ML-For-Beginners/2-Regression/3-Linear/solution/notebook.ipynb

{
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3-final"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3",
   "language": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2,
 "cells": [
  {
   "source": [
    "## Linear and Polynomial Regression for Pumpkin Pricing - Lesson 3\n",
    "\n",
    "Load up required libraries and dataset. Convert the data to a dataframe containing a subset of the data: \n",
    "\n",
    "- Only get pumpkins priced by the bushel\n",
    "- Convert the date to a month\n",
    "- Calculate the price to be an average of high and low prices\n",
    "- Convert the price to reflect the pricing by bushel quantity"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "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": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "    Month  Variety  City  Package  Low Price  High Price      Price\n",
       "70      1        3     1        0          5           3  13.636364\n",
       "71      1        3     1        0         10           7  16.363636\n",
       "72      2        3     1        0         10           7  16.363636\n",
       "73      2        3     1        0          9           6  15.454545\n",
       "74      2        3     1        0          5           3  13.636364"
      ],
      "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>Month</th>\n      <th>Variety</th>\n      <th>City</th>\n      <th>Package</th>\n      <th>Low Price</th>\n      <th>High Price</th>\n      <th>Price</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>70</th>\n      <td>1</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>5</td>\n      <td>3</td>\n      <td>13.636364</td>\n    </tr>\n    <tr>\n      <th>71</th>\n      <td>1</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>10</td>\n      <td>7</td>\n      <td>16.363636</td>\n    </tr>\n    <tr>\n      <th>72</th>\n      <td>2</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>10</td>\n      <td>7</td>\n      <td>16.363636</td>\n    </tr>\n    <tr>\n      <th>73</th>\n      <td>2</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>9</td>\n      <td>6</td>\n      <td>15.454545</td>\n    </tr>\n    <tr>\n      <th>74</th>\n      <td>2</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>5</td>\n      <td>3</td>\n      <td>13.636364</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "metadata": {},
     "execution_count": 2
    }
   ],
   "source": [
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "pumpkins = pumpkins[pumpkins['Package'].str.contains('bushel', case=True, regex=True)]\n",
    "\n",
    "new_columns = ['Package', 'Variety', 'City Name', 'Month', 'Low Price', 'High Price', 'Date']\n",
    "\n",
    "pumpkins = pumpkins.drop([c for c in pumpkins.columns if c not in new_columns], axis=1)\n",
    "\n",
    "price = (pumpkins['Low Price'] + pumpkins['High Price']) / 2\n",
    "\n",
    "month = pd.DatetimeIndex(pumpkins['Date']).month\n",
    "\n",
    "new_pumpkins = pd.DataFrame({'Month': month, 'Variety': pumpkins['Variety'], 'City': pumpkins['City Name'], 'Package': pumpkins['Package'], 'Low Price': pumpkins['Low Price'],'High Price': pumpkins['High Price'], 'Price': price})\n",
    "\n",
    "new_pumpkins.loc[new_pumpkins['Package'].str.contains('1 1/9'), 'Price'] = price/1.1\n",
    "\n",
    "new_pumpkins.loc[new_pumpkins['Package'].str.contains('1/2'), 'Price'] = price*2\n",
    "\n",
    "new_pumpkins.iloc[:, 0:-1] = new_pumpkins.iloc[:, 0:-1].apply(LabelEncoder().fit_transform)\n",
    "\n",
    "new_pumpkins.head()\n"
   ]
  },
  {
   "source": [
    "A scatterplot reminds us that we only have month data from August through December. We probably need more data to be able to draw conclusions in a linear fashion."
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x7f8330f68a30>"
      ]
     },
     "metadata": {},
     "execution_count": 3
    },
    {
     "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 0 368.925 248.518125\" width=\"368.925pt\" 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;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M -0 248.518125 \nL 368.925 248.518125 \nL 368.925 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 26.925 224.64 \nL 361.725 224.64 \nL 361.725 7.2 \nL 26.925 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=\"m920449baf6\" style=\"stroke:#1f77b4;\"/>\n    </defs>\n    <g clip-path=\"url(#pebf26beb55)\">\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"201.474881\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"188.193399\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"188.193399\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"192.62056\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"201.474881\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"188.193399\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"192.62056\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"189.300189\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"201.474881\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"192.62056\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"189.300189\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"201.474881\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"192.62056\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"189.300189\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"201.474881\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"194.83414\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m920449baf6\" y=\"192.62056\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"188.193399\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"197.047721\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"188.193399\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"197.047721\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"197.047721\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"197.047721\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.234091\" xlink:href=\"#m920449baf6\" y=\"92.566727\"/>\n     <u
      "image/png": "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
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "plt.scatter('Month','Price',data=new_pumpkins)"
   ]
  },
  {
   "source": [
    "Try some different correlations"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "0.32363971816089226\n0.6061712937226021\n"
     ]
    }
   ],
   "source": [
    "print(new_pumpkins['City'].corr(new_pumpkins['Price']))\n",
    "\n",
    "print(new_pumpkins['Package'].corr(new_pumpkins['Price']))\n"
   ]
  },
  {
   "source": [
    "Drop unused columns"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\nInt64Index: 415 entries, 70 to 1742\nData columns (total 7 columns):\n #   Column      Non-Null Count  Dtype  \n---  ------      --------------  -----  \n 0   Month       415 non-null    int64  \n 1   Variety     415 non-null    int64  \n 2   City        415 non-null    int64  \n 3   Package     415 non-null    int64  \n 4   Low Price   415 non-null    int64  \n 5   High Price  415 non-null    int64  \n 6   Price       415 non-null    float64\ndtypes: float64(1), int64(6)\nmemory usage: 25.9 KB\n"
     ]
    }
   ],
   "source": [
    "\n",
    "new_pumpkins.dropna(inplace=True)\n",
    "new_pumpkins.info()\n",
    "\n",
    "\n"
   ]
  },
  {
   "source": [
    "Create a new dataframe"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "      Package      Price\n",
       "70          0  13.636364\n",
       "71          0  16.363636\n",
       "72          0  16.363636\n",
       "73          0  15.454545\n",
       "74          0  13.636364\n",
       "...       ...        ...\n",
       "1738        2  30.000000\n",
       "1739        2  28.750000\n",
       "1740        2  25.750000\n",
       "1741        2  24.000000\n",
       "1742        2  24.000000\n",
       "\n",
       "[415 rows x 2 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>Package</th>\n      <th>Price</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>70</th>\n      <td>0</td>\n      <td>13.636364</td>\n    </tr>\n    <tr>\n      <th>71</th>\n      <td>0</td>\n      <td>16.363636</td>\n    </tr>\n    <tr>\n      <th>72</th>\n      <td>0</td>\n      <td>16.363636</td>\n    </tr>\n    <tr>\n      <th>73</th>\n      <td>0</td>\n      <td>15.454545</td>\n    </tr>\n    <tr>\n      <th>74</th>\n      <td>0</td>\n      <td>13.636364</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>1738</th>\n      <td>2</td>\n      <td>30.000000</td>\n    </tr>\n    <tr>\n      <th>1739</th>\n      <td>2</td>\n      <td>28.750000</td>\n    </tr>\n    <tr>\n      <th>1740</th>\n      <td>2</td>\n      <td>25.750000</td>\n    </tr>\n    <tr>\n      <th>1741</th>\n      <td>2</td>\n      <td>24.000000</td>\n    </tr>\n    <tr>\n      <th>1742</th>\n      <td>2</td>\n      <td>24.000000</td>\n    </tr>\n  </tbody>\n</table>\n<p>415 rows × 2 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 6
    }
   ],
   "source": [
    "new_columns = ['Package', 'Price']\n",
    "lin_pumpkins = new_pumpkins.drop([c for c in new_pumpkins.columns if c not in new_columns], axis='columns')\n",
    "\n",
    "lin_pumpkins\n"
   ]
  },
  {
   "source": [
    "Set X and y arrays to correspond to Package and Price"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = lin_pumpkins.values[:, :1]\n",
    "y = lin_pumpkins.values[:, 1:2]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Model Accuracy:  0.3315342327998987\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
    "lin_reg = LinearRegression()\n",
    "lin_reg.fit(X_train,y_train)\n",
    "\n",
    "pred = lin_reg.predict(X_test)\n",
    "\n",
    "accuracy_score = lin_reg.score(X_train,y_train)\n",
    "print('Model Accuracy: ', accuracy_score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "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 0 382.603125 262.19625\" width=\"382.603125pt\" 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;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 262.19625 \nL 382.603125 262.19625 \nL 382.603125 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 40.603125 224.64 \nL 375.403125 224.64 \nL 375.403125 7.2 \nL 40.603125 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=\"m36c1eb7dc6\" style=\"stroke:#000000;\"/>\n    </defs>\n    <g clip-path=\"url(#pa945ba2db5)\">\n     <use style=\"stroke:#000000;\" x=\"284.094034\" xlink:href=\"#m36c1eb7dc6\" y=\"37.055163\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"167.097038\"/>\n     <use style=\"stroke:#000000;\" x=\"360.184943\" xlink:href=\"#m36c1eb7dc6\" y=\"174.359411\"/>\n     <use style=\"stroke:#000000;\" x=\"360.184943\" xlink:href=\"#m36c1eb7dc6\" y=\"184.345175\"/>\n     <use style=\"stroke:#000000;\" x=\"131.912216\" xlink:href=\"#m36c1eb7dc6\" y=\"187.522463\"/>\n     <use style=\"stroke:#000000;\" x=\"131.912216\" xlink:href=\"#m36c1eb7dc6\" y=\"187.522463\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"192.061447\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"188.657209\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"196.60043\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"119.437712\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"59.523131\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"114.44483\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"119.437712\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"99.466185\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"69.508895\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"198.869922\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"210.21738\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"167.097038\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"192.061447\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"94.473303\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"59.523131\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m36c1eb7dc6\" y=\"119.437712\"/>\n     <use style=\"stroke:#000000;\" x=\"284.094034\" xlink:href=\"#m36c1eb7dc6\" y=\"86.983981\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"202.274159\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"192.061447\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m36c1eb7dc6\" y=\"187.522463\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEGCAYAAABiq/5QAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAeyklEQVR4nO3df5RkZX3n8fenq0ekAWGUFkewu1ZDIDNERpxDIJjsyIy7iC6owayexp0Yd1umxeCaPYj2bsSTtEdzREXN9KZVcFwriRCjENQ1TAui5whmRvk5I4o63StMmBFBfrSEdM93/6jb0zU9/aNuTd269ePzOqdPVz11b93vXJpPP/3cW8+jiMDMzDpHV94FmJlZYzn4zcw6jIPfzKzDOPjNzDqMg9/MrMN0511ANY4//vgoFot5l2Fm1lJ27Njxi4jond/eEsFfLBbZvn173mWYmbUUSRMLtXuox8yswzj4zcw6jIPfzKzDOPjNzDqMg9/MrMM4+M0sc6VSiWKxSFdXF8VikVKplHdJHa0lbuc0s9ZVKpUYHBxkamoKgImJCQYHBwEYGBjIs7SO5R6/mWVqeHj4QOjPmpqaYnh4OKeKLNMev6TdwBPADDAdEeskPRf4IlAEdgN/GBGPZlmHmeVncnIyVbtlrxE9/ldGxNqIWJc8vwIYj4iTgfHkuZm1qb6+vlTtlr08hnouBLYmj7cCr8uhBjNrkJGREXp6eg5q6+npYWRkJKeKLOvgD+CfJO2QNJi0nRARewCS789faEdJg5K2S9q+b9++jMs0s6wMDAwwNjZGf38/kujv72dsbMwXdnOkLNfclfTCiHhI0vOBm4F3AjdGxHEV2zwaESuXep9169aFJ2kzM0tH0o6KYfYDMu3xR8RDyfe9wJeBM4GHJa1KiloF7M2yBjMzO1hmwS/pKEnHzD4G/gNwL3AjsCnZbBNwQ1Y1mJnZobK8nfME4MuSZo/zNxHxfyX9M3CdpLcBk8AbM6zBzMzmySz4I+KnwOkLtD8CbMjquGZmtjR/ctfMrMM4+M1q4EnHrJV5kjazlDzpmLU69/jNUvKkY9bqHPxmKXnSMWt1Dn6zlDzpmLU6B79ZSp50zFqdg98sJU86Zq3OwW9Wg4GBAXbv3s3+/fvZvXu3Q38ZQ0NDdHd3I4nu7m6GhobyLqmj+XZOM8vU0NAQo6OjB57PzMwceL5ly5a8yupomU7LXC+eltmsdXV3dzMzM3NIe6FQYHp6OoeKOkcu0zKbmS0U+ku1W/Yc/GaWqUKhkKrdsufgN7NMzU5nUW27Zc8Xd80sU7MXcMfGxpiZmaFQKDA4OOgLuznyxV0zszaV28VdSQVJP5B0U/L8SkkPSroz+To/6xrMzGxOI4Z6LgN2Ac+paPtYRHykAcc2M7N5Mu3xSzoJeA3wmSyPY2Zm1ct6qOfjwOXA/nntl0q6W9I1klYutKOkQUnbJW3ft29fxmWamXWOzIJf0muBvRGxY95Lo8BLgLXAHuCqhfaPiLGIWBcR63p7e7Mq08ys42Q5xn8OcEFy8fbZwHMkfSEiLp7dQNKngZsyrMHMzObJrMcfEe+NiJMiogi8CfhmRFwsaVXFZq8H7s2qBjMzO1QeH+D6S0lrgQB2A2/PoQYzs47VkOCPiFuBW5PHb2nEMc3MbGGeq8fMrMM4+M3MOoyD38yswzj4zcw6jIPfzKzDOPjNzDqMg9+sBmvWrEHSga81a9bkXZJZ1Rz8ZimtWbOGnTt3HtS2c+dOh7+1DAe/WUrzQ3+5drNm4+A3M+swDn4zsw7j4DdLafXq1anazZqNg98spfvuu++QkF+9ejX33XdfThWZpZPHtMxmLc8hb63MPX4zsw7j4Dcz6zCZB7+kgqQfSLopef5cSTdL+nHyfWXWNZjV29DQEN3d3Uiiu7uboaGhvEsyq1ojevyXAbsqnl8BjEfEycB48tysZQwNDTE6OsrMzAwAMzMzjI6OOvytZWQa/JJOAl4DfKai+UJga/J4K/C6LGswq7exsbFU7WbNJuse/8eBy4H9FW0nRMQegOT78xfaUdKgpO2Stu/bty/jMs2qN9vTr7bdrNlkFvySXgvsjYgdtewfEWMRsS4i1vX29ta5OrPaFQqFVO1mzSbLHv85wAWSdgN/B5wr6QvAw5JWASTf92ZYg1ndDQ4Opmo3azaZBX9EvDciToqIIvAm4JsRcTFwI7Ap2WwTcENWNZhlYcuWLWzevPlAD79QKLB582a2bNmSc2XW6p5+GqRDv+pNEVH/d51/EGk98D8i4rWSngdcB/QBk8AbI+KXS+2/bt262L59e+Z1mpk12u23w9lnL71NrTEtaUdErJvf3pApGyLiVuDW5PEjwIZGHNfMrBn9yZ/AJz+Z3/H9yV0zswaoHLqpNvQ//OHae/tLcfCb1cCf3LXlzMzUNk5///3lsI+Ayy/PpjbPzmmW0uwnd2fNfnIX8AXeDnf//XDqqen3m5mBrgZ2w93jN0vJn9y1Sh/+8FyvPk3oz/bqIxob+uDgN0vNn9y1Y46ZC/srqpxt7F3vOjjs8+ShHrOUCoXCgiHvT+62r1p75XfcAWeeWf96Dpd7/GYp+ZO7neGhh+Z69WlC/+mn53r1zRj64OA3S82f3G1fW7fOhf2JJ1a/X+UQzhFHZFdfvTj4zWqwZcsWpqeniQimp6cd+ssolUoUi0W6urooFouUSqW8SzrgjDPmwv6P/qi6fd7whuYZr6+Fx/jNLFOlUonBwUGmpqYAmJiYODAsNjAwkEtNtcx/89Wvwvnn17+WPDRkrp7D5bl6zFpXsVhkYmLikPb+/n52797dkBp+9Ss47rj0+z32GBx7bP3raZTF5urxUI9ZDSQd8mULm5ycTNVeL1//+twQTprQrxzCaeXQX4qD3yylxULe4b+wvr6+VO2H43Wvmwv7aodlTj+9tcfra+HgN7NMjYyM0NPTc1BbT08PIyMjdXn/yvlwbqhydY/Pf34u6O+8sy5ltBRf3DWzTM1ewB0eHmZycpK+vj5GRkZqvrD79NNw5JHp93vwQXjhC2s6ZNvJ7OKupGcDtwFHUP4F8/cR8X5JVwL/DZhdQf19EfG1pd7LF3etmSw1pNMKN0u0ojvugLPOSr/f/v3ZrGDVKvJYiOVfgXMj4klJK4DvSPp68trHIuIjGR7bzFrcZZfBJz6Rbp+jjoInn8ymnnaS5Zq7ERGz/wlWJF/uDlnL27Bh4QXkFmu36lWO11cb+h/60Nx4vUO/Ople3JVUkHQnsBe4OSLuSF66VNLdkq6RtDLLGszqbXx8PFW7La7WxUp27ZoL+/e8J7v62lWmwR8RMxGxFjgJOFPSacAo8BJgLbAHuGqhfSUNStouafu+ffsW2sTMWtD9988FfXeKwebp6bmwr2WxE5vTkNs5I+IxyoutnxcRDye/EPYDnwYWnL8uIsYiYl1ErOvt7W1EmWaWkQsvPPzFSjzrdf1kFvySeiUdlzw+EtgI/FDSqorNXg/cm1UNZlnwGH91Kodwbryxun0uvbTzPkyVhyzv6lkFbJVUoPwL5rqIuEnS/5G0lvKF3t3A2zOswazu9uzZk6q9U9S6WMntt8Pv/E7967HFeZI2s5R8H/+cH/0ITjkl/X5TU7V9CMvS8SRtZlYX73733BBOmtCvHMJx6OfLUzaY2bJq/fRrh/0B1DLc4zdLafXq1anaW1Ut99d//OO+ONsK3OM3S2nVqlXs3LlzwfZWtncvnHBC+v327IEXvKD+9Vh23OM3S6mdPrn7qU/N9erThH5lr96h33rc4zfrMB6vN/f4zTpALeP173ynx+vbVVXBL+k3JY1Lujd5/lJJ/zPb0syaUyt8cveppw5/8rO0UyJb66i2x/9p4L3AvwFExN3Am7IqyqyZbdu27ZCQ37BhA9u2bcuporKvfGUu6I8+uvr99u/35Gedptox/p6I+N68TyxOZ1CPWUvIO+RnrV5d7qWn5aGbzlZtj/8Xkl5CspCKpIsoT6lsZg1WOYRTbei/+tUer7c51fb43wGMAadKehD4GXBxZlWZ2QEzM+nmrZ91223we79
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "\n",
    "plt.scatter(X_test, y_test,  color='black')\n",
    "plt.plot(X_test, pred, color='blue', linewidth=3)\n",
    "\n",
    "plt.xlabel('Package')\n",
    "plt.ylabel('Price')\n",
    "\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "array([[33.15655975]])"
      ]
     },
     "metadata": {},
     "execution_count": 10
    }
   ],
   "source": [
    "lin_reg.predict( np.array([ [2.75] ]) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "      Month  Variety  City  Package      Price\n",
       "70        1        3     1        0  13.636364\n",
       "71        1        3     1        0  16.363636\n",
       "72        2        3     1        0  16.363636\n",
       "73        2        3     1        0  15.454545\n",
       "74        2        3     1        0  13.636364\n",
       "...     ...      ...   ...      ...        ...\n",
       "1738      1        1     9        2  30.000000\n",
       "1739      1        1     9        2  28.750000\n",
       "1740      1        1     9        2  25.750000\n",
       "1741      1        1     9        2  24.000000\n",
       "1742      1        1     9        2  24.000000\n",
       "\n",
       "[415 rows x 5 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>Month</th>\n      <th>Variety</th>\n      <th>City</th>\n      <th>Package</th>\n      <th>Price</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>70</th>\n      <td>1</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>13.636364</td>\n    </tr>\n    <tr>\n      <th>71</th>\n      <td>1</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>16.363636</td>\n    </tr>\n    <tr>\n      <th>72</th>\n      <td>2</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>16.363636</td>\n    </tr>\n    <tr>\n      <th>73</th>\n      <td>2</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>15.454545</td>\n    </tr>\n    <tr>\n      <th>74</th>\n      <td>2</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>13.636364</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>1738</th>\n      <td>1</td>\n      <td>1</td>\n      <td>9</td>\n      <td>2</td>\n      <td>30.000000</td>\n    </tr>\n    <tr>\n      <th>1739</th>\n      <td>1</td>\n      <td>1</td>\n      <td>9</td>\n      <td>2</td>\n      <td>28.750000</td>\n    </tr>\n    <tr>\n      <th>1740</th>\n      <td>1</td>\n      <td>1</td>\n      <td>9</td>\n      <td>2</td>\n      <td>25.750000</td>\n    </tr>\n    <tr>\n      <th>1741</th>\n      <td>1</td>\n      <td>1</td>\n      <td>9</td>\n      <td>2</td>\n      <td>24.000000</td>\n    </tr>\n    <tr>\n      <th>1742</th>\n      <td>1</td>\n      <td>1</td>\n      <td>9</td>\n      <td>2</td>\n      <td>24.000000</td>\n    </tr>\n  </tbody>\n</table>\n<p>415 rows × 5 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 11
    }
   ],
   "source": [
    "new_columns = ['Variety', 'Package', 'City', 'Month', 'Price']\n",
    "poly_pumpkins = new_pumpkins.drop([c for c in new_pumpkins.columns if c not in new_columns], axis='columns')\n",
    "\n",
    "poly_pumpkins"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f8320e9d580>"
      ],
      "text/html": "<style  type=\"text/css\" >\n    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow0_col0 {\n            background-color:  #b40426;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow0_col1 {\n            background-color:  #ead4c8;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow0_col2 {\n            background-color:  #4961d2;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow0_col3 {\n            background-color:  #9bbcff;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow0_col4 {\n            background-color:  #bbd1f8;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow1_col0 {\n            background-color:  #9fbfff;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow1_col1 {\n            background-color:  #b40426;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow1_col2 {\n            background-color:  #3b4cc0;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow1_col3 {\n            background-color:  #3b4cc0;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow1_col4 {\n            background-color:  #3b4cc0;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow2_col0 {\n            background-color:  #3b4cc0;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow2_col1 {\n            background-color:  #a9c6fd;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow2_col2 {\n            background-color:  #b40426;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow2_col3 {\n            background-color:  #edd2c3;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow2_col4 {\n            background-color:  #f5c0a7;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow3_col0 {\n            background-color:  #455cce;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow3_col1 {\n            background-color:  #6485ec;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow3_col2 {\n            background-color:  #ccd9ed;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow3_col3 {\n            background-color:  #b40426;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow3_col4 {\n            background-color:  #f08a6c;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow4_col0 {\n            background-color:  #445acc;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow4_col1 {\n            background-color:  #3b4cc0;\n            color:  #f1f1f1;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow4_col2 {\n            background-color:  #d2dbe8;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow4_col3 {\n            background-color:  #f39778;\n            color:  #000000;\n        }    #T_82ec828a_87fa_11eb_b754_f218988e26cdrow4_col4 {\n            background-color:  #b40426;\n            color:  #f1f1f1;\n        }</style><table id=\"T_82ec828a_87fa_11eb_b754_f218988e26cd\" ><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >Month</th>        <th class=\"col_heading level0 col1\" >Variety</th>        <th class=\"col_heading level0 col2\" >City</th>        <th class=\"col_heading level0 col3\" >Package</th>        <th class=\"col_heading level0 col4\" >Price</th>    </tr></thead><tbody>\n                <tr>\n                        <th id=\"T_82ec828a_87fa_11eb_b754_f218988e26cdlevel0_row0\" class=\"row_heading level0 row0\" >Month</th>\n                        <td id=\"T_82ec828a_87fa_11eb_b754_f
     },
     "metadata": {},
     "execution_count": 12
    }
   ],
   "source": [
    "corr = poly_pumpkins.corr()\n",
    "corr.style.background_gradient(cmap='coolwarm')"
   ]
  },
  {
   "source": [
    "Select the Package/Price columns"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=poly_pumpkins.iloc[:,3:4].values\n",
    "y=poly_pumpkins.iloc[:,4:5].values\n"
   ]
  },
  {
   "source": [
    "Create Polynomial Regression model"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "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 0 382.603125 262.19625\" width=\"382.603125pt\" 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;}\n  </style>\n </defs>\n <g id=\"figure_1\">\n  <g id=\"patch_1\">\n   <path d=\"M 0 262.19625 \nL 382.603125 262.19625 \nL 382.603125 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 40.603125 224.64 \nL 375.403125 224.64 \nL 375.403125 7.2 \nL 40.603125 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=\"m51919dc1bb\" style=\"stroke:#000000;\"/>\n    </defs>\n    <g clip-path=\"url(#p7e8c8f0484)\">\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"201.474881\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"188.193399\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"188.193399\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"192.62056\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"201.474881\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"188.193399\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"192.62056\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"189.300189\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"201.474881\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"192.62056\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"189.300189\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"201.474881\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"192.62056\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"189.300189\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"201.474881\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"194.83414\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"192.62056\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"188.193399\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"197.047721\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"188.193399\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"197.047721\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"197.047721\"/>\n     <use style=\"stroke:#000000;\" x=\"55.821307\" xlink:href=\"#m51919dc1bb\" y=\"197.047721\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m51919dc1bb\" y=\"92.566727\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m51919dc1bb\" y=\"121.785988\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m51919dc1bb\" y=\"92.566727\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m51919dc1bb
      "image/png": "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
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "from sklearn.pipeline import make_pipeline\n",
    "\n",
    "pipeline = make_pipeline(PolynomialFeatures(4), LinearRegression())\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
    "\n",
    "pipeline.fit(np.array(X_train), y_train)\n",
    "\n",
    "y_pred=pipeline.predict(X_test)\n",
    "\n",
    "df = pd.DataFrame({'x': X_test[:,0], 'y': y_pred[:,0]})\n",
    "df.sort_values(by='x',inplace = True)\n",
    "points = pd.DataFrame(df).to_numpy()\n",
    "\n",
    "plt.plot(points[:, 0], points[:, 1],color=\"blue\", linewidth=3)\n",
    "plt.xlabel('Package')\n",
    "plt.ylabel('Price')\n",
    "\n",
    "plt.scatter(X,y, color=\"black\")\n",
    "\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Model Accuracy:  0.8537946517073784\n"
     ]
    }
   ],
   "source": [
    "accuracy_score = pipeline.score(X_train,y_train)\n",
    "print('Model Accuracy: ', accuracy_score)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "array([[46.34509342]])"
      ]
     },
     "metadata": {},
     "execution_count": 16
    }
   ],
   "source": [
    "pipeline.predict( np.array([ [2.75] ]) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ]
}