market_basket_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c6fd080d-b315-46bb-8f2d-49347ed78ea8",
   "metadata": {},
   "source": [
    "# Leveraging the Apriori Algorithm for Market Basket Analysis: A Practical Approach to Boosting Sales\n",
    "## Introduction\n",
    "In the competitive world of retail, understanding customer buying behavior is crucial for optimizing sales strategies. \n",
    "Market basket analysis is a powerful data mining technique that helps retailers uncover associations between products purchased together. \n",
    "By identifying these relationships, businesses can optimize product placement, enhance cross-selling strategies, and tailor marketing efforts to boost sales. \n",
    "The code below illustrates how the Apriori algorithm can be used to identify frequently occurring itemsets in transactional data and solve real-world business challenges."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "7f3adc19-103e-4366-b539-59bed9665702",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: mlxtend in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (0.23.1)\n",
      "Requirement already satisfied: scipy>=1.2.1 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from mlxtend) (1.13.1)\n",
      "Requirement already satisfied: numpy>=1.16.2 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from mlxtend) (1.26.4)\n",
      "Requirement already satisfied: pandas>=0.24.2 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from mlxtend) (2.2.1)\n",
      "Requirement already satisfied: scikit-learn>=1.0.2 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from mlxtend) (1.5.0)\n",
      "Requirement already satisfied: matplotlib>=3.0.0 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from mlxtend) (3.9.0)\n",
      "Requirement already satisfied: joblib>=0.13.2 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from mlxtend) (1.4.2)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (1.2.1)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (0.12.1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (4.53.0)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (1.4.5)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (23.2)\n",
      "Requirement already satisfied: pillow>=8 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (10.2.0)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (3.1.2)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from matplotlib>=3.0.0->mlxtend) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas>=0.24.2->mlxtend) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas>=0.24.2->mlxtend) (2024.1)\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from scikit-learn>=1.0.2->mlxtend) (3.5.0)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\lkaur\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from python-dateutil>=2.7->matplotlib>=3.0.0->mlxtend) (1.16.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip is available: 23.2.1 -> 24.2\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "#Installing the necessary libraries\n",
    "!pip install mlxtend\n",
    "import pandas as pd\n",
    "from mlxtend.frequent_patterns import apriori, association_rules\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from datetime import datetime"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc70f950-53cb-46bd-a525-e8bca1562e4e",
   "metadata": {},
   "source": [
    "## Setting the Stage: The Dataset\n",
    "\n",
    "We began our journey with a dataset containing transactional data from a bakery based in Edinburgh. We did the necessary preprocessing and EDA (as seen in the subsections below) before proceeding with the implementation of the Apriori Algorithm."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a47d3456-3ce9-4c9b-a440-33ecdf67fb34",
   "metadata": {},
   "source": [
    "### Initial Observations\n",
    "\n",
    "This dataset has 20,507 rows and 5 columns: Transaction ID, the date and time of purchase, item names, and whether the purchase was made on a weekday or weekend. Its data from the year 2017.\n",
    "\n",
    "The dataset contained duplicate rows, which we promptly in the steps below removed to ensure the accuracy of our"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "137c7824-022e-47ba-84e3-b10f41fcb04a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df= pd.read_csv('C:/Users/lkaur/Downloads/archive (1)/bread basket.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "1622055f-abbf-4381-a074-3495402e267a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 20507 entries, 0 to 20506\n",
      "Data columns (total 5 columns):\n",
      " #   Column           Non-Null Count  Dtype \n",
      "---  ------           --------------  ----- \n",
      " 0   Transaction      20507 non-null  int64 \n",
      " 1   Item             20507 non-null  object\n",
      " 2   date_time        20507 non-null  object\n",
      " 3   period_day       20507 non-null  object\n",
      " 4   weekday_weekend  20507 non-null  object\n",
      "dtypes: int64(1), object(4)\n",
      "memory usage: 801.2+ KB\n",
      "Minimum date: 01-01-2017 01:21\n",
      "Maximum date: 31-12-2016 17:36\n"
     ]
    }
   ],
   "source": [
    "df.shape\n",
    "df.info()\n",
    "df.head()\n",
    "# Get min and max dates\n",
    "min_date = df['date_time'].min()\n",
    "max_date = df['date_time'].max()\n",
    "\n",
    "print(\"Minimum date:\", min_date)\n",
    "print(\"Maximum date:\", max_date)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "be660bb8-fb85-4990-a8a9-fa9846bd81fb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1620"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#we see that there are a couple of duplicate rows here, lets check how many are there in the dataset\n",
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "d6262419-0321-4ed2-b40e-dbad6d1b03da",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove duplicates\n",
    "df = df.drop_duplicates().reset_index(drop=True) #drop duplicates and reset the index"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe84e6df-11e7-4c77-a90c-ac31bb9689ce",
   "metadata": {
    "jp-MarkdownHeadingCollapsed": true
   },
   "source": [
    "### Initial exploration of the data- Cross tables:\n",
    "\n",
    "To analyze sales distribution across times and days, we used cross tables:  \n",
    "Absolute Cross Table: Provided a view of total transactions by weekdays, weekends, and different day periods, identifying peak shopping times.  \n",
    "Relative Cross Table: Normalized data to show the proportion of sales per period, revealing customer preferences.\n",
    "\n",
    "**Findings**  \n",
    "Afternoon Dominance: The afternoon is the peak shopping period on both weekdays and weekends, indicating a strong preference for shopping later in the day.  \n",
    "Morning Activity: Mornings are the second busiest time, showing a trend of early shoppers.  \n",
    "Low Evening and Night Activity: Shopping activity drops significantly in the evening and night, consistent across all days.\n",
    "\n",
    "**Business Implication**   \n",
    "Staffing and Inventory: Businesses might consider increasing staff and inventory during the afternoon and morning periods to accommodate higher purchase volumes.  \n",
    "Promotions and Marketing: Targeting promotions and marketing efforts during these peak periods could be more effective.  \n",
    "Operational Hours: Given the minimal activity at night, businesses might evaluate the necessity of extended operational hours."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "91eb6e37-2832-46ae-9b31-9620a81349c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross table (absolute):\n",
      "period_day       afternoon  evening  morning  night\n",
      "weekday_weekend                                    \n",
      "weekday               6742      336     4748      4\n",
      "weekend               3945      154     2949      9\n",
      "\n",
      "Cross table (relative):\n",
      "period_day       afternoon  evening  morning  night\n",
      "weekday_weekend                                    \n",
      "weekday              0.570    0.028    0.401  0.000\n",
      "weekend              0.559    0.022    0.418  0.001\n"
     ]
    }
   ],
   "source": [
    "# Cross table (absolute)\n",
    "cross_table_absolute = pd.crosstab(df['weekday_weekend'], df['period_day'])\n",
    "print(\"Cross table (absolute):\")\n",
    "print(cross_table_absolute)\n",
    "\n",
    "# Cross table (relative)\n",
    "cross_table_relative = pd.crosstab(df['weekday_weekend'], df['period_day'], normalize='index').round(3)\n",
    "print(\"\\nCross table (relative):\")\n",
    "print(cross_table_relative)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5f14216f-7fd6-4931-9cdc-a67dbaf6b094",
   "metadata": {
    "jp-MarkdownHeadingCollapsed": true
   },
   "source": [
    "### Understanding Customer Preferences Throughout the Day\n",
    "We also wanted to get some insights into customer preferences at different times of the day. By grouping the data by item and period of the day, we identified the top 10 most popular items for each time period: morning, afternoon, evening, and night.  \n",
    "\n",
    "**Findings**-  \n",
    "Morning, Afternoon and Evening- customers predominantly favor traditional breakfast items like Coffee, Bread, Cake, Tea etc in the morning.    \n",
    "These items are staples for a quick and energizing start to the day, reflecting the typical morning rush where customers seek convenience and comfort.\n",
    "As the day progresses into the afternoon and evening, the preferences remain largely similar.  \n",
    "This indicates that these items are not only popular for breakfast, but also serve as comforting treats for lunch and to wind down the day.  \n",
    "\n",
    "Interestingly, the nighttime preferences show a distinct shift. The top orders at night include Vegan’s Feast, Valentine’s Card, Hot Chocolate. \n",
    "This change suggests that customers are looking for more indulgent and unique items as the day ends. The popularity of the Vegan’s Feast indicates a demand for healthier, plant-based options, while the Valentine’s Card and Hot Chocolate reflect a desire for special treats and perhaps a bit of late-night romance ❤️ or comfort."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "950eeac8-8adc-455e-8247-47e680296442",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x900 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "items = df.groupby(['Item', 'period_day'])['Transaction'].count().reset_index().sort_values(['period_day', 'Transaction'], ascending=False)\n",
    "\n",
    "fig, axs = plt.subplots(2, 2, figsize=(15, 9))\n",
    "plt.subplots_adjust(hspace=0.6)\n",
    "\n",
    "# Define colors for each period of the day\n",
    "colors = {\n",
    "    'morning': 'yellow',\n",
    "    'afternoon': 'orange',\n",
    "    'evening': 'blue',\n",
    "    'night': 'navy'\n",
    "}\n",
    "\n",
    "# Top 10 orders in the morning\n",
    "dfMorning = items[items['period_day'] == 'morning'].head(10)\n",
    "axs[0, 0].bar(dfMorning.Item, dfMorning.Transaction, color=colors['morning'])\n",
    "axs[0, 0].set_title('Top 10 orders in the morning')\n",
    "axs[0, 0].tick_params(axis='x', rotation=45)\n",
    "\n",
    "# Top 10 orders in the afternoon\n",
    "dfAfternoon = items[items['period_day'] == 'afternoon'].head(10)\n",
    "axs[0, 1].bar(dfAfternoon.Item, dfAfternoon.Transaction, color=colors['afternoon'])\n",
    "axs[0, 1].set_title('Top 10 orders in the afternoon')\n",
    "axs[0, 1].tick_params(axis='x', rotation=45)\n",
    "\n",
    "# Top 10 orders in the evening\n",
    "dfEvening = items[items['period_day'] == 'evening'].head(10)\n",
    "axs[1, 0].bar(dfEvening.Item, dfEvening.Transaction, color=colors['evening'])\n",
    "axs[1, 0].set_title('Top 10 orders in the evening')\n",
    "axs[1, 0].tick_params(axis='x', rotation=45)\n",
    "\n",
    "# Top 10 orders in the night\n",
    "dfNight = items[items['period_day'] == 'night'].head(10)\n",
    "axs[1, 1].bar(dfNight.Item, dfNight.Transaction, color=colors['night'])\n",
    "axs[1, 1].set_title('Top 10 orders in the night')\n",
    "axs[1, 1].tick_params(axis='x', rotation=45)\n",
    "\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7e340a70-54e2-4d09-9ef6-62895977aa95",
   "metadata": {
    "jp-MarkdownHeadingCollapsed": true
   },
   "source": [
    "### Understanding Item Popularity and Inventory Needs\n",
    "Absolute Item Frequency  \n",
    "We first counted the absolute frequency of each item, focusing on the top 25 items. This helps us identify which items are most frequently purchased.\n",
    "This information is crucial for inventory management, as it highlights items that need to be stocked more frequently to meet customer demand.\n",
    "\n",
    "Relative Item Frequency  \n",
    "Next, we calculated the relative frequency of each item. This makes it easier to compare the popularity of items, especially when the total number of transactions varies. Relative frequency helps us understand the market share of each item within the dataset.\n",
    "\n",
    "**Findings**  \n",
    "Coffee is the most bought item, followed by Bread and Tea."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "30d2665c-2a12-4b69-8e1b-688cc8094626",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Count the frequency of each item\n",
    "item_counts = df['Item'].value_counts().head(25)  # Get the top 25 items\n",
    "\n",
    "# Calculate relative frequencies\n",
    "relative_frequencies = item_counts / item_counts.sum()\n",
    "\n",
    "# Create subplots\n",
    "fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(14, 6))\n",
    "\n",
    "# Plot absolute item frequency\n",
    "item_counts.plot(kind='bar', color='wheat', ax=axes[0])\n",
    "axes[0].set_xlabel('Item name')\n",
    "axes[0].set_ylabel('Frequency (absolute)')\n",
    "axes[0].set_title('Absolute Item Frequency Plot')\n",
    "\n",
    "# Plot relative item frequency\n",
    "relative_frequencies.plot(kind='bar', color='skyblue', ax=axes[1])\n",
    "axes[1].set_xlabel('Item name')\n",
    "axes[1].set_ylabel('Frequency (relative)')\n",
    "axes[1].set_title('Relative Item Frequency Plot')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb1effb8-a9da-486f-8a09-cd0e6a5839ef",
   "metadata": {
    "jp-MarkdownHeadingCollapsed": true
   },
   "source": [
    "### Patterns and Trends Over Different Time Periods\n",
    "To better understand customer behavior, we analyzed transactions over various time periods. Here are the key findings:\n",
    "\n",
    "**Findings**  \n",
    "Seasonal Trends: The data shows distinct seasonal trends, with transaction peaks in November and early in the year, likely driven by holiday shopping and post-holiday sales. This insight is useful for identifying and preparing for seasonal demand fluctuations.\n",
    "\n",
    "Average Transactions per Weekday: Weekends, particularly Saturdays, see the highest transaction volumes, while the beginning of the week tends to be slower. This information can help optimize staffing and promotional strategies.\n",
    "\n",
    "Average Transactions per Hour: The majority of transactions occur during business hours, especially from late morning to early afternoon, indicating a preference for shopping during these times. This is crucial for effectively managing store operations and ensuring adequate staffing during peak periods."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "163d5f15-9f9b-4904-8a56-c56fe18a55bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x1500 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Create subplots\n",
    "fig, axes = plt.subplots(nrows=3, ncols=1, figsize=(8, 15))\n",
    "\n",
    "# Plot transactions per month\n",
    "transactions_per_month.plot(kind='bar', ax=axes[0], color='skyblue')\n",
    "axes[0].set_title('Transactions per Month')\n",
    "axes[0].set_xlabel('Month')\n",
    "axes[0].set_ylabel('Number of Transactions')\n",
    "for p in axes[0].patches:\n",
    "    axes[0].annotate(str(p.get_height()), (p.get_x() * 1.005, p.get_height() * 1.005))\n",
    "\n",
    "# Plot transactions per weekday\n",
    "avg_transactions_per_weekday.plot(kind='bar', ax=axes[1], color='lightgreen')\n",
    "axes[1].set_title('Avg Transactions per Weekday')\n",
    "axes[1].set_xlabel('Weekday')\n",
    "axes[1].set_ylabel('Number of Transactions')\n",
    "for p in axes[1].patches:\n",
    "    axes[1].annotate(str(p.get_height()), (p.get_x() * 1.005, p.get_height() * 1.005))\n",
    "\n",
    "\n",
    "# Plot transactions per hour\n",
    "avg_transactions_per_hour.plot(kind='bar', ax=axes[2], color='salmon')\n",
    "axes[2].set_title('Avg Transactions per Hour')\n",
    "axes[2].set_xlabel('Hour')\n",
    "axes[2].set_ylabel('Number of Transactions')\n",
    "for p in axes[2].patches:\n",
    "    axes[2].annotate(str(p.get_height()), (p.get_x() * 1.005, p.get_height() * 1.005))\n",
    "\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d46c71b1-9576-4be7-8ed4-f01f88d75f1e",
   "metadata": {},
   "source": [
    "## Apriori Algorithm:\n",
    "\n",
    "The Apriori algorithm identifies frequent itemsets by iteratively exploring item combinations and evaluating their support values. By setting minimum support thresholds, we can filter out less significant itemsets and focus on those with the highest potential impact. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed285ae7-a94e-4405-8b96-c93906ff0d2d",
   "metadata": {},
   "source": [
    "### Data Transformation for Apriori:\n",
    "\n",
    "Before diving into the analysis, it's crucial to transform our data into a format suitable for the Apriori algorithm. This step involves creating a \"basket\" representation of our transactional data, where each transaction is represented as a row, and each item is a column. The resulting matrix has binary values (0s and 1s), where 1 indicates the presence of an item in a transaction, and 0 indicates its absence."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "05868054-ff79-449d-8cb1-4f5b8b8c9d51",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\lkaur\\AppData\\Local\\Temp\\ipykernel_19636\\616742887.py:3: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.\n",
      "  basket = basket.applymap(lambda x: 1 if x > 0 else 0)\n"
     ]
    },
    {
     "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>Item</th>\n",
       "      <th>Adjustment</th>\n",
       "      <th>Afternoon with the baker</th>\n",
       "      <th>Alfajores</th>\n",
       "      <th>Argentina Night</th>\n",
       "      <th>Art Tray</th>\n",
       "      <th>Bacon</th>\n",
       "      <th>Baguette</th>\n",
       "      <th>Bakewell</th>\n",
       "      <th>Bare Popcorn</th>\n",
       "      <th>Basket</th>\n",
       "      <th>...</th>\n",
       "      <th>The BART</th>\n",
       "      <th>The Nomad</th>\n",
       "      <th>Tiffin</th>\n",
       "      <th>Toast</th>\n",
       "      <th>Truffles</th>\n",
       "      <th>Tshirt</th>\n",
       "      <th>Valentine's card</th>\n",
       "      <th>Vegan Feast</th>\n",
       "      <th>Vegan mincepie</th>\n",
       "      <th>Victorian Sponge</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transaction</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>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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>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>9680</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9681</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9682</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9683</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9684</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9465 rows × 94 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Item         Adjustment  Afternoon with the baker  Alfajores  Argentina Night  \\\n",
       "Transaction                                                                     \n",
       "1                     0                         0          0                0   \n",
       "2                     0                         0          0                0   \n",
       "3                     0                         0          0                0   \n",
       "4                     0                         0          0                0   \n",
       "5                     0                         0          0                0   \n",
       "...                 ...                       ...        ...              ...   \n",
       "9680                  0                         0          0                0   \n",
       "9681                  0                         0          0                0   \n",
       "9682                  0                         0          0                0   \n",
       "9683                  0                         0          0                0   \n",
       "9684                  0                         0          0                0   \n",
       "\n",
       "Item         Art Tray  Bacon  Baguette  Bakewell  Bare Popcorn  Basket  ...  \\\n",
       "Transaction                                                             ...   \n",
       "1                   0      0         0         0             0       0  ...   \n",
       "2                   0      0         0         0             0       0  ...   \n",
       "3                   0      0         0         0             0       0  ...   \n",
       "4                   0      0         0         0             0       0  ...   \n",
       "5                   0      0         0         0             0       0  ...   \n",
       "...               ...    ...       ...       ...           ...     ...  ...   \n",
       "9680                0      0         0         0             0       0  ...   \n",
       "9681                0      0         0         0             0       0  ...   \n",
       "9682                0      0         0         0             0       0  ...   \n",
       "9683                0      0         0         0             0       0  ...   \n",
       "9684                0      0         0         0             0       0  ...   \n",
       "\n",
       "Item         The BART  The Nomad  Tiffin  Toast  Truffles  Tshirt  \\\n",
       "Transaction                                                         \n",
       "1                   0          0       0      0         0       0   \n",
       "2                   0          0       0      0         0       0   \n",
       "3                   0          0       0      0         0       0   \n",
       "4                   0          0       0      0         0       0   \n",
       "5                   0          0       0      0         0       0   \n",
       "...               ...        ...     ...    ...       ...     ...   \n",
       "9680                0          0       0      0         0       0   \n",
       "9681                0          0       0      0         1       0   \n",
       "9682                0          0       0      0         0       0   \n",
       "9683                0          0       0      0         0       0   \n",
       "9684                0          0       0      0         0       0   \n",
       "\n",
       "Item         Valentine's card  Vegan Feast  Vegan mincepie  Victorian Sponge  \n",
       "Transaction                                                                   \n",
       "1                           0            0               0                 0  \n",
       "2                           0            0               0                 0  \n",
       "3                           0            0               0                 0  \n",
       "4                           0            0               0                 0  \n",
       "5                           0            0               0                 0  \n",
       "...                       ...          ...             ...               ...  \n",
       "9680                        0            0               0                 0  \n",
       "9681                        0            0               0                 0  \n",
       "9682                        0            0               0                 0  \n",
       "9683                        0            0               0                 0  \n",
       "9684                        0            0               0                 0  \n",
       "\n",
       "[9465 rows x 94 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Convert the DataFrame to the required format for the Apriori algorithm\n",
    "basket = df.groupby(['Transaction', 'Item']).size().unstack(fill_value=0)\n",
    "basket = basket.applymap(lambda x: 1 if x > 0 else 0)\n",
    "basket"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4953acca-96ff-4071-a79e-057a57785dd8",
   "metadata": {},
   "source": [
    "### Exploring Association Rules: Support and Confidence Analysis:  \n",
    "We analyzed association rules by varying support levels from 10% to 0.5% and confidence thresholds from 90% to 10%. This helps identify frequent and reliable product associations.\n",
    "\n",
    "**Understanding the Metrics:**  \n",
    "Support measures how often an itemset appears in the dataset. Adjusting support levels helps determine how frequently items must occur together to be significant.\n",
    "Confidence indicates the reliability of a rule, showing the likelihood of the consequent being purchased when the antecedent is bought. Higher confidence suggests stronger associations.\n",
    "\n",
    "**Findings:**  \n",
    "10% Support: Too few rules with low confidence; not representative.  \n",
    "5% Support: Limited rules at reasonable confidence; need lower support.  \n",
    "1% Support: Dozens of rules, with 13 having at least 50% confidence.  \n",
    "0.5% Support: Too many rules to analyze effectively.  \n",
    "\n",
    "**Conclusion:**  \n",
    "We will use a support level of 1% and a confidence level of 50% to strike a balance between reliability and the number of rules."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "1634cc0f-6428-4aee-8a33-988715753879",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n",
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of rules with support level 10%: [0, 0, 0, 0, 0, 0, 0, 0, 0]\n",
      "Number of rules with support level 5%: [0, 0, 0, 0, 1, 1, 1, 2, 4]\n",
      "Number of rules with support level 1%: [0, 0, 1, 1, 11, 16, 19, 31, 44]\n",
      "Number of rules with support level 0.5%: [0, 1, 2, 4, 17, 25, 35, 57, 103]\n"
     ]
    }
   ],
   "source": [
    "# Support and confidence values\n",
    "support_levels = [0.1, 0.05, 0.01, 0.005]\n",
    "confidence_levels = [0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1]\n",
    "\n",
    "# Initialize lists to store the number of rules\n",
    "rules_sup10 = []\n",
    "rules_sup5 = []\n",
    "rules_sup1 = []\n",
    "rules_sup0_5 = []\n",
    "\n",
    "# Apriori algorithm with different support levels\n",
    "for conf in confidence_levels:\n",
    "    # Support level 10%\n",
    "    frequent_itemsets = apriori(basket, min_support=support_levels[0], use_colnames=True)\n",
    "    rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=conf)\n",
    "    rules_sup10.append(len(rules))\n",
    "    \n",
    "    # Support level 5%\n",
    "    frequent_itemsets = apriori(basket, min_support=support_levels[1], use_colnames=True)\n",
    "    rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=conf)\n",
    "    rules_sup5.append(len(rules))\n",
    "    \n",
    "    # Support level 1%\n",
    "    frequent_itemsets = apriori(basket, min_support=support_levels[2], use_colnames=True)\n",
    "    rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=conf)\n",
    "    rules_sup1.append(len(rules))\n",
    "    \n",
    "    # Support level 0.5%\n",
    "    frequent_itemsets = apriori(basket, min_support=support_levels[3], use_colnames=True)\n",
    "    rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=conf)\n",
    "    rules_sup0_5.append(len(rules))\n",
    "\n",
    "print(\"Number of rules with support level 10%:\", rules_sup10)\n",
    "print(\"Number of rules with support level 5%:\", rules_sup5)\n",
    "print(\"Number of rules with support level 1%:\", rules_sup1)\n",
    "print(\"Number of rules with support level 0.5%:\", rules_sup0_5)\n",
    "\n",
    "# Create subplots\n",
    "fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(14, 10))\n",
    "\n",
    "# Plot for support level 10%\n",
    "sns.lineplot(x=confidence_levels, y=rules_sup10, marker='o', ax=axes[0, 0])\n",
    "axes[0, 0].set_title('Apriori with a support level of 10%')\n",
    "axes[0, 0].set_xlabel('Confidence level')\n",
    "axes[0, 0].set_ylabel('Number of rules found')\n",
    "\n",
    "# Plot for support level 5%\n",
    "sns.lineplot(x=confidence_levels, y=rules_sup5, marker='o', ax=axes[0, 1])\n",
    "axes[0, 1].set_title('Apriori with a support level of 5%')\n",
    "axes[0, 1].set_xlabel('Confidence level')\n",
    "axes[0, 1].set_ylabel('Number of rules found')\n",
    "axes[0, 1].set_yticks(range(0, 11, 2))\n",
    "\n",
    "# Plot for support level 1%\n",
    "sns.lineplot(x=confidence_levels, y=rules_sup1, marker='o', ax=axes[1, 0])\n",
    "axes[1, 0].set_title('Apriori with a support level of 1%')\n",
    "axes[1, 0].set_xlabel('Confidence level')\n",
    "axes[1, 0].set_ylabel('Number of rules found')\n",
    "axes[1, 0].set_yticks(range(0, 51, 10))\n",
    "\n",
    "# Plot for support level 0.5%\n",
    "sns.lineplot(x=confidence_levels, y=rules_sup0_5, marker='o', ax=axes[1, 1])\n",
    "axes[1, 1].set_title('Apriori with a support level of 0.5%')\n",
    "axes[1, 1].set_xlabel('Confidence level')\n",
    "axes[1, 1].set_ylabel('Number of rules found')\n",
    "axes[1, 1].set_yticks(range(0, 131, 20))\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8427122-4fff-41f7-8296-5268f142e3f2",
   "metadata": {},
   "source": [
    "### Interpreting Association Rules: Coffee Connections\n",
    "In our analysis of association rules with a 1% support level and 50% confidence threshold, we uncovered intriguing patterns in customer purchasing behavior, particularly highlighting the prominence of coffee in transactions. \n",
    "\n",
    "**Key Findings from the rules generated**  \n",
    "Hot Chocolate and Coffee: 51% of customers who purchased hot chocolate also bought coffee.  \n",
    "Spanish Brunch and Coffee: 60% of customers who opted for a Spanish brunch also included coffee in their purchase.  \n",
    "Toast and Coffee: A significant 70% of customers who bought toast also chose coffee.  \n",
    "\n",
    "These patterns reveal the centrality of coffee in this bakery's offerings, highlighting its popularity among patrons. Understanding these associations can help the bakery optimize its product placement, promotions, and marketing strategies to capitalize on customers' affinity for coffee."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "57fe093a-0e66-4bcd-9691-1b05fd6b5ea8",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\lkaur\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\mlxtend\\frequent_patterns\\fpcommon.py:109: DeprecationWarning: DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Association Rules:\n",
      "         antecedents consequents  antecedent support  consequent support  \\\n",
      "0        (Alfajores)    (Coffee)            0.036344            0.478394   \n",
      "1             (Cake)    (Coffee)            0.103856            0.478394   \n",
      "2          (Cookies)    (Coffee)            0.054411            0.478394   \n",
      "3    (Hot chocolate)    (Coffee)            0.058320            0.478394   \n",
      "4            (Juice)    (Coffee)            0.038563            0.478394   \n",
      "5        (Medialuna)    (Coffee)            0.061807            0.478394   \n",
      "6           (Pastry)    (Coffee)            0.086107            0.478394   \n",
      "7         (Sandwich)    (Coffee)            0.071844            0.478394   \n",
      "8            (Scone)    (Coffee)            0.034548            0.478394   \n",
      "9   (Spanish Brunch)    (Coffee)            0.018172            0.478394   \n",
      "10           (Toast)    (Coffee)            0.033597            0.478394   \n",
      "\n",
      "     support  confidence      lift  leverage  conviction  zhangs_metric  \n",
      "0   0.019651    0.540698  1.130235  0.002264    1.135648       0.119574  \n",
      "1   0.054728    0.526958  1.101515  0.005044    1.102664       0.102840  \n",
      "2   0.028209    0.518447  1.083723  0.002179    1.083174       0.081700  \n",
      "3   0.029583    0.507246  1.060311  0.001683    1.058553       0.060403  \n",
      "4   0.020602    0.534247  1.116750  0.002154    1.119919       0.108738  \n",
      "5   0.035182    0.569231  1.189878  0.005614    1.210871       0.170091  \n",
      "6   0.047544    0.552147  1.154168  0.006351    1.164682       0.146161  \n",
      "7   0.038246    0.532353  1.112792  0.003877    1.115384       0.109205  \n",
      "8   0.018067    0.522936  1.093107  0.001539    1.093366       0.088224  \n",
      "9   0.010882    0.598837  1.251766  0.002189    1.300235       0.204851  \n",
      "10  0.023666    0.704403  1.472431  0.007593    1.764582       0.332006  \n"
     ]
    }
   ],
   "source": [
    "# Execute the Apriori algorithm with a support level of 1%\n",
    "frequent_itemsets = apriori(basket, min_support=0.01, use_colnames=True)\n",
    "\n",
    "# Generate association rules with a confidence level of 50%\n",
    "rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=0.5)\n",
    "\n",
    "print(\"Association Rules:\")\n",
    "print(rules)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5db444e-5495-401a-a5ea-fd75f409b9cc",
   "metadata": {},
   "source": [
    "### Making the rules from frequent itemset generated above\n",
    "Using the lift metric with a minimum threshold of 1, we identified strong product associations, ensuring they reflect meaningful relationships rather than chance. Sorting these rules by confidence highlights reliable combinations, offering insights for effective bundling and cross-promotion strategies.\n",
    "\n",
    "**Key Metrics and Insights:**  \n",
    "\n",
    "Antecedents and Consequents: Items on the left (e.g., Toast) and right (e.g., Coffee) of the rule, respectively.  \n",
    "Support: The proportion of transactions containing both items.  \n",
    "Confidence: The likelihood of purchasing consequents when antecedents are bought.  \n",
    "Lift: The strength of association compared to random occurrence; values greater than 1 suggest a positive association.  \n",
    "Leverage and Conviction: Measure deviation from independence and reliability of rules.  \n",
    "\n",
    "**Specific Rules:**  \n",
    "\n",
    "Toast => Coffee: Strong association with a support of 2.37% and a confidence of 70.44%. Lift of 1.47 indicates customers frequently buy them together.  \n",
    "Cake => Tea: Moderate association; 2.38% support and 22.89% confidence. Lift of 1.60 suggests they are bought together more often than by chance.  \n",
    "Tea, Coffee => Cake: Strong three-item association with 1% support and 20.13% confidence. Lift of 1.94 shows frequent co-purchase.\n",
    "\n",
    "**General Insights:**  \n",
    "\n",
    "High Confidence and Lift: Indicate strong buying patterns.  \n",
    "Support Levels: Reflect common item pairings, like Cake and Coffee at 5.47%.  \n",
    "Business Implications: we can use the above insights for product placement, cross-selling, and promotions, such as pairing Toast and Coffee together or offering Coffee discounts with Toast purchases."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "3baf5c4a-d520-4754-83d9-5311cba01ff7",
   "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>antecedents</th>\n",
       "      <th>consequents</th>\n",
       "      <th>antecedent support</th>\n",
       "      <th>consequent support</th>\n",
       "      <th>support</th>\n",
       "      <th>confidence</th>\n",
       "      <th>lift</th>\n",
       "      <th>leverage</th>\n",
       "      <th>conviction</th>\n",
       "      <th>zhangs_metric</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>(Toast)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.033597</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.023666</td>\n",
       "      <td>0.704403</td>\n",
       "      <td>1.472431</td>\n",
       "      <td>0.007593</td>\n",
       "      <td>1.764582</td>\n",
       "      <td>0.332006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>(Spanish Brunch)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.018172</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.010882</td>\n",
       "      <td>0.598837</td>\n",
       "      <td>1.251766</td>\n",
       "      <td>0.002189</td>\n",
       "      <td>1.300235</td>\n",
       "      <td>0.204851</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>(Medialuna)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.061807</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.035182</td>\n",
       "      <td>0.569231</td>\n",
       "      <td>1.189878</td>\n",
       "      <td>0.005614</td>\n",
       "      <td>1.210871</td>\n",
       "      <td>0.170091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>(Pastry)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.086107</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.047544</td>\n",
       "      <td>0.552147</td>\n",
       "      <td>1.154168</td>\n",
       "      <td>0.006351</td>\n",
       "      <td>1.164682</td>\n",
       "      <td>0.146161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>(Alfajores)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.036344</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.019651</td>\n",
       "      <td>0.540698</td>\n",
       "      <td>1.130235</td>\n",
       "      <td>0.002264</td>\n",
       "      <td>1.135648</td>\n",
       "      <td>0.119574</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>(Juice)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.038563</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.020602</td>\n",
       "      <td>0.534247</td>\n",
       "      <td>1.116750</td>\n",
       "      <td>0.002154</td>\n",
       "      <td>1.119919</td>\n",
       "      <td>0.108738</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>(Sandwich)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.071844</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.038246</td>\n",
       "      <td>0.532353</td>\n",
       "      <td>1.112792</td>\n",
       "      <td>0.003877</td>\n",
       "      <td>1.115384</td>\n",
       "      <td>0.109205</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>(Cake)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.054728</td>\n",
       "      <td>0.526958</td>\n",
       "      <td>1.101515</td>\n",
       "      <td>0.005044</td>\n",
       "      <td>1.102664</td>\n",
       "      <td>0.102840</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>(Scone)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.034548</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.018067</td>\n",
       "      <td>0.522936</td>\n",
       "      <td>1.093107</td>\n",
       "      <td>0.001539</td>\n",
       "      <td>1.093366</td>\n",
       "      <td>0.088224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>(Cookies)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.054411</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.028209</td>\n",
       "      <td>0.518447</td>\n",
       "      <td>1.083723</td>\n",
       "      <td>0.002179</td>\n",
       "      <td>1.083174</td>\n",
       "      <td>0.081700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>(Hot chocolate)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.058320</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.029583</td>\n",
       "      <td>0.507246</td>\n",
       "      <td>1.060311</td>\n",
       "      <td>0.001683</td>\n",
       "      <td>1.058553</td>\n",
       "      <td>0.060403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>(Brownie)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.040042</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.019651</td>\n",
       "      <td>0.490765</td>\n",
       "      <td>1.025860</td>\n",
       "      <td>0.000495</td>\n",
       "      <td>1.024293</td>\n",
       "      <td>0.026259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>(Muffin)</td>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>0.038457</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.018806</td>\n",
       "      <td>0.489011</td>\n",
       "      <td>1.022193</td>\n",
       "      <td>0.000408</td>\n",
       "      <td>1.020777</td>\n",
       "      <td>0.022579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>(Pastry)</td>\n",
       "      <td>(Bread)</td>\n",
       "      <td>0.086107</td>\n",
       "      <td>0.327205</td>\n",
       "      <td>0.029160</td>\n",
       "      <td>0.338650</td>\n",
       "      <td>1.034977</td>\n",
       "      <td>0.000985</td>\n",
       "      <td>1.017305</td>\n",
       "      <td>0.036980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>(Cake)</td>\n",
       "      <td>(Tea)</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.142631</td>\n",
       "      <td>0.023772</td>\n",
       "      <td>0.228891</td>\n",
       "      <td>1.604781</td>\n",
       "      <td>0.008959</td>\n",
       "      <td>1.111865</td>\n",
       "      <td>0.420538</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>(Tea, Coffee)</td>\n",
       "      <td>(Cake)</td>\n",
       "      <td>0.049868</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.010037</td>\n",
       "      <td>0.201271</td>\n",
       "      <td>1.937977</td>\n",
       "      <td>0.004858</td>\n",
       "      <td>1.121962</td>\n",
       "      <td>0.509401</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>(Sandwich)</td>\n",
       "      <td>(Tea)</td>\n",
       "      <td>0.071844</td>\n",
       "      <td>0.142631</td>\n",
       "      <td>0.014369</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>1.402222</td>\n",
       "      <td>0.004122</td>\n",
       "      <td>1.071712</td>\n",
       "      <td>0.309050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>(Hot chocolate)</td>\n",
       "      <td>(Cake)</td>\n",
       "      <td>0.058320</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.011410</td>\n",
       "      <td>0.195652</td>\n",
       "      <td>1.883874</td>\n",
       "      <td>0.005354</td>\n",
       "      <td>1.114125</td>\n",
       "      <td>0.498236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>(Coffee, Cake)</td>\n",
       "      <td>(Tea)</td>\n",
       "      <td>0.054728</td>\n",
       "      <td>0.142631</td>\n",
       "      <td>0.010037</td>\n",
       "      <td>0.183398</td>\n",
       "      <td>1.285822</td>\n",
       "      <td>0.002231</td>\n",
       "      <td>1.049923</td>\n",
       "      <td>0.235157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>(Tea)</td>\n",
       "      <td>(Cake)</td>\n",
       "      <td>0.142631</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.023772</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>1.604781</td>\n",
       "      <td>0.008959</td>\n",
       "      <td>1.075372</td>\n",
       "      <td>0.439556</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>(Pastry)</td>\n",
       "      <td>(Coffee, Bread)</td>\n",
       "      <td>0.086107</td>\n",
       "      <td>0.090016</td>\n",
       "      <td>0.011199</td>\n",
       "      <td>0.130061</td>\n",
       "      <td>1.444872</td>\n",
       "      <td>0.003448</td>\n",
       "      <td>1.046033</td>\n",
       "      <td>0.336907</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>(Coffee, Bread)</td>\n",
       "      <td>(Pastry)</td>\n",
       "      <td>0.090016</td>\n",
       "      <td>0.086107</td>\n",
       "      <td>0.011199</td>\n",
       "      <td>0.124413</td>\n",
       "      <td>1.444872</td>\n",
       "      <td>0.003448</td>\n",
       "      <td>1.043749</td>\n",
       "      <td>0.338354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Cake)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.054728</td>\n",
       "      <td>0.114399</td>\n",
       "      <td>1.101515</td>\n",
       "      <td>0.005044</td>\n",
       "      <td>1.011905</td>\n",
       "      <td>0.176684</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>(Coffee, Bread)</td>\n",
       "      <td>(Cake)</td>\n",
       "      <td>0.090016</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.010037</td>\n",
       "      <td>0.111502</td>\n",
       "      <td>1.073621</td>\n",
       "      <td>0.000688</td>\n",
       "      <td>1.008606</td>\n",
       "      <td>0.075356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>(Cake)</td>\n",
       "      <td>(Hot chocolate)</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.058320</td>\n",
       "      <td>0.011410</td>\n",
       "      <td>0.109868</td>\n",
       "      <td>1.883874</td>\n",
       "      <td>0.005354</td>\n",
       "      <td>1.057910</td>\n",
       "      <td>0.523553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>(Tea)</td>\n",
       "      <td>(Sandwich)</td>\n",
       "      <td>0.142631</td>\n",
       "      <td>0.071844</td>\n",
       "      <td>0.014369</td>\n",
       "      <td>0.100741</td>\n",
       "      <td>1.402222</td>\n",
       "      <td>0.004122</td>\n",
       "      <td>1.032134</td>\n",
       "      <td>0.334566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Pastry)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.086107</td>\n",
       "      <td>0.047544</td>\n",
       "      <td>0.099382</td>\n",
       "      <td>1.154168</td>\n",
       "      <td>0.006351</td>\n",
       "      <td>1.014740</td>\n",
       "      <td>0.256084</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>(Cake)</td>\n",
       "      <td>(Coffee, Bread)</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.090016</td>\n",
       "      <td>0.010037</td>\n",
       "      <td>0.096643</td>\n",
       "      <td>1.073621</td>\n",
       "      <td>0.000688</td>\n",
       "      <td>1.007336</td>\n",
       "      <td>0.076520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>(Cake)</td>\n",
       "      <td>(Tea, Coffee)</td>\n",
       "      <td>0.103856</td>\n",
       "      <td>0.049868</td>\n",
       "      <td>0.010037</td>\n",
       "      <td>0.096643</td>\n",
       "      <td>1.937977</td>\n",
       "      <td>0.004858</td>\n",
       "      <td>1.051779</td>\n",
       "      <td>0.540090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>(Bread)</td>\n",
       "      <td>(Pastry)</td>\n",
       "      <td>0.327205</td>\n",
       "      <td>0.086107</td>\n",
       "      <td>0.029160</td>\n",
       "      <td>0.089119</td>\n",
       "      <td>1.034977</td>\n",
       "      <td>0.000985</td>\n",
       "      <td>1.003306</td>\n",
       "      <td>0.050231</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Sandwich)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.071844</td>\n",
       "      <td>0.038246</td>\n",
       "      <td>0.079947</td>\n",
       "      <td>1.112792</td>\n",
       "      <td>0.003877</td>\n",
       "      <td>1.008807</td>\n",
       "      <td>0.194321</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Medialuna)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.061807</td>\n",
       "      <td>0.035182</td>\n",
       "      <td>0.073542</td>\n",
       "      <td>1.189878</td>\n",
       "      <td>0.005614</td>\n",
       "      <td>1.012667</td>\n",
       "      <td>0.305936</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>(Tea)</td>\n",
       "      <td>(Coffee, Cake)</td>\n",
       "      <td>0.142631</td>\n",
       "      <td>0.054728</td>\n",
       "      <td>0.010037</td>\n",
       "      <td>0.070370</td>\n",
       "      <td>1.285822</td>\n",
       "      <td>0.002231</td>\n",
       "      <td>1.016827</td>\n",
       "      <td>0.259266</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Hot chocolate)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.058320</td>\n",
       "      <td>0.029583</td>\n",
       "      <td>0.061837</td>\n",
       "      <td>1.060311</td>\n",
       "      <td>0.001683</td>\n",
       "      <td>1.003749</td>\n",
       "      <td>0.109048</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Cookies)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.054411</td>\n",
       "      <td>0.028209</td>\n",
       "      <td>0.058966</td>\n",
       "      <td>1.083723</td>\n",
       "      <td>0.002179</td>\n",
       "      <td>1.004841</td>\n",
       "      <td>0.148110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Toast)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.033597</td>\n",
       "      <td>0.023666</td>\n",
       "      <td>0.049470</td>\n",
       "      <td>1.472431</td>\n",
       "      <td>0.007593</td>\n",
       "      <td>1.016699</td>\n",
       "      <td>0.615122</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Juice)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.038563</td>\n",
       "      <td>0.020602</td>\n",
       "      <td>0.043065</td>\n",
       "      <td>1.116750</td>\n",
       "      <td>0.002154</td>\n",
       "      <td>1.004705</td>\n",
       "      <td>0.200428</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Alfajores)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.036344</td>\n",
       "      <td>0.019651</td>\n",
       "      <td>0.041078</td>\n",
       "      <td>1.130235</td>\n",
       "      <td>0.002264</td>\n",
       "      <td>1.004936</td>\n",
       "      <td>0.220910</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Brownie)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.040042</td>\n",
       "      <td>0.019651</td>\n",
       "      <td>0.041078</td>\n",
       "      <td>1.025860</td>\n",
       "      <td>0.000495</td>\n",
       "      <td>1.001080</td>\n",
       "      <td>0.048327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Muffin)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.038457</td>\n",
       "      <td>0.018806</td>\n",
       "      <td>0.039311</td>\n",
       "      <td>1.022193</td>\n",
       "      <td>0.000408</td>\n",
       "      <td>1.000888</td>\n",
       "      <td>0.041623</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Scone)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.034548</td>\n",
       "      <td>0.018067</td>\n",
       "      <td>0.037765</td>\n",
       "      <td>1.093107</td>\n",
       "      <td>0.001539</td>\n",
       "      <td>1.003343</td>\n",
       "      <td>0.163296</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>(Coffee)</td>\n",
       "      <td>(Spanish Brunch)</td>\n",
       "      <td>0.478394</td>\n",
       "      <td>0.018172</td>\n",
       "      <td>0.010882</td>\n",
       "      <td>0.022747</td>\n",
       "      <td>1.251766</td>\n",
       "      <td>0.002189</td>\n",
       "      <td>1.004682</td>\n",
       "      <td>0.385594</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         antecedents       consequents  antecedent support  \\\n",
       "31           (Toast)          (Coffee)            0.033597   \n",
       "29  (Spanish Brunch)          (Coffee)            0.018172   \n",
       "19       (Medialuna)          (Coffee)            0.061807   \n",
       "22          (Pastry)          (Coffee)            0.086107   \n",
       "1        (Alfajores)          (Coffee)            0.036344   \n",
       "17           (Juice)          (Coffee)            0.038563   \n",
       "24        (Sandwich)          (Coffee)            0.071844   \n",
       "7             (Cake)          (Coffee)            0.103856   \n",
       "27           (Scone)          (Coffee)            0.034548   \n",
       "13         (Cookies)          (Coffee)            0.054411   \n",
       "15   (Hot chocolate)          (Coffee)            0.058320   \n",
       "5          (Brownie)          (Coffee)            0.040042   \n",
       "20          (Muffin)          (Coffee)            0.038457   \n",
       "2           (Pastry)           (Bread)            0.086107   \n",
       "11            (Cake)             (Tea)            0.103856   \n",
       "38     (Tea, Coffee)            (Cake)            0.049868   \n",
       "33        (Sandwich)             (Tea)            0.071844   \n",
       "9    (Hot chocolate)            (Cake)            0.058320   \n",
       "39    (Coffee, Cake)             (Tea)            0.054728   \n",
       "10             (Tea)            (Cake)            0.142631   \n",
       "37          (Pastry)   (Coffee, Bread)            0.086107   \n",
       "36   (Coffee, Bread)          (Pastry)            0.090016   \n",
       "6           (Coffee)            (Cake)            0.478394   \n",
       "34   (Coffee, Bread)            (Cake)            0.090016   \n",
       "8             (Cake)   (Hot chocolate)            0.103856   \n",
       "32             (Tea)        (Sandwich)            0.142631   \n",
       "23          (Coffee)          (Pastry)            0.478394   \n",
       "35            (Cake)   (Coffee, Bread)            0.103856   \n",
       "41            (Cake)     (Tea, Coffee)            0.103856   \n",
       "3            (Bread)          (Pastry)            0.327205   \n",
       "25          (Coffee)        (Sandwich)            0.478394   \n",
       "18          (Coffee)       (Medialuna)            0.478394   \n",
       "40             (Tea)    (Coffee, Cake)            0.142631   \n",
       "14          (Coffee)   (Hot chocolate)            0.478394   \n",
       "12          (Coffee)         (Cookies)            0.478394   \n",
       "30          (Coffee)           (Toast)            0.478394   \n",
       "16          (Coffee)           (Juice)            0.478394   \n",
       "0           (Coffee)       (Alfajores)            0.478394   \n",
       "4           (Coffee)         (Brownie)            0.478394   \n",
       "21          (Coffee)          (Muffin)            0.478394   \n",
       "26          (Coffee)           (Scone)            0.478394   \n",
       "28          (Coffee)  (Spanish Brunch)            0.478394   \n",
       "\n",
       "    consequent support   support  confidence      lift  leverage  conviction  \\\n",
       "31            0.478394  0.023666    0.704403  1.472431  0.007593    1.764582   \n",
       "29            0.478394  0.010882    0.598837  1.251766  0.002189    1.300235   \n",
       "19            0.478394  0.035182    0.569231  1.189878  0.005614    1.210871   \n",
       "22            0.478394  0.047544    0.552147  1.154168  0.006351    1.164682   \n",
       "1             0.478394  0.019651    0.540698  1.130235  0.002264    1.135648   \n",
       "17            0.478394  0.020602    0.534247  1.116750  0.002154    1.119919   \n",
       "24            0.478394  0.038246    0.532353  1.112792  0.003877    1.115384   \n",
       "7             0.478394  0.054728    0.526958  1.101515  0.005044    1.102664   \n",
       "27            0.478394  0.018067    0.522936  1.093107  0.001539    1.093366   \n",
       "13            0.478394  0.028209    0.518447  1.083723  0.002179    1.083174   \n",
       "15            0.478394  0.029583    0.507246  1.060311  0.001683    1.058553   \n",
       "5             0.478394  0.019651    0.490765  1.025860  0.000495    1.024293   \n",
       "20            0.478394  0.018806    0.489011  1.022193  0.000408    1.020777   \n",
       "2             0.327205  0.029160    0.338650  1.034977  0.000985    1.017305   \n",
       "11            0.142631  0.023772    0.228891  1.604781  0.008959    1.111865   \n",
       "38            0.103856  0.010037    0.201271  1.937977  0.004858    1.121962   \n",
       "33            0.142631  0.014369    0.200000  1.402222  0.004122    1.071712   \n",
       "9             0.103856  0.011410    0.195652  1.883874  0.005354    1.114125   \n",
       "39            0.142631  0.010037    0.183398  1.285822  0.002231    1.049923   \n",
       "10            0.103856  0.023772    0.166667  1.604781  0.008959    1.075372   \n",
       "37            0.090016  0.011199    0.130061  1.444872  0.003448    1.046033   \n",
       "36            0.086107  0.011199    0.124413  1.444872  0.003448    1.043749   \n",
       "6             0.103856  0.054728    0.114399  1.101515  0.005044    1.011905   \n",
       "34            0.103856  0.010037    0.111502  1.073621  0.000688    1.008606   \n",
       "8             0.058320  0.011410    0.109868  1.883874  0.005354    1.057910   \n",
       "32            0.071844  0.014369    0.100741  1.402222  0.004122    1.032134   \n",
       "23            0.086107  0.047544    0.099382  1.154168  0.006351    1.014740   \n",
       "35            0.090016  0.010037    0.096643  1.073621  0.000688    1.007336   \n",
       "41            0.049868  0.010037    0.096643  1.937977  0.004858    1.051779   \n",
       "3             0.086107  0.029160    0.089119  1.034977  0.000985    1.003306   \n",
       "25            0.071844  0.038246    0.079947  1.112792  0.003877    1.008807   \n",
       "18            0.061807  0.035182    0.073542  1.189878  0.005614    1.012667   \n",
       "40            0.054728  0.010037    0.070370  1.285822  0.002231    1.016827   \n",
       "14            0.058320  0.029583    0.061837  1.060311  0.001683    1.003749   \n",
       "12            0.054411  0.028209    0.058966  1.083723  0.002179    1.004841   \n",
       "30            0.033597  0.023666    0.049470  1.472431  0.007593    1.016699   \n",
       "16            0.038563  0.020602    0.043065  1.116750  0.002154    1.004705   \n",
       "0             0.036344  0.019651    0.041078  1.130235  0.002264    1.004936   \n",
       "4             0.040042  0.019651    0.041078  1.025860  0.000495    1.001080   \n",
       "21            0.038457  0.018806    0.039311  1.022193  0.000408    1.000888   \n",
       "26            0.034548  0.018067    0.037765  1.093107  0.001539    1.003343   \n",
       "28            0.018172  0.010882    0.022747  1.251766  0.002189    1.004682   \n",
       "\n",
       "    zhangs_metric  \n",
       "31       0.332006  \n",
       "29       0.204851  \n",
       "19       0.170091  \n",
       "22       0.146161  \n",
       "1        0.119574  \n",
       "17       0.108738  \n",
       "24       0.109205  \n",
       "7        0.102840  \n",
       "27       0.088224  \n",
       "13       0.081700  \n",
       "15       0.060403  \n",
       "5        0.026259  \n",
       "20       0.022579  \n",
       "2        0.036980  \n",
       "11       0.420538  \n",
       "38       0.509401  \n",
       "33       0.309050  \n",
       "9        0.498236  \n",
       "39       0.235157  \n",
       "10       0.439556  \n",
       "37       0.336907  \n",
       "36       0.338354  \n",
       "6        0.176684  \n",
       "34       0.075356  \n",
       "8        0.523553  \n",
       "32       0.334566  \n",
       "23       0.256084  \n",
       "35       0.076520  \n",
       "41       0.540090  \n",
       "3        0.050231  \n",
       "25       0.194321  \n",
       "18       0.305936  \n",
       "40       0.259266  \n",
       "14       0.109048  \n",
       "12       0.148110  \n",
       "30       0.615122  \n",
       "16       0.200428  \n",
       "0        0.220910  \n",
       "4        0.048327  \n",
       "21       0.041623  \n",
       "26       0.163296  \n",
       "28       0.385594  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rules = association_rules(frequent_itemsets, metric = \"lift\", min_threshold = 1)\n",
    "rules.sort_values('confidence', ascending = False, inplace = True)\n",
    "rules"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4d6dd7f-6865-4323-a1ff-17a6b7eadafc",
   "metadata": {},
   "source": [
    "### Visualizing Key Product Associations-\n",
    "We utilized the python-igraph package to visualize the most significant association rules, making it easier to identify and interpret key relationships between products. The edges in the graph represent these rules, with the edge highlighted in red indicating the rule with the highest support, emphasizing its prominence among the associations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "86767bc9-c610-4798-9b11-2520e3a40060",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x1400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pip install python-igraph\n",
    "import igraph as ig\n",
    "# Filter rules with confidence > 0.5\n",
    "filtered_rules = rules[rules['confidence'] > 0.5]\n",
    "\n",
    "# Create an igraph graph from the filtered DataFrame\n",
    "g = ig.Graph.TupleList(filtered_rules.itertuples(index=False), directed=True, \n",
    "                       edge_attrs=['support', 'confidence'])\n",
    "\n",
    "# Identify the top 3 support values\n",
    "top_support_indices = filtered_rules.nlargest(3, 'support').index\n",
    "\n",
    "# Map the DataFrame indices to graph edge indices\n",
    "edge_indices = [i for i, edge in enumerate(g.es) if edge.index in top_support_indices]\n",
    "\n",
    "# Plotting the graph\n",
    "layout = g.layout(\"kk\")  # Kamada-Kawai layout\n",
    "fig, ax = plt.subplots(figsize=(20, 14))\n",
    "\n",
    "# Draw the graph with labels\n",
    "visual_style = {\n",
    "    \"vertex_label\": g.vs[\"name\"],\n",
    "    \"edge_label\": [(f\"supp: {edge['support']:.2f}, conf: {edge['confidence']:.2f}\") for edge in g.es],\n",
    "    \"layout\": layout,\n",
    "    \"target\": ax,\n",
    "    \"vertex_size\": 20,\n",
    "    \"bbox\": (700, 500),\n",
    "    \"edge_color\": [\"red\" if i in edge_indices else \"black\" for i in range(len(g.es))]\n",
    "}\n",
    "\n",
    "ig.plot(g, **visual_style)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dd4c6e39-f009-4daa-a0dc-c88085402682",
   "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": "3.12.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}