The Algorithms logo
The Algorithms
Про AlgorithmsПожертвувати

Association

H
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['MILK', 'BREAD', 'BISCUIT'],\n",
       " ['BREAD', 'MILK', 'BISCUIT', 'CORNFLAKES'],\n",
       " ['BREAD', 'TEA', 'BOURNVITA'],\n",
       " ['JAM', 'MAGGI', 'BREAD', 'MILK'],\n",
       " ['MAGGI', 'TEA', 'BISCUIT'],\n",
       " ['BREAD', 'TEA', 'BOURNVITA'],\n",
       " ['MAGGI', 'TEA', 'CORNFLAKES'],\n",
       " ['MAGGI', 'BREAD', 'TEA', 'BISCUIT'],\n",
       " ['JAM', 'MAGGI', 'BREAD', 'TEA'],\n",
       " ['BREAD', 'MILK'],\n",
       " ['COFFEE', 'COCK', 'BISCUIT', 'CORNFLAKES'],\n",
       " ['COFFEE', 'COCK', 'BISCUIT', 'CORNFLAKES'],\n",
       " ['COFFEE', 'SUGER', 'BOURNVITA'],\n",
       " ['BREAD', 'COFFEE', 'COCK'],\n",
       " ['BREAD', 'SUGER', 'BISCUIT'],\n",
       " ['COFFEE', 'SUGER', 'CORNFLAKES'],\n",
       " ['BREAD', 'SUGER', 'BOURNVITA'],\n",
       " ['BREAD', 'COFFEE', 'SUGER'],\n",
       " ['BREAD', 'COFFEE', 'SUGER'],\n",
       " ['TEA', 'MILK', 'COFFEE', 'CORNFLAKES']]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from mlxtend.preprocessing import TransactionEncoder\n",
    "from mlxtend.frequent_patterns import apriori\n",
    "\n",
    "df = pd.read_csv(\"grocery_data.csv\")\n",
    "data = list(df[\"products\"].apply(lambda x:x.split(',')))\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>BISCUIT</th>\n",
       "      <th>BOURNVITA</th>\n",
       "      <th>BREAD</th>\n",
       "      <th>COCK</th>\n",
       "      <th>COFFEE</th>\n",
       "      <th>CORNFLAKES</th>\n",
       "      <th>JAM</th>\n",
       "      <th>MAGGI</th>\n",
       "      <th>MILK</th>\n",
       "      <th>SUGER</th>\n",
       "      <th>TEA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    BISCUIT  BOURNVITA  BREAD  COCK  COFFEE  CORNFLAKES  JAM  MAGGI  MILK  \\\n",
       "0         1          0      1     0       0           0    0      0     1   \n",
       "1         1          0      1     0       0           1    0      0     1   \n",
       "2         0          1      1     0       0           0    0      0     0   \n",
       "3         0          0      1     0       0           0    1      1     1   \n",
       "4         1          0      0     0       0           0    0      1     0   \n",
       "5         0          1      1     0       0           0    0      0     0   \n",
       "6         0          0      0     0       0           1    0      1     0   \n",
       "7         1          0      1     0       0           0    0      1     0   \n",
       "8         0          0      1     0       0           0    1      1     0   \n",
       "9         0          0      1     0       0           0    0      0     1   \n",
       "10        1          0      0     1       1           1    0      0     0   \n",
       "11        1          0      0     1       1           1    0      0     0   \n",
       "12        0          1      0     0       1           0    0      0     0   \n",
       "13        0          0      1     1       1           0    0      0     0   \n",
       "14        1          0      1     0       0           0    0      0     0   \n",
       "15        0          0      0     0       1           1    0      0     0   \n",
       "16        0          1      1     0       0           0    0      0     0   \n",
       "17        0          0      1     0       1           0    0      0     0   \n",
       "18        0          0      1     0       1           0    0      0     0   \n",
       "19        0          0      0     0       1           1    0      0     1   \n",
       "\n",
       "    SUGER  TEA  \n",
       "0       0    0  \n",
       "1       0    0  \n",
       "2       0    1  \n",
       "3       0    0  \n",
       "4       0    1  \n",
       "5       0    1  \n",
       "6       0    1  \n",
       "7       0    1  \n",
       "8       0    1  \n",
       "9       0    0  \n",
       "10      0    0  \n",
       "11      0    0  \n",
       "12      1    0  \n",
       "13      0    0  \n",
       "14      1    0  \n",
       "15      1    0  \n",
       "16      1    0  \n",
       "17      1    0  \n",
       "18      1    0  \n",
       "19      0    1  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "te = TransactionEncoder()\n",
    "\n",
    "te_data = te.fit(data).transform(data).astype(\"int\")\n",
    "df = pd.DataFrame(te_data,columns=te.columns_)\n",
    "df\n",
    "# df.to_csv(\"transformed_data.csv\", encoding='utf-8', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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>support</th>\n",
       "      <th>itemsets</th>\n",
       "      <th>length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.35</td>\n",
       "      <td>(BISCUIT)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(BOURNVITA)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.65</td>\n",
       "      <td>(BREAD)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(COCK)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.40</td>\n",
       "      <td>(COFFEE)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.30</td>\n",
       "      <td>(CORNFLAKES)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(JAM)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.25</td>\n",
       "      <td>(MAGGI)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.25</td>\n",
       "      <td>(MILK)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.30</td>\n",
       "      <td>(SUGER)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.35</td>\n",
       "      <td>(TEA)</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(BISCUIT, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, COCK)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BISCUIT, CORNFLAKES)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(MILK, BISCUIT)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(BISCUIT, SUGER)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, TEA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BREAD, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(COFFEE, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(SUGER, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(TEA, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(COCK, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BREAD, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(JAM, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BREAD, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(MILK, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(BREAD, SUGER)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(CORNFLAKES, BISCUIT, COCK)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(CORNFLAKES, BISCUIT, COFFEE)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, BISCUIT, CORNFLAKES)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>56</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, TEA, MAGGI)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(SUGER, BREAD, BOURNVITA)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(TEA, BREAD, BOURNVITA)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(SUGER, COFFEE, BOURNVITA)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(COCK, BREAD, COFFEE)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BREAD, COFFEE, SUGER)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, MILK, BREAD)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(JAM, BREAD, MAGGI)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, BREAD, JAM)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(JAM, TEA, BREAD)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, BREAD, MAGGI)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(TEA, BREAD, MAGGI)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(CORNFLAKES, COCK, COFFEE)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, MILK, COFFEE)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, COFFEE, SUGER)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, TEA, COFFEE)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, TEA, COFFEE)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>73</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(TEA, CORNFLAKES, MAGGI)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, TEA, CORNFLAKES)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MAGGI, MILK, JAM)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(JAM, TEA, MAGGI)</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, MILK, BISCUIT, BREAD)</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(TEA, BISCUIT, BREAD, MAGGI)</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(CORNFLAKES, BISCUIT, COCK, COFFEE)</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MAGGI, MILK, BREAD, JAM)</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(JAM, TEA, BREAD, MAGGI)</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, MILK, TEA, COFFEE)</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>83 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    support                             itemsets  length\n",
       "0      0.35                            (BISCUIT)       1\n",
       "1      0.20                          (BOURNVITA)       1\n",
       "2      0.65                              (BREAD)       1\n",
       "3      0.15                               (COCK)       1\n",
       "4      0.40                             (COFFEE)       1\n",
       "5      0.30                         (CORNFLAKES)       1\n",
       "6      0.10                                (JAM)       1\n",
       "7      0.25                              (MAGGI)       1\n",
       "8      0.25                               (MILK)       1\n",
       "9      0.30                              (SUGER)       1\n",
       "10     0.35                                (TEA)       1\n",
       "11     0.20                     (BISCUIT, BREAD)       2\n",
       "12     0.10                      (BISCUIT, COCK)       2\n",
       "13     0.10                    (BISCUIT, COFFEE)       2\n",
       "14     0.15                (BISCUIT, CORNFLAKES)       2\n",
       "15     0.10                     (BISCUIT, MAGGI)       2\n",
       "16     0.10                      (MILK, BISCUIT)       2\n",
       "17     0.05                     (BISCUIT, SUGER)       2\n",
       "18     0.10                       (BISCUIT, TEA)       2\n",
       "19     0.15                   (BREAD, BOURNVITA)       2\n",
       "20     0.05                  (COFFEE, BOURNVITA)       2\n",
       "21     0.10                   (SUGER, BOURNVITA)       2\n",
       "22     0.10                     (TEA, BOURNVITA)       2\n",
       "23     0.05                        (COCK, BREAD)       2\n",
       "24     0.15                      (BREAD, COFFEE)       2\n",
       "25     0.05                  (CORNFLAKES, BREAD)       2\n",
       "26     0.10                         (JAM, BREAD)       2\n",
       "27     0.15                       (BREAD, MAGGI)       2\n",
       "28     0.20                        (MILK, BREAD)       2\n",
       "29     0.20                       (BREAD, SUGER)       2\n",
       "..      ...                                  ...     ...\n",
       "53     0.10          (CORNFLAKES, BISCUIT, COCK)       3\n",
       "54     0.10        (CORNFLAKES, BISCUIT, COFFEE)       3\n",
       "55     0.05          (MILK, BISCUIT, CORNFLAKES)       3\n",
       "56     0.10                (BISCUIT, TEA, MAGGI)       3\n",
       "57     0.05            (SUGER, BREAD, BOURNVITA)       3\n",
       "58     0.10              (TEA, BREAD, BOURNVITA)       3\n",
       "59     0.05           (SUGER, COFFEE, BOURNVITA)       3\n",
       "60     0.05                (COCK, BREAD, COFFEE)       3\n",
       "61     0.10               (BREAD, COFFEE, SUGER)       3\n",
       "62     0.05            (CORNFLAKES, MILK, BREAD)       3\n",
       "63     0.10                  (JAM, BREAD, MAGGI)       3\n",
       "64     0.05                   (MILK, BREAD, JAM)       3\n",
       "65     0.05                    (JAM, TEA, BREAD)       3\n",
       "66     0.05                 (MILK, BREAD, MAGGI)       3\n",
       "67     0.10                  (TEA, BREAD, MAGGI)       3\n",
       "68     0.10           (CORNFLAKES, COCK, COFFEE)       3\n",
       "69     0.05           (CORNFLAKES, MILK, COFFEE)       3\n",
       "70     0.05          (CORNFLAKES, COFFEE, SUGER)       3\n",
       "71     0.05            (CORNFLAKES, TEA, COFFEE)       3\n",
       "72     0.05                  (MILK, TEA, COFFEE)       3\n",
       "73     0.05             (TEA, CORNFLAKES, MAGGI)       3\n",
       "74     0.05              (MILK, TEA, CORNFLAKES)       3\n",
       "75     0.05                   (MAGGI, MILK, JAM)       3\n",
       "76     0.05                    (JAM, TEA, MAGGI)       3\n",
       "77     0.05   (CORNFLAKES, MILK, BISCUIT, BREAD)       4\n",
       "78     0.05         (TEA, BISCUIT, BREAD, MAGGI)       4\n",
       "79     0.10  (CORNFLAKES, BISCUIT, COCK, COFFEE)       4\n",
       "80     0.05            (MAGGI, MILK, BREAD, JAM)       4\n",
       "81     0.05             (JAM, TEA, BREAD, MAGGI)       4\n",
       "82     0.05      (CORNFLAKES, MILK, TEA, COFFEE)       4\n",
       "\n",
       "[83 rows x 3 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "apriori_data = apriori(df,min_support=0.01,use_colnames=True)\n",
    "apriori_data.sort_values(by=\"support\",ascending=False)\n",
    "apriori_data['length'] = apriori_data['itemsets'].apply(lambda x:len(x))\n",
    "\n",
    "apriori_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "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>support</th>\n",
       "      <th>itemsets</th>\n",
       "      <th>length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(BISCUIT, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, COCK)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BISCUIT, CORNFLAKES)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(MILK, BISCUIT)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(BISCUIT, SUGER)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(BISCUIT, TEA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BREAD, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(COFFEE, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(SUGER, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(TEA, BOURNVITA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(COCK, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BREAD, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(JAM, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(BREAD, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(MILK, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(BREAD, SUGER)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(TEA, BREAD)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>0.15</td>\n",
       "      <td>(COCK, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(CORNFLAKES, COCK)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(CORNFLAKES, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(COFFEE, SUGER)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(TEA, COFFEE)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(MILK, CORNFLAKES)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(CORNFLAKES, SUGER)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(TEA, CORNFLAKES)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>0.10</td>\n",
       "      <td>(JAM, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, JAM)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(JAM, TEA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>0.20</td>\n",
       "      <td>(TEA, MAGGI)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>0.05</td>\n",
       "      <td>(MILK, TEA)</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    support               itemsets  length\n",
       "11     0.20       (BISCUIT, BREAD)       2\n",
       "12     0.10        (BISCUIT, COCK)       2\n",
       "13     0.10      (BISCUIT, COFFEE)       2\n",
       "14     0.15  (BISCUIT, CORNFLAKES)       2\n",
       "15     0.10       (BISCUIT, MAGGI)       2\n",
       "16     0.10        (MILK, BISCUIT)       2\n",
       "17     0.05       (BISCUIT, SUGER)       2\n",
       "18     0.10         (BISCUIT, TEA)       2\n",
       "19     0.15     (BREAD, BOURNVITA)       2\n",
       "20     0.05    (COFFEE, BOURNVITA)       2\n",
       "21     0.10     (SUGER, BOURNVITA)       2\n",
       "22     0.10       (TEA, BOURNVITA)       2\n",
       "23     0.05          (COCK, BREAD)       2\n",
       "24     0.15        (BREAD, COFFEE)       2\n",
       "25     0.05    (CORNFLAKES, BREAD)       2\n",
       "26     0.10           (JAM, BREAD)       2\n",
       "27     0.15         (BREAD, MAGGI)       2\n",
       "28     0.20          (MILK, BREAD)       2\n",
       "29     0.20         (BREAD, SUGER)       2\n",
       "30     0.20           (TEA, BREAD)       2\n",
       "31     0.15         (COCK, COFFEE)       2\n",
       "32     0.10     (CORNFLAKES, COCK)       2\n",
       "33     0.20   (CORNFLAKES, COFFEE)       2\n",
       "34     0.05         (MILK, COFFEE)       2\n",
       "35     0.20        (COFFEE, SUGER)       2\n",
       "36     0.05          (TEA, COFFEE)       2\n",
       "37     0.05    (CORNFLAKES, MAGGI)       2\n",
       "38     0.10     (MILK, CORNFLAKES)       2\n",
       "39     0.05    (CORNFLAKES, SUGER)       2\n",
       "40     0.10      (TEA, CORNFLAKES)       2\n",
       "41     0.10           (JAM, MAGGI)       2\n",
       "42     0.05            (MILK, JAM)       2\n",
       "43     0.05             (JAM, TEA)       2\n",
       "44     0.05          (MILK, MAGGI)       2\n",
       "45     0.20           (TEA, MAGGI)       2\n",
       "46     0.05            (MILK, TEA)       2"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "apriori_data[(apriori_data['length']==2) & (apriori_data['support']>=0.05)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}
Переглянути на GitHub
Випробувати цей код
Про Алгоритм
import pandas as pd
from mlxtend.preprocessing import TransactionEncoder
from mlxtend.frequent_patterns import apriori

df = pd.read_csv("grocery_data.csv")
data = list(df["products"].apply(lambda x:x.split(',')))
data
[[&#x27;MILK&#x27;, &#x27;BREAD&#x27;, &#x27;BISCUIT&#x27;],
 [&#x27;BREAD&#x27;, &#x27;MILK&#x27;, &#x27;BISCUIT&#x27;, &#x27;CORNFLAKES&#x27;],
 [&#x27;BREAD&#x27;, &#x27;TEA&#x27;, &#x27;BOURNVITA&#x27;],
 [&#x27;JAM&#x27;, &#x27;MAGGI&#x27;, &#x27;BREAD&#x27;, &#x27;MILK&#x27;],
 [&#x27;MAGGI&#x27;, &#x27;TEA&#x27;, &#x27;BISCUIT&#x27;],
 [&#x27;BREAD&#x27;, &#x27;TEA&#x27;, &#x27;BOURNVITA&#x27;],
 [&#x27;MAGGI&#x27;, &#x27;TEA&#x27;, &#x27;CORNFLAKES&#x27;],
 [&#x27;MAGGI&#x27;, &#x27;BREAD&#x27;, &#x27;TEA&#x27;, &#x27;BISCUIT&#x27;],
 [&#x27;JAM&#x27;, &#x27;MAGGI&#x27;, &#x27;BREAD&#x27;, &#x27;TEA&#x27;],
 [&#x27;BREAD&#x27;, &#x27;MILK&#x27;],
 [&#x27;COFFEE&#x27;, &#x27;COCK&#x27;, &#x27;BISCUIT&#x27;, &#x27;CORNFLAKES&#x27;],
 [&#x27;COFFEE&#x27;, &#x27;COCK&#x27;, &#x27;BISCUIT&#x27;, &#x27;CORNFLAKES&#x27;],
 [&#x27;COFFEE&#x27;, &#x27;SUGER&#x27;, &#x27;BOURNVITA&#x27;],
 [&#x27;BREAD&#x27;, &#x27;COFFEE&#x27;, &#x27;COCK&#x27;],
 [&#x27;BREAD&#x27;, &#x27;SUGER&#x27;, &#x27;BISCUIT&#x27;],
 [&#x27;COFFEE&#x27;, &#x27;SUGER&#x27;, &#x27;CORNFLAKES&#x27;],
 [&#x27;BREAD&#x27;, &#x27;SUGER&#x27;, &#x27;BOURNVITA&#x27;],
 [&#x27;BREAD&#x27;, &#x27;COFFEE&#x27;, &#x27;SUGER&#x27;],
 [&#x27;BREAD&#x27;, &#x27;COFFEE&#x27;, &#x27;SUGER&#x27;],
 [&#x27;TEA&#x27;, &#x27;MILK&#x27;, &#x27;COFFEE&#x27;, &#x27;CORNFLAKES&#x27;]]
te = TransactionEncoder()

te_data = te.fit(data).transform(data).astype("int")
df = pd.DataFrame(te_data,columns=te.columns_)
df
# df.to_csv("transformed_data.csv", encoding='utf-8', index=False)
BISCUIT BOURNVITA BREAD COCK COFFEE CORNFLAKES JAM MAGGI MILK SUGER TEA
0 1 0 1 0 0 0 0 0 1 0 0
1 1 0 1 0 0 1 0 0 1 0 0
2 0 1 1 0 0 0 0 0 0 0 1
3 0 0 1 0 0 0 1 1 1 0 0
4 1 0 0 0 0 0 0 1 0 0 1
5 0 1 1 0 0 0 0 0 0 0 1
6 0 0 0 0 0 1 0 1 0 0 1
7 1 0 1 0 0 0 0 1 0 0 1
8 0 0 1 0 0 0 1 1 0 0 1
9 0 0 1 0 0 0 0 0 1 0 0
10 1 0 0 1 1 1 0 0 0 0 0
11 1 0 0 1 1 1 0 0 0 0 0
12 0 1 0 0 1 0 0 0 0 1 0
13 0 0 1 1 1 0 0 0 0 0 0
14 1 0 1 0 0 0 0 0 0 1 0
15 0 0 0 0 1 1 0 0 0 1 0
16 0 1 1 0 0 0 0 0 0 1 0
17 0 0 1 0 1 0 0 0 0 1 0
18 0 0 1 0 1 0 0 0 0 1 0
19 0 0 0 0 1 1 0 0 1 0 1 
apriori_data = apriori(df,min_support=0.01,use_colnames=True)
apriori_data.sort_values(by="support",ascending=False)
apriori_data['length'] = apriori_data['itemsets'].apply(lambda x:len(x))

apriori_data
support itemsets length
0 0.35 (BISCUIT) 1
1 0.20 (BOURNVITA) 1
2 0.65 (BREAD) 1
3 0.15 (COCK) 1
4 0.40 (COFFEE) 1
5 0.30 (CORNFLAKES) 1
6 0.10 (JAM) 1
7 0.25 (MAGGI) 1
8 0.25 (MILK) 1
9 0.30 (SUGER) 1
10 0.35 (TEA) 1
11 0.20 (BISCUIT, BREAD) 2
12 0.10 (BISCUIT, COCK) 2
13 0.10 (BISCUIT, COFFEE) 2
14 0.15 (BISCUIT, CORNFLAKES) 2
15 0.10 (BISCUIT, MAGGI) 2
16 0.10 (MILK, BISCUIT) 2
17 0.05 (BISCUIT, SUGER) 2
18 0.10 (BISCUIT, TEA) 2
19 0.15 (BREAD, BOURNVITA) 2
20 0.05 (COFFEE, BOURNVITA) 2
21 0.10 (SUGER, BOURNVITA) 2
22 0.10 (TEA, BOURNVITA) 2
23 0.05 (COCK, BREAD) 2
24 0.15 (BREAD, COFFEE) 2
25 0.05 (CORNFLAKES, BREAD) 2
26 0.10 (JAM, BREAD) 2
27 0.15 (BREAD, MAGGI) 2
28 0.20 (MILK, BREAD) 2
29 0.20 (BREAD, SUGER) 2
... ... ... ...
53 0.10 (CORNFLAKES, BISCUIT, COCK) 3
54 0.10 (CORNFLAKES, BISCUIT, COFFEE) 3
55 0.05 (MILK, BISCUIT, CORNFLAKES) 3
56 0.10 (BISCUIT, TEA, MAGGI) 3
57 0.05 (SUGER, BREAD, BOURNVITA) 3
58 0.10 (TEA, BREAD, BOURNVITA) 3
59 0.05 (SUGER, COFFEE, BOURNVITA) 3
60 0.05 (COCK, BREAD, COFFEE) 3
61 0.10 (BREAD, COFFEE, SUGER) 3
62 0.05 (CORNFLAKES, MILK, BREAD) 3
63 0.10 (JAM, BREAD, MAGGI) 3
64 0.05 (MILK, BREAD, JAM) 3
65 0.05 (JAM, TEA, BREAD) 3
66 0.05 (MILK, BREAD, MAGGI) 3
67 0.10 (TEA, BREAD, MAGGI) 3
68 0.10 (CORNFLAKES, COCK, COFFEE) 3
69 0.05 (CORNFLAKES, MILK, COFFEE) 3
70 0.05 (CORNFLAKES, COFFEE, SUGER) 3
71 0.05 (CORNFLAKES, TEA, COFFEE) 3
72 0.05 (MILK, TEA, COFFEE) 3
73 0.05 (TEA, CORNFLAKES, MAGGI) 3
74 0.05 (MILK, TEA, CORNFLAKES) 3
75 0.05 (MAGGI, MILK, JAM) 3
76 0.05 (JAM, TEA, MAGGI) 3
77 0.05 (CORNFLAKES, MILK, BISCUIT, BREAD) 4
78 0.05 (TEA, BISCUIT, BREAD, MAGGI) 4
79 0.10 (CORNFLAKES, BISCUIT, COCK, COFFEE) 4
80 0.05 (MAGGI, MILK, BREAD, JAM) 4
81 0.05 (JAM, TEA, BREAD, MAGGI) 4
82 0.05 (CORNFLAKES, MILK, TEA, COFFEE) 4

83 rows × 3 columns

apriori_data[(apriori_data['length']==2) & (apriori_data['support']&gt;=0.05)]
support itemsets length
11 0.20 (BISCUIT, BREAD) 2
12 0.10 (BISCUIT, COCK) 2
13 0.10 (BISCUIT, COFFEE) 2
14 0.15 (BISCUIT, CORNFLAKES) 2
15 0.10 (BISCUIT, MAGGI) 2
16 0.10 (MILK, BISCUIT) 2
17 0.05 (BISCUIT, SUGER) 2
18 0.10 (BISCUIT, TEA) 2
19 0.15 (BREAD, BOURNVITA) 2
20 0.05 (COFFEE, BOURNVITA) 2
21 0.10 (SUGER, BOURNVITA) 2
22 0.10 (TEA, BOURNVITA) 2
23 0.05 (COCK, BREAD) 2
24 0.15 (BREAD, COFFEE) 2
25 0.05 (CORNFLAKES, BREAD) 2
26 0.10 (JAM, BREAD) 2
27 0.15 (BREAD, MAGGI) 2
28 0.20 (MILK, BREAD) 2
29 0.20 (BREAD, SUGER) 2
30 0.20 (TEA, BREAD) 2
31 0.15 (COCK, COFFEE) 2
32 0.10 (CORNFLAKES, COCK) 2
33 0.20 (CORNFLAKES, COFFEE) 2
34 0.05 (MILK, COFFEE) 2
35 0.20 (COFFEE, SUGER) 2
36 0.05 (TEA, COFFEE) 2
37 0.05 (CORNFLAKES, MAGGI) 2
38 0.10 (MILK, CORNFLAKES) 2
39 0.05 (CORNFLAKES, SUGER) 2
40 0.10 (TEA, CORNFLAKES) 2
41 0.10 (JAM, MAGGI) 2
42 0.05 (MILK, JAM) 2
43 0.05 (JAM, TEA) 2
44 0.05 (MILK, MAGGI) 2
45 0.20 (TEA, MAGGI) 2
46 0.05 (MILK, TEA) 2
The Algorithms logo

© The Algorithms 2024

Що таке алгоритм?Про насМови програмуванняЗробити внесокПожертвувати
GitHubGitterXДжерельний кодЗв'язатися
Powered by Vercel