SVR__polynomial.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "VubKFPSGX2Vt"
   },
   "outputs": [],
   "source": [
    "# Importing necessary libraries\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.metrics import mean_absolute_error\n",
    "from sklearn.svm import SVR\n",
    "from sklearn.metrics import r2_score, mean_squared_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 52
    },
    "colab_type": "code",
    "id": "ZWRpf5KhX2V6",
    "outputId": "7cff060e-a092-454b-f711-c63aa027d517"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1400, 15)\n",
      "(1400,)\n"
     ]
    }
   ],
   "source": [
    "# Uploading the input data\n",
    "filepath = ('C:/Users/USER/Desktop/coursera/python/data for dl project/bootstrapped data.csv')\n",
    "data =pd.read_csv(filepath)\n",
    "X = data.iloc[0:1400,:-1]\n",
    "y = data.iloc[0:1400,-1]\n",
    "X.shape\n",
    "print(X.shape)\n",
    "print(y.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 329
    },
    "colab_type": "code",
    "id": "8UXkZIrsX4co",
    "outputId": "612b8d83-3d2e-4dd8-8f51-0a66d48e8ec9"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(15, 15)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Calculating correlation between input features\n",
    "corr = X.corr()\n",
    "import seaborn as sns\n",
    "sns.heatmap(corr)\n",
    "corr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 309
    },
    "colab_type": "code",
    "id": "Ljn9zzZDYBoK",
    "outputId": "b1af3b4e-b07c-4e63-adc3-bed9c5d3fc73"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ True  True  True  True  True  True  True  True  True  True  True  True\n",
      "  True  True  True]\n",
      "[ True  True  True  True  True  True  True False  True  True  True  True\n",
      "  True  True  True]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Hs (X1)</th>\n",
       "      <th>Ht (X2)</th>\n",
       "      <th>Cv (X3)</th>\n",
       "      <th>FF (X4)</th>\n",
       "      <th>FD (X5)</th>\n",
       "      <th>SD (X6)</th>\n",
       "      <th>SA (X7)</th>\n",
       "      <th>MD (X9)</th>\n",
       "      <th>PD (X10)</th>\n",
       "      <th>TD (X11)</th>\n",
       "      <th>P (X12)</th>\n",
       "      <th>E (X13)</th>\n",
       "      <th>FR (X14)</th>\n",
       "      <th>TWL (X15)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.005167</td>\n",
       "      <td>0.005284</td>\n",
       "      <td>0.348857</td>\n",
       "      <td>1.629222</td>\n",
       "      <td>403.767705</td>\n",
       "      <td>47.488970</td>\n",
       "      <td>19.439385</td>\n",
       "      <td>55.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>51.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.004333</td>\n",
       "      <td>0.005024</td>\n",
       "      <td>0.117171</td>\n",
       "      <td>1.664610</td>\n",
       "      <td>124.369644</td>\n",
       "      <td>123.864539</td>\n",
       "      <td>20.786422</td>\n",
       "      <td>50.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>43.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.004267</td>\n",
       "      <td>0.005127</td>\n",
       "      <td>0.136262</td>\n",
       "      <td>1.935838</td>\n",
       "      <td>124.369644</td>\n",
       "      <td>55.876283</td>\n",
       "      <td>32.456879</td>\n",
       "      <td>45.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>42.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.004000</td>\n",
       "      <td>0.002459</td>\n",
       "      <td>0.092059</td>\n",
       "      <td>1.307856</td>\n",
       "      <td>124.567093</td>\n",
       "      <td>187.092365</td>\n",
       "      <td>17.082540</td>\n",
       "      <td>40.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>40.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.005367</td>\n",
       "      <td>0.004437</td>\n",
       "      <td>0.713431</td>\n",
       "      <td>1.469699</td>\n",
       "      <td>493.786526</td>\n",
       "      <td>57.456780</td>\n",
       "      <td>32.922497</td>\n",
       "      <td>60.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>53.666667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Hs (X1)   Ht (X2)   Cv (X3)   FF (X4)     FD (X5)     SD (X6)    SA (X7)  \\\n",
       "0  0.005167  0.005284  0.348857  1.629222  403.767705   47.488970  19.439385   \n",
       "1  0.004333  0.005024  0.117171  1.664610  124.369644  123.864539  20.786422   \n",
       "2  0.004267  0.005127  0.136262  1.935838  124.369644   55.876283  32.456879   \n",
       "3  0.004000  0.002459  0.092059  1.307856  124.567093  187.092365  17.082540   \n",
       "4  0.005367  0.004437  0.713431  1.469699  493.786526   57.456780  32.922497   \n",
       "\n",
       "   MD (X9)  PD (X10)  TD (X11)  P (X12)  E (X13)  FR (X14)  TWL (X15)  \n",
       "0     55.0      45.0      55.0     60.0     35.0      25.0  51.666667  \n",
       "1     50.0      35.0      40.0     55.0     35.0      40.0  43.333333  \n",
       "2     45.0      35.0      40.0     55.0     40.0      30.0  42.666667  \n",
       "3     40.0      45.0      40.0     50.0     25.0      25.0  40.000000  \n",
       "4     60.0      45.0      55.0     60.0     40.0      25.0  53.666667  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculating correlation between input features\n",
    "col = np.full((15),True, dtype=\"bool\")\n",
    "print(col)\n",
    "flag = 0\n",
    "if flag==0:\n",
    "    for i in range(12):\n",
    "        for j in range(i+1,12):\n",
    "            if abs(corr.iloc[i,j])>0.9:\n",
    "                col[j] = False\n",
    "    X = X.iloc[:,col]\n",
    "    flag = 1\n",
    "print(col)\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "estWWcH4X2WM",
    "outputId": "94e0195c-b3c6-4493-fd0f-a4041824966a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1120, 14) (280, 14) (1120, 1) (280, 1)\n"
     ]
    }
   ],
   "source": [
    "# Normalization followed by Splitting data into train and test sets\n",
    "y = np.array(y).reshape(-1,1)\n",
    "scale = StandardScaler()\n",
    "X = scale.fit_transform(X)\n",
    "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=.2,random_state=0)\n",
    "print(X_train.shape,X_test.shape,y_train.shape,y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 52
    },
    "colab_type": "code",
    "id": "cWpCcvwgX2WY",
    "outputId": "de52518f-c330-4c41-8c21-caa1566a02e6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVR(kernel='poly')"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating model\n",
    "regressor = SVR(kernel = 'poly')\n",
    "regressor.fit(X_train, np.ravel(y_train,order='C'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "xIQ4uzZGX2Wm"
   },
   "outputs": [],
   "source": [
    "#regr = make_pipeline(StandardScaler(), SVR(C=1.0, epsilon=0.2))\n",
    "#regr.fit(X,  np.ravel(y,order='C'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "hTbI-R_KX2XD"
   },
   "outputs": [],
   "source": [
    "y_Pred = regressor.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "colab_type": "code",
    "id": "i7iV9hXpX2XP",
    "outputId": "de664c8e-6328-49c3-a31a-4a92440d615c",
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# plt.scatter(y_test,y_Pred,color=\"black\")\n",
    "# plt.plot(y_test,y_Pred,color=\"yellow\",label = \"SVR Model \")\n",
    "# plt.xlabel(\"Actual Reaction time\")\n",
    "# plt.ylabel(\"Predicted Reaction time \")\n",
    "# plt.legend()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "N-ckYuPKX2Xb",
    "outputId": "47fac09a-67d9-407b-96eb-3f416c03e7b4"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2 score: 0.7988666776718358\n",
      "MSE: 31.87285616676569\n",
      "MAE: 3.433249693631649\n",
      "Pearson Correlation coefficient: 0.9046606575489874\n",
      "index: 0.028383419823300643\n"
     ]
    }
   ],
   "source": [
    "# Validating model\n",
    "score = regressor.score(X_test,y_test)\n",
    "r2score = r2_score(y_test,y_Pred)\n",
    "MSE = mean_squared_error(y_test,y_Pred)\n",
    "MAE = mean_absolute_error(y_test,y_Pred)\n",
    "print('R2 score:',r2score)\n",
    "print('MSE:',MSE)\n",
    "print('MAE:',MAE)\n",
    "y_Pred = np.array(y_Pred).reshape(-1,1)\n",
    "r = pd.DataFrame(np.concatenate((y_test,y_Pred), axis = 1)).corr()\n",
    "pear_coff = r.iloc[0,1]\n",
    "print('Pearson Correlation coefficient:',pear_coff)\n",
    "index = pear_coff/MSE\n",
    "print('index:',index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualizing model\n",
    "maxi = max(max(y_Pred), max(y_test))\n",
    "mini = min(min(y_Pred), min(y_test))\n",
    "fig = plt.figure(figsize=(8,6))\n",
    "plt.style.use('ggplot')\n",
    "plt.scatter(y_test, y_Pred, label='SVR polynomial model', c = 'b', marker='o')\n",
    "plt.plot(range(int(mini), int(maxi+1)), range(int(mini), int(maxi+1)),'-.r')\n",
    "plt.title('SVR polynomial model for mental fatigue estimation')\n",
    "plt.xlabel(\"Actual Reaction time\")\n",
    "plt.ylabel(\"Predicted Reaction time \")\n",
    "plt.legend(loc='best')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "FastDTW:  914.4171569259247\n"
     ]
    }
   ],
   "source": [
    "# Calculating FastDTW\n",
    "from fastdtw import fastdtw\n",
    "from scipy.spatial.distance import euclidean\n",
    "\n",
    "\n",
    "distance, path = fastdtw(y_test,y_Pred, dist=euclidean)\n",
    "\n",
    "print('FastDTW: ',distance)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DTW:  7281.347724405707\n"
     ]
    }
   ],
   "source": [
    "# Calculating DTW\n",
    "from dtw import dtw\n",
    "from scipy.spatial.distance import sqeuclidean\n",
    "d, cost_matrix, acc_cost_matrix, path = dtw(y_test,y_Pred, dist=sqeuclidean)\n",
    "print('DTW: ',d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'cdtw'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-42-d8e8f047a2b7>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;31m# Calculating cDTW\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mcdtw\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpydtw\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      3\u001b[0m d = pydtw.dtw(y_test,y_Pred,pydtw.Settings(step = 'p0sym',     \n\u001b[0;32m      4\u001b[0m                                 \u001b[0mwindow\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m'palival'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m                                 \u001b[0mparam\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m2.0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'cdtw'"
     ]
    }
   ],
   "source": [
    "# Calculating cDTW\n",
    "from cdtw import pydtw\n",
    "d = pydtw.dtw(y_test,y_Pred,pydtw.Settings(step = 'p0sym',     \n",
    "                                window = 'palival', \n",
    "                                param = 2.0,        \n",
    "                                norm = False,       \n",
    "                                compute_path = True))\n",
    "d.get_dist()"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "SVR _linear.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}