Collaborative_Recommend_System(item_based).ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 142,
   "id": "1753090b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy.sparse import csr_matrix\n",
    "from sklearn.neighbors import NearestNeighbors\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "id": "d2025666",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>dog_id</th>\n",
       "      <th>breed</th>\n",
       "      <th>size</th>\n",
       "      <th>activity</th>\n",
       "      <th>img</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Airedale</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>American Spaniel</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Basset</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Beagle</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>Bearded Collie</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>Bermaise</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>Bichon Frise</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>Blenheim</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>Bloodhound</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>Border Collie</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>Borzoi</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13</td>\n",
       "      <td>Boston Terrier</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14</td>\n",
       "      <td>Boxer</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15</td>\n",
       "      <td>Bull Mastiff</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>16</td>\n",
       "      <td>Bull Terrier</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>17</td>\n",
       "      <td>Bulldog</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>18</td>\n",
       "      <td>Chihuahua</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>19</td>\n",
       "      <td>Chinese Crested</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20</td>\n",
       "      <td>Corgi</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>21</td>\n",
       "      <td>Pekinese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>22</td>\n",
       "      <td>Siberian Husky</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>23</td>\n",
       "      <td>Komondor</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>24</td>\n",
       "      <td>Newfoundland</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>25</td>\n",
       "      <td>Labrador</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>26</td>\n",
       "      <td>German Sheperd</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>27</td>\n",
       "      <td>Great Dane</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>28</td>\n",
       "      <td>Saint Bernard</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>29</td>\n",
       "      <td>Rottweiler</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>30</td>\n",
       "      <td>Chow</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>31</td>\n",
       "      <td>Dalmation</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>32</td>\n",
       "      <td>Doberman</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>33</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>34</td>\n",
       "      <td>Pug</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>35</td>\n",
       "      <td>Yorkie</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>36</td>\n",
       "      <td>Shar_Pei</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>37</td>\n",
       "      <td>Shih-Tzu</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    dog_id             breed  size  activity  img\n",
       "0        1            Afghan     3         3  NaN\n",
       "1        2          Airedale     3         2  NaN\n",
       "2        3  American Spaniel     2         2  NaN\n",
       "3        4            Basset     2         2  NaN\n",
       "4        5            Beagle     2         3  NaN\n",
       "5        6    Bearded Collie     2         3  NaN\n",
       "6        7          Bermaise     3         2  NaN\n",
       "7        8      Bichon Frise     1         2  NaN\n",
       "8        9          Blenheim     1         2  NaN\n",
       "9       10        Bloodhound     3         2  NaN\n",
       "10      11     Border Collie     2         3  NaN\n",
       "11      12            Borzoi     3         3  NaN\n",
       "12      13    Boston Terrier     2         2  NaN\n",
       "13      14             Boxer     2         2  NaN\n",
       "14      15      Bull Mastiff     2         2  NaN\n",
       "15      16      Bull Terrier     1         2  NaN\n",
       "16      17           Bulldog     1         2  NaN\n",
       "17      18         Chihuahua     1         3  NaN\n",
       "18      19   Chinese Crested     1         2  NaN\n",
       "19      20             Corgi     2         2  NaN\n",
       "20      21          Pekinese     1         2  NaN\n",
       "21      22    Siberian Husky     2         2  NaN\n",
       "22      23          Komondor     3         1  NaN\n",
       "23      24      Newfoundland     3         3  NaN\n",
       "24      25          Labrador     3         2  NaN\n",
       "25      26    German Sheperd     3         2  NaN\n",
       "26      27        Great Dane     3         2  NaN\n",
       "27      28     Saint Bernard     3         2  NaN\n",
       "28      29        Rottweiler     3         2  NaN\n",
       "29      30              Chow     2         2  NaN\n",
       "30      31         Dalmation     3         2  NaN\n",
       "31      32          Doberman     3         2  NaN\n",
       "32      33           Maltese     1         2  NaN\n",
       "33      34               Pug     1         1  NaN\n",
       "34      35            Yorkie     1         2  NaN\n",
       "35      36          Shar_Pei     2         3  NaN\n",
       "36      37          Shih-Tzu     1         2  NaN"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dog_df = pd.read_csv(\"dog_df.csv\")\n",
    "dog_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "a1f86999",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>dog_id</th>\n",
       "      <th>breed</th>\n",
       "      <th>size</th>\n",
       "      <th>activity</th>\n",
       "      <th>img</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Airedale</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>American Spaniel</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Basset</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Beagle</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>Bearded Collie</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>Bermaise</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>Bichon Frise</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>Blenheim</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>Bloodhound</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>Border Collie</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>Borzoi</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13</td>\n",
       "      <td>Boston Terrier</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14</td>\n",
       "      <td>Boxer</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15</td>\n",
       "      <td>Bull Mastiff</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>16</td>\n",
       "      <td>Bull Terrier</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>17</td>\n",
       "      <td>Bulldog</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>18</td>\n",
       "      <td>Chihuahua</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>19</td>\n",
       "      <td>Chinese Crested</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20</td>\n",
       "      <td>Corgi</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>21</td>\n",
       "      <td>Pekinese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>22</td>\n",
       "      <td>Siberian Husky</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>23</td>\n",
       "      <td>Komondor</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>24</td>\n",
       "      <td>Newfoundland</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>25</td>\n",
       "      <td>Labrador</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>26</td>\n",
       "      <td>German Sheperd</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>27</td>\n",
       "      <td>Great Dane</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>28</td>\n",
       "      <td>Saint Bernard</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>29</td>\n",
       "      <td>Rottweiler</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>30</td>\n",
       "      <td>Chow</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>31</td>\n",
       "      <td>Dalmation</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>32</td>\n",
       "      <td>Doberman</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>33</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>34</td>\n",
       "      <td>Pug</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>35</td>\n",
       "      <td>Yorkie</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>36</td>\n",
       "      <td>Shar_Pei</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>37</td>\n",
       "      <td>Shih-Tzu</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    dog_id             breed  size  activity  img\n",
       "0        1            Afghan     3         3  NaN\n",
       "1        2          Airedale     3         2  NaN\n",
       "2        3  American Spaniel     2         2  NaN\n",
       "3        4            Basset     2         2  NaN\n",
       "4        5            Beagle     2         3  NaN\n",
       "5        6    Bearded Collie     2         3  NaN\n",
       "6        7          Bermaise     3         2  NaN\n",
       "7        8      Bichon Frise     1         2  NaN\n",
       "8        9          Blenheim     1         2  NaN\n",
       "9       10        Bloodhound     3         2  NaN\n",
       "10      11     Border Collie     2         3  NaN\n",
       "11      12            Borzoi     3         3  NaN\n",
       "12      13    Boston Terrier     2         2  NaN\n",
       "13      14             Boxer     2         2  NaN\n",
       "14      15      Bull Mastiff     2         2  NaN\n",
       "15      16      Bull Terrier     1         2  NaN\n",
       "16      17           Bulldog     1         2  NaN\n",
       "17      18         Chihuahua     1         3  NaN\n",
       "18      19   Chinese Crested     1         2  NaN\n",
       "19      20             Corgi     2         2  NaN\n",
       "20      21          Pekinese     1         2  NaN\n",
       "21      22    Siberian Husky     2         2  NaN\n",
       "22      23          Komondor     3         1  NaN\n",
       "23      24      Newfoundland     3         3  NaN\n",
       "24      25          Labrador     3         2  NaN\n",
       "25      26    German Sheperd     3         2  NaN\n",
       "26      27        Great Dane     3         2  NaN\n",
       "27      28     Saint Bernard     3         2  NaN\n",
       "28      29        Rottweiler     3         2  NaN\n",
       "29      30              Chow     2         2  NaN\n",
       "30      31         Dalmation     3         2  NaN\n",
       "31      32          Doberman     3         2  NaN\n",
       "32      33           Maltese     1         2  NaN\n",
       "33      34               Pug     1         1  NaN\n",
       "34      35            Yorkie     1         2  NaN\n",
       "35      36          Shar_Pei     2         3  NaN\n",
       "36      37          Shih-Tzu     1         2  NaN"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dog_df.drop_duplicates(subset=['dog_id'], keep='first')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "id": "255deb53",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>occupation</th>\n",
       "      <th>place</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>m</td>\n",
       "      <td>21</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>m</td>\n",
       "      <td>22</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>m</td>\n",
       "      <td>24</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>m</td>\n",
       "      <td>25</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>m</td>\n",
       "      <td>26</td>\n",
       "      <td>2</td>\n",
       "      <td>1</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>295</th>\n",
       "      <td>296</td>\n",
       "      <td>f</td>\n",
       "      <td>59</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>297</td>\n",
       "      <td>f</td>\n",
       "      <td>65</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>298</td>\n",
       "      <td>f</td>\n",
       "      <td>68</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>299</td>\n",
       "      <td>f</td>\n",
       "      <td>69</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>300</td>\n",
       "      <td>f</td>\n",
       "      <td>70</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>300 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     user_id gender  age  occupation  place\n",
       "0          1      m   21           1      1\n",
       "1          2      m   22           1      1\n",
       "2          3      m   24           2      1\n",
       "3          4      m   25           2      1\n",
       "4          5      m   26           2      1\n",
       "..       ...    ...  ...         ...    ...\n",
       "295      296      f   59           5      2\n",
       "296      297      f   65           5      2\n",
       "297      298      f   68           5      2\n",
       "298      299      f   69           5      2\n",
       "299      300      f   70           5      2\n",
       "\n",
       "[300 rows x 5 columns]"
      ]
     },
     "execution_count": 144,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_df = pd.read_csv(\"user_df.csv\")\n",
    "user_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "57212690",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "user_id       0\n",
       "gender        0\n",
       "age           0\n",
       "occupation    0\n",
       "place         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_df_duplicated = user_df[user_df.duplicated('user_id')]\n",
    "user_df_duplicated.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "2aaa9181",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "user_id       0\n",
       "gender        0\n",
       "age           0\n",
       "occupation    0\n",
       "place         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "f9d6434d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>dog_id</th>\n",
       "      <th>rating</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1550</th>\n",
       "      <td>300</td>\n",
       "      <td>8</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1551</th>\n",
       "      <td>300</td>\n",
       "      <td>17</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1552</th>\n",
       "      <td>300</td>\n",
       "      <td>35</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1553</th>\n",
       "      <td>300</td>\n",
       "      <td>34</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1554</th>\n",
       "      <td>300</td>\n",
       "      <td>33</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1555 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      user_id  dog_id  rating\n",
       "0           1       1       5\n",
       "1           1      12       5\n",
       "2           1      24       5\n",
       "3           1       5       4\n",
       "4           1       6       5\n",
       "...       ...     ...     ...\n",
       "1550      300       8       5\n",
       "1551      300      17       4\n",
       "1552      300      35       5\n",
       "1553      300      34       5\n",
       "1554      300      33       5\n",
       "\n",
       "[1555 rows x 3 columns]"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_dog_df = pd.read_csv('user_dog_df.csv')\n",
    "user_dog_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "69651b3c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "user_id    27\n",
       "dog_id     27\n",
       "rating     27\n",
       "dtype: int64"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "duplicate =user_dog_df[user_dog_df.duplicated(['user_id', 'dog_id'])]\n",
    "duplicate.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "05f537d5",
   "metadata": {},
   "outputs": [],
   "source": [
    "user_dog_df = user_dog_df.drop_duplicates(subset=['user_id', 'dog_id'], keep='first')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "adea5364",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 1528 entries, 0 to 1551\n",
      "Data columns (total 3 columns):\n",
      " #   Column   Non-Null Count  Dtype\n",
      "---  ------   --------------  -----\n",
      " 0   user_id  1528 non-null   int64\n",
      " 1   dog_id   1528 non-null   int64\n",
      " 2   rating   1528 non-null   int64\n",
      "dtypes: int64(3)\n",
      "memory usage: 47.8 KB\n"
     ]
    }
   ],
   "source": [
    "user_dog_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "id": "bac7a089",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "user_id    0\n",
       "dog_id     0\n",
       "rating     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "user_dog_df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "id": "1d3549b6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>user_id</th>\n",
       "      <th>dog_id</th>\n",
       "      <th>rating</th>\n",
       "      <th>breed</th>\n",
       "      <th>size</th>\n",
       "      <th>activity</th>\n",
       "      <th>img</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Afghan</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1523</th>\n",
       "      <td>295</td>\n",
       "      <td>33</td>\n",
       "      <td>4</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1524</th>\n",
       "      <td>296</td>\n",
       "      <td>33</td>\n",
       "      <td>5</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1525</th>\n",
       "      <td>298</td>\n",
       "      <td>33</td>\n",
       "      <td>4</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1526</th>\n",
       "      <td>299</td>\n",
       "      <td>33</td>\n",
       "      <td>5</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1527</th>\n",
       "      <td>300</td>\n",
       "      <td>33</td>\n",
       "      <td>3</td>\n",
       "      <td>Maltese</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1528 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      user_id  dog_id  rating    breed  size  activity  img\n",
       "0           1       1       5   Afghan     3         3  NaN\n",
       "1           2       1       5   Afghan     3         3  NaN\n",
       "2           4       1       5   Afghan     3         3  NaN\n",
       "3           5       1       5   Afghan     3         3  NaN\n",
       "4           6       1       5   Afghan     3         3  NaN\n",
       "...       ...     ...     ...      ...   ...       ...  ...\n",
       "1523      295      33       4  Maltese     1         2  NaN\n",
       "1524      296      33       5  Maltese     1         2  NaN\n",
       "1525      298      33       4  Maltese     1         2  NaN\n",
       "1526      299      33       5  Maltese     1         2  NaN\n",
       "1527      300      33       3  Maltese     1         2  NaN\n",
       "\n",
       "[1528 rows x 7 columns]"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_df = pd.merge(user_dog_df, dog_df, how='inner', on='dog_id')\n",
    "merged_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7fb97437",
   "metadata": {},
   "source": [
    "### Training KNN model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "78bc79d5",
   "metadata": {},
   "source": [
    "Reshaping **user_dog_df** We want the data to be [breed, users] array. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "id": "8287dbb5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>breed</th>\n",
       "      <th>Afghan</th>\n",
       "      <th>Airedale</th>\n",
       "      <th>American Spaniel</th>\n",
       "      <th>Basset</th>\n",
       "      <th>Beagle</th>\n",
       "      <th>Bearded Collie</th>\n",
       "      <th>Bermaise</th>\n",
       "      <th>Bichon Frise</th>\n",
       "      <th>Blenheim</th>\n",
       "      <th>Bloodhound</th>\n",
       "      <th>...</th>\n",
       "      <th>Komondor</th>\n",
       "      <th>Labrador</th>\n",
       "      <th>Maltese</th>\n",
       "      <th>Newfoundland</th>\n",
       "      <th>Pekinese</th>\n",
       "      <th>Pug</th>\n",
       "      <th>Shar_Pei</th>\n",
       "      <th>Shih-Tzu</th>\n",
       "      <th>Siberian Husky</th>\n",
       "      <th>Yorkie</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>user_id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>287 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "breed    Afghan  Airedale  American Spaniel  Basset  Beagle  Bearded Collie  \\\n",
       "user_id                                                                       \n",
       "1           5.0       0.0               0.0     0.0     4.0             5.0   \n",
       "2           5.0       0.0               0.0     0.0     5.0             0.0   \n",
       "3           0.0       0.0               0.0     0.0     5.0             5.0   \n",
       "4           5.0       0.0               0.0     0.0     5.0             0.0   \n",
       "5           5.0       0.0               0.0     0.0     4.0             5.0   \n",
       "...         ...       ...               ...     ...     ...             ...   \n",
       "296         0.0       0.0               0.0     0.0     0.0             0.0   \n",
       "297         0.0       0.0               0.0     0.0     0.0             0.0   \n",
       "298         0.0       0.0               0.0     0.0     0.0             0.0   \n",
       "299         0.0       0.0               0.0     0.0     0.0             0.0   \n",
       "300         0.0       0.0               0.0     0.0     0.0             0.0   \n",
       "\n",
       "breed    Bermaise  Bichon Frise  Blenheim  Bloodhound  ...  Komondor  \\\n",
       "user_id                                                ...             \n",
       "1             0.0           0.0       0.0         0.0  ...       0.0   \n",
       "2             0.0           0.0       0.0         0.0  ...       0.0   \n",
       "3             0.0           0.0       0.0         0.0  ...       0.0   \n",
       "4             0.0           0.0       0.0         0.0  ...       0.0   \n",
       "5             0.0           0.0       0.0         0.0  ...       0.0   \n",
       "...           ...           ...       ...         ...  ...       ...   \n",
       "296           0.0           0.0       0.0         0.0  ...       0.0   \n",
       "297           0.0           5.0       0.0         0.0  ...       0.0   \n",
       "298           0.0           5.0       0.0         0.0  ...       0.0   \n",
       "299           0.0           4.0       0.0         0.0  ...       0.0   \n",
       "300           0.0           5.0       0.0         0.0  ...       0.0   \n",
       "\n",
       "breed    Labrador  Maltese  Newfoundland  Pekinese  Pug  Shar_Pei  Shih-Tzu  \\\n",
       "user_id                                                                       \n",
       "1             0.0      0.0           5.0       0.0  0.0       5.0       0.0   \n",
       "2             0.0      0.0           5.0       0.0  2.0       5.0       2.0   \n",
       "3             0.0      0.0           5.0       0.0  0.0       1.0       0.0   \n",
       "4             0.0      0.0           5.0       0.0  2.0       5.0       0.0   \n",
       "5             0.0      0.0           5.0       0.0  0.0       0.0       0.0   \n",
       "...           ...      ...           ...       ...  ...       ...       ...   \n",
       "296           0.0      5.0           0.0       0.0  5.0       0.0       0.0   \n",
       "297           0.0      0.0           0.0       0.0  5.0       0.0       0.0   \n",
       "298           0.0      4.0           0.0       0.0  0.0       0.0       0.0   \n",
       "299           0.0      5.0           0.0       0.0  5.0       0.0       0.0   \n",
       "300           0.0      3.0           0.0       0.0  5.0       0.0       0.0   \n",
       "\n",
       "breed    Siberian Husky  Yorkie  \n",
       "user_id                          \n",
       "1                   0.0     0.0  \n",
       "2                   0.0     2.0  \n",
       "3                   0.0     1.0  \n",
       "4                   0.0     2.0  \n",
       "5                   0.0     0.0  \n",
       "...                 ...     ...  \n",
       "296                 0.0     5.0  \n",
       "297                 0.0     4.0  \n",
       "298                 0.0     4.0  \n",
       "299                 0.0     0.0  \n",
       "300                 0.0     5.0  \n",
       "\n",
       "[287 rows x 32 columns]"
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# pivot and create user-breed matrix\n",
    "user_breed_df = merged_df.pivot(\n",
    "    index='user_id',\n",
    "    columns='breed',\n",
    "      values='rating').fillna(0)\n",
    "\n",
    "user_breed_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "74b62ac1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 287 entries, 1 to 300\n",
      "Data columns (total 32 columns):\n",
      " #   Column            Non-Null Count  Dtype  \n",
      "---  ------            --------------  -----  \n",
      " 0   Afghan            287 non-null    float64\n",
      " 1   Airedale          287 non-null    float64\n",
      " 2   American Spaniel  287 non-null    float64\n",
      " 3   Basset            287 non-null    float64\n",
      " 4   Beagle            287 non-null    float64\n",
      " 5   Bearded Collie    287 non-null    float64\n",
      " 6   Bermaise          287 non-null    float64\n",
      " 7   Bichon Frise      287 non-null    float64\n",
      " 8   Blenheim          287 non-null    float64\n",
      " 9   Bloodhound        287 non-null    float64\n",
      " 10  Border Collie     287 non-null    float64\n",
      " 11  Borzoi            287 non-null    float64\n",
      " 12  Boston Terrier    287 non-null    float64\n",
      " 13  Boxer             287 non-null    float64\n",
      " 14  Bull Mastiff      287 non-null    float64\n",
      " 15  Bull Terrier      287 non-null    float64\n",
      " 16  Bulldog           287 non-null    float64\n",
      " 17  Chihuahua         287 non-null    float64\n",
      " 18  Chinese Crested   287 non-null    float64\n",
      " 19  Chow              287 non-null    float64\n",
      " 20  Corgi             287 non-null    float64\n",
      " 21  German Sheperd    287 non-null    float64\n",
      " 22  Komondor          287 non-null    float64\n",
      " 23  Labrador          287 non-null    float64\n",
      " 24  Maltese           287 non-null    float64\n",
      " 25  Newfoundland      287 non-null    float64\n",
      " 26  Pekinese          287 non-null    float64\n",
      " 27  Pug               287 non-null    float64\n",
      " 28  Shar_Pei          287 non-null    float64\n",
      " 29  Shih-Tzu          287 non-null    float64\n",
      " 30  Siberian Husky    287 non-null    float64\n",
      " 31  Yorkie            287 non-null    float64\n",
      "dtypes: float64(32)\n",
      "memory usage: 74.0 KB\n"
     ]
    }
   ],
   "source": [
    "user_breed_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "f4dd9bd8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<287x32 sparse matrix of type '<class 'numpy.float64'>'\n",
       "\twith 1528 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transform matrix to scipy sparse matrix\n",
    "user_breed_sparse_df = csr_matrix(user_breed_df.values)\n",
    "user_breed_sparse_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2fa8329e",
   "metadata": {},
   "source": [
    "#### Fitting K-Nearest Neighbours model to the scipy sparse matrix:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "533ab52a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "NearestNeighbors(algorithm='brute', metric='cosine')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn_model = NearestNeighbors(metric='cosine', algorithm='brute')\n",
    "knn_model.fit(user_breed_sparse_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "02c0f7eb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# function to find top n similar users of the given input user \n",
    "# input to this function is the user and number of top similar users you want.\n",
    "\n",
    "def get_similar_users(user, n = 5):\n",
    "    knn_input = user_breed_df.iloc[0,:].values.reshape(1,-1)\n",
    "    distances, indices = knn_model.kneighbors(knn_input, n_neighbors=n+1)\n",
    "  \n",
    "    print(\"Top\",n,\"users who are very much similar to the User-\",user, \"are: \")\n",
    "    print(\" \")\n",
    "    for i in range(1,len(distances[0])):\n",
    "        print(i,\". User:\", indices[0][i]+1, \"separated by distance of\",distances[0][i])\n",
    "    return indices.flatten()[1:] + 1, distances.flatten()[1:]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6aa85dc2",
   "metadata": {},
   "source": [
    "#### Specify User id and Number of similar users we want to consider here"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "0b7f8efd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Few of breeds rated by the user:\n",
      "['Borzoi',\n",
      " 'Newfoundland',\n",
      " 'Beagle',\n",
      " 'Bearded Collie',\n",
      " 'Border Collie',\n",
      " 'Shar_Pei',\n",
      " 'Pug',\n",
      " 'Yorkie']\n",
      "Top 5 users who are very much similar to the User- 7 are: \n",
      " \n",
      "1 . User: 21 separated by distance of 1.1102230246251565e-16\n",
      "2 . User: 17 separated by distance of 0.006369426751592466\n",
      "3 . User: 37 separated by distance of 0.03506106087571981\n",
      "4 . User: 91 separated by distance of 0.039874889844745076\n",
      "5 . User: 5 separated by distance of 0.08306797895907736\n"
     ]
    }
   ],
   "source": [
    "from pprint import pprint\n",
    "user_id = 7\n",
    "print(\"Few of breeds rated by the user:\")\n",
    "pprint(list(merged_df[merged_df['user_id'] == user_id]['breed'])[:10])\n",
    "similar_user_list, distance_list = get_similar_users(user_id,5)\n",
    "# "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "30309ff2",
   "metadata": {},
   "source": [
    "#### We will have to pick the top breeds to recommend."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "7442561d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([21, 17, 37, 91,  5], dtype=int64),\n",
       " array([1.11022302e-16, 6.36942675e-03, 3.50610609e-02, 3.98748898e-02,\n",
       "        8.30679790e-02]))"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "similar_user_list, distance_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "db7207f3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([6.75427605e-16, 3.87497517e-02, 2.13301362e-01, 2.42587307e-01,\n",
       "       5.05361579e-01])"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weightage_list = distance_list/np.sum(distance_list)\n",
    "weightage_list"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9b7ed06",
   "metadata": {},
   "source": [
    "Getting ratings of all breeds by similar users"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "aa96833b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5., 0., 0., 0., 5., 0., 0., 0., 0., 0., 5., 0., 0., 0., 0., 0.,\n",
       "        0., 0., 0., 0., 0., 0., 0., 0., 0., 5., 0., 2., 5., 2., 0., 2.],\n",
       "       [5., 0., 0., 0., 5., 5., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 5., 0., 5., 0.],\n",
       "       [5., 0., 0., 0., 5., 4., 0., 0., 0., 0., 5., 4., 0., 0., 0., 0.,\n",
       "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 5., 0., 5., 0.],\n",
       "       [5., 0., 0., 0., 5., 5., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "        0., 0., 0., 0., 0., 0., 0., 0., 0., 4., 0., 0., 1., 0., 0., 1.],\n",
       "       [5., 0., 0., 0., 5., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
       "        0., 0., 0., 0., 0., 0., 0., 0., 0., 5., 0., 0., 5., 0., 0., 0.]])"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "breed_rtngs_sim_users = user_breed_df.values[similar_user_list]\n",
    "breed_rtngs_sim_users"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "0ecd20e2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Afghan', 'Airedale', 'American Spaniel', 'Basset', 'Beagle',\n",
       "       'Bearded Collie', 'Bermaise', 'Bichon Frise', 'Blenheim', 'Bloodhound',\n",
       "       'Border Collie', 'Borzoi', 'Boston Terrier', 'Boxer', 'Bull Mastiff',\n",
       "       'Bull Terrier', 'Bulldog', 'Chihuahua', 'Chinese Crested', 'Chow',\n",
       "       'Corgi', 'German Sheperd', 'Komondor', 'Labrador', 'Maltese',\n",
       "       'Newfoundland', 'Pekinese', 'Pug', 'Shar_Pei', 'Shih-Tzu',\n",
       "       'Siberian Husky', 'Yorkie'],\n",
       "      dtype='object', name='breed')"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "breeds_list = user_breed_df.columns\n",
    "breeds_list "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "bd4b77bf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Weightage list shape: 5\n",
      "breed_rtngs_sim_users shape: (5, 32)\n",
      "Number of breeds: 32\n"
     ]
    }
   ],
   "source": [
    "print(\"Weightage list shape:\", len(weightage_list))\n",
    "print(\"breed_rtngs_sim_users shape:\", breed_rtngs_sim_users.shape)\n",
    "print(\"Number of breeds:\", len(breeds_list))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "7903d4df",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5, 32)"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weightage_list = weightage_list[:,np.newaxis] + np.zeros(len(breeds_list))\n",
    "weightage_list.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "d7614ea1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
       "       5.00000000e+00, 2.25989074e+00, 0.00000000e+00, 0.00000000e+00,\n",
       "       0.00000000e+00, 0.00000000e+00, 1.06650681e+00, 8.53205450e-01,\n",
       "       0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
       "       0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
       "       0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
       "       0.00000000e+00, 3.49715712e+00, 0.00000000e+00, 1.35085521e-15,\n",
       "       4.02965077e+00, 1.35085521e-15, 1.26025557e+00, 2.42587307e-01])"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_rating_matrix = weightage_list*breed_rtngs_sim_users\n",
    "mean_rating_list = new_rating_matrix.sum(axis =0)\n",
    "mean_rating_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "ce5596db",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pprint import pprint\n",
    "def recommend_breeds(n):\n",
    "  n = min(len(mean_rating_list),n)\n",
    "  # print(np.argsort(mean_rating_list)[::-1][:n])\n",
    "  pprint(list(breeds_list[np.argsort(mean_rating_list)[::-1][:n]]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "e628e7af",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Breeds recommended based on similar users are: \n",
      "['Afghan', 'Beagle', 'Shar_Pei', 'Newfoundland', 'Bearded Collie']\n"
     ]
    }
   ],
   "source": [
    "print(\"Breeds recommended based on similar users are: \")\n",
    "recommend_breeds(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f7987bc",
   "metadata": {},
   "source": [
    "#### Breed Recommendation using KNN with Input as Breed and Number of breeds you want to get recommended:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "66a072f1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>user_id</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>...</th>\n",
       "      <th>291</th>\n",
       "      <th>292</th>\n",
       "      <th>293</th>\n",
       "      <th>294</th>\n",
       "      <th>295</th>\n",
       "      <th>296</th>\n",
       "      <th>297</th>\n",
       "      <th>298</th>\n",
       "      <th>299</th>\n",
       "      <th>300</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>breed</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Afghan</th>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Airedale</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>American Spaniel</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Basset</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Beagle</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bearded Collie</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bermaise</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bichon Frise</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Blenheim</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bloodhound</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Border Collie</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Borzoi</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boston Terrier</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boxer</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bull Mastiff</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bull Terrier</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bulldog</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chihuahua</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chinese Crested</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chow</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Corgi</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>German Sheperd</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Komondor</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Labrador</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Maltese</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Newfoundland</th>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pekinese</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pug</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Shar_Pei</th>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Shih-Tzu</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Siberian Husky</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yorkie</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>32 rows × 287 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "user_id           1    2    3    4    5    6    7    8    9    10   ...  291  \\\n",
       "breed                                                               ...        \n",
       "Afghan            5.0  5.0  0.0  5.0  5.0  5.0  0.0  0.0  0.0  5.0  ...  0.0   \n",
       "Airedale          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "American Spaniel  0.0  0.0  0.0  0.0  0.0  0.0  0.0  4.0  4.0  0.0  ...  0.0   \n",
       "Basset            0.0  0.0  0.0  0.0  0.0  0.0  0.0  4.0  4.0  0.0  ...  0.0   \n",
       "Beagle            4.0  5.0  5.0  5.0  4.0  5.0  5.0  0.0  5.0  5.0  ...  0.0   \n",
       "Bearded Collie    5.0  0.0  5.0  0.0  5.0  0.0  4.0  0.0  5.0  5.0  ...  0.0   \n",
       "Bermaise          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Bichon Frise      0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  5.0   \n",
       "Blenheim          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Bloodhound        0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Border Collie     4.0  5.0  0.0  4.0  4.0  0.0  5.0  0.0  5.0  0.0  ...  0.0   \n",
       "Borzoi            5.0  0.0  5.0  0.0  5.0  0.0  5.0  0.0  5.0  5.0  ...  0.0   \n",
       "Boston Terrier    0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Boxer             0.0  0.0  0.0  0.0  0.0  0.0  0.0  4.0  4.0  0.0  ...  0.0   \n",
       "Bull Mastiff      0.0  0.0  0.0  0.0  0.0  0.0  0.0  5.0  5.0  0.0  ...  0.0   \n",
       "Bull Terrier      0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Bulldog           0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  5.0   \n",
       "Chihuahua         0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Chinese Crested   0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Chow              0.0  0.0  0.0  0.0  0.0  0.0  0.0  5.0  4.0  0.0  ...  0.0   \n",
       "Corgi             0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "German Sheperd    0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Komondor          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Labrador          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Maltese           0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  5.0   \n",
       "Newfoundland      5.0  5.0  5.0  5.0  5.0  5.0  5.0  0.0  5.0  5.0  ...  0.0   \n",
       "Pekinese          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Pug               0.0  2.0  0.0  2.0  0.0  0.0  2.0  0.0  0.0  0.0  ...  5.0   \n",
       "Shar_Pei          5.0  5.0  1.0  5.0  0.0  5.0  5.0  0.0  0.0  0.0  ...  0.0   \n",
       "Shih-Tzu          0.0  2.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0   \n",
       "Siberian Husky    0.0  0.0  0.0  0.0  0.0  0.0  0.0  4.0  5.0  0.0  ...  0.0   \n",
       "Yorkie            0.0  2.0  1.0  2.0  0.0  0.0  1.0  0.0  0.0  0.0  ...  5.0   \n",
       "\n",
       "user_id           292  293  294  295  296  297  298  299  300  \n",
       "breed                                                          \n",
       "Afghan            0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Airedale          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "American Spaniel  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Basset            0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Beagle            0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bearded Collie    0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bermaise          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bichon Frise      5.0  0.0  5.0  5.0  0.0  5.0  5.0  4.0  5.0  \n",
       "Blenheim          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bloodhound        0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Border Collie     0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Borzoi            0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Boston Terrier    0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Boxer             0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bull Mastiff      0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bull Terrier      0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Bulldog           0.0  5.0  4.0  4.0  5.0  5.0  5.0  5.0  4.0  \n",
       "Chihuahua         0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Chinese Crested   0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Chow              0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Corgi             0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "German Sheperd    0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Komondor          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Labrador          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Maltese           5.0  5.0  5.0  4.0  5.0  0.0  4.0  5.0  3.0  \n",
       "Newfoundland      0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Pekinese          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Pug               5.0  5.0  5.0  5.0  5.0  5.0  0.0  5.0  5.0  \n",
       "Shar_Pei          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Shih-Tzu          0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Siberian Husky    0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  0.0  \n",
       "Yorkie            0.0  4.0  5.0  5.0  5.0  4.0  4.0  0.0  5.0  \n",
       "\n",
       "[32 rows x 287 columns]"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# pivot and create breed-user matrix\n",
    "breed_user_df = merged_df.pivot(\n",
    "    index='breed',\n",
    "    columns='user_id',\n",
    "      values='rating').fillna(0)\n",
    "\n",
    "breed_user_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "12616731",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<32x287 sparse matrix of type '<class 'numpy.float64'>'\n",
       "\twith 1528 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transform matrix to scipy sparse matrix\n",
    "breed_user_sparse_df = csr_matrix(breed_user_df.values)\n",
    "breed_user_sparse_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d92377f2",
   "metadata": {},
   "source": [
    "Extracting breeds into a list:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "64bef989",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Afghan',\n",
       " 'Airedale',\n",
       " 'American Spaniel',\n",
       " 'Basset',\n",
       " 'Beagle',\n",
       " 'Bearded Collie',\n",
       " 'Bermaise',\n",
       " 'Bichon Frise',\n",
       " 'Blenheim',\n",
       " 'Bloodhound',\n",
       " 'Border Collie',\n",
       " 'Borzoi',\n",
       " 'Boston Terrier',\n",
       " 'Boxer',\n",
       " 'Bull Mastiff',\n",
       " 'Bull Terrier',\n",
       " 'Bulldog',\n",
       " 'Chihuahua',\n",
       " 'Chinese Crested',\n",
       " 'Chow',\n",
       " 'Corgi',\n",
       " 'German Sheperd',\n",
       " 'Komondor',\n",
       " 'Labrador',\n",
       " 'Maltese',\n",
       " 'Newfoundland',\n",
       " 'Pekinese',\n",
       " 'Pug',\n",
       " 'Shar_Pei',\n",
       " 'Shih-Tzu',\n",
       " 'Siberian Husky',\n",
       " 'Yorkie']"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "breed_list = list(breed_user_df.index)\n",
    "breed_list"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "190605b4",
   "metadata": {},
   "source": [
    "Creating a dictionary with breed as key and its index from the list as value:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "2f179aaa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'Afghan': 0, 'Airedale': 1, 'American Spaniel': 2, 'Basset': 3, 'Beagle': 4, 'Bearded Collie': 5, 'Bermaise': 6, 'Bichon Frise': 7, 'Blenheim': 8, 'Bloodhound': 9, 'Border Collie': 10, 'Borzoi': 11, 'Boston Terrier': 12, 'Boxer': 13, 'Bull Mastiff': 14, 'Bull Terrier': 15, 'Bulldog': 16, 'Chihuahua': 17, 'Chinese Crested': 18, 'Chow': 19, 'Corgi': 20, 'German Sheperd': 21, 'Komondor': 22, 'Labrador': 23, 'Maltese': 24, 'Newfoundland': 25, 'Pekinese': 26, 'Pug': 27, 'Shar_Pei': 28, 'Shih-Tzu': 29, 'Siberian Husky': 30, 'Yorkie': 31}\n"
     ]
    }
   ],
   "source": [
    "breed_dict = {breed : index for index, breed in enumerate(breed_list)}\n",
    "print(breed_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "3dd232b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "case_insensitive_breed_list = [i.lower() for i in breed_list]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe0cd75a",
   "metadata": {},
   "source": [
    "Fitting a KNN model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "id": "359d0a57",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "NearestNeighbors(algorithm='brute', metric='cosine')"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn_breed_model = NearestNeighbors(metric='cosine', algorithm='brute')\n",
    "knn_breed_model.fit(breed_user_sparse_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "e5994fb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "## function to find top n similar users of the given input user \n",
    "def get_similar_breeds(breed, n = 10):\n",
    "  ## input to this function is breed and number of top similar breeds you want.\n",
    "    index = breed_dict[breed]\n",
    "    knn_input = np.asarray([breed_user_df.values[index]])\n",
    "    n = min(len(breed_list)-1,n)\n",
    "    distances, indices = knn_breed_model.kneighbors(knn_input, n_neighbors=n+1)\n",
    "  \n",
    "    print(\"Top\",n,\"breeds which are very much similar to the Breed-\",breed, \"are: \")\n",
    "    print(\" \")\n",
    "    for i in range(1,len(distances[0])):\n",
    "        print(breed_list[indices[0][i]])\n",
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4c247b84",
   "metadata": {},
   "source": [
    "#### Testing the recommender system with basic input with breed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "0ade42e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top 6 breeds which are very much similar to the Breed- Newfoundland are: \n",
      " \n",
      "Afghan\n",
      "Borzoi\n",
      "Beagle\n",
      "Border Collie\n",
      "Shar_Pei\n",
      "Bearded Collie\n"
     ]
    }
   ],
   "source": [
    "from pprint import pprint\n",
    "breed = 'Newfoundland'\n",
    "\n",
    "get_similar_breeds(breed, 6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "21529ab6",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "38c911d9",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}