{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![MLU Logo](../../data/MLU_Logo.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's get the dataset below. We are using MNIST dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install -q -r ../../requirements.txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading /home/ec2-user/.mxnet/datasets/mnist/train-images-idx3-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/mnist/train-images-idx3-ubyte.gz...\n",
      "Downloading /home/ec2-user/.mxnet/datasets/mnist/train-labels-idx1-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/mnist/train-labels-idx1-ubyte.gz...\n",
      "Downloading /home/ec2-user/.mxnet/datasets/mnist/t10k-images-idx3-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/mnist/t10k-images-idx3-ubyte.gz...\n",
      "Downloading /home/ec2-user/.mxnet/datasets/mnist/t10k-labels-idx1-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/mnist/t10k-labels-idx1-ubyte.gz...\n"
     ]
    }
   ],
   "source": [
    "from mxnet import gluon\n",
    "import numpy as np\n",
    "\n",
    "# Grab the MNIST dataset\n",
    "x_train, y_train = gluon.data.vision.MNIST(train=True)[:]\n",
    "x_test, y_test = gluon.data.vision.MNIST(train=False)[:]\n",
    "\n",
    "x_train = x_train.asnumpy()\n",
    "x_test = x_test.asnumpy()\n",
    "\n",
    "# reshape and scale to be in [0,1]\n",
    "x_train = x_train.reshape(60000, 784)\n",
    "x_test = x_test.reshape(10000, 784)\n",
    "x_train = x_train.astype('float32')\n",
    "x_test = x_test.astype('float32')\n",
    "x_train /= 255\n",
    "x_test /= 255"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's plot our dataset and our samples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2880x1440 with 8 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "np.random.seed(74656)\n",
    "mask = np.random.randn(28,28)\n",
    "thresh = np.sort(mask.flatten())[27]\n",
    "\n",
    "plt.figure(figsize=(40,20))\n",
    "for i in range(4):\n",
    "    full = x_train[i].reshape(28,28)\n",
    "    sub = np.ma.masked_where(mask > thresh, full)\n",
    "    plt.subplot(2,4,i+1)\n",
    "    plt.axis('off')\n",
    "    plt.imshow(full)\n",
    "    plt.subplot(2,4,i+5)\n",
    "    plt.axis('off')\n",
    "    plt.imshow(sub)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will first fit __the bagging model__. In the RandomForestClassifier(), we will use __max_features = None__ (use all features) and that will make it equal to a bagging model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   1 out of   1 | elapsed:   11.0s finished\n",
      "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n",
      "[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8632\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   2 out of   2 | elapsed:   11.1s finished\n",
      "[Parallel(n_jobs=2)]: Using backend ThreadingBackend with 2 concurrent workers.\n",
      "[Parallel(n_jobs=2)]: Done   2 out of   2 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=2)]: Done   2 out of   2 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8607\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   3 out of   3 | elapsed:   14.7s finished\n",
      "[Parallel(n_jobs=3)]: Using backend ThreadingBackend with 3 concurrent workers.\n",
      "[Parallel(n_jobs=3)]: Done   3 out of   3 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9036\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   2 out of   4 | elapsed:   16.7s remaining:   16.7s\n",
      "[Parallel(n_jobs=-1)]: Done   4 out of   4 | elapsed:   17.2s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   2 out of   4 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=4)]: Done   4 out of   4 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9175\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   5 out of   5 | elapsed:   26.8s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   5 out of   5 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9305\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   6 out of   6 | elapsed:   28.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=-1)]: Done   6 out of   6 | elapsed:   28.0s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   6 out of   6 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=4)]: Done   6 out of   6 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9325\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   7 out of   7 | elapsed:   30.7s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   7 out of   7 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9352\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   8 out of   8 | elapsed:   33.2s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   8 out of   8 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9379\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   9 out of   9 | elapsed:   42.8s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   9 out of   9 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9387\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  10 out of  10 | elapsed:   44.6s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  10 out of  10 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9432\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  11 out of  11 | elapsed:   46.5s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  11 out of  11 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9439\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  12 out of  12 | elapsed:   49.8s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  12 out of  12 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9456\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7f1365a99860>]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD4CAYAAADiry33AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAAfCUlEQVR4nO3de3SddZ3v8fc39+aeNml6Sdr0ktLWQmkbyr2g6AgjiqMyogvRUg7iAkXHM4rOGV2zcGbwjM6Rs/QchgMIKIqCoKiM6DhOQxWhSa/0QlJ6TVrSnba5tEma2/f8sXdLGtJm0+6dZ++dz2utrOznlv19mvSTX36/53l+5u6IiEjqSgu6ABERiS8FvYhIilPQi4ikOAW9iEiKU9CLiKS4jKALGElpaalXVVUFXYaISNKor69vdfeykbYlZNBXVVVRV1cXdBkiIknDzPacbpu6bkREUpyCXkQkxSnoRURSnIJeRCTFKehFRFKcgl5EJMUp6EVEUlxCXkcvIjIe9A8M0tzWza7WY+w51EVX7wCfuXpOzN9HQS8iEkfDwzz8+Ri7D3Wx73AX/YNvzgkyuSCbO66ajZnFtAYFvYjIOToR5rsPdbG79dgZwzw3K52qSXksnFrIdYumUFWax6zSPGZOyqUsPzvmIQ8KehGRqPQPDLK/rYddh46xu/UYuyOf9xzqYt+RLvoG3hrmC6YWhMN8Uh5VpXlUlcYvzM9EQS8i49Lx/gE6e/ojH30nP3cMWdfW1ceeQ6cP85mT8pg/tYD3LprCrBNhPimXsoKxD/MzUdCLSNLp7R8cEs5vBnTHkMA+9fObrzsir4/3D476PvnZGVROzOW8KW+G+cxJucwqzUu4MD8TBb2IJLwD7d08s66Zn69vZu/hrqhCOjcrnYKcDApyMinIyaAoN4uKibkUnliXnUFBTgaFEzJP7lOQk0Fh5HV+dgYZ6alxBbqCXkQSUk/fAL/b2sJT9U2saQwx6LB81kTeOX/yyZB+M6AjYT4h9UI6FhT0IpIw3J3Nze08VdfELzY009HTz7SiHO5851w+sqyCmZPygi4xKSnoRSRwoc7j/Hx9M0/XN/FaSyfZGWm89x1TuLGmgsvmlJKelhx94YlKQS8igegbGOQ/tx/kqbom/uu1g/QPOosri/nGBxfx/sXTKJqQGXSJKSOqoDeza4H7gXTgIXe/b9j2EuARYA7QA9zq7q8O2Z4O1AHN7n59jGoXkSS0/Y0Onqpr4ufrmzl0rJfS/GxuvWIWNy6roLq8IOjyUtKoQR8J6e8B7wGagLVm9py7bx2y21eBDe7+V2Y2P7L/NUO23w1sAwpjVrmIJI22rl6e27ifp+qa2NzcTma6cc38cm6sqWDFvDIyNXAaV9G06JcDO9x9J4CZPQncAAwN+oXAPwO4+3YzqzKzcndvMbMK4H3APwJ/E9PqRSRhDQw6tY0hnq5v4ndbWugdGGTB1EK+dv1CbrhwGpPys4MucdyIJuinA/uGLDcBFw/bZyPwIWCNmS0HZgIVQAvwHeBLwBn/JjOz24HbAWbMmBFFWSKSiHaGjvJUfRPPrGuipeM4xbmZfPziGXxkWQWLphcFXd64FE3QjzTc7cOW7wPuN7MNwGZgPdBvZtcDB9293syuPtObuPuDwIMANTU1w7++iCSwzp4+fr3pAE/VN1G/5whpBlfNK+Pr76/kmgWTyc5ID7rEcS2aoG8CKocsVwD7h+7g7h3ASgAL3xO8K/JxE/ABM/tLIAcoNLMfuvvNMahdRMbI4KDT2dNPW3cv7d19p3zU7z7Cv7/6Bt19A8wuy+PL187nQ0unU16YE3TZEhFN0K8Fqs1sFtBMOLw/PnQHMysGuty9F7gNqI2E/1ciH0Ra9P9dIS8SDHen83g/7V3hgO7o7qNtWGi3dYXXn1zu7qW9q4/O4/34af7OLsjO4INLpnNjTQVLKouT5vkv48moQe/u/WZ2F/AC4csrH3H3LWZ2R2T7A8AC4HEzGyA8SLsqjjWLyDDuzq7WY9TvOcKrze0c7uqjrav3lNBu7+5j8AydohlpRnFuJoUTMimakMmk/Cxml+VRHFk+sb5oQibFuVknX0/MyyIrQ1fNJDLz0/2aDlBNTY3X1dUFXYZIwurpG2Djvjbq9x5h3Z4j1O85wpGuPiD8xMWyguxTg3nI6xOhXZx76rrcrHS1xpOYmdW7e81I23RnrEgSeKO9h/pIoNfvPcKW5vaTsxbNKcvjPQvLWTazhGUzS5hdmk+aHhkgQyjoRRJM/8Ag29/ofDPY9xyhua0bgJzMNBZXFHP7itksm1nCkhklTMzLCrhiSXQKepGAtXf1sW7fEep3h0N9w742uvsGAJhSmMOyqhJWXTGLZTNLWDitUHeRytumoBcZQ+7Ozsig6Ym+9caDRwFITzMWTi3koxdVnuyGmVY8IeCKJRUo6EXiqLt3gE1NIw+aFk3IZOmMYj64ZDpLZ5SwuLKI3Cz9l5TY00+VSAydMmi65zBb9ndo0FQCp6AXOUv9A4NsO9BJ/Z7D1O9tY91pBk2Xzihh6UwNmkpwFPQiUWrr6mX93raTLfaRBk1vuzI8aLpgqgZNJXEo6EVGMHzQtG7PEXZo0FSSlIJehPCg6camtpPBvm7vqYOmy2aW8FcaNJUkpZ9WGZcOtHefckPS1tMOmk5kdmmeBk0lqSnoJaW1dfXS0HKUhpZOGls6ea2lk8aWoxw61gu8OWj66asid5pWllCiQVNJMQp6SQnt3X00tnS+GeoHw69DncdP7pOfncHcyflcs2AyC6YWatBUxg0FvSSVzp4+Gg8epeGNcJCHA72Tlo43Az03K53qyflcNa+MeeX5VJcXMK+8gGlFOXo6o4xLCnpJSMeO94cDPdLl0tBylMaWTva395zcJyczjbmT87l8TmkkzPOZV17A9OIJ6lMXGUJBL4HrGxjk+c0H2Lq/g4ZIqJ+48QggKyONuWX5LJ818WTrfF55PhUluaQr0EVGpaCXQA0OOl96ehPPrm8mKz2N2WV5LJ1Zwk0XVVJdXsB5UwqYMVGBLnIuFPQSGHfnH5/fxrPrm/nCu+dx5zvnkKGBUZGYU9BLYB5YvZOH1+ziU5dV8blr5mqgVCRO1HySQPxk7V6++ZvtfGDxNL52/UKFvEgcKehlzL2w5Q2+8sxmVswr41s3LtYVMiJxpqCXMfXyzkN89sfruaCimAduXkpWhn4EReJN/8tkzGzd38Ftj9UxY2Iu3//URXowmMgYUdDLmNh7qItbHnmF/JwMHr91uZ4nIzKGFPQSdwc7e7j54ZfpHxzkB6uW69ntImNMQS9x1dHTxycfWUuo8zjf/9RFzJ1cEHRJIuOOgl7ipqdvgNseq6OxpZMHPrGMJTNKgi5JZFzSaJjERf/AIJ/78Xpe2XWY+2+6kKvmlQVdksi4pRa9xJy783fPvspvt7bw9fcv5IYLpwddksi4pqCXmPuXF17jJ3X7+Oy75rLy8llBlyMy7inoJaYeenEn/+e/Xudjy2fwN++ZF3Q5IoKCXmLo2fVNfOPX27j2HVP4xgcX6fk1IglCQS8x8YftB/nbpzZx6exJfOemC/X8eJEEoqCXc1a/5wifeaKe86YU8OAty8jJTA+6JBEZQkEv56ShpZNbH13LlMIcHl25nIKczKBLEpFhFPRy1pqOdHHLw6+QnZHGD1ZdTFlBdtAlicgIFPRyVg4dPc4tD79CV28/j69aTuXE3KBLEpHT0J2x8rYdPd7PykfX0tzWzQ9vu5j5UwqDLklEziCqFr2ZXWtmr5nZDjO7Z4TtJWb2rJltMrNXzGxRZH2lmf3BzLaZ2RYzuzvWJyBj63j/AHf8oJ4t+zv43seXclHVxKBLEpFRjBr0ZpYOfA+4DlgIfMzMFg7b7avABne/ALgFuD+yvh/4orsvAC4B7hzhWEkSA4POF3+6kTU7Wvnmhy/g3QvLgy5JRKIQTYt+ObDD3Xe6ey/wJHDDsH0WAr8HcPftQJWZlbv7AXdfF1nfCWwD9OCTJOTu/MMvt/CrTQf46l/O5yPLKoIuSUSiFE3QTwf2DVlu4q1hvRH4EICZLQdmAqckgZlVAUuAl0d6EzO73czqzKwuFApFVbyMnf/9+x08/tIePr1iNrevmBN0OSLyNkQT9CPd4ujDlu8DSsxsA/BZYD3hbpvwFzDLB34GfN7dO0Z6E3d/0N1r3L2mrEyPtE0kP/jzHv7XfzTwkWUV3HPd/KDLEZG3KZqrbpqAyiHLFcD+oTtEwnslgIUfcLIr8oGZZRIO+Sfc/ZkY1Cxj6NebDvC1X7zKNfMnc9+Hztfza0SSUDQt+rVAtZnNMrMs4CbguaE7mFlxZBvAbUCtu3dEQv9hYJu7/2ssC5f4W9PYyud/sp6amSV89+NLyUjXbRciyWjUFr2795vZXcALQDrwiLtvMbM7ItsfABYAj5vZALAVWBU5/HLgE8DmSLcOwFfd/fnYnobE2qamNj79gzrmlOXz0C0XMSFLz68RSVZR3TAVCebnh617YMjrl4DqEY5bw8h9/JLA9h7qYuX311KSl8Vjty6nKFfPrxFJZvpbXE7R3tXHykdfoX/QefzW5ZQX5gRdkoicIwW9nNQ3MMhnnqhn7+Eu/u0Ty5hdlh90SSISA3rWjQDhG6L+x7Ov8qfXD/HtGxdzyexJQZckIjGiFr0A8MDqnScn9P6w7noVSSkKeuH5zQf45m+28/7F0zSht0gKUtCPc+v3HuELP9nAspkl/MtHLtANUSIpSEE/ju073MV/e7yO8sIcHvyE5noVSVUajB2nOnr6uPXRtRzvH+TJ2y9iUr6mARRJVWrRj0N9A4Pc+cQ6drUe499uXsbcybqMUiSVqUU/zrg7X39uCy82tvI/P3wBl80tDbokEYkztejHmYde3MWPXt7LZ66ew19fVDn6ASKS9BT048gLW97gn/59G+87fyp/+xfnBV2OiIwRBf04sampjbufXM/iimK+/deLSUvTZZQi44WCfhxobutm1WN1lOZn8/9uqdFllCLjjAZjU1xnTx+rHl1LT+8AP7rtYsoKdBmlyHijoE9h/QOD3PWj9TQePMqjKy+iurwg6JJEJADquklR7s4//HIrqxtC3HvDIq6s1oTrIuOVgj5Fff+Pu/nBn/dw+4rZfPziGUGXIyIBUtCnoP/Y2sK9v97Ke99Rzj3Xzg+6HBEJmII+xbza3M7nnlzP+dOL+M5Hl+gyShFR0KeSA+3drHpsLcUTMnnolhomZOkyShHRVTcp49jxflY9Wsex4wM8/ZlLmaxJvUUkQi36FDAw6Hzux+vZ/kYH3/34EuZPKQy6JBFJIGrRp4B7f7WV328/yL03vIOrz5scdDkikmDUok9yj/1pN4/+aTe3Xj6LT1xaFXQ5IpKAFPRJ7A/bD/IPv9zCuxeU83fvWxB0OSKSoBT0SWrr/g7u+tE6Fkwt5P6bLiRdl1GKyGko6JNQS0cPqx5bS0FOJg9/8iLysjXUIiKnp4RIMl29/ax6bC3t3X08dcelTCnSZZQicmZq0SeRgUHn7ic3sHV/+DLKd0wrCrokEUkCCvok8s/Pb+N3W1v4++sX8q755UGXIyJJQkGfJH5W38RDa3bxyUtnsvLyWUGXIyJJREGfJH748h4WTC3k769fGHQpIpJkFPRJoL2rj4372njPwnIy0vUtE5G3R6mRBNbsaGXQ4ap5pUGXIiJJSEGfBGobQhTkZLC4ojjoUkQkCSnoE5y7U9sY4oq5peq2EZGzElVymNm1Zvaame0ws3tG2F5iZs+a2SYze8XMFkV7rJzZjoNHOdDew4p5mtxbRM7OqEFvZunA94DrgIXAx8xs+KUfXwU2uPsFwC3A/W/jWDmD1Q0hAAW9iJy1aFr0y4Ed7r7T3XuBJ4Ebhu2zEPg9gLtvB6rMrDzKY+UMahtbmVOWx/TiCUGXIiJJKpqgnw7sG7LcFFk31EbgQwBmthyYCVREeSyR4243szozqwuFQtFVn+J6+gZ4eechteZF5JxEE/QjPf/Why3fB5SY2Qbgs8B6oD/KY8Mr3R909xp3rykrU7ABvLLrMMf7BxX0InJOonl6ZRNQOWS5Atg/dAd37wBWApiZAbsiH7mjHSun92JjiKyMNC6ZNSnoUkQkiUXTol8LVJvZLDPLAm4Cnhu6g5kVR7YB3AbURsJ/1GPl9GobWlleNZEJWelBlyIiSWzUFr2795vZXcALQDrwiLtvMbM7ItsfABYAj5vZALAVWHWmY+NzKqnljfYeXmvp5MPLRhzSEBGJWlQTj7j788Dzw9Y9MOT1S0B1tMfK6GobwwPSV1arf15Ezo1utUxQtQ0hJhdkM39KQdCliEiSU9AnoIFBZ82OVq6sLiM8ti0icvYU9Aloc3M7bV19rNDTKkUkBhT0Cai2IYSZ+udFJDYU9AmotiHE+dOLmJiXNfrOIiKjUNAnmI6ePtbva2OFWvMiEiMK+gTzpx2tDAy6HnsgIjGjoE8wtY2t5GdnsGRGcdCliEiKUNAnEHentiHEZXMmkanZpEQkRpQmCWRX6zGajnSr20ZEYkpBn0BqI7NJXaWgF5EYUtAnkNrGVqom5VI5MTfoUkQkhSjoE8Tx/gFeel2zSYlI7CnoE0T97iN09w3o+nkRiTkFfYJY3RgiM924dI5mkxKR2FLQJ4jahlaWzSwhLzuqKQJERKKmoE8ABzt72HagQ/3zIhIXCvoE8GJDK4D650UkLhT0CaC2MURpfhYLpxYGXYqIpCAFfcAGB501jeHZpNLSNJuUiMSegj5gWw90cOhYr2aTEpG4UdAHbHXksQeaTUpE4kVBH7DahhDvmFZIaX520KWISIpS0Afo6PF+6vccUWteROJKQR+gl14/RP+gq39eROJKQR+g2oYQuVnp1MycGHQpIpLCFPQBqm0McensSWRl6NsgIvGjhAnInkPH2HOoS489EJG4U9AH5MRsUgp6EYk3BX1AVje0UjlxAlWTNJuUiMSXgj4AfQODvPR6KyuqyzDTYw9EJL4U9AFYt+cIx3oH1G0jImNCQR+A2sYQGWnGZZpNSkTGgII+ALUNrSydUUJBTmbQpYjIOKCgH2OHjh7n1f3tuhtWRMaMgn6MrdnRirueVikiY0dBP8ZWN4Qoyc1k0fSioEsRkXFCQT+G3J0XG1u5orqMdM0mJSJjJKqgN7Nrzew1M9thZveMsL3IzH5pZhvNbIuZrRyy7QuRda+a2Y/NLCeWJ5BMth3oJNR5nBXV6p8XkbEzatCbWTrwPeA6YCHwMTNbOGy3O4Gt7r4YuBr4tpllmdl04HNAjbsvAtKBm2JYf1KpbdRjD0Rk7EXTol8O7HD3ne7eCzwJ3DBsHwcKLHybZz5wGOiPbMsAJphZBpAL7I9J5UmotiHE/CkFlBeO2z9qRCQA0QT9dGDfkOWmyLqhvgssIBzim4G73X3Q3ZuBbwF7gQNAu7v/dqQ3MbPbzazOzOpCodDbPI3E19XbT93uI2rNi8iYiyboRxo19GHL7wU2ANOAC4HvmlmhmZUQbv3PimzLM7ObR3oTd3/Q3WvcvaasLPXC8OWdh+kdGGSFLqsUkTEWTdA3AZVDlit4a/fLSuAZD9sB7ALmA+8Gdrl7yN37gGeAy8697OSzuiFETmYaNVUlQZciIuNMNEG/Fqg2s1lmlkV4MPW5YfvsBa4BMLNy4DxgZ2T9JWaWG+m/vwbYFqvik0ltY4hLZk8iJzM96FJEZJzJGG0Hd+83s7uAFwhfNfOIu28xszsi2x8A7gUeNbPNhLt6vuzurUCrmT0NrCM8OLseeDA+p5K4mo50sTN0jJsvnhl0KSIyDo0a9ADu/jzw/LB1Dwx5vR/4i9Mc+3Xg6+dQY9KrbWgFdFmliARDd8aOgdqGENOKcphTlhd0KSIyDino46x/YJA/vt7KinmaTUpEgqGgj7MN+9ro7OlXt42IBEZBH2e1DSHSDC6fo+fbiEgwFPRxtrqxlQsriynK1WxSIhIMBX0cHTnWy6amNnXbiEigFPRx9MfXw7NJKehFJEgK+jiqbQhRNCGTxRXFQZciIuOYgj5O3J3ahlaumFuq2aREJFAK+jhpPHiUNzp6WDFPV9uISLAU9HFS26DZpEQkMSjo42R1Q4jqyflMLZoQdCkiMs4p6OOgp2+AV3Yd5kpNMiIiCUBBHwcv7zrM8f5B9c+LSEJQ0MdBbUOIrIw0Lp41KehSREQU9PFQ2xDi4lkTmZCl2aREJHgK+hjb39ZN48GjmgRcRBKGgj7G1jRqNikRSSwK+hhb3RhiSmEO88rzgy5FRARQ0MfUwKCzprGVK6tLNZuUiCQMBX0MbWpqo727T902IpJQFPQxVNvQihlcMVfXz4tI4lDQx1BtY4gLKoopycsKuhQRkZMU9DHS3t3Hhn1tXFWt1ryIJBYFfYz8aUcrA4POleqfF5EEo6CPkdrGEAXZGVxYWRx0KSIip1DQx8CJ2aQumzuJzHT9k4pIYlEqxcDroWM0t3XrskoRSUgK+hg4OZuUnm8jIglIQR8DLzaGmF2aR+XE3KBLERF5CwX9OTreP8Cfdx5Wt42IJCwF/Tmq232E7r4BzSYlIgkrI+gCYumLP91IeWE2iyuLubCymPLCnLi/Z21DiKz0NC6ZrdmkRCQxpUzQ9/YP0tDSyS82NNM/6ADh0K8oPhn851cUUZiTGdP3Xd0QoqaqhNyslPmnFJEUkzLplJWRxi8/ewU9fQNsPdDBxn1t4Y+mdn67teXkfnPK8k4G/wUVxSyYWkB2xtlN+Xewo4ftb3Ryz3XzY3UaIiIxlzJBf0JOZjpLZ5SwdEbJyXXtXX1sag4H/4Z97dQ2tPLMumYAMtONhVMLWVxZfLL1P7s0j7S00Z8nX3tiNildVikiCSzlgn4kRbmZXFldxpWRQHZ3DrT3hIO/qY1N+9r5WX0Tj7+0B4CC7AzOryg6Gf4XVhYzpeit/f21DSFK87OZP6VgTM9HROTtiCrozexa4H4gHXjI3e8btr0I+CEwI/I1v+Xu349sKwYeAhYBDtzq7i/F6gTOhpkxrXgC04oncN35U4Hw7FA7Q0fZsK+NjU1tbGpq56EXd9I3MHJ//6JpRazZ0crV88qiav2LiARl1KA3s3Tge8B7gCZgrZk95+5bh+x2J7DV3d9vZmXAa2b2hLv3Ev4F8Rt3/4iZZQEJeVdReppRXV5AdXkBN9ZUAtDTN8C2E/39Te1s3Nd2Sn8/aBJwEUl80bTolwM73H0ngJk9CdwADA16BwosPFFqPnAY6DezQmAF8CmASPD3xqz6OMvJTGfJjBKWDO3v7+5jc1M7G5vaONDezXsWlgdYoYjI6KIJ+unAviHLTcDFw/b5LvAcsB8oAD7q7oNmNhsIAd83s8VAPXC3ux8758oDUjQhkyuqS7lCE4yISJKI5s7YkTqgfdjye4ENwDTgQuC7kdZ8BrAU+L/uvgQ4Btwz4puY3W5mdWZWFwqFoqteRERGFU3QNwGVQ5YrCLfch1oJPONhO4BdwPzIsU3u/nJkv6cJB/9buPuD7l7j7jVlZer3FhGJlWiCfi1QbWazIoOpNxHuphlqL3ANgJmVA+cBO939DWCfmZ0X2e8aTu3bFxGROBu1j97d+83sLuAFwpdXPuLuW8zsjsj2B4B7gUfNbDPhrp4vu3tr5Et8Fngi8ktiJ+HWv4iIjBFzH97dHryamhqvq6sLugwRkaRhZvXuXjPSNj2mWEQkxSnoRURSnIJeRCTFJWQfvZmFgD1neXgp0DrqXslJ55a8Uvn8dG6JYaa7j3htekIG/bkws7rTDUgkO51b8krl89O5JT513YiIpDgFvYhIikvFoH8w6ALiSOeWvFL5/HRuCS7l+uhFRORUqdiiFxGRIRT0IiIpLmWC3syuNbPXzGyHmY34zPtkZWaVZvYHM9tmZlvM7O6ga4o1M0s3s/Vm9quga4klMys2s6fNbHvk+3dp0DXFkpl9IfIz+aqZ/djMcoKu6WyZ2SNmdtDMXh2ybqKZ/c7MGiOfS870NRJVSgT9kHltrwMWAh8zs4XBVhVT/cAX3X0BcAlwZ4qdH8DdwLagi4iDE3MmzwcWk0LnaGbTgc8BNe6+iPDTbW8Ktqpz8ihw7bB19wC/d/dq4PecZuKkRJcSQc+QeW0j89KemNc2Jbj7AXdfF3ndSTgspgdbVeyYWQXwPuChoGuJpSFzJj8M4TmT3b0t0KJiLwOYYGYZQC5vnZQoabh7LeH5roe6AXgs8vox4INjWVOspErQjzSvbcoE4VBmVgUsAV4eZddk8h3gS8BgwHXE2tA5k9eb2UNmlhd0UbHi7s3AtwhPPHQAaHf33wZbVcyVu/sBCDe4gMkB13NWUiXoo5nXNumZWT7wM+Dz7t4RdD2xYGbXAwfdvT7oWuIg6jmTk1Gkv/oGYBbh+aLzzOzmYKuSkaRK0Eczr21SM7NMwiH/hLs/E3Q9MXQ58AEz2024y+1dZvbDYEuKmajnTE5S7wZ2uXvI3fuAZ4DLAq4p1lrMbCpA5PPBgOs5K6kS9NHMa5u0zMwI9/Nuc/d/DbqeWHL3r7h7hbtXEf6+/ae7p0SrcBzMmbwXuMTMciM/o9eQQoPNEc8Bn4y8/iTwiwBrOWujzhmbDE43r23AZcXS5cAngM1mtiGy7qvu/nxwJUmUUnbOZHd/2cyeBtYRvjJsPUn8yAAz+zFwNVBqZk3A14H7gJ+a2SrCv9huDK7Cs6dHIIiIpLhU6boREZHTUNCLiKQ4Bb2ISIpT0IuIpDgFvYhIilPQi4ikOAW9iEiK+//UE8xtC89XeQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "simple_bag_test = []\n",
    "\n",
    "for num in range(12):\n",
    "    simple_bagging = RandomForestClassifier(max_features = None, # uses all features\n",
    "                                            n_estimators = num+1,\n",
    "                                            n_jobs = -1,\n",
    "                                            verbose = 1,\n",
    "                                            random_state = 8675309)\n",
    "    simple_bagging.fit(x_train,y_train)\n",
    "    score = simple_bagging.score(x_test,y_test)\n",
    "    print(score)\n",
    "    simple_bag_test.append(score)   \n",
    "\n",
    "plt.plot(simple_bag_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our __random forest__ model is below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   1 out of   1 | elapsed:    0.4s finished\n",
      "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n",
      "[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8153\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   2 out of   2 | elapsed:    0.4s finished\n",
      "[Parallel(n_jobs=2)]: Using backend ThreadingBackend with 2 concurrent workers.\n",
      "[Parallel(n_jobs=2)]: Done   2 out of   2 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=2)]: Done   2 out of   2 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8234\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   3 out of   3 | elapsed:    0.5s finished\n",
      "[Parallel(n_jobs=3)]: Using backend ThreadingBackend with 3 concurrent workers.\n",
      "[Parallel(n_jobs=3)]: Done   3 out of   3 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8865\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   2 out of   4 | elapsed:    0.6s remaining:    0.6s\n",
      "[Parallel(n_jobs=-1)]: Done   4 out of   4 | elapsed:    0.6s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   2 out of   4 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=4)]: Done   4 out of   4 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.91\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   5 out of   5 | elapsed:    1.0s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   5 out of   5 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9252\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   6 out of   6 | elapsed:    1.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=-1)]: Done   6 out of   6 | elapsed:    1.0s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   6 out of   6 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=4)]: Done   6 out of   6 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9312\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   7 out of   7 | elapsed:    1.1s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   7 out of   7 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9373\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   8 out of   8 | elapsed:    1.2s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   8 out of   8 | elapsed:    0.0s finished\n",
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9423\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   9 out of   9 | elapsed:    1.5s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done   9 out of   9 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9441\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  10 out of  10 | elapsed:    1.5s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  10 out of  10 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9491\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  11 out of  11 | elapsed:    1.7s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  11 out of  11 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9506\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9531\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done  12 out of  12 | elapsed:    1.8s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  12 out of  12 | elapsed:    0.0s finished\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7f137a86c978>]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sqrt_features_test = []\n",
    "\n",
    "for num in range(12):\n",
    "    sqrt_features = RandomForestClassifier(max_features = 'sqrt',\n",
    "                                           n_estimators = num+1,\n",
    "                                           n_jobs = -1,\n",
    "                                           verbose = 1,\n",
    "                                           random_state = 8675309)\n",
    "    sqrt_features.fit(x_train,y_train)\n",
    "    score = sqrt_features.score(x_test,y_test)\n",
    "    print(score)\n",
    "    sqrt_features_test.append(score)   \n",
    "\n",
    "plt.plot(sqrt_features_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np \n",
    "x = np.arange(12)\n",
    "\n",
    "plt.figure(figsize=(10,10))\n",
    "plt.plot(x, simple_bag_test, label='Simple Bagged')\n",
    "plt.plot(x, sqrt_features_test, label='Random Forest (Sqrt Number of Features)')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_mxnet_p36",
   "language": "python",
   "name": "conda_mxnet_p36"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}