{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------ITEMSET--------------\n",
      "{frozenset({'6'}), frozenset({'5'}), frozenset({'2'}), frozenset({'4'}), frozenset({'3'}), frozenset({'7'}), frozenset({'1'}), frozenset({'0'}), frozenset({'8'})}\n",
      "---------------TRANSACTION LIST----------------\n",
      "[frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '4', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '4', '1'}), frozenset({'0', '4', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '2', '1'}), frozenset({'0', '4', '1'}), frozenset({'0', '7', '1'}), frozenset({'0', '4', '7', '1'}), frozenset({'6', '0', '7', '1'}), frozenset({'0', '2', '1'}), frozenset({'1', '4', '0'}), frozenset({'0', '4', '1'}), frozenset({'0', '1'}), frozenset({'0', '2', '1'}), frozenset({'0', '2', '1'}), frozenset({'1', '4', '0'}), frozenset({'0', '2', '1'}), frozenset({'6', '0', '1'}), frozenset({'0', '4', '1', '5'}), frozenset({'0', '4', '1', '5'}), frozenset({'1', '2', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '2', '0'}), frozenset({'6', '0', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '2', '0'}), frozenset({'0', '2', '1'}), frozenset({'0', '4', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '2', '1'}), frozenset({'0', '4', '1'}), frozenset({'6', '1', '0'}), frozenset({'6', '1', '0'}), frozenset({'0', '2', '1'}), frozenset({'6', '0', '1'}), frozenset({'0', '2', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'6', '0', '7', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'6', '1', '0'}), frozenset({'0', '4', '1', '5'}), frozenset({'8', '0', '7', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '2', '1'}), frozenset({'0', '2', '1'}), frozenset({'0', '2', '1'}), frozenset({'0', '2', '1'}), frozenset({'0', '4', '1'}), frozenset({'0', '4', '1'}), frozenset({'0', '3', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '1'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '2', '1'}), frozenset({'8', '0', '7', '1'}), frozenset({'0', '4', '1'}), frozenset({'1', '0'}), frozenset({'1', '2', '0'}), frozenset({'0', '3', '1'}), frozenset({'0', '7', '1'}), frozenset({'0', '2', '1'}), frozenset({'0', '2', '1'}), frozenset({'0', '3', '1'}), frozenset({'0', '7', '1'}), frozenset({'0', '4', '1'}), frozenset({'0', '2', '1'}), frozenset({'1', '2', '0'}), frozenset({'0', '7', '1', '5'}), frozenset({'0', '4', '1'}), frozenset({'0', '2', '1'}), frozenset({'6', '0', '1'}), frozenset({'0', '4', '1', '5'}), frozenset({'0', '4', '3', '1'}), frozenset({'0', '4', '3', '1'}), frozenset({'0', '4', '1'}), frozenset({'1', '2', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '2', '1'}), frozenset({'1', '2', '0'}), frozenset({'6', '1', '0'}), frozenset({'1', '4', '0'}), frozenset({'0', '7', '1'}), frozenset({'0', '2', '1'})]\n",
      "MINIMUM SUPPORT 0.0069328715049722794\n",
      "\n",
      "------------------------ FREQUENT ITEMSET:\n",
      "item: ('1', '7', '5') , 0.009\n",
      "item: ('7',) , 0.010\n",
      "item: ('6', '7') , 0.011\n",
      "item: ('6', '1', '7') , 0.020\n",
      "item: ('1', '4', '7') , 0.023\n",
      "item: ('5',) , 0.025\n",
      "item: ('4', '7') , 0.025\n",
      "item: ('1', '5') , 0.062\n",
      "item: ('1', '4', '3') , 0.066\n",
      "item: ('1', '7', '8') , 0.067\n",
      "item: ('4', '3') , 0.079\n",
      "item: ('7', '8') , 0.080\n",
      "item: ('6',) , 0.099\n",
      "item: ('1', '8') , 0.099\n",
      "item: ('1', '4', '5') , 0.099\n",
      "item: ('1', '7') , 0.104\n",
      "item: ('4', '5') , 0.109\n",
      "item: ('1', '3') , 0.124\n",
      "item: ('3',) , 0.149\n",
      "item: ('6', '1') , 0.149\n",
      "item: ('8',) , 0.158\n",
      "item: ('1', '2') , 0.936\n",
      "item: ('2',) , 1.337\n",
      "item: ('1', '4') , 1.767\n",
      "item: ('1',) , 2.000\n",
      "item: ('4',) , 2.525\n",
      "\n",
      "------------------------ RULES:\n",
      "Rule: ('1', '8') ==> ('7',) , 0.673, 68.007\n",
      "Rule: ('7',) ==> ('1', '8') , 6.733, 68.007\n",
      "Rule: ('7',) ==> ('8',) , 8.100, 51.131\n",
      "Rule: ('8',) ==> ('7',) , 0.506, 51.131\n",
      "Rule: ('7',) ==> ('1', '5') , 0.867, 14.005\n",
      "Rule: ('7',) ==> ('6', '1') , 2.067, 13.916\n",
      "Rule: ('7',) ==> ('6',) , 1.100, 11.110\n",
      "Rule: ('7',) ==> ('1',) , 10.500, 5.250\n",
      "Rule: ('1', '7') ==> ('8',) , 0.641, 4.048\n",
      "Rule: ('5',) ==> ('1', '4') , 4.000, 2.263\n",
      "Rule: ('5',) ==> ('4',) , 4.400, 1.743\n",
      "Rule: ('7', '5') ==> ('1',) , 2.889, 1.444\n",
      "Rule: ('7',) ==> ('1', '4') , 2.367, 1.339\n",
      "Rule: ('5',) ==> ('1',) , 2.500, 1.250\n",
      "Rule: ('7',) ==> ('4',) , 2.550, 1.010\n",
      "Rule: ('6', '7') ==> ('1',) , 1.879, 0.939\n",
      "Rule: ('6',) ==> ('1',) , 1.500, 0.750\n",
      "Rule: ('1', '5') ==> ('4',) , 1.600, 0.634\n",
      "Rule: ('4', '7') ==> ('1',) , 0.928, 0.464\n",
      "Rule: ('4', '5') ==> ('1',) , 0.909, 0.455\n",
      "Rule: ('4', '3') ==> ('1',) , 0.833, 0.417\n",
      "Rule: ('3',) ==> ('1',) , 0.833, 0.417\n",
      "Rule: ('7', '8') ==> ('1',) , 0.831, 0.416\n",
      "Rule: ('1',) ==> ('4',) , 0.884, 0.350\n",
      "Rule: ('4',) ==> ('1',) , 0.700, 0.350\n",
      "Rule: ('2',) ==> ('1',) , 0.700, 0.350\n",
      "Rule: ('8',) ==> ('1',) , 0.625, 0.312\n",
      "Rule: ('1', '3') ==> ('4',) , 0.533, 0.211\n",
      "Rule: ('3',) ==> ('4',) , 0.533, 0.211\n",
      "29\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "\n",
    "from itertools import chain, combinations\n",
    "from collections import defaultdict\n",
    "from optparse import OptionParser\n",
    "\n",
    "# from apriori import (\n",
    "#     getItemSetTransactionList,\n",
    "#     dataFromFile,\n",
    "#     joinSet,\n",
    "#     printResults,\n",
    "#     returnItemsWithMinSupport,\n",
    "#     runApriori,\n",
    "#     subsets,\n",
    "# )\n",
    "\n",
    "\n",
    "itemresult = set()\n",
    "freqSet = defaultdict(int)\n",
    "freqSet2 = defaultdict(int)\n",
    "utilSet = defaultdict(int)\n",
    "utilSet2 = defaultdict(int)\n",
    "\n",
    "freqitemset=[]\n",
    "freqitemset2=[]\n",
    "largeSet = dict()\n",
    "minConfidence=0.5\n",
    "\n",
    "#### from collections import defaultdict\n",
    "def dataFromFile(fname):\n",
    "    \"\"\"Function which reads from the file and yields a generator\"\"\"\n",
    "    with open(fname, \"r\") as file_iter:\n",
    "        for line in file_iter:\n",
    "            line = line.strip().rstrip(\",\")  # Remove trailing comma\n",
    "            record = frozenset(line.split(\",\"))\n",
    "            yield record\n",
    "            \n",
    "\n",
    "\n",
    "def getItemSetTransactionList(data_iterator):\n",
    "    transactionList = list()\n",
    "    itemSet = set()\n",
    "    for record in data_iterator:\n",
    "        transaction = frozenset(record)\n",
    "        transactionList.append(transaction)\n",
    "        for item in transaction:\n",
    "            itemSet.add(frozenset([item]))  # Generate 1-itemSets\n",
    "    return itemSet, transactionList\n",
    "\n",
    "def getminsup(itemSet,transactionList):\n",
    "    for item in itemSet:\n",
    "#         print(item)\n",
    "        for transaction in transactionList:\n",
    "            if item.issubset(transaction):\n",
    "                freqSet[item] += 1\n",
    "#                 print(freqSet)\n",
    "    \n",
    "    sum=0  \n",
    "    for item, count in freqSet.items():\n",
    "        support = float(count) / float(len(transactionList))\n",
    "#         print(support)\n",
    "#         print(utilSet)\n",
    "        ut=utilSet[item]\n",
    "        utility1=support*ut\n",
    "        sum=sum+utility1\n",
    "        utilSet2[item]=utility1\n",
    "#         print(utilSet2)\n",
    "    aveutil=sum/len(itemSet)\n",
    "#     print(aveutil)\n",
    "    minsup=aveutil/len(transactionList)\n",
    "#     print(minsup)\n",
    "\n",
    "    return minsup\n",
    "\n",
    "\n",
    "def getfreqitem2(itemSet,transactionList,minimumSupport,freqSet,k):\n",
    "    _itemSet=set()\n",
    "    localSet = defaultdict(int)\n",
    "    for item in itemSet:\n",
    "#         print(\"item\")\n",
    "#         print(item)\n",
    "        for transaction in transactionList:\n",
    "            if item.issubset(transaction):\n",
    "                freqSet[item] += 1\n",
    "                localSet[item] += 1\n",
    "#                 print(localSet)\n",
    "    \n",
    "    sum=0  \n",
    "    for item, count in localSet.items():\n",
    "        support = float(count) / float(len(transactionList))\n",
    "        ut=0\n",
    "        for item1,util in utilSet.items():\n",
    "            if(item1.issubset(item)):\n",
    "                ut=ut+float(util)\n",
    "        averageutil=ut/k\n",
    "#         print(averageutil)\n",
    "        utility1=support*averageutil\n",
    "#         print(utility1)\n",
    "        utilSet2[item]=utility1\n",
    "#     print(\"utilset\",utilSet2)\n",
    "#     print(\"localset\",localSet)\n",
    "    \n",
    "    for item in itemSet:\n",
    "#         print(item)\n",
    "#         print(utilSet2[item])\n",
    "        if(utilSet2[item])>=minimumSupport:\n",
    "            _itemSet.add(item)\n",
    "    return _itemSet\n",
    "\n",
    "\n",
    "def subsets(arr):\n",
    "    \"\"\" Returns non empty subsets of arr\"\"\"\n",
    "    return chain(*[combinations(arr, i + 1) for i, a in enumerate(arr)])\n",
    "\n",
    "def joinSet(itemSet, length):\n",
    "    \"\"\"Join a set with itself and returns the n-element itemsets\"\"\"\n",
    "    itemSet=frozenset(itemSet)\n",
    "    return set(\n",
    "        [i.union(j) for i in itemSet for j in itemSet if len(i.union(j)) == length]\n",
    "    )\n",
    "\n",
    "def getSupport(item):\n",
    "        \"\"\"local function which Returns the support of an item\"\"\"\n",
    "        return float(utilSet2[item])\n",
    "\n",
    "\n",
    "inFile = dataFromFile(\"zoo.csv\")\n",
    "itemSet, transactionList = getItemSetTransactionList(inFile)\n",
    "print(\"------ITEMSET--------------\")\n",
    "print(itemSet)\n",
    "print(\"---------------TRANSACTION LIST----------------\")\n",
    "print(transactionList)\n",
    "\n",
    "\n",
    "\n",
    "utilSet[frozenset({'1'})]=2\n",
    "utilSet[frozenset({'2'})]=5\n",
    "utilSet[frozenset({'3'})]=3\n",
    "utilSet[frozenset({'4'})]=5\n",
    "utilSet[frozenset({'5'})]=0.5\n",
    "utilSet[frozenset({'6'})]=1\n",
    "utilSet[frozenset({'7'})]=0.1\n",
    "utilSet[frozenset({'8'})]=8\n",
    "utilSet[frozenset({'9'})]=4\n",
    "\n",
    "largeSet = dict()\n",
    "    # Global dictionary which stores (key=n-itemSets,value=support)\n",
    "    # which satisfy minSupport\n",
    "\n",
    "assocRules = dict()\n",
    "    # Dictionary which stores Association Rules\n",
    "minsup=getminsup(itemSet,transactionList)\n",
    "print(\"MINIMUM SUPPORT\",minsup)\n",
    "oneCSet = getfreqitem2(itemSet, transactionList, minsup,freqSet,1)\n",
    "# print(oneCSet)\n",
    "\n",
    "currentLSet = oneCSet\n",
    "k = 2\n",
    "# currentLSet = joinSet(currentLSet, k)\n",
    "# print(\"2 itemset\")\n",
    "# print(currentLSet)\n",
    "# freqitemset2 = getfreqitem2(currentLSet, transactionList, minsup,freqSet,k)\n",
    "# print(\"freq item 2\")\n",
    "# print(freqitemset2)\n",
    "# k=3\n",
    "# currentLSet = joinSet(oneCSet, k)\n",
    "# print(currentLSet)\n",
    "# oneCSet = getfreqitem2(currentLSet, transactionList, minsup,freqSet,k)\n",
    "# print(\"freq item 3\")\n",
    "# print(oneCSet)\n",
    "\n",
    "while currentLSet != set([]):\n",
    "    largeSet[k - 1] = currentLSet\n",
    "    currentLSet = joinSet(currentLSet, k)\n",
    "#     print(currentLSet)\n",
    "    currentCSet = getfreqitem2(\n",
    "        currentLSet, transactionList, minsup,freqSet,k\n",
    "    )\n",
    "    currentLSet = currentCSet\n",
    "#     print(currentLSet)\n",
    "    k = k + 1\n",
    "\n",
    "    \n",
    "# print(largeSet)\n",
    "       \n",
    "toRetItems = []\n",
    "for key, value in largeSet.items():\n",
    "    toRetItems.extend([(tuple(item), getSupport(item)) for item in value])\n",
    "\n",
    "toRetRules = []\n",
    "for key, value in list(largeSet.items())[1:]:\n",
    "    for item in value:\n",
    "        _subsets = map(frozenset, [x for x in subsets(item)])\n",
    "        for element in _subsets:\n",
    "            remain = item.difference(element)\n",
    "            if len(remain) > 0:\n",
    "                confidence = getSupport(item) / getSupport(element)\n",
    "                if confidence >= minConfidence:\n",
    "                    lift=confidence/getSupport(remain)\n",
    "                    toRetRules.append(((tuple(element), tuple(remain)), confidence,lift))\n",
    "\n",
    "print(\"\\n------------------------ FREQUENT ITEMSET:\")\n",
    "\"\"\"prints the generated itemsets sorted by support and the confidence rules sorted by confidence\"\"\"\n",
    "for item, support in sorted(toRetItems, key=lambda x: x[1]):\n",
    "    print(\"item: %s , %.3f\" % (str(item), support))\n",
    "    \n",
    "from operator import itemgetter\n",
    "res = sorted(toRetRules, key = itemgetter(2),reverse=True)\n",
    "# print(str(res))\n",
    "print(\"\\n------------------------ RULES:\")\n",
    "for rule, confidence,lift in (res):\n",
    "    pre, post = rule\n",
    "    print(\"Rule: %s ==> %s , %.3f, %.3f\" % (str(pre), str(post), confidence, lift))\n",
    "\n",
    "print(len(res))\n",
    "# for rule, confidence in sorted(toRetRules, key=lambda x: x[1]):\n",
    "#     pre, post = rule\n",
    "#     print(\"Rule: %s ==> %s , %.3f\" % (str(pre), str(post), confidence))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}