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": "3.7.0"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "python37364bit8d3b438fb5fc4430a93ac2cb74d693a7",
   "display_name": "Python 3.7.0 64-bit ('3.7')"
  },
  "metadata": {
   "interpreter": {
    "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
   }
  }
 },
 "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 0x7fe57097e828>"
      ]
     },
     "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;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 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=\"m6e6fd13ccb\" style=\"stroke:#1f77b4;\"/>\n    </defs>\n    <g clip-path=\"url(#p5cb0483da8)\">\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"201.41676\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"188.144301\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"188.144301\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"192.568454\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"201.41676\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"188.144301\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"192.568454\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"189.250339\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"201.41676\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"192.568454\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"189.250339\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"201.41676\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"192.568454\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"189.250339\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"201.41676\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"194.780531\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"194.325\" xlink:href=\"#m6e6fd13ccb\" y=\"192.568454\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"188.144301\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"196.992607\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"188.144301\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"196.992607\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"196.992607\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"196.992607\"/>\n     <use style=\"fill:#1f77b4;stroke:#1f77b4;\" x=\"118.573479\" xlink:href=\"#m6e6fd13ccb\" y=\"92.58
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAD4CAYAAAD1jb0+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAahUlEQVR4nO3df5Bd9Xnf8fdHawFrTCLLLIrQDwtjjZjWqiV7g8So08o4qhjw4A11W6vg4o5rJW08xUMqGwVNYndgIKME3DYZZ8B2rBSC7bHVhQKpqjHSZOIBOStLZsGgymB+LQraGMtgsgaxevrHPStWd+/VnrN77z0/7uc1s7P3PPdczjMHnWfP/Z7vD0UEZmZWPnPyTsDMzGbGBdzMrKRcwM3MSsoF3MyspFzAzcxK6m2dPNi5554by5Yt6+QhzcxKb//+/X8fEX318Y4W8GXLljE0NNTJQ5qZlZ6kZxvF3YRiZlZSLuBmZiXlAm5mVlIu4GZmJeUCbmZWUh3thWKdMXhghO27DvHisTHOn9fLlo0rGFi9KO+0zKzFXMArZvDACFt3DjN2fByAkWNjbN05DOAiblYxbkKpmO27Dp0s3hPGjo+zfdehnDIys3ZxAa+YF4+NZYqbWXm5gFfM+fN6M8XNrLxcwCtmy8YVzJ2jU2Jz54gtG1fklJGZtYsLeBVpmm0zq4RUBVzSM5KGJR2UNJTE5kvaLelw8vud7U3V0ti+6xDHx09d5/T4ePghplkFZbkD/1BErIqI/mT7BuC7EbEc+G6ybTnzQ0yz7jGbJpSPAjuS1zuAgdmnY7Plh5hm3SNtAQ/g/0raL2lzElsQEUeS138HLGh5dpbZlo0r6J3bc0qsd26PH2KaVVDakZj/NCJGJJ0H7Jb05OQ3IyIkRaMPJgV/M8DSpUtnlaxNb2K0pYfSm1WfIhrW3eYfkL4A/AL4NLA+Io5IWgjsjYjT3ub19/eHV+QxM8tG0v5Jzx9PmrYJRdLZks6ZeA38C+Ax4D7g2mS3a4F7W5eumZlNJ00TygLgf0ma2P8vI+L/SPpb4FuSPgU8C/zr9qVpZmb1pi3gEfE08P4G8Z8CH25HUmZmNj2PxDQzKynPB15BV9/5MN976uWT2+sunM/dn74kx4zMrB18B14x9cUb4HtPvczVdz6cU0Zm1i4u4BVTX7yni5tZebmAm5mVlAu4mVlJuYBXzLoL52eKm1l5uYBXzL/qX0rdgjzMUS1uZtXiAl4x23cd4kTd9DYnAi/oYFZB7gdeMV7QIZsNt+3l8NHXTm4vP+9sdl+/Pr+EzDLwHXjFeEGH9OqLN8Dho6+x4ba9+SRklpELeMVs2biiYRu4F3SYqr54Txc3KxoX8IoZevblhm3gQ896II9Z1biAV8w9+57PFDez8nIBr5jxJissNYt3s+XnnZ0pblY0LuAV0yNlinez3devn1Ks3QvFyiR1N0JJPcAQMBIRH5H0deCfAz9PdvlkRBxsfYqWxaY1S7jrkecaxm0qF+tsBg+MeMHsAsnSD/w64AngVybFtkTEt1ubks3GTQMrgVqb93gEPRKb1iw5GTebqcEDI2zdOczY8XEARo6NsXXnMICLeE5SFXBJi4ErgJuB69uakc3aTQMrXbCt5bbvOnSyeE8YOz7O9l2HXMBzkrYN/EvA54ATdfGbJT0q6XZJZzb6oKTNkoYkDY2Ojs4mVzPLkUf5Fs+0BVzSR4CjEbG/7q2twEXArwPzgc83+nxE3BER/RHR39fXN9t8zSwnHuVbPGnuwNcBV0p6BvgGcKmkuyLiSNS8Dvw5cHEb8zSznG3ZuILeuT2nxHrn9niUb46mLeARsTUiFkfEMuDjwEMRcY2khQCSBAwAj7U1UzPL1cDqRdxy1UoWzetFwKJ5vdxy1Uq3f+doNrMR3i2pDxBwEPjt1qRkZkU1sHqRC3aBZCrgEbEX2Ju8vrQN+ZiZWUoeiWlmVlIu4GZmJeUCbmZWUi7gZmYl5QJuZlZSLuBmZiXlVekryFN+prfshgemxJ659YocMimHbYPDnumyQHwHXjETU36OHBsjeGvKz8EDI3mnVjiNivfp4t1u2+Awdz3y3MnVncYjuOuR59g2OJxzZt3LBbxiTjflp9lseL3V4nEBrxhP+Wnt4vVWi8cFvGI85ae1i9dbLR4X8IrxlJ/WLs3WVfV6q/lxAa8YT/mZXrPeJu6F0thNAyu5Zu3Sk3fcPRLXrF3qXig5UnSw/aq/vz+GhoY6djwzsyqQtD8i+uvjvgM3Myup1AN5JPUAQ8BIRHxE0gXUllh7F7Af+EREvNGeNC0LD+RJ74IbHmDyd1ABP3ETSlNrbt7NS6++dZkvOOcM9t24IceMuluWO/DrgCcmbf8hcHtEvBf4GfCpViZmM+OBPOnVF2+ASOI2VX3xBnjp1TdYc/PunDKyVAVc0mLgCuArybaAS4FvJ7vsoLYupuXMA3nSa/b0x72aG6sv3tPFrf3S3oF/CfgccCLZfhdwLCLeTLZfABp+R5e0WdKQpKHR0dFZJWvT80Aes+4xbQGX9BHgaETsn8kBIuKOiOiPiP6+vr6Z/CcsAw/kMeseae7A1wFXSnqG2kPLS4H/BsyTNPEQdDHgRtYC8ECe9JqNH/S4wsYWnHNGpri137QFPCK2RsTiiFgGfBx4KCKuBvYAH0t2uxa4t21ZWmoeyJPeT269Ykqxdi+U5vbduGFKsXYvlHxlGsgjaT3wX5JuhO+hdkc+HzgAXBMRr5/u8x7IY2aWXbOBPJkWdIiIvcDe5PXTwMWtSM7MzLLzSEwzs5IqxZJqHlmYzUU3Psgvx99qGjurRzx58+U5ZlRcXiLMyqzwd+AeWZhNffEG+OV4cNGND+aUUXF5iTAru8IXcI8szKa+eE8X72ZeIszKrvAF3CMLrV28RJiVXeELuEcWWrt4iTAru8IXcI8szOasnsbFp1m8m3mJMCu7whdwjyzM5smbL59SrN0LpTEvEWZlV4puhAOrF7lgZ+BinV7/u+ez58lRXjw2xq/96ln0v3t+3imZpVaKAm7WDhNdVCd6OU10UQV8w2ClUPgmFLN2cRdVKzvfgVfQsgZLgj3jGfamcBfV7Dwqulh8B14xjYr36eLdzEuqZeNR0cXjAm5mqbjJqXhcwM0sFTc5FU+aNTHPkvR9ST+U9LikLybxr0v6iaSDyc+q9qdrZnnxqOjiSXMH/jpwaUS8H1gFXCZpbfLelohYlfwcbFuWZpa7LRtX0DPn1EFiPXPkUdE5SrMmZkTEL5LNucmPn/MU1LoLGw9EaRY3S2vo2ZcZP3HqpT9+Ihh69uWcMrJUbeCSeiQdBI4CuyNiX/LWzZIelXS7pDPblqWl9r2nGl9MzeJmaXn63eJJVcAjYjwiVgGLgYslvQ/YClwE/Dq1hY0/3+izkjZLGpI0NDo62qK0zazTPP1u8WTqhRIRx4A9wGURcSRpXnkd+HOaLHAcEXdERH9E9Pf19c0+YzPLhaffLZ40vVD6JM1LXvcCG4AnJS1MYgIGgMfamaiZ5ct34MWTZij9QmCHpB5qBf9bEXG/pIck9QECDgK/3cY8zcyszrQFPCIeBVY3iF/alozMzCwVj8Q0MyspF3Azs5JyAa+YXzmzJ1PcLK0F55yRKW7t5wJeMa+8Pp4pbpbWS6++kSlu7ecCbmZWUi7gZmYl5QJeMW4Dt3ZxG3jxuIBXzJVN1idsFu9mX/o3jaewbxbvdvtu3DClWC845wz23bghp4zMixpXzOlmjLtpYGWHsym2ZkuBbd91yAv1NuFiXSy+A68Yz1eRnpcIs7JzAa+YZvPCeb64qbxEmJWdm1Aq5u1n9PDaG1P7fL/9DD/ErLdl4wo++82pKwF6ibDmtg0Oc8++5xmPoEdi05olbprLke/AK6ZR8T5dvJv9/uBwpni32zY4zF2PPHeyOW48grseeY5tPl+5cQG3ruVRq9l4SbXicQE3s1T8gLx4XMDNLBUvqVY8aZZUO0vS9yX9UNLjkr6YxC+QtE/SjyV9U5KHYxWAe6Gk51Gr2WxasyRT3NovzR3468ClEfF+YBVwmaS
     },
     "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": [
      "0.3236397181608923\n0.6061712937226016\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:  0.3315342327998989\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;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 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=\"m88dd73df7b\" style=\"stroke:#000000;\"/>\n    </defs>\n    <g clip-path=\"url(#p21e702bfe1)\">\n     <use style=\"stroke:#000000;\" x=\"283.754646\" xlink:href=\"#m88dd73df7b\" y=\"37.110092\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"167.061394\"/>\n     <use style=\"stroke:#000000;\" x=\"359.506166\" xlink:href=\"#m88dd73df7b\" y=\"174.318709\"/>\n     <use style=\"stroke:#000000;\" x=\"359.506166\" xlink:href=\"#m88dd73df7b\" y=\"184.297517\"/>\n     <use style=\"stroke:#000000;\" x=\"132.251604\" xlink:href=\"#m88dd73df7b\" y=\"187.472593\"/>\n     <use style=\"stroke:#000000;\" x=\"132.251604\" xlink:href=\"#m88dd73df7b\" y=\"187.472593\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"192.008415\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"188.606548\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"196.544237\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"119.435262\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"59.562411\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"114.445858\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"119.435262\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"99.477645\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"69.541219\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"198.812148\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"210.151703\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"167.061394\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"192.008415\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"94.488241\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"59.562411\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m88dd73df7b\" y=\"119.435262\"/>\n     <use style=\"stroke:#000000;\" x=\"283.754646\" xlink:href=\"#m88dd73df7b\" y=\"87.004134\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"202.214015\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"192.008415\"/>\n     <use style=\"stroke:#000000;\" x=\"56.500084\" xlink:href=\"#m88dd73df7b\" y=\"187.472593\"/>\n     <use style=\"stroke:#000000;\" x=\"208.00312
      "image/png": "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
     },
     "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 0x7fe5709abfd0>"
      ],
      "text/html": "<style  type=\"text/css\" >\n#T_374540ec_b1df_11eb_9c12_acde48001122row0_col0,#T_374540ec_b1df_11eb_9c12_acde48001122row1_col1,#T_374540ec_b1df_11eb_9c12_acde48001122row2_col2,#T_374540ec_b1df_11eb_9c12_acde48001122row3_col3,#T_374540ec_b1df_11eb_9c12_acde48001122row4_col4{\n            background-color:  #b40426;\n            color:  #f1f1f1;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row0_col1{\n            background-color:  #ead4c8;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row0_col2{\n            background-color:  #4961d2;\n            color:  #f1f1f1;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row0_col3{\n            background-color:  #9bbcff;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row0_col4{\n            background-color:  #bbd1f8;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row1_col0{\n            background-color:  #9fbfff;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row1_col2,#T_374540ec_b1df_11eb_9c12_acde48001122row1_col3,#T_374540ec_b1df_11eb_9c12_acde48001122row1_col4,#T_374540ec_b1df_11eb_9c12_acde48001122row2_col0,#T_374540ec_b1df_11eb_9c12_acde48001122row4_col1{\n            background-color:  #3b4cc0;\n            color:  #f1f1f1;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row2_col1{\n            background-color:  #a9c6fd;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row2_col3{\n            background-color:  #edd2c3;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row2_col4{\n            background-color:  #f5c0a7;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row3_col0{\n            background-color:  #455cce;\n            color:  #f1f1f1;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row3_col1{\n            background-color:  #6485ec;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row3_col2{\n            background-color:  #ccd9ed;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row3_col4{\n            background-color:  #f08a6c;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row4_col0{\n            background-color:  #445acc;\n            color:  #f1f1f1;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row4_col2{\n            background-color:  #d2dbe8;\n            color:  #000000;\n        }#T_374540ec_b1df_11eb_9c12_acde48001122row4_col3{\n            background-color:  #f39778;\n            color:  #000000;\n        }</style><table id=\"T_374540ec_b1df_11eb_9c12_acde48001122\" ><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_374540ec_b1df_11eb_9c12_acde48001122level0_row0\" class=\"row_heading level0 row0\" >Month</th>\n                        <td id=\"T_374540ec_b1df_11eb_9c12_acde48001122row0_col0\" class=\"data row0 col0\" >1.000000</td>\n                        <td id=\"T_374540ec_b1df_11eb_9c12_acde48001122row0_col1\" class=\"data row0 col1\" >0.171330</td>\n                        <td id=\"T_374540ec_b1df_11eb_9c12_acde48001122row0_col2\" class=\"data row0 col2\" >-0.188728</td>\n                        <td id=\"T_374540ec_b1df_11eb_9c12_acde48001122row0_col3\" class=\"data row0 col3\" >-0.144847</td>\n                        <td id=\"T_374540ec_b1df_11eb_9c12_acde48001122row0_col4\" class=\"data row0 col4\" >-0.148783</td>\n            </tr>\n            <tr>\n                        <th id=\"T_374540ec_b1df_11eb_9c12_acde48001122level0_row1\" class=\"row_heading level0 row1\" >Variety</th>\n                        <td id=\"T_374540ec_b1d
     },
     "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;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 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=\"m903ea3a5b7\" style=\"stroke:#000000;\"/>\n    </defs>\n    <g clip-path=\"url(#p48264b39a0)\">\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"199.44082\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"186.475104\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"186.475104\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"190.79701\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"199.44082\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"186.475104\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"190.79701\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"187.555581\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"199.44082\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"190.79701\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"187.555581\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"199.44082\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"190.79701\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"187.555581\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"199.44082\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"192.957962\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"190.79701\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"186.475104\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"195.118915\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"186.475104\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"195.118915\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"195.118915\"/>\n     <use style=\"stroke:#000000;\" x=\"58.76331\" xlink:href=\"#m903ea3a5b7\" y=\"195.118915\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m903ea3a5b7\" y=\"93.121949\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m903ea3a5b7\" y=\"121.646525\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m903ea3a5b7\" y=\"93.121949\"/>\n     <use style=\"stroke:#000000;\" x=\"208.003125\" xlink:href=\"#m903ea3a5b7\" y=\"121.
      "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": []
  }
 ]
}