].disabled = !msg[key];\n",
       "        fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n",
       "    if (msg['mode'] === 'PAN') {\n",
       "        fig.buttons['Pan'].classList.add('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    } else if (msg['mode'] === 'ZOOM') {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.add('active');\n",
       "    } else {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Called whenever the canvas gets updated.\n",
       "    this.send_message('ack', {});\n",
       "};\n",
       "\n",
       "// A function to construct a web socket function for onmessage handling.\n",
       "// Called in the figure constructor.\n",
       "mpl.figure.prototype._make_on_message_function = function (fig) {\n",
       "    return function socket_on_message(evt) {\n",
       "        if (evt.data instanceof Blob) {\n",
       "            var img = evt.data;\n",
       "            if (img.type !== 'image/png') {\n",
       "                /* FIXME: We get \"Resource interpreted as Image but\n",
       "                 * transferred with MIME type text/plain:\" errors on\n",
       "                 * Chrome.  But how to set the MIME type?  It doesn't seem\n",
       "                 * to be part of the websocket stream */\n",
       "                img.type = 'image/png';\n",
       "            }\n",
       "\n",
       "            /* Free the memory for the previous frames */\n",
       "            if (fig.imageObj.src) {\n",
       "                (window.URL || window.webkitURL).revokeObjectURL(\n",
       "                    fig.imageObj.src\n",
       "                );\n",
       "            }\n",
       "\n",
       "            fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
       "                img\n",
       "            );\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        } else if (\n",
       "            typeof evt.data === 'string' &&\n",
       "            evt.data.slice(0, 21) === 'data:image/png;base64'\n",
       "        ) {\n",
       "            fig.imageObj.src = evt.data;\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        var msg = JSON.parse(evt.data);\n",
       "        var msg_type = msg['type'];\n",
       "\n",
       "        // Call the  \"handle_{type}\" callback, which takes\n",
       "        // the figure and JSON message as its only arguments.\n",
       "        try {\n",
       "            var callback = fig['handle_' + msg_type];\n",
       "        } catch (e) {\n",
       "            console.log(\n",
       "                \"No handler for the '\" + msg_type + \"' message type: \",\n",
       "                msg\n",
       "            );\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        if (callback) {\n",
       "            try {\n",
       "                // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
       "                callback(fig, msg);\n",
       "            } catch (e) {\n",
       "                console.log(\n",
       "                    \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n",
       "                    e,\n",
       "                    e.stack,\n",
       "                    msg\n",
       "                );\n",
       "            }\n",
       "        }\n",
       "    };\n",
       "};\n",
       "\n",
       "// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
       "mpl.findpos = function (e) {\n",
       "    //this section is from http://www.quirksmode.org/js/events_properties.html\n",
       "    var targ;\n",
       "    if (!e) {\n",
       "        e = window.event;\n",
       "    }\n",
       "    if (e.target) {\n",
       "        targ = e.target;\n",
       "    } else if (e.srcElement) {\n",
       "        targ = e.srcElement;\n",
       "    }\n",
       "    if (targ.nodeType === 3) {\n",
       "        // defeat Safari bug\n",
       "        targ = targ.parentNode;\n",
       "    }\n",
       "\n",
       "    // pageX,Y are the mouse positions relative to the document\n",
       "    var boundingRect = targ.getBoundingClientRect();\n",
       "    var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n",
       "    var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n",
       "\n",
       "    return { x: x, y: y };\n",
       "};\n",
       "\n",
       "/*\n",
       " * return a copy of an object with only non-object keys\n",
       " * we need this to avoid circular references\n",
       " * http://stackoverflow.com/a/24161582/3208463\n",
       " */\n",
       "function simpleKeys(original) {\n",
       "    return Object.keys(original).reduce(function (obj, key) {\n",
       "        if (typeof original[key] !== 'object') {\n",
       "            obj[key] = original[key];\n",
       "        }\n",
       "        return obj;\n",
       "    }, {});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.mouse_event = function (event, name) {\n",
       "    var canvas_pos = mpl.findpos(event);\n",
       "\n",
       "    if (name === 'button_press') {\n",
       "        this.canvas.focus();\n",
       "        this.canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    var x = canvas_pos.x * this.ratio;\n",
       "    var y = canvas_pos.y * this.ratio;\n",
       "\n",
       "    this.send_message(name, {\n",
       "        x: x,\n",
       "        y: y,\n",
       "        button: event.button,\n",
       "        step: event.step,\n",
       "        guiEvent: simpleKeys(event),\n",
       "    });\n",
       "\n",
       "    /* This prevents the web browser from automatically changing to\n",
       "     * the text insertion cursor when the button is pressed.  We want\n",
       "     * to control all of the cursor setting manually through the\n",
       "     * 'cursor' event from matplotlib */\n",
       "    event.preventDefault();\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (_event, _name) {\n",
       "    // Handle any extra behaviour associated with a key event\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.key_event = function (event, name) {\n",
       "    // Prevent repeat events\n",
       "    if (name === 'key_press') {\n",
       "        if (event.key === this._key) {\n",
       "            return;\n",
       "        } else {\n",
       "            this._key = event.key;\n",
       "        }\n",
       "    }\n",
       "    if (name === 'key_release') {\n",
       "        this._key = null;\n",
       "    }\n",
       "\n",
       "    var value = '';\n",
       "    if (event.ctrlKey && event.key !== 'Control') {\n",
       "        value += 'ctrl+';\n",
       "    }\n",
       "    else if (event.altKey && event.key !== 'Alt') {\n",
       "        value += 'alt+';\n",
       "    }\n",
       "    else if (event.shiftKey && event.key !== 'Shift') {\n",
       "        value += 'shift+';\n",
       "    }\n",
       "\n",
       "    value += 'k' + event.key;\n",
       "\n",
       "    this._key_event_extra(event, name);\n",
       "\n",
       "    this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onclick = function (name) {\n",
       "    if (name === 'download') {\n",
       "        this.handle_save(this, null);\n",
       "    } else {\n",
       "        this.send_message('toolbar_button', { name: name });\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n",
       "    this.message.textContent = tooltip;\n",
       "};\n",
       "\n",
       "///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n",
       "// prettier-ignore\n",
       "var _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\n",
       "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
       "\n",
       "mpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
       "\n",
       "mpl.default_extension = \"png\";/* global mpl */\n",
       "\n",
       "var comm_websocket_adapter = function (comm) {\n",
       "    // Create a \"websocket\"-like object which calls the given IPython comm\n",
       "    // object with the appropriate methods. Currently this is a non binary\n",
       "    // socket, so there is still some room for performance tuning.\n",
       "    var ws = {};\n",
       "\n",
       "    ws.binaryType = comm.kernel.ws.binaryType;\n",
       "    ws.readyState = comm.kernel.ws.readyState;\n",
       "    function updateReadyState(_event) {\n",
       "        if (comm.kernel.ws) {\n",
       "            ws.readyState = comm.kernel.ws.readyState;\n",
       "        } else {\n",
       "            ws.readyState = 3; // Closed state.\n",
       "        }\n",
       "    }\n",
       "    comm.kernel.ws.addEventListener('open', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('close', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('error', updateReadyState);\n",
       "\n",
       "    ws.close = function () {\n",
       "        comm.close();\n",
       "    };\n",
       "    ws.send = function (m) {\n",
       "        //console.log('sending', m);\n",
       "        comm.send(m);\n",
       "    };\n",
       "    // Register the callback with on_msg.\n",
       "    comm.on_msg(function (msg) {\n",
       "        //console.log('receiving', msg['content']['data'], msg);\n",
       "        var data = msg['content']['data'];\n",
       "        if (data['blob'] !== undefined) {\n",
       "            data = {\n",
       "                data: new Blob(msg['buffers'], { type: data['blob'] }),\n",
       "            };\n",
       "        }\n",
       "        // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
       "        ws.onmessage(data);\n",
       "    });\n",
       "    return ws;\n",
       "};\n",
       "\n",
       "mpl.mpl_figure_comm = function (comm, msg) {\n",
       "    // This is the function which gets called when the mpl process\n",
       "    // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
       "\n",
       "    var id = msg.content.data.id;\n",
       "    // Get hold of the div created by the display call when the Comm\n",
       "    // socket was opened in Python.\n",
       "    var element = document.getElementById(id);\n",
       "    var ws_proxy = comm_websocket_adapter(comm);\n",
       "\n",
       "    function ondownload(figure, _format) {\n",
       "        window.open(figure.canvas.toDataURL());\n",
       "    }\n",
       "\n",
       "    var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n",
       "\n",
       "    // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
       "    // web socket which is closed, not our websocket->open comm proxy.\n",
       "    ws_proxy.onopen();\n",
       "\n",
       "    fig.parent_element = element;\n",
       "    fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
       "    if (!fig.cell_info) {\n",
       "        console.error('Failed to find cell for figure', id, fig);\n",
       "        return;\n",
       "    }\n",
       "    fig.cell_info[0].output_area.element.on(\n",
       "        'cleared',\n",
       "        { fig: fig },\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_close = function (fig, msg) {\n",
       "    var width = fig.canvas.width / fig.ratio;\n",
       "    fig.cell_info[0].output_area.element.off(\n",
       "        'cleared',\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "    fig.resizeObserverInstance.unobserve(fig.canvas_div);\n",
       "\n",
       "    // Update the output cell to use the data from the current canvas.\n",
       "    fig.push_to_output();\n",
       "    var dataURL = fig.canvas.toDataURL();\n",
       "    // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
       "    // the notebook keyboard shortcuts fail.\n",
       "    IPython.keyboard_manager.enable();\n",
       "    fig.parent_element.innerHTML =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "    fig.close_ws(fig, msg);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.close_ws = function (fig, msg) {\n",
       "    fig.send_message('closing', msg);\n",
       "    // fig.ws.close()\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.push_to_output = function (_remove_interactive) {\n",
       "    // Turn the data on the canvas into data in the output cell.\n",
       "    var width = this.canvas.width / this.ratio;\n",
       "    var dataURL = this.canvas.toDataURL();\n",
       "    this.cell_info[1]['text/html'] =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Tell IPython that the notebook contents must change.\n",
       "    IPython.notebook.set_dirty(true);\n",
       "    this.send_message('ack', {});\n",
       "    var fig = this;\n",
       "    // Wait a second, then push the new image to the DOM so\n",
       "    // that it is saved nicely (might be nice to debounce this).\n",
       "    setTimeout(function () {\n",
       "        fig.push_to_output();\n",
       "    }, 1000);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'btn-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'btn-group';\n",
       "    var button;\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'btn-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        button = fig.buttons[name] = document.createElement('button');\n",
       "        button.classList = 'btn btn-default';\n",
       "        button.href = '#';\n",
       "        button.title = name;\n",
       "        button.innerHTML = '<i class=\"fa ' + image + ' fa-lg\"></i>';\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    // Add the status bar.\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message pull-right';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "\n",
       "    // Add the close button to the window.\n",
       "    var buttongrp = document.createElement('div');\n",
       "    buttongrp.classList = 'btn-group inline pull-right';\n",
       "    button = document.createElement('button');\n",
       "    button.classList = 'btn btn-mini btn-primary';\n",
       "    button.href = '#';\n",
       "    button.title = 'Stop Interaction';\n",
       "    button.innerHTML = '<i class=\"fa fa-power-off icon-remove icon-large\"></i>';\n",
       "    button.addEventListener('click', function (_evt) {\n",
       "        fig.handle_close(fig, {});\n",
       "    });\n",
       "    button.addEventListener(\n",
       "        'mouseover',\n",
       "        on_mouseover_closure('Stop Interaction')\n",
       "    );\n",
       "    buttongrp.appendChild(button);\n",
       "    var titlebar = this.root.querySelector('.ui-dialog-titlebar');\n",
       "    titlebar.insertBefore(buttongrp, titlebar.firstChild);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._remove_fig_handler = function (event) {\n",
       "    var fig = event.data.fig;\n",
       "    if (event.target !== this) {\n",
       "        // Ignore bubbled events from children.\n",
       "        return;\n",
       "    }\n",
       "    fig.close_ws(fig, {});\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (el) {\n",
       "    el.style.boxSizing = 'content-box'; // override notebook setting of border-box.\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (el) {\n",
       "    // this is important to make the div 'focusable\n",
       "    el.setAttribute('tabindex', 0);\n",
       "    // reach out to IPython and tell the keyboard manager to turn it's self\n",
       "    // off when our div gets focus\n",
       "\n",
       "    // location in version 3\n",
       "    if (IPython.notebook.keyboard_manager) {\n",
       "        IPython.notebook.keyboard_manager.register_events(el);\n",
       "    } else {\n",
       "        // location in version 2\n",
       "        IPython.keyboard_manager.register_events(el);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (event, _name) {\n",
       "    var manager = IPython.notebook.keyboard_manager;\n",
       "    if (!manager) {\n",
       "        manager = IPython.keyboard_manager;\n",
       "    }\n",
       "\n",
       "    // Check for shift+enter\n",
       "    if (event.shiftKey && event.which === 13) {\n",
       "        this.canvas_div.blur();\n",
       "        // select the cell after this one\n",
       "        var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
       "        IPython.notebook.select(index + 1);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    fig.ondownload(fig, null);\n",
       "};\n",
       "\n",
       "mpl.find_output_cell = function (html_output) {\n",
       "    // Return the cell and output element which can be found *uniquely* in the notebook.\n",
       "    // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
       "    // IPython event is triggered only after the cells have been serialised, which for\n",
       "    // our purposes (turning an active figure into a static one), is too late.\n",
       "    var cells = IPython.notebook.get_cells();\n",
       "    var ncells = cells.length;\n",
       "    for (var i = 0; i < ncells; i++) {\n",
       "        var cell = cells[i];\n",
       "        if (cell.cell_type === 'code') {\n",
       "            for (var j = 0; j < cell.output_area.outputs.length; j++) {\n",
       "                var data = cell.output_area.outputs[j];\n",
       "                if (data.data) {\n",
       "                    // IPython >= 3 moved mimebundle to data attribute of output\n",
       "                    data = data.data;\n",
       "                }\n",
       "                if (data['text/html'] === html_output) {\n",
       "                    return [cell, data, j];\n",
       "                }\n",
       "            }\n",
       "        }\n",
       "    }\n",
       "};\n",
       "\n",
       "// Register the function which deals with the matplotlib target/channel.\n",
       "// The kernel may be null if the page has been refreshed.\n",
       "if (IPython.notebook.kernel !== null) {\n",
       "    IPython.notebook.kernel.comm_manager.register_target(\n",
       "        'matplotlib',\n",
       "        mpl.mpl_figure_comm\n",
       "    );\n",
       "}\n"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<img src=\"data:image/png;base64,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\" width=\"1500\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.animation.FuncAnimation at 0x1bf73db7e20>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "if colab:\n",
    "    def init():\n",
    "      fig, lines = plot_multi(x_train, y_train, x_test, y_test, \n",
    "           [\"linear regression\", \"ridge regression\", \"differential regression\"],\n",
    "           [linpred, ridgepred, diffpred])\n",
    "      plt.close(fig)\n",
    "      return lines\n",
    "else:\n",
    "    fig, lines = plot_multi(x_train, y_train, x_test, y_test, \n",
    "       [\"linear regression\", \"ridge regression\", \"differential regression\"],\n",
    "       [linpred, ridgepred, diffpred])\n",
    "\n",
    "def animate(i):\n",
    "    seed = np.random.randint(8192)\n",
    "    x_train, y_train, z_train = bs.trainSet(m, seed=seed)\n",
    "    \n",
    "    linreg.fit(x_train, y_train)\n",
    "    linpred = linreg.predict(x_test)\n",
    "    ridgereg.fit(x_train, y_train)\n",
    "    ridgepred = ridgereg.predict(x_test)\n",
    "    diffreg.fit(x_train, y_train, z_train)\n",
    "    diffpred = diffreg.predict(x_test)\n",
    "    \n",
    "    lines[0].set_data(x_train, y_train)\n",
    "    lines[1].set_data(x_test, linpred)\n",
    "    lines[3].set_data(x_train, y_train)\n",
    "    lines[4].set_data(x_test, ridgepred)\n",
    "    lines[6].set_data(x_train, y_train)\n",
    "    lines[7].set_data(x_test, diffpred)\n",
    "    \n",
    "    return lines\n",
    "\n",
    "# slow on colab\n",
    "FuncAnimation(fig, animate, init_func=init if colab else None, frames=20 if colab else 200, interval=500, blit=True)\n",
    "#anim = FuncAnimation(fig, animate, init_func=init if colab else None, frames=20 if colab else 200, interval=500, blit=True)\n",
    "#f = r\"animation.gif\" \n",
    "#writergif = PillowWriter(fps=1) \n",
    "#anim.save(f, writer=writergif)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Classic regression overfits, as illustrated by the wigly shape of its predictions, which also vary significantly in response to the noise in the dataset, a phenomenon known as variance. Cross-validated Tikhonov regularization clearly stabilizes regression, in return for a bias whereby the model struggles to match the correct shape. The results of differential regression, by contrast, appear to be consistently correct (given the small dataset) with much lower variance."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bachelier basket dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Black & Scholes dataset is one-dimensional, contrarily to most real-world problems in finance, where the market state that affects the price and risk of Derivatives transactions and trading books is typically high-dimensional. To illustrate differential regression in the context of an equally simple but higher dimension example, we consider basket options in the correlated Gaussian Bachelier model. The simulation of the dataset is essentially a carbon-copy of the Black & Scholes simulator. This example is also interesting because the price and risks of a basket option only depend on the initial price of the underlying basket under the Gaussian assumption, irrespective of single stocks. This is therefore a single-dimensional problem, but of course, the fitting algorithm is unaware of this fact and treats the dataset as multi-dimensional. We can, however, conveniently visualize results with two-dimensional graphs where the horizontal axis is indexed by the initial basket.\n",
    "\n",
    "First, we have Bachelier analytics that provide the correct pricing function to easily measure performance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def Bachelier(S, K, sigma, T):\n",
    "    d = (S - K) / sigma / np.sqrt(T)\n",
    "    return  sigma * np.sqrt(T) * (d * norm.cdf(d) + norm.pdf(d))\n",
    "\n",
    "def BachelierDelta(S, K, sigma, T):\n",
    "    d = (S - K) / sigma / np.sqrt(T)\n",
    "    return norm.cdf(d)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, we use helper functions to generate random correlation matrices, basket weights and volatilities, so we can easily test the methods in different circumstances without dealing with real market data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# generates a random correlation matrix\n",
    "def genCorrel(n):\n",
    "    randoms = np.random.uniform(low=-1., high=1., size=(2*n, n))\n",
    "    cov = randoms.T @ randoms\n",
    "    invvols = np.diag(1. / np.sqrt(np.diagonal(cov)))\n",
    "    return np.linalg.multi_dot([invvols, cov, invvols])\n",
    "\n",
    "# generates random weights\n",
    "def genWeights(n):\n",
    "    w = np.random.uniform(size=n)\n",
    "    return w / w.sum()\n",
    "\n",
    "# generates random volatilities such that the volatility of the basket matches a given target\n",
    "def genVols(n, correl, weights, bkt_vol=20):\n",
    "    vols = np.random.uniform(size=n)\n",
    "    weighted_vols = (weights * vols).reshape(-1,1)\n",
    "    v = np.sqrt(np.linalg.multi_dot([weighted_vols.T, correl, weighted_vols]).reshape(1))\n",
    "    vols = vols * bkt_vol / v\n",
    "    return vols"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally, we have a simulator very similar to Black & Scholes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "class BachelierSimulator():\n",
    "    \n",
    "    # None = generate randomly\n",
    "    def __init__(self, n, T, K, vols=None, correl=None, weights=None, bkt_vol=20, seed=0, lower=10, upper=200):\n",
    "        self.n = n\n",
    "        self.T = T\n",
    "        self.sqrtT = np.sqrt(T)\n",
    "        self.K = K\n",
    "        \n",
    "        np.random.seed(seed)\n",
    "        self.weights = genWeights(n) if weights is None else weights\n",
    "        self.correl = genCorrel(n) if correl is None else correl\n",
    "        self.vols = genVols(n, self.correl, self.weights, bkt_vol) if vols is None else vols\n",
    "        self.bkt_vol = bkt_vol\n",
    "        \n",
    "        vT = np.diag(self.vols) * self.sqrtT\n",
    "        self.cov = np.linalg.multi_dot([vT, self.correl, vT])\n",
    "        self.chol = np.linalg.cholesky(self.cov) \n",
    "        \n",
    "        self.lower = lower\n",
    "        self.upper = upper\n",
    "        \n",
    "    def trainSet(self, m, seed=0):\n",
    "        np.random.seed(seed)\n",
    "\n",
    "        s0 = np.random.uniform(low=self.lower, high=self.upper, size = (m, self.n))\n",
    "        b0 = np.dot(s0, self.weights)\n",
    "        wT = np.random.normal(size=(m, self.n))\n",
    "        sT = s0 + wT @ self.chol.T\n",
    "        bT = np.dot(sT, self.weights)\n",
    "        pay = np.maximum(0, bT - self.K)\n",
    "        deriv = np.where(bT > self.K, 1, 0).reshape(-1, 1) * self.weights.reshape(1, -1)\n",
    "        \n",
    "        return s0.reshape(-1, self.n), b0.reshape(-1, 1), pay.reshape(-1, 1), deriv.reshape(-1, self.n)\n",
    "    \n",
    "    def testSet(self, m, seed=1024): # must be a different seed\n",
    "        np.random.seed(seed)\n",
    "        \n",
    "        s0 = np.random.uniform(low=self.lower, high=self.upper, size = (m, self.n))\n",
    "        b0 = np.dot(s0, self.weights).reshape((-1, 1))\n",
    "        prices = Bachelier(b0, self.K, self.bkt_vol, self.T)\n",
    "        deltas = BachelierDelta(b0, self.K, self.bkt_vol, self.T) @ self.weights.reshape((1, -1))\n",
    "        return s0, b0, prices.reshape(-1, 1), deltas.reshape(-1, self.n)    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We now have all the pieces we need to learn basket option prices."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dimension, readers are encouraged to play with different dimensions by changing the value of n\n",
    "n = 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "using seed 4172\n"
     ]
    }
   ],
   "source": [
    "# parameters and constants\n",
    "\n",
    "# basket volatility is fixed but the volatilities of single stocks are randomly generated\n",
    "bkt_vol = 20\n",
    "K = 110\n",
    "T = 3\n",
    "\n",
    "# we need a larger dataset in higher dimension, at least 1,000 examples\n",
    "m = 1000\n",
    "M = 5000\n",
    "lower = 10\n",
    "upper = 200\n",
    "\n",
    "# generate random correlation, weights and volatility\n",
    "seed = np.random.randint(8192)\n",
    "correl = genCorrel(n)\n",
    "weights = genWeights(n)\n",
    "vols = genVols(n, correl, weights, bkt_vol)\n",
    "\n",
    "# re-seed for dataset\n",
    "seed = np.random.randint(8192)\n",
    "print(\"using seed\", seed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# simulate dataset\n",
    "\n",
    "bach = BachelierSimulator(n, T, K, vols, correl, weights, bkt_vol, seed)\n",
    "x_train, bkt_train, y_train, z_train = bach.trainSet(m, seed=seed)\n",
    "x_test, bkt_test, y_test, z_test = bach.testSet(M)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# learn and predict\n",
    "\n",
    "#linreg = make_polynomial()\n",
    "#linreg.fit(x_train, y_train)\n",
    "#linpred = linreg.predict(x_test)\n",
    "\n",
    "# linear regression is numerically unstable with nearly colinear features\n",
    "# normally, this is resolved by SVD inversion in the normal equation\n",
    "# since SVD is not implemented in the linear regression of scikit-learn\n",
    "# we use a ridge regression with small alpha as a walkaround\n",
    "\n",
    "linreg = make_ridge(alpha=1.0e-04)\n",
    "linreg.fit(x_train, y_train)\n",
    "linpred = linreg.predict(x_test)\n",
    "\n",
    "ridgereg = make_ridge_cv()\n",
    "ridgereg.fit(x_train, y_train)\n",
    "ridgepred = ridgereg.predict(x_test)\n",
    "alpha = ridgereg['ridgecv'].alpha_\n",
    "\n",
    "diffreg = DifferentialRegression()\n",
    "diffreg.fit(x_train, y_train, z_train)\n",
    "diffpred = diffreg.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ridge regression alpha = 0.5462\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "/* Put everything inside the global mpl namespace */\n",
       "/* global mpl */\n",
       "window.mpl = {};\n",
       "\n",
       "mpl.get_websocket_type = function () {\n",
       "    if (typeof WebSocket !== 'undefined') {\n",
       "        return WebSocket;\n",
       "    } else if (typeof MozWebSocket !== 'undefined') {\n",
       "        return MozWebSocket;\n",
       "    } else {\n",
       "        alert(\n",
       "            'Your browser does not have WebSocket support. ' +\n",
       "                'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
       "                'Firefox 4 and 5 are also supported but you ' +\n",
       "                'have to enable WebSockets in about:config.'\n",
       "        );\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n",
       "    this.id = figure_id;\n",
       "\n",
       "    this.ws = websocket;\n",
       "\n",
       "    this.supports_binary = this.ws.binaryType !== undefined;\n",
       "\n",
       "    if (!this.supports_binary) {\n",
       "        var warnings = document.getElementById('mpl-warnings');\n",
       "        if (warnings) {\n",
       "            warnings.style.display = 'block';\n",
       "            warnings.textContent =\n",
       "                'This browser does not support binary websocket messages. ' +\n",
       "                'Performance may be slow.';\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.imageObj = new Image();\n",
       "\n",
       "    this.context = undefined;\n",
       "    this.message = undefined;\n",
       "    this.canvas = undefined;\n",
       "    this.rubberband_canvas = undefined;\n",
       "    this.rubberband_context = undefined;\n",
       "    this.format_dropdown = undefined;\n",
       "\n",
       "    this.image_mode = 'full';\n",
       "\n",
       "    this.root = document.createElement('div');\n",
       "    this.root.setAttribute('style', 'display: inline-block');\n",
       "    this._root_extra_style(this.root);\n",
       "\n",
       "    parent_element.appendChild(this.root);\n",
       "\n",
       "    this._init_header(this);\n",
       "    this._init_canvas(this);\n",
       "    this._init_toolbar(this);\n",
       "\n",
       "    var fig = this;\n",
       "\n",
       "    this.waiting = false;\n",
       "\n",
       "    this.ws.onopen = function () {\n",
       "        fig.send_message('supports_binary', { value: fig.supports_binary });\n",
       "        fig.send_message('send_image_mode', {});\n",
       "        if (fig.ratio !== 1) {\n",
       "            fig.send_message('set_dpi_ratio', { dpi_ratio: fig.ratio });\n",
       "        }\n",
       "        fig.send_message('refresh', {});\n",
       "    };\n",
       "\n",
       "    this.imageObj.onload = function () {\n",
       "        if (fig.image_mode === 'full') {\n",
       "            // Full images could contain transparency (where diff images\n",
       "            // almost always do), so we need to clear the canvas so that\n",
       "            // there is no ghosting.\n",
       "            fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
       "        }\n",
       "        fig.context.drawImage(fig.imageObj, 0, 0);\n",
       "    };\n",
       "\n",
       "    this.imageObj.onunload = function () {\n",
       "        fig.ws.close();\n",
       "    };\n",
       "\n",
       "    this.ws.onmessage = this._make_on_message_function(this);\n",
       "\n",
       "    this.ondownload = ondownload;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_header = function () {\n",
       "    var titlebar = document.createElement('div');\n",
       "    titlebar.classList =\n",
       "        'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n",
       "    var titletext = document.createElement('div');\n",
       "    titletext.classList = 'ui-dialog-title';\n",
       "    titletext.setAttribute(\n",
       "        'style',\n",
       "        'width: 100%; text-align: center; padding: 3px;'\n",
       "    );\n",
       "    titlebar.appendChild(titletext);\n",
       "    this.root.appendChild(titlebar);\n",
       "    this.header = titletext;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._init_canvas = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var canvas_div = (this.canvas_div = document.createElement('div'));\n",
       "    canvas_div.setAttribute(\n",
       "        'style',\n",
       "        'border: 1px solid #ddd;' +\n",
       "            'box-sizing: content-box;' +\n",
       "            'clear: both;' +\n",
       "            'min-height: 1px;' +\n",
       "            'min-width: 1px;' +\n",
       "            'outline: 0;' +\n",
       "            'overflow: hidden;' +\n",
       "            'position: relative;' +\n",
       "            'resize: both;'\n",
       "    );\n",
       "\n",
       "    function on_keyboard_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.key_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    canvas_div.addEventListener(\n",
       "        'keydown',\n",
       "        on_keyboard_event_closure('key_press')\n",
       "    );\n",
       "    canvas_div.addEventListener(\n",
       "        'keyup',\n",
       "        on_keyboard_event_closure('key_release')\n",
       "    );\n",
       "\n",
       "    this._canvas_extra_style(canvas_div);\n",
       "    this.root.appendChild(canvas_div);\n",
       "\n",
       "    var canvas = (this.canvas = document.createElement('canvas'));\n",
       "    canvas.classList.add('mpl-canvas');\n",
       "    canvas.setAttribute('style', 'box-sizing: content-box;');\n",
       "\n",
       "    this.context = canvas.getContext('2d');\n",
       "\n",
       "    var backingStore =\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        this.context.webkitBackingStorePixelRatio ||\n",
       "        this.context.mozBackingStorePixelRatio ||\n",
       "        this.context.msBackingStorePixelRatio ||\n",
       "        this.context.oBackingStorePixelRatio ||\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        1;\n",
       "\n",
       "    this.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
       "\n",
       "    var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n",
       "        'canvas'\n",
       "    ));\n",
       "    rubberband_canvas.setAttribute(\n",
       "        'style',\n",
       "        'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n",
       "    );\n",
       "\n",
       "    // Apply a ponyfill if ResizeObserver is not implemented by browser.\n",
       "    if (this.ResizeObserver === undefined) {\n",
       "        if (window.ResizeObserver !== undefined) {\n",
       "            this.ResizeObserver = window.ResizeObserver;\n",
       "        } else {\n",
       "            var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n",
       "            this.ResizeObserver = obs.ResizeObserver;\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n",
       "        var nentries = entries.length;\n",
       "        for (var i = 0; i < nentries; i++) {\n",
       "            var entry = entries[i];\n",
       "            var width, height;\n",
       "            if (entry.contentBoxSize) {\n",
       "                if (entry.contentBoxSize instanceof Array) {\n",
       "                    // Chrome 84 implements new version of spec.\n",
       "                    width = entry.contentBoxSize[0].inlineSize;\n",
       "                    height = entry.contentBoxSize[0].blockSize;\n",
       "                } else {\n",
       "                    // Firefox implements old version of spec.\n",
       "                    width = entry.contentBoxSize.inlineSize;\n",
       "                    height = entry.contentBoxSize.blockSize;\n",
       "                }\n",
       "            } else {\n",
       "                // Chrome <84 implements even older version of spec.\n",
       "                width = entry.contentRect.width;\n",
       "                height = entry.contentRect.height;\n",
       "            }\n",
       "\n",
       "            // Keep the size of the canvas and rubber band canvas in sync with\n",
       "            // the canvas container.\n",
       "            if (entry.devicePixelContentBoxSize) {\n",
       "                // Chrome 84 implements new version of spec.\n",
       "                canvas.setAttribute(\n",
       "                    'width',\n",
       "                    entry.devicePixelContentBoxSize[0].inlineSize\n",
       "                );\n",
       "                canvas.setAttribute(\n",
       "                    'height',\n",
       "                    entry.devicePixelContentBoxSize[0].blockSize\n",
       "                );\n",
       "            } else {\n",
       "                canvas.setAttribute('width', width * fig.ratio);\n",
       "                canvas.setAttribute('height', height * fig.ratio);\n",
       "            }\n",
       "            canvas.setAttribute(\n",
       "                'style',\n",
       "                'width: ' + width + 'px; height: ' + height + 'px;'\n",
       "            );\n",
       "\n",
       "            rubberband_canvas.setAttribute('width', width);\n",
       "            rubberband_canvas.setAttribute('height', height);\n",
       "\n",
       "            // And update the size in Python. We ignore the initial 0/0 size\n",
       "            // that occurs as the element is placed into the DOM, which should\n",
       "            // otherwise not happen due to the minimum size styling.\n",
       "            if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n",
       "                fig.request_resize(width, height);\n",
       "            }\n",
       "        }\n",
       "    });\n",
       "    this.resizeObserverInstance.observe(canvas_div);\n",
       "\n",
       "    function on_mouse_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.mouse_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousedown',\n",
       "        on_mouse_event_closure('button_press')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseup',\n",
       "        on_mouse_event_closure('button_release')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'dblclick',\n",
       "        on_mouse_event_closure('dblclick')\n",
       "    );\n",
       "    // Throttle sequential mouse events to 1 every 20ms.\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousemove',\n",
       "        on_mouse_event_closure('motion_notify')\n",
       "    );\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseenter',\n",
       "        on_mouse_event_closure('figure_enter')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseleave',\n",
       "        on_mouse_event_closure('figure_leave')\n",
       "    );\n",
       "\n",
       "    canvas_div.addEventListener('wheel', function (event) {\n",
       "        if (event.deltaY < 0) {\n",
       "            event.step = 1;\n",
       "        } else {\n",
       "            event.step = -1;\n",
       "        }\n",
       "        on_mouse_event_closure('scroll')(event);\n",
       "    });\n",
       "\n",
       "    canvas_div.appendChild(canvas);\n",
       "    canvas_div.appendChild(rubberband_canvas);\n",
       "\n",
       "    this.rubberband_context = rubberband_canvas.getContext('2d');\n",
       "    this.rubberband_context.strokeStyle = '#000000';\n",
       "\n",
       "    this._resize_canvas = function (width, height, forward) {\n",
       "        if (forward) {\n",
       "            canvas_div.style.width = width + 'px';\n",
       "            canvas_div.style.height = height + 'px';\n",
       "        }\n",
       "    };\n",
       "\n",
       "    // Disable right mouse context menu.\n",
       "    this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n",
       "        event.preventDefault();\n",
       "        return false;\n",
       "    });\n",
       "\n",
       "    function set_focus() {\n",
       "        canvas.focus();\n",
       "        canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    window.setTimeout(set_focus, 100);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'mpl-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'mpl-button-group';\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'mpl-button-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        var button = (fig.buttons[name] = document.createElement('button'));\n",
       "        button.classList = 'mpl-widget';\n",
       "        button.setAttribute('role', 'button');\n",
       "        button.setAttribute('aria-disabled', 'false');\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "\n",
       "        var icon_img = document.createElement('img');\n",
       "        icon_img.src = '_images/' + image + '.png';\n",
       "        icon_img.srcset = '_images/' + image + '_large.png 2x';\n",
       "        icon_img.alt = tooltip;\n",
       "        button.appendChild(icon_img);\n",
       "\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    var fmt_picker = document.createElement('select');\n",
       "    fmt_picker.classList = 'mpl-widget';\n",
       "    toolbar.appendChild(fmt_picker);\n",
       "    this.format_dropdown = fmt_picker;\n",
       "\n",
       "    for (var ind in mpl.extensions) {\n",
       "        var fmt = mpl.extensions[ind];\n",
       "        var option = document.createElement('option');\n",
       "        option.selected = fmt === mpl.default_extension;\n",
       "        option.innerHTML = fmt;\n",
       "        fmt_picker.appendChild(option);\n",
       "    }\n",
       "\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n",
       "    // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
       "    // which will in turn request a refresh of the image.\n",
       "    this.send_message('resize', { width: x_pixels, height: y_pixels });\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_message = function (type, properties) {\n",
       "    properties['type'] = type;\n",
       "    properties['figure_id'] = this.id;\n",
       "    this.ws.send(JSON.stringify(properties));\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_draw_message = function () {\n",
       "    if (!this.waiting) {\n",
       "        this.waiting = true;\n",
       "        this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    var format_dropdown = fig.format_dropdown;\n",
       "    var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
       "    fig.ondownload(fig, format);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_resize = function (fig, msg) {\n",
       "    var size = msg['size'];\n",
       "    if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n",
       "        fig._resize_canvas(size[0], size[1], msg['forward']);\n",
       "        fig.send_message('refresh', {});\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_rubberband = function (fig, msg) {\n",
       "    var x0 = msg['x0'] / fig.ratio;\n",
       "    var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n",
       "    var x1 = msg['x1'] / fig.ratio;\n",
       "    var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n",
       "    x0 = Math.floor(x0) + 0.5;\n",
       "    y0 = Math.floor(y0) + 0.5;\n",
       "    x1 = Math.floor(x1) + 0.5;\n",
       "    y1 = Math.floor(y1) + 0.5;\n",
       "    var min_x = Math.min(x0, x1);\n",
       "    var min_y = Math.min(y0, y1);\n",
       "    var width = Math.abs(x1 - x0);\n",
       "    var height = Math.abs(y1 - y0);\n",
       "\n",
       "    fig.rubberband_context.clearRect(\n",
       "        0,\n",
       "        0,\n",
       "        fig.canvas.width / fig.ratio,\n",
       "        fig.canvas.height / fig.ratio\n",
       "    );\n",
       "\n",
       "    fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_figure_label = function (fig, msg) {\n",
       "    // Updates the figure title.\n",
       "    fig.header.textContent = msg['label'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_cursor = function (fig, msg) {\n",
       "    var cursor = msg['cursor'];\n",
       "    switch (cursor) {\n",
       "        case 0:\n",
       "            cursor = 'pointer';\n",
       "            break;\n",
       "        case 1:\n",
       "            cursor = 'default';\n",
       "            break;\n",
       "        case 2:\n",
       "            cursor = 'crosshair';\n",
       "            break;\n",
       "        case 3:\n",
       "            cursor = 'move';\n",
       "            break;\n",
       "    }\n",
       "    fig.rubberband_canvas.style.cursor = cursor;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_message = function (fig, msg) {\n",
       "    fig.message.textContent = msg['message'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_draw = function (fig, _msg) {\n",
       "    // Request the server to send over a new figure.\n",
       "    fig.send_draw_message();\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_image_mode = function (fig, msg) {\n",
       "    fig.image_mode = msg['mode'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n",
       "    for (var key in msg) {\n",
       "        if (!(key in fig.buttons)) {\n",
       "            continue;\n",
       "        }\n",
       "        fig.buttons[key].disabled = !msg[key];\n",
       "        fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n",
       "    if (msg['mode'] === 'PAN') {\n",
       "        fig.buttons['Pan'].classList.add('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    } else if (msg['mode'] === 'ZOOM') {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.add('active');\n",
       "    } else {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Called whenever the canvas gets updated.\n",
       "    this.send_message('ack', {});\n",
       "};\n",
       "\n",
       "// A function to construct a web socket function for onmessage handling.\n",
       "// Called in the figure constructor.\n",
       "mpl.figure.prototype._make_on_message_function = function (fig) {\n",
       "    return function socket_on_message(evt) {\n",
       "        if (evt.data instanceof Blob) {\n",
       "            var img = evt.data;\n",
       "            if (img.type !== 'image/png') {\n",
       "                /* FIXME: We get \"Resource interpreted as Image but\n",
       "                 * transferred with MIME type text/plain:\" errors on\n",
       "                 * Chrome.  But how to set the MIME type?  It doesn't seem\n",
       "                 * to be part of the websocket stream */\n",
       "                img.type = 'image/png';\n",
       "            }\n",
       "\n",
       "            /* Free the memory for the previous frames */\n",
       "            if (fig.imageObj.src) {\n",
       "                (window.URL || window.webkitURL).revokeObjectURL(\n",
       "                    fig.imageObj.src\n",
       "                );\n",
       "            }\n",
       "\n",
       "            fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
       "                img\n",
       "            );\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        } else if (\n",
       "            typeof evt.data === 'string' &&\n",
       "            evt.data.slice(0, 21) === 'data:image/png;base64'\n",
       "        ) {\n",
       "            fig.imageObj.src = evt.data;\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        var msg = JSON.parse(evt.data);\n",
       "        var msg_type = msg['type'];\n",
       "\n",
       "        // Call the  \"handle_{type}\" callback, which takes\n",
       "        // the figure and JSON message as its only arguments.\n",
       "        try {\n",
       "            var callback = fig['handle_' + msg_type];\n",
       "        } catch (e) {\n",
       "            console.log(\n",
       "                \"No handler for the '\" + msg_type + \"' message type: \",\n",
       "                msg\n",
       "            );\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        if (callback) {\n",
       "            try {\n",
       "                // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
       "                callback(fig, msg);\n",
       "            } catch (e) {\n",
       "                console.log(\n",
       "                    \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n",
       "                    e,\n",
       "                    e.stack,\n",
       "                    msg\n",
       "                );\n",
       "            }\n",
       "        }\n",
       "    };\n",
       "};\n",
       "\n",
       "// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
       "mpl.findpos = function (e) {\n",
       "    //this section is from http://www.quirksmode.org/js/events_properties.html\n",
       "    var targ;\n",
       "    if (!e) {\n",
       "        e = window.event;\n",
       "    }\n",
       "    if (e.target) {\n",
       "        targ = e.target;\n",
       "    } else if (e.srcElement) {\n",
       "        targ = e.srcElement;\n",
       "    }\n",
       "    if (targ.nodeType === 3) {\n",
       "        // defeat Safari bug\n",
       "        targ = targ.parentNode;\n",
       "    }\n",
       "\n",
       "    // pageX,Y are the mouse positions relative to the document\n",
       "    var boundingRect = targ.getBoundingClientRect();\n",
       "    var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n",
       "    var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n",
       "\n",
       "    return { x: x, y: y };\n",
       "};\n",
       "\n",
       "/*\n",
       " * return a copy of an object with only non-object keys\n",
       " * we need this to avoid circular references\n",
       " * http://stackoverflow.com/a/24161582/3208463\n",
       " */\n",
       "function simpleKeys(original) {\n",
       "    return Object.keys(original).reduce(function (obj, key) {\n",
       "        if (typeof original[key] !== 'object') {\n",
       "            obj[key] = original[key];\n",
       "        }\n",
       "        return obj;\n",
       "    }, {});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.mouse_event = function (event, name) {\n",
       "    var canvas_pos = mpl.findpos(event);\n",
       "\n",
       "    if (name === 'button_press') {\n",
       "        this.canvas.focus();\n",
       "        this.canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    var x = canvas_pos.x * this.ratio;\n",
       "    var y = canvas_pos.y * this.ratio;\n",
       "\n",
       "    this.send_message(name, {\n",
       "        x: x,\n",
       "        y: y,\n",
       "        button: event.button,\n",
       "        step: event.step,\n",
       "        guiEvent: simpleKeys(event),\n",
       "    });\n",
       "\n",
       "    /* This prevents the web browser from automatically changing to\n",
       "     * the text insertion cursor when the button is pressed.  We want\n",
       "     * to control all of the cursor setting manually through the\n",
       "     * 'cursor' event from matplotlib */\n",
       "    event.preventDefault();\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (_event, _name) {\n",
       "    // Handle any extra behaviour associated with a key event\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.key_event = function (event, name) {\n",
       "    // Prevent repeat events\n",
       "    if (name === 'key_press') {\n",
       "        if (event.key === this._key) {\n",
       "            return;\n",
       "        } else {\n",
       "            this._key = event.key;\n",
       "        }\n",
       "    }\n",
       "    if (name === 'key_release') {\n",
       "        this._key = null;\n",
       "    }\n",
       "\n",
       "    var value = '';\n",
       "    if (event.ctrlKey && event.key !== 'Control') {\n",
       "        value += 'ctrl+';\n",
       "    }\n",
       "    else if (event.altKey && event.key !== 'Alt') {\n",
       "        value += 'alt+';\n",
       "    }\n",
       "    else if (event.shiftKey && event.key !== 'Shift') {\n",
       "        value += 'shift+';\n",
       "    }\n",
       "\n",
       "    value += 'k' + event.key;\n",
       "\n",
       "    this._key_event_extra(event, name);\n",
       "\n",
       "    this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onclick = function (name) {\n",
       "    if (name === 'download') {\n",
       "        this.handle_save(this, null);\n",
       "    } else {\n",
       "        this.send_message('toolbar_button', { name: name });\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n",
       "    this.message.textContent = tooltip;\n",
       "};\n",
       "\n",
       "///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n",
       "// prettier-ignore\n",
       "var _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\n",
       "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
       "\n",
       "mpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
       "\n",
       "mpl.default_extension = \"png\";/* global mpl */\n",
       "\n",
       "var comm_websocket_adapter = function (comm) {\n",
       "    // Create a \"websocket\"-like object which calls the given IPython comm\n",
       "    // object with the appropriate methods. Currently this is a non binary\n",
       "    // socket, so there is still some room for performance tuning.\n",
       "    var ws = {};\n",
       "\n",
       "    ws.binaryType = comm.kernel.ws.binaryType;\n",
       "    ws.readyState = comm.kernel.ws.readyState;\n",
       "    function updateReadyState(_event) {\n",
       "        if (comm.kernel.ws) {\n",
       "            ws.readyState = comm.kernel.ws.readyState;\n",
       "        } else {\n",
       "            ws.readyState = 3; // Closed state.\n",
       "        }\n",
       "    }\n",
       "    comm.kernel.ws.addEventListener('open', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('close', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('error', updateReadyState);\n",
       "\n",
       "    ws.close = function () {\n",
       "        comm.close();\n",
       "    };\n",
       "    ws.send = function (m) {\n",
       "        //console.log('sending', m);\n",
       "        comm.send(m);\n",
       "    };\n",
       "    // Register the callback with on_msg.\n",
       "    comm.on_msg(function (msg) {\n",
       "        //console.log('receiving', msg['content']['data'], msg);\n",
       "        var data = msg['content']['data'];\n",
       "        if (data['blob'] !== undefined) {\n",
       "            data = {\n",
       "                data: new Blob(msg['buffers'], { type: data['blob'] }),\n",
       "            };\n",
       "        }\n",
       "        // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
       "        ws.onmessage(data);\n",
       "    });\n",
       "    return ws;\n",
       "};\n",
       "\n",
       "mpl.mpl_figure_comm = function (comm, msg) {\n",
       "    // This is the function which gets called when the mpl process\n",
       "    // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
       "\n",
       "    var id = msg.content.data.id;\n",
       "    // Get hold of the div created by the display call when the Comm\n",
       "    // socket was opened in Python.\n",
       "    var element = document.getElementById(id);\n",
       "    var ws_proxy = comm_websocket_adapter(comm);\n",
       "\n",
       "    function ondownload(figure, _format) {\n",
       "        window.open(figure.canvas.toDataURL());\n",
       "    }\n",
       "\n",
       "    var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n",
       "\n",
       "    // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
       "    // web socket which is closed, not our websocket->open comm proxy.\n",
       "    ws_proxy.onopen();\n",
       "\n",
       "    fig.parent_element = element;\n",
       "    fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
       "    if (!fig.cell_info) {\n",
       "        console.error('Failed to find cell for figure', id, fig);\n",
       "        return;\n",
       "    }\n",
       "    fig.cell_info[0].output_area.element.on(\n",
       "        'cleared',\n",
       "        { fig: fig },\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_close = function (fig, msg) {\n",
       "    var width = fig.canvas.width / fig.ratio;\n",
       "    fig.cell_info[0].output_area.element.off(\n",
       "        'cleared',\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "    fig.resizeObserverInstance.unobserve(fig.canvas_div);\n",
       "\n",
       "    // Update the output cell to use the data from the current canvas.\n",
       "    fig.push_to_output();\n",
       "    var dataURL = fig.canvas.toDataURL();\n",
       "    // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
       "    // the notebook keyboard shortcuts fail.\n",
       "    IPython.keyboard_manager.enable();\n",
       "    fig.parent_element.innerHTML =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "    fig.close_ws(fig, msg);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.close_ws = function (fig, msg) {\n",
       "    fig.send_message('closing', msg);\n",
       "    // fig.ws.close()\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.push_to_output = function (_remove_interactive) {\n",
       "    // Turn the data on the canvas into data in the output cell.\n",
       "    var width = this.canvas.width / this.ratio;\n",
       "    var dataURL = this.canvas.toDataURL();\n",
       "    this.cell_info[1]['text/html'] =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Tell IPython that the notebook contents must change.\n",
       "    IPython.notebook.set_dirty(true);\n",
       "    this.send_message('ack', {});\n",
       "    var fig = this;\n",
       "    // Wait a second, then push the new image to the DOM so\n",
       "    // that it is saved nicely (might be nice to debounce this).\n",
       "    setTimeout(function () {\n",
       "        fig.push_to_output();\n",
       "    }, 1000);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'btn-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'btn-group';\n",
       "    var button;\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'btn-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        button = fig.buttons[name] = document.createElement('button');\n",
       "        button.classList = 'btn btn-default';\n",
       "        button.href = '#';\n",
       "        button.title = name;\n",
       "        button.innerHTML = '<i class=\"fa ' + image + ' fa-lg\"></i>';\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    // Add the status bar.\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message pull-right';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "\n",
       "    // Add the close button to the window.\n",
       "    var buttongrp = document.createElement('div');\n",
       "    buttongrp.classList = 'btn-group inline pull-right';\n",
       "    button = document.createElement('button');\n",
       "    button.classList = 'btn btn-mini btn-primary';\n",
       "    button.href = '#';\n",
       "    button.title = 'Stop Interaction';\n",
       "    button.innerHTML = '<i class=\"fa fa-power-off icon-remove icon-large\"></i>';\n",
       "    button.addEventListener('click', function (_evt) {\n",
       "        fig.handle_close(fig, {});\n",
       "    });\n",
       "    button.addEventListener(\n",
       "        'mouseover',\n",
       "        on_mouseover_closure('Stop Interaction')\n",
       "    );\n",
       "    buttongrp.appendChild(button);\n",
       "    var titlebar = this.root.querySelector('.ui-dialog-titlebar');\n",
       "    titlebar.insertBefore(buttongrp, titlebar.firstChild);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._remove_fig_handler = function (event) {\n",
       "    var fig = event.data.fig;\n",
       "    if (event.target !== this) {\n",
       "        // Ignore bubbled events from children.\n",
       "        return;\n",
       "    }\n",
       "    fig.close_ws(fig, {});\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (el) {\n",
       "    el.style.boxSizing = 'content-box'; // override notebook setting of border-box.\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (el) {\n",
       "    // this is important to make the div 'focusable\n",
       "    el.setAttribute('tabindex', 0);\n",
       "    // reach out to IPython and tell the keyboard manager to turn it's self\n",
       "    // off when our div gets focus\n",
       "\n",
       "    // location in version 3\n",
       "    if (IPython.notebook.keyboard_manager) {\n",
       "        IPython.notebook.keyboard_manager.register_events(el);\n",
       "    } else {\n",
       "        // location in version 2\n",
       "        IPython.keyboard_manager.register_events(el);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (event, _name) {\n",
       "    var manager = IPython.notebook.keyboard_manager;\n",
       "    if (!manager) {\n",
       "        manager = IPython.keyboard_manager;\n",
       "    }\n",
       "\n",
       "    // Check for shift+enter\n",
       "    if (event.shiftKey && event.which === 13) {\n",
       "        this.canvas_div.blur();\n",
       "        // select the cell after this one\n",
       "        var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
       "        IPython.notebook.select(index + 1);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    fig.ondownload(fig, null);\n",
       "};\n",
       "\n",
       "mpl.find_output_cell = function (html_output) {\n",
       "    // Return the cell and output element which can be found *uniquely* in the notebook.\n",
       "    // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
       "    // IPython event is triggered only after the cells have been serialised, which for\n",
       "    // our purposes (turning an active figure into a static one), is too late.\n",
       "    var cells = IPython.notebook.get_cells();\n",
       "    var ncells = cells.length;\n",
       "    for (var i = 0; i < ncells; i++) {\n",
       "        var cell = cells[i];\n",
       "        if (cell.cell_type === 'code') {\n",
       "            for (var j = 0; j < cell.output_area.outputs.length; j++) {\n",
       "                var data = cell.output_area.outputs[j];\n",
       "                if (data.data) {\n",
       "                    // IPython >= 3 moved mimebundle to data attribute of output\n",
       "                    data = data.data;\n",
       "                }\n",
       "                if (data['text/html'] === html_output) {\n",
       "                    return [cell, data, j];\n",
       "                }\n",
       "            }\n",
       "        }\n",
       "    }\n",
       "};\n",
       "\n",
       "// Register the function which deals with the matplotlib target/channel.\n",
       "// The kernel may be null if the page has been refreshed.\n",
       "if (IPython.notebook.kernel !== null) {\n",
       "    IPython.notebook.kernel.comm_manager.register_target(\n",
       "        'matplotlib',\n",
       "        mpl.mpl_figure_comm\n",
       "    );\n",
       "}\n"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<img src=\"data:image/png;base64,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\" width=\"1500\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot results\n",
    "\n",
    "def plot_one(ax, bkt_train, y_train, bkt_test, y_test, pred):\n",
    "    ax.set_xlim(0, 225)\n",
    "    ax.set_ylim(-20, 100)\n",
    "    samples, = ax.plot(bkt_train, y_train, 'co', markersize=5, markerfacecolor=\"white\", label=\"samples\")\n",
    "    predict, = ax.plot(bkt_test, pred, 'b.', label=\"predict\")\n",
    "    correct, = ax.plot(bkt_test, y_test, 'r.', label=\"correct\")\n",
    "    return samples, predict, correct\n",
    "\n",
    "def plot_multi(bkt_train, y_train, bkt_test, y_test, titles, preds):\n",
    "    nplots = len(preds)\n",
    "    nrows = (nplots - 1) // 3 + 1\n",
    "    ncols = min(nplots, 3)\n",
    "    \n",
    "    fig, axs = plt.subplots(nrows, ncols, squeeze=False)\n",
    "    fig.set_size_inches(ncols * 5, nrows * 5)\n",
    "\n",
    "    lines = []\n",
    "    for i, ax in enumerate(axs.flatten()):\n",
    "        if i < nplots:\n",
    "            samples, predict, correct = plot_one(ax, bkt_train, y_train, bkt_test, y_test, preds[i])\n",
    "            lines.extend([samples, predict, correct])\n",
    "            ax.legend()\n",
    "            ax.set_title(titles[i])\n",
    "    \n",
    "    return fig, lines\n",
    "\n",
    "print(\"Ridge regression alpha = %.4f\" % alpha)\n",
    "fig, lines = plot_multi(bkt_train, y_train, bkt_test, y_test, \n",
    "           [\"linear regression\", \"ridge regression\", \"differential regression\"],\n",
    "           [linpred, ridgepred, diffpred])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And animate (allowing about 10 seconds for rendering on colab):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "/* Put everything inside the global mpl namespace */\n",
       "/* global mpl */\n",
       "window.mpl = {};\n",
       "\n",
       "mpl.get_websocket_type = function () {\n",
       "    if (typeof WebSocket !== 'undefined') {\n",
       "        return WebSocket;\n",
       "    } else if (typeof MozWebSocket !== 'undefined') {\n",
       "        return MozWebSocket;\n",
       "    } else {\n",
       "        alert(\n",
       "            'Your browser does not have WebSocket support. ' +\n",
       "                'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
       "                'Firefox 4 and 5 are also supported but you ' +\n",
       "                'have to enable WebSockets in about:config.'\n",
       "        );\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure = function (figure_id, websocket, ondownload, parent_element) {\n",
       "    this.id = figure_id;\n",
       "\n",
       "    this.ws = websocket;\n",
       "\n",
       "    this.supports_binary = this.ws.binaryType !== undefined;\n",
       "\n",
       "    if (!this.supports_binary) {\n",
       "        var warnings = document.getElementById('mpl-warnings');\n",
       "        if (warnings) {\n",
       "            warnings.style.display = 'block';\n",
       "            warnings.textContent =\n",
       "                'This browser does not support binary websocket messages. ' +\n",
       "                'Performance may be slow.';\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.imageObj = new Image();\n",
       "\n",
       "    this.context = undefined;\n",
       "    this.message = undefined;\n",
       "    this.canvas = undefined;\n",
       "    this.rubberband_canvas = undefined;\n",
       "    this.rubberband_context = undefined;\n",
       "    this.format_dropdown = undefined;\n",
       "\n",
       "    this.image_mode = 'full';\n",
       "\n",
       "    this.root = document.createElement('div');\n",
       "    this.root.setAttribute('style', 'display: inline-block');\n",
       "    this._root_extra_style(this.root);\n",
       "\n",
       "    parent_element.appendChild(this.root);\n",
       "\n",
       "    this._init_header(this);\n",
       "    this._init_canvas(this);\n",
       "    this._init_toolbar(this);\n",
       "\n",
       "    var fig = this;\n",
       "\n",
       "    this.waiting = false;\n",
       "\n",
       "    this.ws.onopen = function () {\n",
       "        fig.send_message('supports_binary', { value: fig.supports_binary });\n",
       "        fig.send_message('send_image_mode', {});\n",
       "        if (fig.ratio !== 1) {\n",
       "            fig.send_message('set_dpi_ratio', { dpi_ratio: fig.ratio });\n",
       "        }\n",
       "        fig.send_message('refresh', {});\n",
       "    };\n",
       "\n",
       "    this.imageObj.onload = function () {\n",
       "        if (fig.image_mode === 'full') {\n",
       "            // Full images could contain transparency (where diff images\n",
       "            // almost always do), so we need to clear the canvas so that\n",
       "            // there is no ghosting.\n",
       "            fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
       "        }\n",
       "        fig.context.drawImage(fig.imageObj, 0, 0);\n",
       "    };\n",
       "\n",
       "    this.imageObj.onunload = function () {\n",
       "        fig.ws.close();\n",
       "    };\n",
       "\n",
       "    this.ws.onmessage = this._make_on_message_function(this);\n",
       "\n",
       "    this.ondownload = ondownload;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_header = function () {\n",
       "    var titlebar = document.createElement('div');\n",
       "    titlebar.classList =\n",
       "        'ui-dialog-titlebar ui-widget-header ui-corner-all ui-helper-clearfix';\n",
       "    var titletext = document.createElement('div');\n",
       "    titletext.classList = 'ui-dialog-title';\n",
       "    titletext.setAttribute(\n",
       "        'style',\n",
       "        'width: 100%; text-align: center; padding: 3px;'\n",
       "    );\n",
       "    titlebar.appendChild(titletext);\n",
       "    this.root.appendChild(titlebar);\n",
       "    this.header = titletext;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (_canvas_div) {};\n",
       "\n",
       "mpl.figure.prototype._init_canvas = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var canvas_div = (this.canvas_div = document.createElement('div'));\n",
       "    canvas_div.setAttribute(\n",
       "        'style',\n",
       "        'border: 1px solid #ddd;' +\n",
       "            'box-sizing: content-box;' +\n",
       "            'clear: both;' +\n",
       "            'min-height: 1px;' +\n",
       "            'min-width: 1px;' +\n",
       "            'outline: 0;' +\n",
       "            'overflow: hidden;' +\n",
       "            'position: relative;' +\n",
       "            'resize: both;'\n",
       "    );\n",
       "\n",
       "    function on_keyboard_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.key_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    canvas_div.addEventListener(\n",
       "        'keydown',\n",
       "        on_keyboard_event_closure('key_press')\n",
       "    );\n",
       "    canvas_div.addEventListener(\n",
       "        'keyup',\n",
       "        on_keyboard_event_closure('key_release')\n",
       "    );\n",
       "\n",
       "    this._canvas_extra_style(canvas_div);\n",
       "    this.root.appendChild(canvas_div);\n",
       "\n",
       "    var canvas = (this.canvas = document.createElement('canvas'));\n",
       "    canvas.classList.add('mpl-canvas');\n",
       "    canvas.setAttribute('style', 'box-sizing: content-box;');\n",
       "\n",
       "    this.context = canvas.getContext('2d');\n",
       "\n",
       "    var backingStore =\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        this.context.webkitBackingStorePixelRatio ||\n",
       "        this.context.mozBackingStorePixelRatio ||\n",
       "        this.context.msBackingStorePixelRatio ||\n",
       "        this.context.oBackingStorePixelRatio ||\n",
       "        this.context.backingStorePixelRatio ||\n",
       "        1;\n",
       "\n",
       "    this.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
       "\n",
       "    var rubberband_canvas = (this.rubberband_canvas = document.createElement(\n",
       "        'canvas'\n",
       "    ));\n",
       "    rubberband_canvas.setAttribute(\n",
       "        'style',\n",
       "        'box-sizing: content-box; position: absolute; left: 0; top: 0; z-index: 1;'\n",
       "    );\n",
       "\n",
       "    // Apply a ponyfill if ResizeObserver is not implemented by browser.\n",
       "    if (this.ResizeObserver === undefined) {\n",
       "        if (window.ResizeObserver !== undefined) {\n",
       "            this.ResizeObserver = window.ResizeObserver;\n",
       "        } else {\n",
       "            var obs = _JSXTOOLS_RESIZE_OBSERVER({});\n",
       "            this.ResizeObserver = obs.ResizeObserver;\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.resizeObserverInstance = new this.ResizeObserver(function (entries) {\n",
       "        var nentries = entries.length;\n",
       "        for (var i = 0; i < nentries; i++) {\n",
       "            var entry = entries[i];\n",
       "            var width, height;\n",
       "            if (entry.contentBoxSize) {\n",
       "                if (entry.contentBoxSize instanceof Array) {\n",
       "                    // Chrome 84 implements new version of spec.\n",
       "                    width = entry.contentBoxSize[0].inlineSize;\n",
       "                    height = entry.contentBoxSize[0].blockSize;\n",
       "                } else {\n",
       "                    // Firefox implements old version of spec.\n",
       "                    width = entry.contentBoxSize.inlineSize;\n",
       "                    height = entry.contentBoxSize.blockSize;\n",
       "                }\n",
       "            } else {\n",
       "                // Chrome <84 implements even older version of spec.\n",
       "                width = entry.contentRect.width;\n",
       "                height = entry.contentRect.height;\n",
       "            }\n",
       "\n",
       "            // Keep the size of the canvas and rubber band canvas in sync with\n",
       "            // the canvas container.\n",
       "            if (entry.devicePixelContentBoxSize) {\n",
       "                // Chrome 84 implements new version of spec.\n",
       "                canvas.setAttribute(\n",
       "                    'width',\n",
       "                    entry.devicePixelContentBoxSize[0].inlineSize\n",
       "                );\n",
       "                canvas.setAttribute(\n",
       "                    'height',\n",
       "                    entry.devicePixelContentBoxSize[0].blockSize\n",
       "                );\n",
       "            } else {\n",
       "                canvas.setAttribute('width', width * fig.ratio);\n",
       "                canvas.setAttribute('height', height * fig.ratio);\n",
       "            }\n",
       "            canvas.setAttribute(\n",
       "                'style',\n",
       "                'width: ' + width + 'px; height: ' + height + 'px;'\n",
       "            );\n",
       "\n",
       "            rubberband_canvas.setAttribute('width', width);\n",
       "            rubberband_canvas.setAttribute('height', height);\n",
       "\n",
       "            // And update the size in Python. We ignore the initial 0/0 size\n",
       "            // that occurs as the element is placed into the DOM, which should\n",
       "            // otherwise not happen due to the minimum size styling.\n",
       "            if (fig.ws.readyState == 1 && width != 0 && height != 0) {\n",
       "                fig.request_resize(width, height);\n",
       "            }\n",
       "        }\n",
       "    });\n",
       "    this.resizeObserverInstance.observe(canvas_div);\n",
       "\n",
       "    function on_mouse_event_closure(name) {\n",
       "        return function (event) {\n",
       "            return fig.mouse_event(event, name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousedown',\n",
       "        on_mouse_event_closure('button_press')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseup',\n",
       "        on_mouse_event_closure('button_release')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'dblclick',\n",
       "        on_mouse_event_closure('dblclick')\n",
       "    );\n",
       "    // Throttle sequential mouse events to 1 every 20ms.\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mousemove',\n",
       "        on_mouse_event_closure('motion_notify')\n",
       "    );\n",
       "\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseenter',\n",
       "        on_mouse_event_closure('figure_enter')\n",
       "    );\n",
       "    rubberband_canvas.addEventListener(\n",
       "        'mouseleave',\n",
       "        on_mouse_event_closure('figure_leave')\n",
       "    );\n",
       "\n",
       "    canvas_div.addEventListener('wheel', function (event) {\n",
       "        if (event.deltaY < 0) {\n",
       "            event.step = 1;\n",
       "        } else {\n",
       "            event.step = -1;\n",
       "        }\n",
       "        on_mouse_event_closure('scroll')(event);\n",
       "    });\n",
       "\n",
       "    canvas_div.appendChild(canvas);\n",
       "    canvas_div.appendChild(rubberband_canvas);\n",
       "\n",
       "    this.rubberband_context = rubberband_canvas.getContext('2d');\n",
       "    this.rubberband_context.strokeStyle = '#000000';\n",
       "\n",
       "    this._resize_canvas = function (width, height, forward) {\n",
       "        if (forward) {\n",
       "            canvas_div.style.width = width + 'px';\n",
       "            canvas_div.style.height = height + 'px';\n",
       "        }\n",
       "    };\n",
       "\n",
       "    // Disable right mouse context menu.\n",
       "    this.rubberband_canvas.addEventListener('contextmenu', function (_e) {\n",
       "        event.preventDefault();\n",
       "        return false;\n",
       "    });\n",
       "\n",
       "    function set_focus() {\n",
       "        canvas.focus();\n",
       "        canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    window.setTimeout(set_focus, 100);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'mpl-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'mpl-button-group';\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'mpl-button-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        var button = (fig.buttons[name] = document.createElement('button'));\n",
       "        button.classList = 'mpl-widget';\n",
       "        button.setAttribute('role', 'button');\n",
       "        button.setAttribute('aria-disabled', 'false');\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "\n",
       "        var icon_img = document.createElement('img');\n",
       "        icon_img.src = '_images/' + image + '.png';\n",
       "        icon_img.srcset = '_images/' + image + '_large.png 2x';\n",
       "        icon_img.alt = tooltip;\n",
       "        button.appendChild(icon_img);\n",
       "\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    var fmt_picker = document.createElement('select');\n",
       "    fmt_picker.classList = 'mpl-widget';\n",
       "    toolbar.appendChild(fmt_picker);\n",
       "    this.format_dropdown = fmt_picker;\n",
       "\n",
       "    for (var ind in mpl.extensions) {\n",
       "        var fmt = mpl.extensions[ind];\n",
       "        var option = document.createElement('option');\n",
       "        option.selected = fmt === mpl.default_extension;\n",
       "        option.innerHTML = fmt;\n",
       "        fmt_picker.appendChild(option);\n",
       "    }\n",
       "\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.request_resize = function (x_pixels, y_pixels) {\n",
       "    // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
       "    // which will in turn request a refresh of the image.\n",
       "    this.send_message('resize', { width: x_pixels, height: y_pixels });\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_message = function (type, properties) {\n",
       "    properties['type'] = type;\n",
       "    properties['figure_id'] = this.id;\n",
       "    this.ws.send(JSON.stringify(properties));\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.send_draw_message = function () {\n",
       "    if (!this.waiting) {\n",
       "        this.waiting = true;\n",
       "        this.ws.send(JSON.stringify({ type: 'draw', figure_id: this.id }));\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    var format_dropdown = fig.format_dropdown;\n",
       "    var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
       "    fig.ondownload(fig, format);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_resize = function (fig, msg) {\n",
       "    var size = msg['size'];\n",
       "    if (size[0] !== fig.canvas.width || size[1] !== fig.canvas.height) {\n",
       "        fig._resize_canvas(size[0], size[1], msg['forward']);\n",
       "        fig.send_message('refresh', {});\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_rubberband = function (fig, msg) {\n",
       "    var x0 = msg['x0'] / fig.ratio;\n",
       "    var y0 = (fig.canvas.height - msg['y0']) / fig.ratio;\n",
       "    var x1 = msg['x1'] / fig.ratio;\n",
       "    var y1 = (fig.canvas.height - msg['y1']) / fig.ratio;\n",
       "    x0 = Math.floor(x0) + 0.5;\n",
       "    y0 = Math.floor(y0) + 0.5;\n",
       "    x1 = Math.floor(x1) + 0.5;\n",
       "    y1 = Math.floor(y1) + 0.5;\n",
       "    var min_x = Math.min(x0, x1);\n",
       "    var min_y = Math.min(y0, y1);\n",
       "    var width = Math.abs(x1 - x0);\n",
       "    var height = Math.abs(y1 - y0);\n",
       "\n",
       "    fig.rubberband_context.clearRect(\n",
       "        0,\n",
       "        0,\n",
       "        fig.canvas.width / fig.ratio,\n",
       "        fig.canvas.height / fig.ratio\n",
       "    );\n",
       "\n",
       "    fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_figure_label = function (fig, msg) {\n",
       "    // Updates the figure title.\n",
       "    fig.header.textContent = msg['label'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_cursor = function (fig, msg) {\n",
       "    var cursor = msg['cursor'];\n",
       "    switch (cursor) {\n",
       "        case 0:\n",
       "            cursor = 'pointer';\n",
       "            break;\n",
       "        case 1:\n",
       "            cursor = 'default';\n",
       "            break;\n",
       "        case 2:\n",
       "            cursor = 'crosshair';\n",
       "            break;\n",
       "        case 3:\n",
       "            cursor = 'move';\n",
       "            break;\n",
       "    }\n",
       "    fig.rubberband_canvas.style.cursor = cursor;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_message = function (fig, msg) {\n",
       "    fig.message.textContent = msg['message'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_draw = function (fig, _msg) {\n",
       "    // Request the server to send over a new figure.\n",
       "    fig.send_draw_message();\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_image_mode = function (fig, msg) {\n",
       "    fig.image_mode = msg['mode'];\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_history_buttons = function (fig, msg) {\n",
       "    for (var key in msg) {\n",
       "        if (!(key in fig.buttons)) {\n",
       "            continue;\n",
       "        }\n",
       "        fig.buttons[key].disabled = !msg[key];\n",
       "        fig.buttons[key].setAttribute('aria-disabled', !msg[key]);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_navigate_mode = function (fig, msg) {\n",
       "    if (msg['mode'] === 'PAN') {\n",
       "        fig.buttons['Pan'].classList.add('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    } else if (msg['mode'] === 'ZOOM') {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.add('active');\n",
       "    } else {\n",
       "        fig.buttons['Pan'].classList.remove('active');\n",
       "        fig.buttons['Zoom'].classList.remove('active');\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Called whenever the canvas gets updated.\n",
       "    this.send_message('ack', {});\n",
       "};\n",
       "\n",
       "// A function to construct a web socket function for onmessage handling.\n",
       "// Called in the figure constructor.\n",
       "mpl.figure.prototype._make_on_message_function = function (fig) {\n",
       "    return function socket_on_message(evt) {\n",
       "        if (evt.data instanceof Blob) {\n",
       "            var img = evt.data;\n",
       "            if (img.type !== 'image/png') {\n",
       "                /* FIXME: We get \"Resource interpreted as Image but\n",
       "                 * transferred with MIME type text/plain:\" errors on\n",
       "                 * Chrome.  But how to set the MIME type?  It doesn't seem\n",
       "                 * to be part of the websocket stream */\n",
       "                img.type = 'image/png';\n",
       "            }\n",
       "\n",
       "            /* Free the memory for the previous frames */\n",
       "            if (fig.imageObj.src) {\n",
       "                (window.URL || window.webkitURL).revokeObjectURL(\n",
       "                    fig.imageObj.src\n",
       "                );\n",
       "            }\n",
       "\n",
       "            fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
       "                img\n",
       "            );\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        } else if (\n",
       "            typeof evt.data === 'string' &&\n",
       "            evt.data.slice(0, 21) === 'data:image/png;base64'\n",
       "        ) {\n",
       "            fig.imageObj.src = evt.data;\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        var msg = JSON.parse(evt.data);\n",
       "        var msg_type = msg['type'];\n",
       "\n",
       "        // Call the  \"handle_{type}\" callback, which takes\n",
       "        // the figure and JSON message as its only arguments.\n",
       "        try {\n",
       "            var callback = fig['handle_' + msg_type];\n",
       "        } catch (e) {\n",
       "            console.log(\n",
       "                \"No handler for the '\" + msg_type + \"' message type: \",\n",
       "                msg\n",
       "            );\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        if (callback) {\n",
       "            try {\n",
       "                // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
       "                callback(fig, msg);\n",
       "            } catch (e) {\n",
       "                console.log(\n",
       "                    \"Exception inside the 'handler_\" + msg_type + \"' callback:\",\n",
       "                    e,\n",
       "                    e.stack,\n",
       "                    msg\n",
       "                );\n",
       "            }\n",
       "        }\n",
       "    };\n",
       "};\n",
       "\n",
       "// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
       "mpl.findpos = function (e) {\n",
       "    //this section is from http://www.quirksmode.org/js/events_properties.html\n",
       "    var targ;\n",
       "    if (!e) {\n",
       "        e = window.event;\n",
       "    }\n",
       "    if (e.target) {\n",
       "        targ = e.target;\n",
       "    } else if (e.srcElement) {\n",
       "        targ = e.srcElement;\n",
       "    }\n",
       "    if (targ.nodeType === 3) {\n",
       "        // defeat Safari bug\n",
       "        targ = targ.parentNode;\n",
       "    }\n",
       "\n",
       "    // pageX,Y are the mouse positions relative to the document\n",
       "    var boundingRect = targ.getBoundingClientRect();\n",
       "    var x = e.pageX - (boundingRect.left + document.body.scrollLeft);\n",
       "    var y = e.pageY - (boundingRect.top + document.body.scrollTop);\n",
       "\n",
       "    return { x: x, y: y };\n",
       "};\n",
       "\n",
       "/*\n",
       " * return a copy of an object with only non-object keys\n",
       " * we need this to avoid circular references\n",
       " * http://stackoverflow.com/a/24161582/3208463\n",
       " */\n",
       "function simpleKeys(original) {\n",
       "    return Object.keys(original).reduce(function (obj, key) {\n",
       "        if (typeof original[key] !== 'object') {\n",
       "            obj[key] = original[key];\n",
       "        }\n",
       "        return obj;\n",
       "    }, {});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.mouse_event = function (event, name) {\n",
       "    var canvas_pos = mpl.findpos(event);\n",
       "\n",
       "    if (name === 'button_press') {\n",
       "        this.canvas.focus();\n",
       "        this.canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    var x = canvas_pos.x * this.ratio;\n",
       "    var y = canvas_pos.y * this.ratio;\n",
       "\n",
       "    this.send_message(name, {\n",
       "        x: x,\n",
       "        y: y,\n",
       "        button: event.button,\n",
       "        step: event.step,\n",
       "        guiEvent: simpleKeys(event),\n",
       "    });\n",
       "\n",
       "    /* This prevents the web browser from automatically changing to\n",
       "     * the text insertion cursor when the button is pressed.  We want\n",
       "     * to control all of the cursor setting manually through the\n",
       "     * 'cursor' event from matplotlib */\n",
       "    event.preventDefault();\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (_event, _name) {\n",
       "    // Handle any extra behaviour associated with a key event\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.key_event = function (event, name) {\n",
       "    // Prevent repeat events\n",
       "    if (name === 'key_press') {\n",
       "        if (event.key === this._key) {\n",
       "            return;\n",
       "        } else {\n",
       "            this._key = event.key;\n",
       "        }\n",
       "    }\n",
       "    if (name === 'key_release') {\n",
       "        this._key = null;\n",
       "    }\n",
       "\n",
       "    var value = '';\n",
       "    if (event.ctrlKey && event.key !== 'Control') {\n",
       "        value += 'ctrl+';\n",
       "    }\n",
       "    else if (event.altKey && event.key !== 'Alt') {\n",
       "        value += 'alt+';\n",
       "    }\n",
       "    else if (event.shiftKey && event.key !== 'Shift') {\n",
       "        value += 'shift+';\n",
       "    }\n",
       "\n",
       "    value += 'k' + event.key;\n",
       "\n",
       "    this._key_event_extra(event, name);\n",
       "\n",
       "    this.send_message(name, { key: value, guiEvent: simpleKeys(event) });\n",
       "    return false;\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onclick = function (name) {\n",
       "    if (name === 'download') {\n",
       "        this.handle_save(this, null);\n",
       "    } else {\n",
       "        this.send_message('toolbar_button', { name: name });\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onmouseover = function (tooltip) {\n",
       "    this.message.textContent = tooltip;\n",
       "};\n",
       "\n",
       "///////////////// REMAINING CONTENT GENERATED BY embed_js.py /////////////////\n",
       "// prettier-ignore\n",
       "var _JSXTOOLS_RESIZE_OBSERVER=function(A){var t,i=new WeakMap,n=new WeakMap,a=new WeakMap,r=new WeakMap,o=new Set;function s(e){if(!(this instanceof s))throw new TypeError(\"Constructor requires 'new' operator\");i.set(this,e)}function h(){throw new TypeError(\"Function is not a constructor\")}function c(e,t,i,n){e=0 in arguments?Number(arguments[0]):0,t=1 in arguments?Number(arguments[1]):0,i=2 in arguments?Number(arguments[2]):0,n=3 in arguments?Number(arguments[3]):0,this.right=(this.x=this.left=e)+(this.width=i),this.bottom=(this.y=this.top=t)+(this.height=n),Object.freeze(this)}function d(){t=requestAnimationFrame(d);var s=new WeakMap,p=new Set;o.forEach((function(t){r.get(t).forEach((function(i){var r=t instanceof window.SVGElement,o=a.get(t),d=r?0:parseFloat(o.paddingTop),f=r?0:parseFloat(o.paddingRight),l=r?0:parseFloat(o.paddingBottom),u=r?0:parseFloat(o.paddingLeft),g=r?0:parseFloat(o.borderTopWidth),m=r?0:parseFloat(o.borderRightWidth),w=r?0:parseFloat(o.borderBottomWidth),b=u+f,F=d+l,v=(r?0:parseFloat(o.borderLeftWidth))+m,W=g+w,y=r?0:t.offsetHeight-W-t.clientHeight,E=r?0:t.offsetWidth-v-t.clientWidth,R=b+v,z=F+W,M=r?t.width:parseFloat(o.width)-R-E,O=r?t.height:parseFloat(o.height)-z-y;if(n.has(t)){var k=n.get(t);if(k[0]===M&&k[1]===O)return}n.set(t,[M,O]);var S=Object.create(h.prototype);S.target=t,S.contentRect=new c(u,d,M,O),s.has(i)||(s.set(i,[]),p.add(i)),s.get(i).push(S)}))})),p.forEach((function(e){i.get(e).call(e,s.get(e),e)}))}return s.prototype.observe=function(i){if(i instanceof window.Element){r.has(i)||(r.set(i,new Set),o.add(i),a.set(i,window.getComputedStyle(i)));var n=r.get(i);n.has(this)||n.add(this),cancelAnimationFrame(t),t=requestAnimationFrame(d)}},s.prototype.unobserve=function(i){if(i instanceof window.Element&&r.has(i)){var n=r.get(i);n.has(this)&&(n.delete(this),n.size||(r.delete(i),o.delete(i))),n.size||r.delete(i),o.size||cancelAnimationFrame(t)}},A.DOMRectReadOnly=c,A.ResizeObserver=s,A.ResizeObserverEntry=h,A}; // eslint-disable-line\n",
       "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Left button pans, Right button zooms\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\\nx/y fixes axis, CTRL fixes aspect\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
       "\n",
       "mpl.extensions = [\"eps\", \"jpeg\", \"pgf\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
       "\n",
       "mpl.default_extension = \"png\";/* global mpl */\n",
       "\n",
       "var comm_websocket_adapter = function (comm) {\n",
       "    // Create a \"websocket\"-like object which calls the given IPython comm\n",
       "    // object with the appropriate methods. Currently this is a non binary\n",
       "    // socket, so there is still some room for performance tuning.\n",
       "    var ws = {};\n",
       "\n",
       "    ws.binaryType = comm.kernel.ws.binaryType;\n",
       "    ws.readyState = comm.kernel.ws.readyState;\n",
       "    function updateReadyState(_event) {\n",
       "        if (comm.kernel.ws) {\n",
       "            ws.readyState = comm.kernel.ws.readyState;\n",
       "        } else {\n",
       "            ws.readyState = 3; // Closed state.\n",
       "        }\n",
       "    }\n",
       "    comm.kernel.ws.addEventListener('open', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('close', updateReadyState);\n",
       "    comm.kernel.ws.addEventListener('error', updateReadyState);\n",
       "\n",
       "    ws.close = function () {\n",
       "        comm.close();\n",
       "    };\n",
       "    ws.send = function (m) {\n",
       "        //console.log('sending', m);\n",
       "        comm.send(m);\n",
       "    };\n",
       "    // Register the callback with on_msg.\n",
       "    comm.on_msg(function (msg) {\n",
       "        //console.log('receiving', msg['content']['data'], msg);\n",
       "        var data = msg['content']['data'];\n",
       "        if (data['blob'] !== undefined) {\n",
       "            data = {\n",
       "                data: new Blob(msg['buffers'], { type: data['blob'] }),\n",
       "            };\n",
       "        }\n",
       "        // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
       "        ws.onmessage(data);\n",
       "    });\n",
       "    return ws;\n",
       "};\n",
       "\n",
       "mpl.mpl_figure_comm = function (comm, msg) {\n",
       "    // This is the function which gets called when the mpl process\n",
       "    // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
       "\n",
       "    var id = msg.content.data.id;\n",
       "    // Get hold of the div created by the display call when the Comm\n",
       "    // socket was opened in Python.\n",
       "    var element = document.getElementById(id);\n",
       "    var ws_proxy = comm_websocket_adapter(comm);\n",
       "\n",
       "    function ondownload(figure, _format) {\n",
       "        window.open(figure.canvas.toDataURL());\n",
       "    }\n",
       "\n",
       "    var fig = new mpl.figure(id, ws_proxy, ondownload, element);\n",
       "\n",
       "    // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
       "    // web socket which is closed, not our websocket->open comm proxy.\n",
       "    ws_proxy.onopen();\n",
       "\n",
       "    fig.parent_element = element;\n",
       "    fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
       "    if (!fig.cell_info) {\n",
       "        console.error('Failed to find cell for figure', id, fig);\n",
       "        return;\n",
       "    }\n",
       "    fig.cell_info[0].output_area.element.on(\n",
       "        'cleared',\n",
       "        { fig: fig },\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_close = function (fig, msg) {\n",
       "    var width = fig.canvas.width / fig.ratio;\n",
       "    fig.cell_info[0].output_area.element.off(\n",
       "        'cleared',\n",
       "        fig._remove_fig_handler\n",
       "    );\n",
       "    fig.resizeObserverInstance.unobserve(fig.canvas_div);\n",
       "\n",
       "    // Update the output cell to use the data from the current canvas.\n",
       "    fig.push_to_output();\n",
       "    var dataURL = fig.canvas.toDataURL();\n",
       "    // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
       "    // the notebook keyboard shortcuts fail.\n",
       "    IPython.keyboard_manager.enable();\n",
       "    fig.parent_element.innerHTML =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "    fig.close_ws(fig, msg);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.close_ws = function (fig, msg) {\n",
       "    fig.send_message('closing', msg);\n",
       "    // fig.ws.close()\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.push_to_output = function (_remove_interactive) {\n",
       "    // Turn the data on the canvas into data in the output cell.\n",
       "    var width = this.canvas.width / this.ratio;\n",
       "    var dataURL = this.canvas.toDataURL();\n",
       "    this.cell_info[1]['text/html'] =\n",
       "        '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function () {\n",
       "    // Tell IPython that the notebook contents must change.\n",
       "    IPython.notebook.set_dirty(true);\n",
       "    this.send_message('ack', {});\n",
       "    var fig = this;\n",
       "    // Wait a second, then push the new image to the DOM so\n",
       "    // that it is saved nicely (might be nice to debounce this).\n",
       "    setTimeout(function () {\n",
       "        fig.push_to_output();\n",
       "    }, 1000);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function () {\n",
       "    var fig = this;\n",
       "\n",
       "    var toolbar = document.createElement('div');\n",
       "    toolbar.classList = 'btn-toolbar';\n",
       "    this.root.appendChild(toolbar);\n",
       "\n",
       "    function on_click_closure(name) {\n",
       "        return function (_event) {\n",
       "            return fig.toolbar_button_onclick(name);\n",
       "        };\n",
       "    }\n",
       "\n",
       "    function on_mouseover_closure(tooltip) {\n",
       "        return function (event) {\n",
       "            if (!event.currentTarget.disabled) {\n",
       "                return fig.toolbar_button_onmouseover(tooltip);\n",
       "            }\n",
       "        };\n",
       "    }\n",
       "\n",
       "    fig.buttons = {};\n",
       "    var buttonGroup = document.createElement('div');\n",
       "    buttonGroup.classList = 'btn-group';\n",
       "    var button;\n",
       "    for (var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            /* Instead of a spacer, we start a new button group. */\n",
       "            if (buttonGroup.hasChildNodes()) {\n",
       "                toolbar.appendChild(buttonGroup);\n",
       "            }\n",
       "            buttonGroup = document.createElement('div');\n",
       "            buttonGroup.classList = 'btn-group';\n",
       "            continue;\n",
       "        }\n",
       "\n",
       "        button = fig.buttons[name] = document.createElement('button');\n",
       "        button.classList = 'btn btn-default';\n",
       "        button.href = '#';\n",
       "        button.title = name;\n",
       "        button.innerHTML = '<i class=\"fa ' + image + ' fa-lg\"></i>';\n",
       "        button.addEventListener('click', on_click_closure(method_name));\n",
       "        button.addEventListener('mouseover', on_mouseover_closure(tooltip));\n",
       "        buttonGroup.appendChild(button);\n",
       "    }\n",
       "\n",
       "    if (buttonGroup.hasChildNodes()) {\n",
       "        toolbar.appendChild(buttonGroup);\n",
       "    }\n",
       "\n",
       "    // Add the status bar.\n",
       "    var status_bar = document.createElement('span');\n",
       "    status_bar.classList = 'mpl-message pull-right';\n",
       "    toolbar.appendChild(status_bar);\n",
       "    this.message = status_bar;\n",
       "\n",
       "    // Add the close button to the window.\n",
       "    var buttongrp = document.createElement('div');\n",
       "    buttongrp.classList = 'btn-group inline pull-right';\n",
       "    button = document.createElement('button');\n",
       "    button.classList = 'btn btn-mini btn-primary';\n",
       "    button.href = '#';\n",
       "    button.title = 'Stop Interaction';\n",
       "    button.innerHTML = '<i class=\"fa fa-power-off icon-remove icon-large\"></i>';\n",
       "    button.addEventListener('click', function (_evt) {\n",
       "        fig.handle_close(fig, {});\n",
       "    });\n",
       "    button.addEventListener(\n",
       "        'mouseover',\n",
       "        on_mouseover_closure('Stop Interaction')\n",
       "    );\n",
       "    buttongrp.appendChild(button);\n",
       "    var titlebar = this.root.querySelector('.ui-dialog-titlebar');\n",
       "    titlebar.insertBefore(buttongrp, titlebar.firstChild);\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._remove_fig_handler = function (event) {\n",
       "    var fig = event.data.fig;\n",
       "    if (event.target !== this) {\n",
       "        // Ignore bubbled events from children.\n",
       "        return;\n",
       "    }\n",
       "    fig.close_ws(fig, {});\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function (el) {\n",
       "    el.style.boxSizing = 'content-box'; // override notebook setting of border-box.\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function (el) {\n",
       "    // this is important to make the div 'focusable\n",
       "    el.setAttribute('tabindex', 0);\n",
       "    // reach out to IPython and tell the keyboard manager to turn it's self\n",
       "    // off when our div gets focus\n",
       "\n",
       "    // location in version 3\n",
       "    if (IPython.notebook.keyboard_manager) {\n",
       "        IPython.notebook.keyboard_manager.register_events(el);\n",
       "    } else {\n",
       "        // location in version 2\n",
       "        IPython.keyboard_manager.register_events(el);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function (event, _name) {\n",
       "    var manager = IPython.notebook.keyboard_manager;\n",
       "    if (!manager) {\n",
       "        manager = IPython.keyboard_manager;\n",
       "    }\n",
       "\n",
       "    // Check for shift+enter\n",
       "    if (event.shiftKey && event.which === 13) {\n",
       "        this.canvas_div.blur();\n",
       "        // select the cell after this one\n",
       "        var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
       "        IPython.notebook.select(index + 1);\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_save = function (fig, _msg) {\n",
       "    fig.ondownload(fig, null);\n",
       "};\n",
       "\n",
       "mpl.find_output_cell = function (html_output) {\n",
       "    // Return the cell and output element which can be found *uniquely* in the notebook.\n",
       "    // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
       "    // IPython event is triggered only after the cells have been serialised, which for\n",
       "    // our purposes (turning an active figure into a static one), is too late.\n",
       "    var cells = IPython.notebook.get_cells();\n",
       "    var ncells = cells.length;\n",
       "    for (var i = 0; i < ncells; i++) {\n",
       "        var cell = cells[i];\n",
       "        if (cell.cell_type === 'code') {\n",
       "            for (var j = 0; j < cell.output_area.outputs.length; j++) {\n",
       "                var data = cell.output_area.outputs[j];\n",
       "                if (data.data) {\n",
       "                    // IPython >= 3 moved mimebundle to data attribute of output\n",
       "                    data = data.data;\n",
       "                }\n",
       "                if (data['text/html'] === html_output) {\n",
       "                    return [cell, data, j];\n",
       "                }\n",
       "            }\n",
       "        }\n",
       "    }\n",
       "};\n",
       "\n",
       "// Register the function which deals with the matplotlib target/channel.\n",
       "// The kernel may be null if the page has been refreshed.\n",
       "if (IPython.notebook.kernel !== null) {\n",
       "    IPython.notebook.kernel.comm_manager.register_target(\n",
       "        'matplotlib',\n",
       "        mpl.mpl_figure_comm\n",
       "    );\n",
       "}\n"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<img src=\"data:image/png;base64,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\" width=\"1500\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.animation.FuncAnimation at 0x1bf77aacbe0>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "if colab:\n",
    "    def init():\n",
    "      fig, lines = plot_multi(bkt_train, y_train, bkt_test, y_test, \n",
    "           [\"linear regression\", \"ridge regression\", \"differential regression\"],\n",
    "           [linpred, ridgepred, diffpred])\n",
    "      plt.close(fig)\n",
    "      return lines\n",
    "else:\n",
    "    fig, lines = plot_multi(bkt_train, y_train, bkt_test, y_test, \n",
    "       [\"linear regression\", \"ridge regression\", \"differential regression\"],\n",
    "       [linpred, ridgepred, diffpred])\n",
    "\n",
    "def animate(i):\n",
    "    seed = np.random.randint(8192)\n",
    "    x_train, bkt_train, y_train, z_train = bach.trainSet(m, seed=seed)\n",
    "    \n",
    "    linreg.fit(x_train, y_train)\n",
    "    linpred = linreg.predict(x_test)\n",
    "    ridgereg.fit(x_train, y_train)\n",
    "    ridgepred = ridgereg.predict(x_test)\n",
    "    diffreg.fit(x_train, y_train, z_train)\n",
    "    diffpred = diffreg.predict(x_test)\n",
    "    \n",
    "    lines[0].set_data(bkt_train, y_train)\n",
    "    lines[1].set_data(bkt_test, linpred)\n",
    "    lines[3].set_data(bkt_train, y_train)\n",
    "    lines[4].set_data(bkt_test, ridgepred)\n",
    "    lines[6].set_data(bkt_train, y_train)\n",
    "    lines[7].set_data(bkt_test, diffpred)\n",
    "    \n",
    "    return lines\n",
    "\n",
    "# slow on colab\n",
    "FuncAnimation(fig, animate, init_func=init if colab else None, frames=20 if colab else 200, interval=500, blit=True)\n",
    "#anim = FuncAnimation(fig, animate, init_func=init if colab else None, frames=20 if colab else 200, interval=500, blit=True)\n",
    "#f = r\"animation.gif\" \n",
    "#writergif = PillowWriter(fps=2) \n",
    "#anim.save(f, writer=writergif)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Differential regression shines in higher dimension 3 to 7. Above dimension 7 to 10, however, all forms of linear regression become very slow, and rapidly fill computer memory. Linear regression is not effective in high dimension, and differential regularization does not provide a silver bullet. It gives a sharp improvement over classic regression and well-known forms of regularization. But its applicability remains limited to dimension under about 10. \n",
    "\n",
    "In real-world applications in finance, where dimension routinely stands in the hundreds, linear regression, differential or otherwise, is only possible when coupled with effective dimension reduction. Dimension reduction is not only strictly necessary for linear regression, it also facilitates, stabilizes and speeds-up more sophisticated ML models like neural networks. It is a recommended pre-processing step in all circumstances.\n",
    "\n",
    "Classic dimension reduction algorithms like principal components analysis (PCA) are however unsafe, prone to truncate subspaces of little variation, which may still affect prices and risk in a substantial manner. By contrast, <b> differential PCA </b>, developed as a part of the differential ML ecosystem, provides a safe and effective dimension reduction, once again, leveraging differential labels. In the basket example, differential PCA univoquely identifies the underlying basket as the only relevant regression feature, safely reducing dimension to one. Differential PCA is covered in the Risk article <b> Axes that matter: PCA with a difference. </b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "include_colab_link": true,
   "machine_shape": "hm",
   "name": "DifferentialRegression.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}