ML-For-Beginners/2-Regression/4-Logistic/solution/notebook.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Logistic Regression - Lesson 4\n",
    "\n",
    "Load up required libraries and dataset. Convert the data to a dataframe containing a subset of the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "   City Name Type       Package      Variety Sub Variety  Grade     Date  \\\n",
       "0  BALTIMORE  NaN  24 inch bins          NaN         NaN    NaN  4/29/17   \n",
       "1  BALTIMORE  NaN  24 inch bins          NaN         NaN    NaN   5/6/17   \n",
       "2  BALTIMORE  NaN  24 inch bins  HOWDEN TYPE         NaN    NaN  9/24/16   \n",
       "3  BALTIMORE  NaN  24 inch bins  HOWDEN TYPE         NaN    NaN  9/24/16   \n",
       "4  BALTIMORE  NaN  24 inch bins  HOWDEN TYPE         NaN    NaN  11/5/16   \n",
       "\n",
       "   Low Price  High Price  Mostly Low  ...  Unit of Sale Quality Condition  \\\n",
       "0      270.0       280.0       270.0  ...           NaN     NaN       NaN   \n",
       "1      270.0       280.0       270.0  ...           NaN     NaN       NaN   \n",
       "2      160.0       160.0       160.0  ...           NaN     NaN       NaN   \n",
       "3      160.0       160.0       160.0  ...           NaN     NaN       NaN   \n",
       "4       90.0       100.0        90.0  ...           NaN     NaN       NaN   \n",
       "\n",
       "  Appearance Storage  Crop Repack  Trans Mode  Unnamed: 24  Unnamed: 25  \n",
       "0        NaN     NaN   NaN      E         NaN          NaN          NaN  \n",
       "1        NaN     NaN   NaN      E         NaN          NaN          NaN  \n",
       "2        NaN     NaN   NaN      N         NaN          NaN          NaN  \n",
       "3        NaN     NaN   NaN      N         NaN          NaN          NaN  \n",
       "4        NaN     NaN   NaN      N         NaN          NaN          NaN  \n",
       "\n",
       "[5 rows x 26 columns]"
      ],
      "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>City Name</th>\n      <th>Type</th>\n      <th>Package</th>\n      <th>Variety</th>\n      <th>Sub Variety</th>\n      <th>Grade</th>\n      <th>Date</th>\n      <th>Low Price</th>\n      <th>High Price</th>\n      <th>Mostly Low</th>\n      <th>...</th>\n      <th>Unit of Sale</th>\n      <th>Quality</th>\n      <th>Condition</th>\n      <th>Appearance</th>\n      <th>Storage</th>\n      <th>Crop</th>\n      <th>Repack</th>\n      <th>Trans Mode</th>\n      <th>Unnamed: 24</th>\n      <th>Unnamed: 25</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>BALTIMORE</td>\n      <td>NaN</td>\n      <td>24 inch bins</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>4/29/17</td>\n      <td>270.0</td>\n      <td>280.0</td>\n      <td>270.0</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>E</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>BALTIMORE</td>\n      <td>NaN</td>\n      <td>24 inch bins</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>5/6/17</td>\n      <td>270.0</td>\n      <td>280.0</td>\n      <td>270.0</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>E</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>BALTIMORE</td>\n      <td>NaN</td>\n      <td>24 inch bins</td>\n      <td>HOWDEN TYPE</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>9/24/16</td>\n      <td>160.0</td>\n      <td>160.0</td>\n      <td>160.0</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>N</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>BALTIMORE</td>\n      <td>NaN</td>\n      <td>24 inch bins</td>\n      <td>HOWDEN TYPE</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>9/24/16</td>\n      <td>160.0</td>\n      <td>160.0</td>\n      <td>160.0</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>N</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>BALTIMORE</td>\n      <td>NaN</td>\n      <td>24 inch bins</td>\n      <td>HOWDEN TYPE</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>11/5/16</td>\n      <td>90.0</td>\n      <td>100.0</td>\n      <td>90.0</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>N</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 26 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 1
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "pumpkins = pd.read_csv('../../data/US-pumpkins.csv')\n",
    "\n",
    "pumpkins.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "new_columns = ['Color','Origin','Item Size','Variety','City Name','Package']\n",
    "\n",
    "new_pumpkins = pumpkins.drop([c for c in pumpkins.columns if c not in new_columns], axis=1)\n",
    "\n",
    "new_pumpkins.dropna(inplace=True)\n",
    "\n",
    "new_pumpkins = new_pumpkins.apply(LabelEncoder().fit_transform)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the data shape, size, and quality"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<bound method DataFrame.info of       City Name  Package  Variety  Origin  Item Size  Color\n",
       "2             1        3        4       3          3      0\n",
       "3             1        3        4      17          3      0\n",
       "4             1        3        4       5          2      0\n",
       "5             1        3        4       5          2      0\n",
       "6             1        4        4       5          3      0\n",
       "...         ...      ...      ...     ...        ...    ...\n",
       "1694         12        3        5       4          6      1\n",
       "1695         12        3        5       4          6      1\n",
       "1696         12        3        5       4          6      1\n",
       "1697         12        3        5       4          6      1\n",
       "1698         12        3        5       4          6      1\n",
       "\n",
       "[991 rows x 6 columns]>"
      ]
     },
     "metadata": {},
     "execution_count": 3
    }
   ],
   "source": [
    "new_pumpkins.info"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Working with Item Size to Color, create a scatterplot using Seaborn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x7fa3b8ae2668>"
      ]
     },
     "metadata": {},
     "execution_count": 4
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 1080x1080 with 36 Axes>",
      "image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"1058.15625pt\" version=\"1.1\" viewBox=\"0 0 1054.56875 1058.15625\" width=\"1054.56875pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <defs>\n  <style type=\"text/css\">\n*{stroke-linecap:butt;stroke-linejoin:round;white-space:pre;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 1058.15625 \nL 1054.56875 1058.15625 \nL 1054.56875 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n  </g>\n  <g id=\"axes_1\">\n   <g id=\"patch_2\">\n    <path d=\"M 43.78125 163.6 \nL 193.702083 163.6 \nL 193.702083 7.2 \nL 43.78125 7.2 \nz\n\" style=\"fill:#ffffff;\"/>\n   </g>\n   <g id=\"PathCollection_1\">\n    <defs>\n     <path d=\"M 0 3 \nC 0.795609 3 1.55874 2.683901 2.12132 2.12132 \nC 2.683901 1.55874 3 0.795609 3 0 \nC 3 -0.795609 2.683901 -1.55874 2.12132 -2.12132 \nC 1.55874 -2.683901 0.795609 -3 0 -3 \nC -0.795609 -3 -1.55874 -2.683901 -2.12132 -2.12132 \nC -2.683901 -1.55874 -3 -0.795609 -3 0 \nC -3 0.795609 -2.683901 1.55874 -2.12132 2.12132 \nC -1.55874 2.683901 -0.795609 3 0 3 \nz\n\" id=\"mb4aa9031fa\" style=\"stroke:#ffffff;stroke-width:0.48;\"/>\n    </defs>\n    <g clip-path=\"url(#pf514e1a819)\">\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"fill:#1f77b4;stroke:#ffffff;stroke-width:0.48;\" x=\"64.453472\" xlink:href=\"#mb4aa9031fa\" y=\"142.142425\"/>\n     <use style=\"f
      "image/png": "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
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "\n",
    "g = sns.PairGrid(new_pumpkins)\n",
    "g.map(sns.scatterplot)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/seaborn/categorical.py:1296: UserWarning: 80.6% of the points cannot be placed; you may want to decrease the size of the markers or use stripplot.\n  warnings.warn(msg, UserWarning)\n/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/seaborn/categorical.py:1296: UserWarning: 37.2% of the points cannot be placed; you may want to decrease the size of the markers or use stripplot.\n  warnings.warn(msg, UserWarning)\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa3580851d0>"
      ]
     },
     "metadata": {},
     "execution_count": 5
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"262.19625pt\" version=\"1.1\" viewBox=\"0 0 376.240625 262.19625\" width=\"376.240625pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <defs>\n  <style type=\"text/css\">\n*{stroke-linecap:butt;stroke-linejoin:round;white-space:pre;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 262.19625 \nL 376.240625 262.19625 \nL 376.240625 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n  </g>\n  <g id=\"axes_1\">\n   <g id=\"patch_2\">\n    <path d=\"M 34.240625 224.64 \nL 369.040625 224.64 \nL 369.040625 7.2 \nL 34.240625 7.2 \nz\n\" style=\"fill:#ffffff;\"/>\n   </g>\n   <g id=\"matplotlib.axis_1\">\n    <g id=\"xtick_1\">\n     <g id=\"line2d_1\">\n      <defs>\n       <path d=\"M 0 0 \nL 0 3.5 \n\" id=\"mcee3428d9b\" style=\"stroke:#000000;stroke-width:0.8;\"/>\n      </defs>\n      <g>\n       <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"117.940625\" xlink:href=\"#mcee3428d9b\" y=\"224.64\"/>\n      </g>\n     </g>\n     <g id=\"text_1\">\n      <!-- 0 -->\n      <defs>\n       <path d=\"M 31.78125 66.40625 \nQ 24.171875 66.40625 20.328125 58.90625 \nQ 16.5 51.421875 16.5 36.375 \nQ 16.5 21.390625 20.328125 13.890625 \nQ 24.171875 6.390625 31.78125 6.390625 \nQ 39.453125 6.390625 43.28125 13.890625 \nQ 47.125 21.390625 47.125 36.375 \nQ 47.125 51.421875 43.28125 58.90625 \nQ 39.453125 66.40625 31.78125 66.40625 \nz\nM 31.78125 74.21875 \nQ 44.046875 74.21875 50.515625 64.515625 \nQ 56.984375 54.828125 56.984375 36.375 \nQ 56.984375 17.96875 50.515625 8.265625 \nQ 44.046875 -1.421875 31.78125 -1.421875 \nQ 19.53125 -1.421875 13.0625 8.265625 \nQ 6.59375 17.96875 6.59375 36.375 \nQ 6.59375 54.828125 13.0625 64.515625 \nQ 19.53125 74.21875 31.78125 74.21875 \nz\n\" id=\"DejaVuSans-48\"/>\n      </defs>\n      <g transform=\"translate(114.759375 239.238437)scale(0.1 -0.1)\">\n       <use xlink:href=\"#DejaVuSans-48\"/>\n      </g>\n     </g>\n    </g>\n    <g id=\"xtick_2\">\n     <g id=\"line2d_2\">\n      <g>\n       <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"285.340625\" xlink:href=\"#mcee3428d9b\" y=\"224.64\"/>\n      </g>\n     </g>\n     <g id=\"text_2\">\n      <!-- 1 -->\n      <defs>\n       <path d=\"M 12.40625 8.296875 \nL 28.515625 8.296875 \nL 28.515625 63.921875 \nL 10.984375 60.40625 \nL 10.984375 69.390625 \nL 28.421875 72.90625 \nL 38.28125 72.90625 \nL 38.28125 8.296875 \nL 54.390625 8.296875 \nL 54.390625 0 \nL 12.40625 0 \nz\n\" id=\"DejaVuSans-49\"/>\n      </defs>\n      <g transform=\"translate(282.159375 239.238437)scale(0.1 -0.1)\">\n       <use xlink:href=\"#DejaVuSans-49\"/>\n      </g>\n     </g>\n    </g>\n    <g id=\"text_3\">\n     <!-- Color -->\n     <defs>\n      <path d=\"M 64.40625 67.28125 \nL 64.40625 56.890625 \nQ 59.421875 61.53125 53.78125 63.8125 \nQ 48.140625 66.109375 41.796875 66.109375 \nQ 29.296875 66.109375 22.65625 58.46875 \nQ 16.015625 50.828125 16.015625 36.375 \nQ 16.015625 21.96875 22.65625 14.328125 \nQ 29.296875 6.6875 41.796875 6.6875 \nQ 48.140625 6.6875 53.78125 8.984375 \nQ 59.421875 11.28125 64.40625 15.921875 \nL 64.40625 5.609375 \nQ 59.234375 2.09375 53.4375 0.328125 \nQ 47.65625 -1.421875 41.21875 -1.421875 \nQ 24.65625 -1.421875 15.125 8.703125 \nQ 5.609375 18.84375 5.609375 36.375 \nQ 5.609375 53.953125 15.125 64.078125 \nQ 24.65625 74.21875 41.21875 74.21875 \nQ 47.75 74.21875 53.53125 72.484375 \nQ 59.328125 70.75 64.40625 67.28125 \nz\n\" id=\"DejaVuSans-67\"/>\n      <path d=\"M 30.609375 48.390625 \nQ 23.390625 48.390625 19.1875 42.75 \nQ 14.984375 37.109375 14.984375 27.296875 \nQ 14.984375 17.484375 19.15625 11.84375 \nQ 23.34375 6.203125 30.609375 6.203125 \nQ 37.796875 6.203125 41.984375 11.859375 \nQ 46.1875 17.53125 46.1875 27.296875 \nQ 46.1875 37.015625 41.984375 42.703125 \nQ 37.796875 48.390625 30.60
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAEGCAYAAABvtY4XAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nO3deXyU9bn38c+VnT0IYREJAQQRWSXgvtu64FKt1eKpFotirWufnlbbp62hPbVq69Pt6Klo61K3o10sinVfwLpAUFYFZJWwJkQCCWS/nj8mJJnMZIFkSObO9/165UXua373df9I7nznnt9MJubuiIhI8CS09wRERCQ2FPAiIgGlgBcRCSgFvIhIQCngRUQCKqm9J1Bf3759PSsrq72nISISNxYtWlTg7hnRbutQAZ+VlUVubm57T0NEJG6Y2cbGbtMSjYhIQCngRUQCSgEvIhJQCngRkYBSwIuIBJQCXkQkoBTwIiIBpYAXEQmomP6ik5mlAw8DYwAHvuXu77f1cbLumBu2fe0JSXxRNoC8L/Zy/tiBXH3CEEorqvnDm5+xYH0hEzPTufXskXRPTeKZBZ/z/OLNDOiZxi1njWBYRnc+WLeTh+ato9qda04ayqkjM9hUuJffvv6ZesZRzzvnrAg7LzbcPbWtT71Db28hvHMPbF0CQ0+DU74HCUnwwQOwci70PRJO/yH0PBxW/QsWPATJXeCk22DwZNj+Ccz7FewtgAnfgPFXqGdrenZwFss/+GFmjwHz3f1hM0sBurr7rsbGZ2dn+4H+Juv8+fO5au7uJsf8/OJjWJpXxHOL8mprU8cO5MxR/fjec0tqawN6pvH4jClc8Pt3Ka+qBiAxwZhz40nc+NRHbNi5N9g9vzWFC/4Q3vOfN57ETXHaM5q4D/m/XApr36jbPu7b0L0/vDGrrtZ/LEy9D/58DqHrKiC5K1w/L1Tbu7Nu7BVPQO4j6nkwPW9eFAr+dmZmi9w9O9ptiTk5ObE6aC/gl8D0nJwccnJyqnJyckqb2mf27Nk5M2fOPKDjnPY/y5sdU1pRzb/X7qwNBIB1BSVUVFWxvqAuEIrLKgH4eFPdfZA7mMH8zwoC1rOa9QUlzfYEmL8mPntGc9vZI5sd02GVFcOcm8JruzdDUR4Ub6urlewIfVG2La2rVVeEsmnju+H7u8Pql9qvJ8C2ujtwqisAhw1x0LPvSDh8Au1t1qxZW3NycmZHuy2Wa/BDgXzgETP72MweNrNuDQeZ2UwzyzWz3Pz8/JhMZPBhXRh8WNew2qD0LmT2CZ9OgsHRA3tE7D+yfw+SEy1gPcNrjfU8akD3uO0ZOMldQleX9fXOCn2EjesK/UZF7j9wXGStz7D27ZkRpeeAOOnZcFwHFMuATwKOBf7H3ScCJcAdDQe5+2x3z3b37IyMqG+I1qTGHnLv/2EfltGNW84aQc6Fo0nvmgxAj7Qkfv6VMdxw+nBGDQiFRVKC8d2zR3LF5EwuGDewts/ZR/dn2pRMbj93VCftOSRuewZOQmJoqSCle2i7Wz845xdw5k8gfUiolpgK59wFk6+FYafX7Ggw8Ruhj5O/C1bzY3/4RDjhpnbuOSNKz6vio+fQ01r4jWtH7h6TD2AAsKHe9inA3Kb2mTRpkh+sIbe/6ENuf9G/98w8d3cv2FPqyzfv8qqq6tox+8orfemmXV5SVlFbq66u9k+2FPmO3aVh/TYWlPi6/OKwmnrGX8/958W8efM8MEp3u2/+2L2irK5WVem+ZbF7yc7wsfmr3b/YGF4r2uK+bYV6tlXPdgbkeiOZGusnWecD17r7KjPLAbq5+/cbG38wT7KKiHRmTT3JGuv3g78ZeLLmFTTrgGtifDwREakR04B398VA1HsWERGJLf0mq4hIQCngRUQCSgEvIhJQCngRkYBSwIuIBJQCXkQkoBTwIiIBpYAXEQkoBbyISEAp4EVEAkoBLyISUAp4EZGAUsCLiASUAl5EJKAU8CIiAaWAFxEJKAW8iEhAKeBFRAJKAS8iElAKeBGRgFLAi4gElAJeRCSgFPAiIgEV04A3sw1mtszMFptZbiyPlXXH3NoPgLX5xby9agf7yqtqx+wsLuPNldvZsbu0tlZaUcW81fms3r6ntubuLNpYyIL1hVRXe21dPeOvZ8Pzol08eink9Ap9AJTtgc9eg51r68ZUV8H6+ZC3KHzfbctg7VtQWV5XK9oMq1+BvYV1NfWMv56/mRh+XsSAuXvzow62udkGINvdC1oyPjs723NzD/x+oKkf3r7dU3hm5vFsKNjLd576iPLKapITjfsun8CEI9K5Yvb7bC0Khcn0E7P40flHc/WfP+SDdaFvzITB6Tx93fH84c3PeODtteoZRz0Liuv9wNXYcPfUlp1UbSXaD2+X3rDvC8DgzB/DlOvgkamwfVno9hFfhmnPwJybYfGToVrvLLjmX7DmdXjhNvAqSO4K054O9Xv8YvWMp55Eyd2copacURHMbJG7Z0e7LTEnJ+egmrbErFmzbgNm5+Tk7G3J+NmzZ+fMnDnzgI7R3JXZ3vIqdu+r4K8f5dX+wFc7fPz5LnbuLef9tTtrxy7etIteXZN56sNNtbVtu0vpmZbE7974rPZbEtSe6QHrGc1tZ4+MWo+Zt++OrFXWPTrh8w8gKQ2W/7WuVrg2FAjv/qauVroLMHjv91BR8+NUXQH5q2DL4rrgCWxPgtUzms/mw6T/aHpMFLNmzdqak5MzO9ptSQfc7cA48KqZOfCgu0dMwsxmAjMBMjMzYzKJguJyCvaUhdUKS8rJr7cMsF9e4b6I2uZd+6hucIcb7z0b1oLYMy5UlcPuzZH1XZ9H1vZsg9IGV3nF+WCJnaDn9mD1jGbroubHHKBYP8l6srsfC5wH3GhmpzYc4O6z3T3b3bMzMjIO+AAtecj91UmD+OqkI8Jql0wcxGXZg8NqwzK6MePkoXRLqftmpCYlMP3ELEYP7Bmong1rwzK68a2A9YwLmSfC5BmQkFxXS0uHE26CXvW/7wYTvwGjLw7ff8K00Eeget4c/J7R/HR782MOUEzX4MMOZJYDFLv7rxsb01Zr8It+fDYPv7ueTYV7mTp2IOeNHUhlVTV/+WAjCzcUMmFwOtNPHEpKUgJvfLqd5xdvYUDPVK47ZRj9eqaxcttuHntvA1XVzlXHZzH2iF7sLC5TzzjrecOTH4WdF4d8/X2/+uvwqb1h6q9g1Vzoc2QoILukw6YFkPsIJKfBcTdAxkjYtQk+eABK8mHClTD8TKjYF6ptXQJDT4NJ10BCAix9Tj3jrec9Q+rOi77j4Kb5B3V6NbUGH7OAN7NuQIK776n5/DXgZ+7+cmP7HGzAi4h0Vk0FfCzX4PsD/zCz/cd5qqlwFxGRthWzgHf3dcD4WPUXEZGm6TdZRUQCSgEvIhJQCngRkYBSwIuIBJQCXkQkoBTwIiIBpYAXEQkoBbyISEAp4EVEAkoBLyISUAp4EZGAUsCLiASUAl5EJKAU8CIiAaWAFxEJKAW8iEhAKeBFRAJKAS8iElAKeBGRgFLAi4gElAJeRCSgFPAiIgGlgBcRCaiYB7yZJZrZx2b2YqyPJSIidZIOwTFuBT4FesbqAFl3zA3bvv74TNbvLiPvi32cP3YA3zn9SErKK7n35VUsWF/IxMx0bj93FOldk3l4/nqeX7yZAT3T+N6Xj2L04T15c+V2/vj2OqrdmXHyUM4bO5A1O/Zw78ur1DOOev761dVh58U7N4xhyJAhsToN40PeInj7LigpgInfgCnXwZ7t8HoObF0Cw06DM38CiSkw715YORf6HAln3wmHDYOlz8KC2ZCUBqd8D4afET89OyFz99g1NzsCeAz4BfB/3P2CpsZnZ2d7bm7uAR3j7c82MP1PK5oc8+OpR7M0r4g5S7bU1s4+uh9njurPj/6xrLbWt3sKj14zmYvvf4+qaq/5P8Dfv30iNz71EVuKSgPecwoX3//v8J43nMiNT8Znz2g23D21ydsDrbQIfjMWyorqal/9E+Q+AhvfratNmg7dB8A7d9fV+o6E8++Dxy+sqyWmwHVvwSPnH3zPqff
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "sns.swarmplot(x=\"Color\", y=\"Item Size\", data=new_pumpkins)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7fa3e8a91320>"
      ]
     },
     "metadata": {},
     "execution_count": 6
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 360x360 with 1 Axes>",
      "image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"366.15625pt\" version=\"1.1\" viewBox=\"0 0 366.470312 366.15625\" width=\"366.470312pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <defs>\n  <style type=\"text/css\">\n*{stroke-linecap:butt;stroke-linejoin:round;white-space:pre;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 366.15625 \nL 366.470312 366.15625 \nL 366.470312 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n  </g>\n  <g id=\"axes_1\">\n   <g id=\"patch_2\">\n    <path d=\"M 42.620313 328.6 \nL 359.270312 328.6 \nL 359.270312 7.2 \nL 42.620313 7.2 \nz\n\" style=\"fill:#ffffff;\"/>\n   </g>\n   <g id=\"PolyCollection_1\">\n    <defs>\n     <path d=\"M 122.072034 -52.165341 \nL 121.493591 -52.165341 \nL 121.375819 -55.000167 \nL 121.227151 -57.834992 \nL 121.046341 -60.669818 \nL 120.834389 -63.504644 \nL 120.594591 -66.33947 \nL 120.331957 -69.174296 \nL 120.051876 -72.009121 \nL 119.758106 -74.843947 \nL 119.45037 -77.678773 \nL 119.122081 -80.513599 \nL 118.75887 -83.348424 \nL 118.338621 -86.18325 \nL 117.833506 -89.018076 \nL 117.214174 -91.852902 \nL 116.455645 -94.687728 \nL 115.543896 -97.522553 \nL 114.481643 -100.357379 \nL 113.291582 -103.192205 \nL 112.015627 -106.027031 \nL 110.709303 -108.861856 \nL 109.43161 -111.696682 \nL 108.231883 -114.531508 \nL 107.13636 -117.366334 \nL 106.137791 -120.20116 \nL 105.191355 -123.035985 \nL 104.219132 -125.870811 \nL 103.123658 -128.705637 \nL 101.808838 -131.540463 \nL 100.204437 -134.375288 \nL 98.288812 -137.210114 \nL 96.104251 -140.04494 \nL 93.760286 -142.879766 \nL 91.422659 -145.714592 \nL 89.288817 -148.549417 \nL 87.554104 -151.384243 \nL 86.375416 -154.219069 \nL 85.840226 -157.053895 \nL 85.948148 -159.88872 \nL 86.609674 -162.723546 \nL 87.662933 -165.558372 \nL 88.905156 -168.393198 \nL 90.132143 -171.228024 \nL 91.177109 -174.062849 \nL 91.940483 -176.897675 \nL 92.404383 -179.732501 \nL 92.629056 -182.567327 \nL 92.732757 -185.402152 \nL 92.860196 -188.236978 \nL 93.147082 -191.071804 \nL 93.688876 -193.90663 \nL 94.520493 -196.741455 \nL 95.610864 -199.576281 \nL 96.872649 -202.411107 \nL 98.183854 -205.245933 \nL 99.415544 -208.080759 \nL 100.458725 -210.915584 \nL 101.244092 -213.75041 \nL 101.750356 -216.585236 \nL 101.999858 -219.420062 \nL 102.043314 -222.254887 \nL 101.938159 -225.089713 \nL 101.72646 -227.924539 \nL 101.418401 -230.759365 \nL 100.985978 -233.594191 \nL 100.369006 -236.429016 \nL 99.492492 -239.263842 \nL 98.29144 -242.098668 \nL 96.737062 -244.933494 \nL 94.85756 -247.768319 \nL 92.747538 -250.603145 \nL 90.562422 -253.437971 \nL 88.497764 -256.272797 \nL 86.756927 -259.107623 \nL 85.513809 -261.942448 \nL 84.878843 -264.777274 \nL 84.876249 -267.6121 \nL 85.438219 -270.446926 \nL 86.417982 -273.281751 \nL 87.619355 -276.116577 \nL 88.836553 -278.951403 \nL 89.895643 -281.786229 \nL 90.688686 -284.621055 \nL 91.193334 -287.45588 \nL 91.474101 -290.290706 \nL 91.665642 -293.125532 \nL 91.942351 -295.960358 \nL 92.481351 -298.795183 \nL 93.426942 -301.630009 \nL 94.86371 -304.464835 \nL 96.80302 -307.299661 \nL 99.184309 -310.134487 \nL 101.889318 -312.969312 \nL 104.764869 -315.804138 \nL 107.648648 -318.638964 \nL 110.392687 -321.47379 \nL 112.880605 -324.308615 \nL 115.036708 -327.143441 \nL 116.827049 -329.978267 \nL 118.25412 -332.813093 \nL 125.311505 -332.813093 \nL 125.311505 -332.813093 \nL 126.738576 -329.978267 \nL 128.528917 -327.143441 \nL 130.68502 -324.308615 \nL 133.172938 -321.47379 \nL 135.916977 -318.638964 \nL 138.800756 -315.804138 \nL 141.676307 -312.969312 \nL 144.381316 -310.134487 \nL 146.762605 -307.299661 \nL 148.701915 -304.464835 \nL 150.138683 -301.630009 \nL 151.084274 -298.795183 \nL 151.623274 -295.960358 \nL 151.899983 -293.125532 \nL 152.091524 -290.290706 \nL 152.372291 -287.45588 \nL 152.876939 -
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAW4AAAFuCAYAAAChovKPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nOzdd3xUVcL/8c+Znt4JJUCAQOhNrKgoYEGwu/Z1H3VFXQtgWVGxrFjW7q7rumtZ19+jz9rbiqKugoKKFOkdAiGN9D595vz+SOJaKAmZmXNn5rxfL15KEu79AuE7d8499xwhpUTTNE2LHibVATRN07Su0cWtaZoWZXRxa5qmRRld3JqmaVFGF7emaVqUsagO0BWnnnqqXLhwoeoYmqZpkSL29cGouuKuqalRHUHTNE25qCpuTdM0TRe3pmla1NHFrWmaFmV0cWuapkUZXdyapmlRRhe3pmlalNHFrWmaFmV0cWuapkUZXdyapmlRRhe3pmlalNHFrWmaFmV0cWuapkWZqFodUNO06NDc3ExRUdEPPxdCUFhYiN1uV5gqduji1jQt5B577DG+/PLLn3zsoosu4uqrr1aUKLbo4tY0LeQ2bVjPqEwv0/u5APi/Hcls3LBBcarYoce4NU0Lqfr6eqpr6xiZ6WN4pp/hmX6GpPnYvn0bwWBQdbyYoItb07SQ2rJlCwD5Kf4fPjYg1Y/L7aG4uFhVrJiirLiFEIVCiDU/+tEkhJitKo+maaGxbt06zCYYmPrf4h6S5gNg/fr1qmLFFGXFLaXcKqUcK6UcCxwGOIF3VeXRNC001q1bS35KALv5vx/rkRAkzd5W6lr3GWWoZAqwU0qp30dpWhRraWlhy5YtDEv3/uTjQsCwNA+rVq7Q49whYJTivhD4174+IYSYKYRYKYRYWV1dHeFYmqZ1xerVqwkEgozO9P7ic6OyfNQ3NLJz504FyWKL8uIWQtiAM4A39/V5KeVzUsoJUsoJOTk5kQ2naVqXfPfddyRYoCDN/4vPjWov8++++y7SsWKO8uIGpgHfSykrVQfRNO3Q+f1+ln71JWMyPVj20SzpdsmgtABffbk44tlijRGK+yL2M0yiaVr0WL9+PQ1NzRze45fDJB0Oz3GzbfsOKioqIpgs9ih9clIIkQScBOjnYEPs888/57PPPtvv5wsLC7n88ssjmEiLdf/5z3+wm2F01oGK28trO5L4/PPPufTSSyOYLrYoLW4pZSuQpTJDLGppaeHxJ56g1SuRtqRffF4EvCxbtowjjzyS4cOHK0ioxRqXy8WiLz7n8Bz3T6YB/lxOQpDCdD8ff7SASy65BCFE5ELGEL1WSQx6++23cba24hx+BsGk7F9+QcBH6vo3eemlf/Loo49EPqAWc5YsWYLT5eb4oZ6Dfu3xvdw8v7mC9evXM3r06Aikiz1GGOPWQqihoYHX33gDf3q/fZc2gNmKO3ckK1Ys1w9EaCHx3rvv0DNJMiT9l7NJfu7wHA+JVnjvvfcikCw26eKOMc8++yxOpwtP3mEH/Dpvj2FgT+axxx/H5/NFKJ0WizZv3symzVuY2tuJqRMjHw4LHNfTxZdfLkY/m3FodHHHkFWrVvHJJ5/g6TmSYELGgb/YbMXZ7yj2FBfz2muvRSagFpPefPNNEixwXK+DD5N0mNrHTTAQ1Ffdh0gXd4xoaWnhkUcfhYRUvL3HdurXBNL74cvI5+WX/59+mk07JKWlpSxetIgTertIsMhO/7rcxCATcjy8+87bNDc3hzFhbNLFHQOklDz88MNUVlbi7H8cmDp/z9nT/2gCJivz7rqb1tbWMKbUYtErr7yC2SSZ1tfV5V97Rr4Lp8vNu+/qteW6Shd3DHjrrbdYsmQJ7rwJBFJyu/RrpTWB1oEnUFFRzqOPPoqUnb9q0uJbSUkJn332KSf2cpFu7/r3Tf+UAOOyvbzx+ms0NTWFIWHs0sUd5VauXMmzz/4Nf3o/fLkjD+kYgZSeePqMZ/Hixfzf//1fiBNqser555/HKiSn53f9arvDuQOdtLY6efXVV0OYLPbp4o5iO3bsYN5ddxFwpOEacHzb2pmHyNtzNL7MgTz//PP85z//CWFKLRZt3LiRr776iml9W0mzHfq7tH7JASb2dPPOO2+zd+/eECaMbbq4o1RVVRW/v+023EETrYNPAoutewcUAveA4wik9OShhx5i9erVoQmqxZxAIMCf//QU6Q4OaWz7584d6EIE/Tz77F9DkC4+6OKOQrW1tcyeM4f6xmZaC07a52Pth8RkxlkwBb89ldtvv4NNmzaF5rhaTFmwYAFbt23nooHNOELw7HWWI8gZ/Z18+eVXrFixovsHjAO6uKNMQ0MDs+fcRMXeKloLTiKYmBnaE1jstA4+GTdWbr7lFrZt2xba42tRrb6+nuef+ztD0/0clbv/xaS6alo/Fz2TJE89+QQeT+fng8crXdxRpKmpiZtuvpnS0jJaC6Z2eQZJZ0lbEi1DTsUVNDPnppv1HG/tB0899SQuZyu/KWzpzi2VX7Ca4DeDmygrr+Cll14K3YFjlC7uKNF2pT2Hol27aS2YTCC1V1jPJ+3JtAw+hVZfkFmzZ7Njx46wnk8zvsWLF/Pll19xdn4rfZICIT/+iEw/J/R288brr+thuoPQxR0FGhoamD27rbSdBVMIpOVF5LzSkUrLkGm0eCWzZs/RwyZxrLa2liefeJwBqQFO6+cO23kuKnCS4ZA8+MD9uFzdv/EZq3RxG1xdXR2zZs+muKQEZ8HUiJV2B+lIpaVwGq1+mD1nDlu2bIno+TX1gsEgDz7wAK7WZmYOa8YcxtZIsEiuGtpIWVk5Tz/9dPhOFOV0cRtYbW0tN86axZ6SMloLTiKQ1kdJDmlPoWXINJwBM3Nuukm/jY0zr7/+Oqu+/55LB7eEZYjk54Zn+JnR38lHH33EokWLwn6+aKSL26Cqq6u54cYbKSvfS+vgk8I+pn0w0p7cfsPSwk0338yGDRuU5tEiY/Xq1Tz//PMc0cPDpC6s/tddZw9wUZAW4JGH/0hxcXHEzhstdHEbUNuV9uy2KX+DTyKQ0lN1JKC9vAun4cbGzbfcwsaNG1VH0sKoqqqKP9xzNz0TAlw5tDWks0gOxmKC60c0YZUe7pp3p14A7Wd0cRtMxzztvZVVtAw+2TCl3aFtquA0PMLGLbfeyvbt21VH0sLA4/Fw99134Xa2cOPIhi4t2RoqmY4g1w1vpLS0lIcefJBgMBjxDEali9tAmpubufmWW36Ypx0M0zzt7pK2RFoGn4orYOKmm25m9+7dqiNpIRQMBnnwwQfZumUrM4c10TtJXWEOy/BzUUErS7/+mueee05ZDqPRxW0QXq+X2++4g51FRbQOOlH5mPbBdIx5N3v8zLnpJqqqqlRH0kLkxRdf5Msvv+T8Qa1MyAnd05GH6uQ8N5P7uHnttdf48MMPVccxBF3cBiCl5PHHH2fD+vW48o8jkN5XdaROkY5UWgefTENTC7fffoeedxsD3n//fV599VVO6O0O63ztrhACfj24ldFZPp544gm+/fZb1ZGU08VtAP/617/a9orsPRZ/1iDVcbokmJhJ64BJ7CzayQMPPKDHIaPYF198wVNPPcmYLC+XDYnszciDMZvguhHN9E/2cc/dd7Nu3TrVkZTSxa3YmjVreO755/FlDsDbe5zqOIckkN4Xd94RLF26lNdff111HO0QLF++nAcfeIAhaX5uGNmMxYDNkGCR3Dy6kSybl7m33RbXN8YN+NcTP1pbW3nwwYfAkYo7/9hubYSgmi93OP6MfF548UWKiopUx9G6YOXKlcy78076JPqYM7oJm1l1ov1LtUl+P6aBBFzcfNOcuF0ATRe3Qs888wxV1VW05h8HZqvqON0jBO7+RxM0WZl///34fD7VibROWLlyJXfcfju5dg+/H9NAooJpf12V5Qgyd0w9Fl8Lc2bPisvyVlrcQoh0IcRbQogtQojNQoijVeaJpM2bN/PRRx/hyR1JMLmH6jghIa0JOPsdw66iIj744APVcbSDWLFixQ+lPXdsAynd2IIs0nITg9w
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "sns.catplot(x=\"Color\", y=\"Item Size\",\n",
    "            kind=\"violin\", data=new_pumpkins)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "Selected_features = ['Origin','Item Size','Variety','City Name','Package']\n",
    "\n",
    "X = new_pumpkins[Selected_features]\n",
    "y = new_pumpkins['Color']\n",
    "\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.83      0.98      0.90       166\n",
      "           1       0.00      0.00      0.00        33\n",
      "\n",
      "    accuracy                           0.81       199\n",
      "   macro avg       0.42      0.49      0.45       199\n",
      "weighted avg       0.69      0.81      0.75       199\n",
      "\n",
      "Predicted labels:  [0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0\n",
      " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
      " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
      " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0\n",
      " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
      " 0 0 0 0 0 1 0 0 0 0 0 0 0 0]\n",
      "Accuracy:  0.8140703517587939\n",
      "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score, classification_report \n",
    "from sklearn.linear_model import LogisticRegression\n",
    "model = LogisticRegression()\n",
    "model.fit(X_train, y_train)\n",
    "predictions = model.predict(X_test)\n",
    "\n",
    "print(classification_report(y_test, predictions))\n",
    "print('Predicted labels: ', predictions)\n",
    "print('Accuracy: ', accuracy_score(y_test, predictions))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "array([[162,   4],\n",
       "       [ 33,   0]])"
      ]
     },
     "metadata": {},
     "execution_count": 9
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "confusion_matrix(y_test, predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n  FutureWarning\n/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n  FutureWarning\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7fa3c8a0f710>"
      ]
     },
     "metadata": {},
     "execution_count": 10
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"248.518125pt\" version=\"1.1\" viewBox=\"0 0 372.103125 248.518125\" width=\"372.103125pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <defs>\n  <style type=\"text/css\">\n*{stroke-linecap:butt;stroke-linejoin:round;white-space:pre;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 248.518125 \nL 372.103125 248.518125 \nL 372.103125 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n  </g>\n  <g id=\"axes_1\">\n   <g id=\"patch_2\">\n    <path d=\"M 30.103125 224.64 \nL 364.903125 224.64 \nL 364.903125 7.2 \nL 30.103125 7.2 \nz\n\" style=\"fill:#ffffff;\"/>\n   </g>\n   <g id=\"PolyCollection_1\">\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 61.82295 202.776198 \nL 61.82295 214.756364 \nL 69.157013 190.796033 \nL 76.491077 174.323306 \nL 76.491077 148.865455 \nL 76.491077 148.865455 \nL 69.157013 178.815868 \nL 61.82295 202.776198 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 92.99272 118.915041 \nL 92.99272 130.895207 \nL 92.99272 118.915041 \nL 92.99272 118.915041 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 124.16249 82.974545 \nL 124.16249 88.964628 \nL 124.16249 82.974545 \nL 124.16249 82.974545 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 142.497649 76.984463 \nL 142.497649 82.974545 \nL 146.16468 76.984463 \nL 146.16468 65.004298 \nL 146.16468 65.004298 \nL 142.497649 76.984463 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 175.500934 59.014215 \nL 175.500934 65.004298 \nL 175.500934 59.014215 \nL 175.500934 59.014215 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 184.668514 53.024132 \nL 184.668514 59.014215 \nL 184.668514 53.024132 \nL 184.668514 53.024132 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 234.173443 41.043967 \nL 234.173443 53.024132 \nL 234.173443 41.043967 \nL 234.173443 41.043967 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 314.848141 35.053884 \nL 314.848141 41.043967 \nL 314.848141 35.053884 \nL 314.848141 35.053884 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n    <path clip-path=\"url(#pfd33e0a8e5)\" d=\"M 333.1833 23.073719 \nL 333.1833 35.053884 \nL 333.1833 23.073719 \nL 333.1833 23.073719 \nz\n\" style=\"fill:#ff7f0e;fill-opacity:0.2;stroke:#ff7f0e;stroke-opacity:0.2;\"/>\n   </g>\n   <g id=\"matplotlib.axis_1\">\n    <g id=\"xtick_1\">\n     <g id=\"line2d_1\">\n      <defs>\n       <path d=\"M 0 0 \nL 0 3.5 \n\" id=\"m729210be6a\" style=\"stroke:#000000;stroke-width:0.8;\"/>\n      </defs>\n      <g>\n       <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"45.321307\" xlink:href=\"#m729210be6a\" y=\"224.64\"/>\n      </g>\n     </g>\n     <g id=\"text_1\">\n      <!-- 0.0 -->\n      <defs>\n       <path d=\"M 31.78125 66.40625 \nQ 24.171875 66.40625 20.328125 58.90625 \nQ 16.5 51.421875 16.5 36.375 \nQ 16.5 21.390625 20.328125 13.890625 \nQ 24.171875 6.390625 31.78125 6.390625 \nQ 39.453125 6.390625 43.28125 13.890625 \nQ 47.125 21.390625 47.125 36.375 \nQ 47.125 51.421875 43.28125 58.90625 \nQ 39.453125 66.40625 31.78125 66.40625 \nz\nM 31.78125 74.21875 \nQ 44.046875 74.21875 50.515625 64.515625 \nQ 56.984375 54.828125 56.984375 36.375 \nQ 56.984375 17.96875 50.515625 8.265625 \nQ 44.046875 -1.421875 31.
      "image/png": "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
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "from sklearn.metrics import roc_curve, roc_auc_score\n",
    "\n",
    "y_scores = model.predict_proba(X_test)\n",
    "# calculate ROC curve\n",
    "fpr, tpr, thresholds = roc_curve(y_test, y_scores[:,1])\n",
    "sns.lineplot([0, 1], [0, 1])\n",
    "sns.lineplot(fpr, tpr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "0.6997079225994889\n"
     ]
    }
   ],
   "source": [
    "auc = roc_auc_score(y_test,y_scores[:,1])\n",
    "print(auc)"
   ]
  }
 ],
 "metadata": {
  "environment": {
   "name": "tf2-gpu.2-4.m65",
   "type": "gcloud",
   "uri": "gcr.io/deeplearning-platform-release/tf2-gpu.2-4:m65"
  },
  "kernelspec": {
   "name": "python37364bit8d3b438fb5fc4430a93ac2cb74d693a7",
   "display_name": "Python 3.7.0 64-bit ('3.7')"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  },
  "metadata": {
   "interpreter": {
    "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}