model_1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read the CSV and Perform Basic Data Cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "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>koi_disposition</th>\n",
       "      <th>koi_fpflag_nt</th>\n",
       "      <th>koi_fpflag_ss</th>\n",
       "      <th>koi_fpflag_co</th>\n",
       "      <th>koi_fpflag_ec</th>\n",
       "      <th>koi_period</th>\n",
       "      <th>koi_period_err1</th>\n",
       "      <th>koi_period_err2</th>\n",
       "      <th>koi_time0bk</th>\n",
       "      <th>koi_time0bk_err1</th>\n",
       "      <th>koi_time0bk_err2</th>\n",
       "      <th>koi_impact</th>\n",
       "      <th>koi_impact_err1</th>\n",
       "      <th>koi_impact_err2</th>\n",
       "      <th>koi_duration</th>\n",
       "      <th>koi_duration_err1</th>\n",
       "      <th>koi_duration_err2</th>\n",
       "      <th>koi_depth</th>\n",
       "      <th>koi_depth_err1</th>\n",
       "      <th>koi_depth_err2</th>\n",
       "      <th>koi_prad</th>\n",
       "      <th>koi_prad_err1</th>\n",
       "      <th>koi_prad_err2</th>\n",
       "      <th>koi_teq</th>\n",
       "      <th>koi_insol</th>\n",
       "      <th>koi_insol_err1</th>\n",
       "      <th>koi_insol_err2</th>\n",
       "      <th>koi_model_snr</th>\n",
       "      <th>koi_tce_plnt_num</th>\n",
       "      <th>koi_steff</th>\n",
       "      <th>koi_steff_err1</th>\n",
       "      <th>koi_steff_err2</th>\n",
       "      <th>koi_slogg</th>\n",
       "      <th>koi_slogg_err1</th>\n",
       "      <th>koi_slogg_err2</th>\n",
       "      <th>koi_srad</th>\n",
       "      <th>koi_srad_err1</th>\n",
       "      <th>koi_srad_err2</th>\n",
       "      <th>ra</th>\n",
       "      <th>dec</th>\n",
       "      <th>koi_kepmag</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CONFIRMED</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>54.418383</td>\n",
       "      <td>2.479000e-04</td>\n",
       "      <td>-2.479000e-04</td>\n",
       "      <td>162.513840</td>\n",
       "      <td>0.003520</td>\n",
       "      <td>-0.003520</td>\n",
       "      <td>0.586</td>\n",
       "      <td>0.059</td>\n",
       "      <td>-0.443</td>\n",
       "      <td>4.50700</td>\n",
       "      <td>0.11600</td>\n",
       "      <td>-0.11600</td>\n",
       "      <td>874.8</td>\n",
       "      <td>35.5</td>\n",
       "      <td>-35.5</td>\n",
       "      <td>2.83</td>\n",
       "      <td>0.32</td>\n",
       "      <td>-0.19</td>\n",
       "      <td>443</td>\n",
       "      <td>9.11</td>\n",
       "      <td>2.87</td>\n",
       "      <td>-1.62</td>\n",
       "      <td>25.8</td>\n",
       "      <td>2</td>\n",
       "      <td>5455</td>\n",
       "      <td>81</td>\n",
       "      <td>-81</td>\n",
       "      <td>4.467</td>\n",
       "      <td>0.064</td>\n",
       "      <td>-0.096</td>\n",
       "      <td>0.927</td>\n",
       "      <td>0.105</td>\n",
       "      <td>-0.061</td>\n",
       "      <td>291.93423</td>\n",
       "      <td>48.141651</td>\n",
       "      <td>15.347</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>FALSE POSITIVE</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>19.899140</td>\n",
       "      <td>1.490000e-05</td>\n",
       "      <td>-1.490000e-05</td>\n",
       "      <td>175.850252</td>\n",
       "      <td>0.000581</td>\n",
       "      <td>-0.000581</td>\n",
       "      <td>0.969</td>\n",
       "      <td>5.126</td>\n",
       "      <td>-0.077</td>\n",
       "      <td>1.78220</td>\n",
       "      <td>0.03410</td>\n",
       "      <td>-0.03410</td>\n",
       "      <td>10829.0</td>\n",
       "      <td>171.0</td>\n",
       "      <td>-171.0</td>\n",
       "      <td>14.60</td>\n",
       "      <td>3.92</td>\n",
       "      <td>-1.31</td>\n",
       "      <td>638</td>\n",
       "      <td>39.30</td>\n",
       "      <td>31.04</td>\n",
       "      <td>-10.49</td>\n",
       "      <td>76.3</td>\n",
       "      <td>1</td>\n",
       "      <td>5853</td>\n",
       "      <td>158</td>\n",
       "      <td>-176</td>\n",
       "      <td>4.544</td>\n",
       "      <td>0.044</td>\n",
       "      <td>-0.176</td>\n",
       "      <td>0.868</td>\n",
       "      <td>0.233</td>\n",
       "      <td>-0.078</td>\n",
       "      <td>297.00482</td>\n",
       "      <td>48.134129</td>\n",
       "      <td>15.436</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>FALSE POSITIVE</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.736952</td>\n",
       "      <td>2.630000e-07</td>\n",
       "      <td>-2.630000e-07</td>\n",
       "      <td>170.307565</td>\n",
       "      <td>0.000115</td>\n",
       "      <td>-0.000115</td>\n",
       "      <td>1.276</td>\n",
       "      <td>0.115</td>\n",
       "      <td>-0.092</td>\n",
       "      <td>2.40641</td>\n",
       "      <td>0.00537</td>\n",
       "      <td>-0.00537</td>\n",
       "      <td>8079.2</td>\n",
       "      <td>12.8</td>\n",
       "      <td>-12.8</td>\n",
       "      <td>33.46</td>\n",
       "      <td>8.50</td>\n",
       "      <td>-2.83</td>\n",
       "      <td>1395</td>\n",
       "      <td>891.96</td>\n",
       "      <td>668.95</td>\n",
       "      <td>-230.35</td>\n",
       "      <td>505.6</td>\n",
       "      <td>1</td>\n",
       "      <td>5805</td>\n",
       "      <td>157</td>\n",
       "      <td>-174</td>\n",
       "      <td>4.564</td>\n",
       "      <td>0.053</td>\n",
       "      <td>-0.168</td>\n",
       "      <td>0.791</td>\n",
       "      <td>0.201</td>\n",
       "      <td>-0.067</td>\n",
       "      <td>285.53461</td>\n",
       "      <td>48.285210</td>\n",
       "      <td>15.597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CONFIRMED</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2.525592</td>\n",
       "      <td>3.760000e-06</td>\n",
       "      <td>-3.760000e-06</td>\n",
       "      <td>171.595550</td>\n",
       "      <td>0.001130</td>\n",
       "      <td>-0.001130</td>\n",
       "      <td>0.701</td>\n",
       "      <td>0.235</td>\n",
       "      <td>-0.478</td>\n",
       "      <td>1.65450</td>\n",
       "      <td>0.04200</td>\n",
       "      <td>-0.04200</td>\n",
       "      <td>603.3</td>\n",
       "      <td>16.9</td>\n",
       "      <td>-16.9</td>\n",
       "      <td>2.75</td>\n",
       "      <td>0.88</td>\n",
       "      <td>-0.35</td>\n",
       "      <td>1406</td>\n",
       "      <td>926.16</td>\n",
       "      <td>874.33</td>\n",
       "      <td>-314.24</td>\n",
       "      <td>40.9</td>\n",
       "      <td>1</td>\n",
       "      <td>6031</td>\n",
       "      <td>169</td>\n",
       "      <td>-211</td>\n",
       "      <td>4.438</td>\n",
       "      <td>0.070</td>\n",
       "      <td>-0.210</td>\n",
       "      <td>1.046</td>\n",
       "      <td>0.334</td>\n",
       "      <td>-0.133</td>\n",
       "      <td>288.75488</td>\n",
       "      <td>48.226200</td>\n",
       "      <td>15.509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CONFIRMED</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.134435</td>\n",
       "      <td>1.050000e-05</td>\n",
       "      <td>-1.050000e-05</td>\n",
       "      <td>172.979370</td>\n",
       "      <td>0.001900</td>\n",
       "      <td>-0.001900</td>\n",
       "      <td>0.762</td>\n",
       "      <td>0.139</td>\n",
       "      <td>-0.532</td>\n",
       "      <td>3.14020</td>\n",
       "      <td>0.06730</td>\n",
       "      <td>-0.06730</td>\n",
       "      <td>686.0</td>\n",
       "      <td>18.7</td>\n",
       "      <td>-18.7</td>\n",
       "      <td>2.77</td>\n",
       "      <td>0.90</td>\n",
       "      <td>-0.30</td>\n",
       "      <td>1160</td>\n",
       "      <td>427.65</td>\n",
       "      <td>420.33</td>\n",
       "      <td>-136.70</td>\n",
       "      <td>40.2</td>\n",
       "      <td>2</td>\n",
       "      <td>6046</td>\n",
       "      <td>189</td>\n",
       "      <td>-232</td>\n",
       "      <td>4.486</td>\n",
       "      <td>0.054</td>\n",
       "      <td>-0.229</td>\n",
       "      <td>0.972</td>\n",
       "      <td>0.315</td>\n",
       "      <td>-0.105</td>\n",
       "      <td>296.28613</td>\n",
       "      <td>48.224670</td>\n",
       "      <td>15.714</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  koi_disposition  koi_fpflag_nt  koi_fpflag_ss  koi_fpflag_co  koi_fpflag_ec  \\\n",
       "0       CONFIRMED              0              0              0              0   \n",
       "1  FALSE POSITIVE              0              1              0              0   \n",
       "2  FALSE POSITIVE              0              1              0              0   \n",
       "3       CONFIRMED              0              0              0              0   \n",
       "4       CONFIRMED              0              0              0              0   \n",
       "\n",
       "   koi_period  koi_period_err1  koi_period_err2  koi_time0bk  \\\n",
       "0   54.418383     2.479000e-04    -2.479000e-04   162.513840   \n",
       "1   19.899140     1.490000e-05    -1.490000e-05   175.850252   \n",
       "2    1.736952     2.630000e-07    -2.630000e-07   170.307565   \n",
       "3    2.525592     3.760000e-06    -3.760000e-06   171.595550   \n",
       "4    4.134435     1.050000e-05    -1.050000e-05   172.979370   \n",
       "\n",
       "   koi_time0bk_err1  koi_time0bk_err2  koi_impact  koi_impact_err1  \\\n",
       "0          0.003520         -0.003520       0.586            0.059   \n",
       "1          0.000581         -0.000581       0.969            5.126   \n",
       "2          0.000115         -0.000115       1.276            0.115   \n",
       "3          0.001130         -0.001130       0.701            0.235   \n",
       "4          0.001900         -0.001900       0.762            0.139   \n",
       "\n",
       "   koi_impact_err2  koi_duration  koi_duration_err1  koi_duration_err2  \\\n",
       "0           -0.443       4.50700            0.11600           -0.11600   \n",
       "1           -0.077       1.78220            0.03410           -0.03410   \n",
       "2           -0.092       2.40641            0.00537           -0.00537   \n",
       "3           -0.478       1.65450            0.04200           -0.04200   \n",
       "4           -0.532       3.14020            0.06730           -0.06730   \n",
       "\n",
       "   koi_depth  koi_depth_err1  koi_depth_err2  koi_prad  koi_prad_err1  \\\n",
       "0      874.8            35.5           -35.5      2.83           0.32   \n",
       "1    10829.0           171.0          -171.0     14.60           3.92   \n",
       "2     8079.2            12.8           -12.8     33.46           8.50   \n",
       "3      603.3            16.9           -16.9      2.75           0.88   \n",
       "4      686.0            18.7           -18.7      2.77           0.90   \n",
       "\n",
       "   koi_prad_err2  koi_teq  koi_insol  koi_insol_err1  koi_insol_err2  \\\n",
       "0          -0.19      443       9.11            2.87           -1.62   \n",
       "1          -1.31      638      39.30           31.04          -10.49   \n",
       "2          -2.83     1395     891.96          668.95         -230.35   \n",
       "3          -0.35     1406     926.16          874.33         -314.24   \n",
       "4          -0.30     1160     427.65          420.33         -136.70   \n",
       "\n",
       "   koi_model_snr  koi_tce_plnt_num  koi_steff  koi_steff_err1  koi_steff_err2  \\\n",
       "0           25.8                 2       5455              81             -81   \n",
       "1           76.3                 1       5853             158            -176   \n",
       "2          505.6                 1       5805             157            -174   \n",
       "3           40.9                 1       6031             169            -211   \n",
       "4           40.2                 2       6046             189            -232   \n",
       "\n",
       "   koi_slogg  koi_slogg_err1  koi_slogg_err2  koi_srad  koi_srad_err1  \\\n",
       "0      4.467           0.064          -0.096     0.927          0.105   \n",
       "1      4.544           0.044          -0.176     0.868          0.233   \n",
       "2      4.564           0.053          -0.168     0.791          0.201   \n",
       "3      4.438           0.070          -0.210     1.046          0.334   \n",
       "4      4.486           0.054          -0.229     0.972          0.315   \n",
       "\n",
       "   koi_srad_err2         ra        dec  koi_kepmag  \n",
       "0         -0.061  291.93423  48.141651      15.347  \n",
       "1         -0.078  297.00482  48.134129      15.436  \n",
       "2         -0.067  285.53461  48.285210      15.597  \n",
       "3         -0.133  288.75488  48.226200      15.509  \n",
       "4         -0.105  296.28613  48.224670      15.714  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"exoplanet_data.csv\")\n",
    "# Drop the null columns where all values are null\n",
    "df = df.dropna(axis='columns', how='all')\n",
    "# Drop the null rows\n",
    "df = df.dropna()\n",
    "pd.set_option('display.max_columns', 500)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Select your features (columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set features. This will also be used as your x values.\n",
    "selected_features = df[['koi_period', 'koi_fpflag_nt', 'koi_fpflag_ss', 'koi_fpflag_co', 'koi_fpflag_ec']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create a Train Test Split\n",
    "\n",
    "Use `koi_disposition` for the y values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape: (6991, 5) (6991, 1)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "#Check Data is 2 dimensional\n",
    "y= df['koi_disposition'].values.reshape(-1,1)\n",
    "X= selected_features\n",
    "\n",
    "print('Shape:', X.shape, y.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "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>koi_period</th>\n",
       "      <th>koi_fpflag_nt</th>\n",
       "      <th>koi_fpflag_ss</th>\n",
       "      <th>koi_fpflag_co</th>\n",
       "      <th>koi_fpflag_ec</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6122</th>\n",
       "      <td>6.768901</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6370</th>\n",
       "      <td>0.733726</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2879</th>\n",
       "      <td>7.652707</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>107</th>\n",
       "      <td>7.953547</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>4.959319</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      koi_period  koi_fpflag_nt  koi_fpflag_ss  koi_fpflag_co  koi_fpflag_ec\n",
       "6122    6.768901              0              0              0              0\n",
       "6370    0.733726              0              1              0              1\n",
       "2879    7.652707              1              0              0              0\n",
       "107     7.953547              0              0              0              0\n",
       "29      4.959319              0              0              0              0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X,y, random_state=42)\n",
    "X_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pre-processing\n",
    "\n",
    "Scale the data using the MinMaxScaler and perform some feature selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Scale the data with MinMaxScaler\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "X_minmax = MinMaxScaler().fit(X_train)\n",
    "\n",
    "X_train_scaled = X_minmax.transform(X_train)\n",
    "X_test_scaled = X_minmax.transform(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train the Model\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
       "    decision_function_shape='ovr', degree=3, gamma='auto_deprecated',\n",
       "    kernel='linear', max_iter=-1, probability=False, random_state=None,\n",
       "    shrinking=True, tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "#Using Support Vector Machine (Classifier)\n",
    "from sklearn.svm import SVC\n",
    "model = SVC(kernel='linear')\n",
    "model.fit(X_train_scaled, np.ravel(y_train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
       "    decision_function_shape='ovr', degree=3, gamma='auto_deprecated',\n",
       "    kernel='linear', max_iter=-1, probability=False, random_state=None,\n",
       "    shrinking=True, tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model2 = SVC (kernel='linear')\n",
    "model2.fit(X_test_scaled, np.ravel(y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Data Score: 0.778180431050925\n",
      "Testing Data Score: 0.7848970251716247\n"
     ]
    }
   ],
   "source": [
    "print(f\"Training Data Score: {model.score(X_train_scaled, y_train)}\")\n",
    "print(f\"Testing Data Score: {model2.score(X_test_scaled, y_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hyperparameter Tuning\n",
    "\n",
    "Use `GridSearchCV` to tune the model's parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create the GridSearchCV model\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "param_grid = {'C':[1, 200,400,800],\n",
    "             'gamma':[1, 0.0001, 0.005, 0.001]}\n",
    "grid = GridSearchCV(model, param_grid, verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_split.py:1978: FutureWarning: The default value of cv will change from 3 to 5 in version 0.22. Specify it explicitly to silence this warning.\n",
      "  warnings.warn(CV_WARNING, FutureWarning)\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 remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:    0.0s remaining:    0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 3 folds for each of 16 candidates, totalling 48 fits\n",
      "[CV] C=1, gamma=1 ....................................................\n",
      "[CV] ........................ C=1, gamma=1, score=0.780, total=   0.1s\n",
      "[CV] C=1, gamma=1 ....................................................\n",
      "[CV] ........................ C=1, gamma=1, score=0.772, total=   0.1s\n",
      "[CV] C=1, gamma=1 ....................................................\n",
      "[CV] ........................ C=1, gamma=1, score=0.779, total=   0.1s\n",
      "[CV] C=1, gamma=0.0001 ...............................................\n",
      "[CV] ................... C=1, gamma=0.0001, score=0.780, total=   0.1s\n",
      "[CV] C=1, gamma=0.0001 ...............................................\n",
      "[CV] ................... C=1, gamma=0.0001, score=0.772, total=   0.1s\n",
      "[CV] C=1, gamma=0.0001 ...............................................\n",
      "[CV] ................... C=1, gamma=0.0001, score=0.779, total=   0.1s\n",
      "[CV] C=1, gamma=0.005 ................................................\n",
      "[CV] .................... C=1, gamma=0.005, score=0.780, total=   0.1s\n",
      "[CV] C=1, gamma=0.005 ................................................\n",
      "[CV] .................... C=1, gamma=0.005, score=0.772, total=   0.1s\n",
      "[CV] C=1, gamma=0.005 ................................................\n",
      "[CV] .................... C=1, gamma=0.005, score=0.779, total=   0.1s\n",
      "[CV] C=1, gamma=0.001 ................................................\n",
      "[CV] .................... C=1, gamma=0.001, score=0.780, total=   0.1s\n",
      "[CV] C=1, gamma=0.001 ................................................\n",
      "[CV] .................... C=1, gamma=0.001, score=0.772, total=   0.1s\n",
      "[CV] C=1, gamma=0.001 ................................................\n",
      "[CV] .................... C=1, gamma=0.001, score=0.779, total=   0.1s\n",
      "[CV] C=200, gamma=1 ..................................................\n",
      "[CV] ...................... C=200, gamma=1, score=0.784, total=   0.1s\n",
      "[CV] C=200, gamma=1 ..................................................\n",
      "[CV] ...................... C=200, gamma=1, score=0.774, total=   0.1s\n",
      "[CV] C=200, gamma=1 ..................................................\n",
      "[CV] ...................... C=200, gamma=1, score=0.782, total=   0.1s\n",
      "[CV] C=200, gamma=0.0001 .............................................\n",
      "[CV] ................. C=200, gamma=0.0001, score=0.784, total=   0.1s\n",
      "[CV] C=200, gamma=0.0001 .............................................\n",
      "[CV] ................. C=200, gamma=0.0001, score=0.774, total=   0.1s\n",
      "[CV] C=200, gamma=0.0001 .............................................\n",
      "[CV] ................. C=200, gamma=0.0001, score=0.782, total=   0.1s\n",
      "[CV] C=200, gamma=0.005 ..............................................\n",
      "[CV] .................. C=200, gamma=0.005, score=0.784, total=   0.1s\n",
      "[CV] C=200, gamma=0.005 ..............................................\n",
      "[CV] .................. C=200, gamma=0.005, score=0.774, total=   0.1s\n",
      "[CV] C=200, gamma=0.005 ..............................................\n",
      "[CV] .................. C=200, gamma=0.005, score=0.782, total=   0.1s\n",
      "[CV] C=200, gamma=0.001 ..............................................\n",
      "[CV] .................. C=200, gamma=0.001, score=0.784, total=   0.1s\n",
      "[CV] C=200, gamma=0.001 ..............................................\n",
      "[CV] .................. C=200, gamma=0.001, score=0.774, total=   0.1s\n",
      "[CV] C=200, gamma=0.001 ..............................................\n",
      "[CV] .................. C=200, gamma=0.001, score=0.782, total=   0.1s\n",
      "[CV] C=400, gamma=1 ..................................................\n",
      "[CV] ...................... C=400, gamma=1, score=0.784, total=   0.1s\n",
      "[CV] C=400, gamma=1 ..................................................\n",
      "[CV] ...................... C=400, gamma=1, score=0.774, total=   0.1s\n",
      "[CV] C=400, gamma=1 ..................................................\n",
      "[CV] ...................... C=400, gamma=1, score=0.782, total=   0.1s\n",
      "[CV] C=400, gamma=0.0001 .............................................\n",
      "[CV] ................. C=400, gamma=0.0001, score=0.784, total=   0.1s\n",
      "[CV] C=400, gamma=0.0001 .............................................\n",
      "[CV] ................. C=400, gamma=0.0001, score=0.774, total=   0.1s\n",
      "[CV] C=400, gamma=0.0001 .............................................\n",
      "[CV] ................. C=400, gamma=0.0001, score=0.782, total=   0.1s\n",
      "[CV] C=400, gamma=0.005 ..............................................\n",
      "[CV] .................. C=400, gamma=0.005, score=0.784, total=   0.1s\n",
      "[CV] C=400, gamma=0.005 ..............................................\n",
      "[CV] .................. C=400, gamma=0.005, score=0.774, total=   0.1s\n",
      "[CV] C=400, gamma=0.005 ..............................................\n",
      "[CV] .................. C=400, gamma=0.005, score=0.782, total=   0.1s\n",
      "[CV] C=400, gamma=0.001 ..............................................\n",
      "[CV] .................. C=400, gamma=0.001, score=0.784, total=   0.1s\n",
      "[CV] C=400, gamma=0.001 ..............................................\n",
      "[CV] .................. C=400, gamma=0.001, score=0.774, total=   0.1s\n",
      "[CV] C=400, gamma=0.001 ..............................................\n",
      "[CV] .................. C=400, gamma=0.001, score=0.782, total=   0.1s\n",
      "[CV] C=800, gamma=1 ..................................................\n",
      "[CV] ...................... C=800, gamma=1, score=0.784, total=   0.2s\n",
      "[CV] C=800, gamma=1 ..................................................\n",
      "[CV] ...................... C=800, gamma=1, score=0.774, total=   0.1s\n",
      "[CV] C=800, gamma=1 ..................................................\n",
      "[CV] ...................... C=800, gamma=1, score=0.782, total=   0.3s\n",
      "[CV] C=800, gamma=0.0001 .............................................\n",
      "[CV] ................. C=800, gamma=0.0001, score=0.784, total=   0.2s\n",
      "[CV] C=800, gamma=0.0001 .............................................\n",
      "[CV] ................. C=800, gamma=0.0001, score=0.774, total=   0.1s\n",
      "[CV] C=800, gamma=0.0001 .............................................\n",
      "[CV] ................. C=800, gamma=0.0001, score=0.782, total=   0.3s\n",
      "[CV] C=800, gamma=0.005 ..............................................\n",
      "[CV] .................. C=800, gamma=0.005, score=0.784, total=   0.2s\n",
      "[CV] C=800, gamma=0.005 ..............................................\n",
      "[CV] .................. C=800, gamma=0.005, score=0.774, total=   0.1s\n",
      "[CV] C=800, gamma=0.005 ..............................................\n",
      "[CV] .................. C=800, gamma=0.005, score=0.782, total=   0.3s\n",
      "[CV] C=800, gamma=0.001 ..............................................\n",
      "[CV] .................. C=800, gamma=0.001, score=0.784, total=   0.2s\n",
      "[CV] C=800, gamma=0.001 ..............................................\n",
      "[CV] .................. C=800, gamma=0.001, score=0.774, total=   0.1s\n",
      "[CV] C=800, gamma=0.001 ..............................................\n",
      "[CV] .................. C=800, gamma=0.001, score=0.782, total=   0.3s\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Done  48 out of  48 | elapsed:    4.6s finished\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv='warn', error_score='raise-deprecating',\n",
       "             estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
       "                           decision_function_shape='ovr', degree=3,\n",
       "                           gamma='auto_deprecated', kernel='linear',\n",
       "                           max_iter=-1, probability=False, random_state=None,\n",
       "                           shrinking=True, tol=0.001, verbose=False),\n",
       "             iid='warn', n_jobs=None,\n",
       "             param_grid={'C': [1, 200, 400, 800],\n",
       "                         'gamma': [1, 0.0001, 0.005, 0.001]},\n",
       "             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n",
       "             scoring=None, verbose=3)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the model with GridSearch\n",
    "grid.fit(X_train_scaled, np.ravel(y_train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'C': 200, 'gamma': 1}\n",
      "0.7802784665267977\n"
     ]
    }
   ],
   "source": [
    "print(grid.best_params_)\n",
    "print(grid.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions=grid.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['FALSE POSITIVE', 'CANDIDATE', 'FALSE POSITIVE', ..., 'CANDIDATE',\n",
       "       'CANDIDATE', 'CANDIDATE'], dtype=object)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                precision    recall  f1-score   support\n",
      "\n",
      "     CANDIDATE       0.46      0.99      0.63       411\n",
      "     CONFIRMED       0.00      0.00      0.00       484\n",
      "FALSE POSITIVE       0.98      1.00      0.99       853\n",
      "\n",
      "      accuracy                           0.72      1748\n",
      "     macro avg       0.48      0.66      0.54      1748\n",
      "  weighted avg       0.59      0.72      0.63      1748\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, predictions, ))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Save the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['OswaldVinueza.sav']"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# save your model by updating \"your_name\" with your name\n",
    "# and \"your_model\" with your model variable\n",
    "# be sure to turn this in to BCS\n",
    "# if joblib fails to import, try running the command to install in terminal/git-bash\n",
    "import joblib\n",
    "filename = 'OswaldVinueza.sav'\n",
    "joblib.dump(predictions, filename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernel_info": {
   "name": "dev"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  },
  "nteract": {
   "version": "0.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}