N5_Training.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Running Machine Learning algorithms\n",
    "\n",
    "Neural Network/ Naive Bayes\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.9.0\n"
     ]
    }
   ],
   "source": [
    "import json\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import nltk\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set_style(\"darkgrid\")\n",
    "from scipy.sparse import csr_matrix, coo_matrix, hstack, vstack, save_npz,  load_npz\n",
    "from functools import reduce\n",
    "\n",
    "import keras\n",
    "\n",
    "print(keras.__version__)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load dataset "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "ym = np.load(\"data/train_P4_md.npy\")\n",
    "Xm = load_npz(\"data/train_P4_md_X.npz\")\n",
    "yc = np.load(\"data/train_P4_code.npy\")\n",
    "Xc = load_npz(\"data/train_P4_code_X.npz\")\n",
    "\n",
    "ym_v = np.load(\"data/valid_P4_md.npy\")\n",
    "Xm_v = load_npz(\"data/valid_P4_md_X.npz\")\n",
    "yc_v = np.load(\"data/valid_P4_code.npy\")\n",
    "Xc_v = load_npz(\"data/valid_P4_code_X.npz\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(75520, 440) (75520,) (206602, 502) (206602,)\n",
      "<class 'scipy.sparse._csr.csr_matrix'> <class 'numpy.ndarray'> <class 'scipy.sparse._csr.csr_matrix'> <class 'numpy.ndarray'>\n"
     ]
    }
   ],
   "source": [
    "print(Xm.shape,ym.shape,Xc.shape,yc.shape)\n",
    "print(type(Xm),type(ym),type(Xc),type(yc))\n",
    "print(Xm_v.shape,ym_v.shape,Xc_v.shape,yc_v.shape)\n",
    "print(type(Xm_v),type(ym_v),type(Xc_v),type(yc_v))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.metrics import mean_squared_error, log_loss, accuracy_score, precision_score, roc_curve"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "Xc_train, Xc_test, yc_train, yc_test = train_test_split(Xc, yc,\n",
    "                                                       shuffle = True,\n",
    "                                                       random_state = 137,\n",
    "                                                       test_size = .05)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "Xm_train, Xm_test, ym_train, ym_test = train_test_split(Xm, ym,\n",
    "                                                       shuffle = True,\n",
    "                                                       random_state = 137,\n",
    "                                                       test_size = .05)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(196271, 502) (10331, 502) (196271,) (10331,)\n",
      "<class 'scipy.sparse._csr.csr_matrix'> <class 'scipy.sparse._csr.csr_matrix'> <class 'numpy.ndarray'> <class 'numpy.ndarray'>\n"
     ]
    }
   ],
   "source": [
    "print(Xc_train.shape, Xc_test.shape, yc_train.shape, yc_test.shape)\n",
    "print(type(Xc_train), type(Xc_test), type(yc_train), type(yc_test))\n",
    "print(Xm_train.shape, Xm_test.shape, ym_train.shape, ym_test.shape)\n",
    "print(type(Xm_train), type(Xm_test), type(ym_train), type(ym_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(196271, 502) (10331, 502) (196271,) (10331,)\n",
      "<class 'scipy.sparse._csr.csr_matrix'> <class 'scipy.sparse._csr.csr_matrix'> <class 'numpy.ndarray'> <class 'numpy.ndarray'>\n"
     ]
    }
   ],
   "source": [
    "print(Xc_train.shape, Xc_test.shape, yc_train.shape, yc_test.shape)\n",
    "print(type(Xc_train), type(Xc_test), type(yc_train), type(yc_test))\n",
    "print(Xm_train.shape, Xm_test.shape, ym_train.shape, ym_test.shape)\n",
    "print(type(Xm_train), type(Xm_test), type(ym_train), type(ym_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dense array is needed for training\n",
    "Xc_train_ar = Xc_train.toarray()\n",
    "Xc_test_ar = Xc_test.toarray()\n",
    "Xm_train_ar = Xm_train.toarray()\n",
    "Xm_test_ar = Xm_test.toarray()\n",
    "\n",
    "Xc_v_ar = Xc_v.toarray() # validation set\n",
    "Xm_v_ar = Xm_v.toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.   0.   0.   0.01 0.   0.   0.19 0.02 0.01 0.   0.   0.   0.   0.  ] \n",
      " [0.   0.   0.   0.12 0.09 0.   1.19 0.36 0.32 0.   0.   0.   0.   0.  ] \n",
      "\n",
      "\n",
      "[0.   0.   0.03 0.   0.   0.   0.   0.   0.   0.   0.   0.01 0.06 0.06] \n",
      " [0.   0.   0.45 0.   0.07 0.   0.   0.   0.   0.   0.   0.14 0.31 0.31] \n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(np.round(np.mean(Xc_train_ar,axis=0)[:14],2),\"\\n\" ,np.round(np.std(Xc_train_ar,axis=0)[:14],2),\"\\n\\n\" )\n",
    "#print(np.mean(Xc_train_ar,axis=0)[240:260],\"\\n\\n\" ,np.std(Xc_train_ar,axis=0)[240:260],\"\\n\\n\" )\n",
    "print(np.round(np.mean(Xc_train_ar,axis=0)[-14:],2),\"\\n\" ,np.round(np.std(Xc_train_ar,axis=0)[-14:],2),\"\\n\\n\" )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "#correct 6240 total num 10331\n",
      "Mean Sq Error:  0.396 X Entropy error:  13.6772\n",
      "Accuracy Score:  0.604 Precision Score:  0.6818\n"
     ]
    }
   ],
   "source": [
    "def textoutput(ytest, ypred):\n",
    "     yc_correctness = (ytest==ypred)\n",
    "     print(\"#correct\", yc_correctness.sum(), \"total num\", yc_correctness.size)\n",
    "     print(\"Mean Sq Error: \",round(mean_squared_error(ytest*1, 1*ypred),3),\n",
    "          \"X Entropy error: \", round(log_loss(ytest*1, 1*ypred),4))\n",
    "     print(\"Accuracy Score: \",round(accuracy_score(ytest*1, 1*ypred),4),\n",
    "          \"Precision Score: \", round(precision_score(ytest*1, 1*ypred),4))\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Gaussian Naive Bayes\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "GaussianNB()"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gnb =  GaussianNB()\n",
    "gnb.fit(Xc_train.toarray(),yc_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "yc_predict = gnb.predict(Xc_test.toarray())\n",
    "textoutput(yc_test, yc_predict)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Neural Network\n",
    "\n",
    "Reference\n",
    "https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html#sklearn.neural_network.MLPClassifier\n",
    "https://scikit-learn.org/stable/modules/neural_networks_supervised.html#mlp-tips"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier(activation=&#x27;logistic&#x27;, alpha=0.001, hidden_layer_sizes=100,\n",
       "              learning_rate=&#x27;invscaling&#x27;, learning_rate_init=0.01,\n",
       "              random_state=137, solver=&#x27;sgd&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier(activation=&#x27;logistic&#x27;, alpha=0.001, hidden_layer_sizes=100,\n",
       "              learning_rate=&#x27;invscaling&#x27;, learning_rate_init=0.01,\n",
       "              random_state=137, solver=&#x27;sgd&#x27;)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier(activation='logistic', alpha=0.001, hidden_layer_sizes=100,\n",
       "              learning_rate='invscaling', learning_rate_init=0.01,\n",
       "              random_state=137, solver='sgd')"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mlp = MLPClassifier(solver='sgd', alpha=1e-3,\n",
    "                    activation=\"logistic\", learning_rate_init=0.01,\n",
    "                        hidden_layer_sizes=(100), random_state=137, learning_rate=\"invscaling\")\n",
    "mlp.fit(Xc_train.toarray(),yc_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "#correct 6785 total num 10331\n",
      "Mean Sq Error:  0.343 X Entropy error:  11.8552\n",
      "Accuracy Score:  0.6568 Precision Score:  0.6568\n"
     ]
    }
   ],
   "source": [
    "yc_predict_mlp = mlp.predict(Xc_test.toarray())\n",
    "textoutput(yc_test, yc_predict_mlp)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## random forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(min_samples_split=8)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(min_samples_split=8)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(min_samples_split=8)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc = RandomForestClassifier(min_samples_split = 8)\n",
    "rfc.fit(Xc_train.toarray(),yc_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "#correct 8685 total num 10331\n",
      "Mean Sq Error:  0.159 X Entropy error:  5.503\n",
      "Accuracy Score:  0.8407 Precision Score:  0.8391\n"
     ]
    }
   ],
   "source": [
    "yc_predict_rfc = rfc.predict(Xc_test.toarray())\n",
    "textoutput(yc_test, yc_predict_rfc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ROC curve\n",
    "\n",
    "The plot shows a little bit of overtraining for Random Forest Classifier, but nothing too worrying as the test set performs wonderfully"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fprs1, tprs1, cutoffs1 = roc_curve(np.array(yc_test), gnb.predict_proba(Xc_test_ar)[:,1])\n",
    "fprs1a, tprs1a, cutoffs1a = roc_curve(np.array(yc_train), gnb.predict_proba(Xc_train_ar)[:,1])\n",
    "\n",
    "fprs2, tprs2, cutoffs2 = roc_curve(np.array(yc_test), rfc.predict_proba(Xc_test_ar)[:,1])\n",
    "fprs3, tprs3, cutoffs3 = roc_curve(np.array(yc_train), rfc.predict_proba(Xc_train_ar)[:,1])\n",
    "\n",
    "fprs4, tprs4, cutoffs4 = roc_curve(np.array(yc_test), mlp.predict_proba(Xc_test_ar)[:,1])\n",
    "fprs4a, tprs4a, cutoffs4a = roc_curve(np.array(yc_train), mlp.predict_proba(Xc_train_ar)[:,1])\n",
    "fig = plt.figure(figsize=(10,8))\n",
    "\n",
    "plt.plot(fprs1, tprs1, label=\"Gaussian Naive Bayes\")\n",
    "plt.plot(fprs1a, tprs1a, 'b', label=\"Gaussian Naive Bayes (train)\", alpha=0.5)\n",
    "plt.plot(fprs2, tprs2, \"r\", label=\"Random Forest\")\n",
    "plt.plot(fprs3, tprs3, \"r\", label=\"Random Forest (train)\", alpha=0.5)\n",
    "plt.plot(fprs4, tprs4, \"g\", label=\"Neural Network\")\n",
    "plt.plot(fprs4a, tprs4a, \"g\", label=\"Neural Network (train)\", alpha=0.5)\n",
    "plt.plot([0,1], [0,1], 'k--', label=\"Random Guess Curve\")\n",
    "\n",
    "\n",
    "plt.xlabel(\"False Positive Rate\", fontsize=16)\n",
    "plt.ylabel(\"True Positive Rate\", fontsize=16)\n",
    "plt.xticks(fontsize=14)\n",
    "plt.yticks(fontsize=14)\n",
    "plt.legend(fontsize=14)\n",
    "\n",
    "plt.show()\n",
    "fig.savefig(\"roc_ml.pdf\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "Yc_predict_prob = gnb.predict_proba(Xc_test.toarray())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Kendal Tau \n",
    "\n",
    "This is described in another notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "from bisect import bisect\n",
    "\n",
    "\n",
    "# Actually O(N^2), but fast in practice for our data\n",
    "def count_inversions(a):\n",
    "    inversions = 0\n",
    "    sorted_so_far = []\n",
    "    for i, u in enumerate(a):  # O(N)\n",
    "        j = bisect(sorted_so_far, u)  # O(log N)\n",
    "        inversions += i - j\n",
    "        sorted_so_far.insert(j, u)  # O(N)\n",
    "    return inversions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here is the formula, where $S_i$  is the number of inversions in the predicted ranks and $n_i$ is the number of cells for notebook $i$\n",
    "\n",
    "$K=1-4 \\frac{\\sum_i S}{\\sum_i n (n-1)}$ "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def kendall_tau(ground_truth, predictions):\n",
    "    total_inversions = 0  # total inversions in predicted ranks across all instances\n",
    "    total_2max = 0  # maximum possible inversions across all instances\n",
    "    for gt, pred in zip(ground_truth, predictions):\n",
    "        ranks = [gt.index(x) for x in pred]  # rank predicted order in terms of ground truth\n",
    "        total_inversions += count_inversions(ranks)\n",
    "        n = len(gt)\n",
    "        total_2max += n * (n - 1)\n",
    "    return 1 - 4 * total_inversions / total_2max"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "testlist = [[\"ukraine\", \"UK\", \"spain\", \"sweden\", \"serbia\", \"italy\"],] #eurovision 2022\n",
    "shuffled_list=[]\n",
    "for l in testlist:\n",
    "    shuffled_list.append(l.copy())\n",
    "    random.shuffle(shuffled_list[-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['sweden', 'spain', 'ukraine', 'UK', 'italy', 'serbia']]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "shuffled_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.19999999999999996"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kendall_tau(testlist, shuffled_list)"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "4976e0179d97dd6d59b1329a76e601e17b789c2571b41c8b57f5fd69821c0dd3"
  },
  "kernelspec": {
   "display_name": "Python 3.8.13 ('mlp')",
   "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}