Implement apriori

Data.txt

@@ -0,0 +1,9 @@
+I1,I2,I5
+I2,I4
+I2,I3
+I1,I2,I4
+I1,I3
+I2,I3
+I1,I3
+I1,I2,I3,I5
+I1,I2,I3

TEST.md

@@ -0,0 +1,2 @@
+This is for testing purposes only
+Testing the commit signing key

apriori.ipynb

@@ -0,0 +1,238 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from utils import *\n",
+    "from functions import load_transaction_data, get_frequent,join_set_itemsets,count_occurences,write_rules,powerset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "38d9e47d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "9\n"
+     ]
+    }
+   ],
+   "source": [
+    "path_to_data = 'Data.txt'\n",
+    "min_support = 2/9\n",
+    "min_confidence = 0.3 # 30 percent\n",
+    "order = ['I' + str(i) for i in range(1,6)]\n",
+    "#print(order)\n",
+    "\n",
+    "with open(path_to_data, \"r\") as file:\n",
+    "    data = file.read()\n",
+    "transactions = data.split(\"\\n\")\n",
+    "num_trans = len(transactions)\n",
+    "\n",
+    "print(num_trans)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "759093e0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "L1 \n",
+      "\n",
+      "([['I1'], ['I2'], ['I3'], ['I4'], ['I5']], [6, 7, 6, 2, 2])\n"
+     ]
+    }
+   ],
+   "source": [
+    "Transactions = load_transaction_data(path_to_data, order)\n",
+    "\n",
+    "#innitialization\n",
+    "#for itemsets of 1\n",
+    "C = {}\n",
+    "L = {}\n",
+    "itemset_size = 1\n",
+    "Discarded = {itemset_size : []}\n",
+    "C.update({itemset_size : [ [f] for f in order ]})\n",
+    "\n",
+    "#creating L1 (Frequent itemsets)\n",
+    "supp_cnt_L = {}\n",
+    "f, sup, new_discarded = get_frequent(C[itemset_size], Transactions, min_support, Discarded)\n",
+    "Discarded.update({ itemset_size: new_discarded}) #updates to discarded itemsets from first iteration\n",
+    "L.update({itemset_size : f})\n",
+    "supp_cnt_L.update({itemset_size : sup})\n",
+    "\n",
+    "result = (L[1], supp_cnt_L[1])\n",
+    "print(\"L1 \\n\")\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "50c396b0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Result C2 \n",
+      "\n",
+      "([['I1', 'I2'], ['I1', 'I3'], ['I1', 'I4'], ['I1', 'I5'], ['I2', 'I3'], ['I2', 'I4'], ['I2', 'I5'], ['I3', 'I4'], ['I3', 'I5'], ['I4', 'I5']], [4, 4, 1, 2, 4, 2, 2, 0, 1, 0])\n",
+      "\n",
+      "Result L2 \n",
+      "\n",
+      "([['I1', 'I2'], ['I1', 'I3'], ['I1', 'I5'], ['I2', 'I3'], ['I2', 'I4'], ['I2', 'I5']], [4, 4, 2, 4, 2, 2])\n",
+      "\n",
+      "Result C3 \n",
+      "\n",
+      "([['I1', 'I2', 'I3'], ['I1', 'I2', 'I5'], ['I1', 'I3', 'I5'], ['I2', 'I3', 'I4'], ['I2', 'I3', 'I5'], ['I2', 'I4', 'I5']], [2, 2, 1, 0, 1, 0])\n",
+      "\n",
+      "Result L3 \n",
+      "\n",
+      "([['I1', 'I2', 'I3'], ['I1', 'I2', 'I5']], [2, 2])\n",
+      "\n",
+      "Result C4 \n",
+      "\n",
+      "([['I1', 'I2', 'I3', 'I5']], [1])\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "k = itemset_size + 1\n",
+    "convergence = False\n",
+    "while not  convergence:\n",
+    "    C.update({k:join_set_itemsets(L[k-1], order)})\n",
+    "    print(\"Result C{} \\n\".format(k))\n",
+    "    result = C[k], [count_occurences(it, Transactions) for it in C[k]]\n",
+    "    print (result)\n",
+    "    print()\n",
+    "    f, sup, new_discarded = get_frequent(C[k],Transactions, min_support, Discarded)\n",
+    "    Discarded.update({k : new_discarded})\n",
+    "    L.update({k : f})\n",
+    "    supp_cnt_L.update({k : sup})\n",
+    "    if len(L[k]) == 0:\n",
+    "        convergence = True\n",
+    "    else:\n",
+    "        print(\"Result L{} \\n\".format(k))\n",
+    "        result = L[k], supp_cnt_L[k]\n",
+    "        print(result)\n",
+    "        print()\n",
+    "    k += 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "101df4e0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Freq. Itemset: {'I2', 'I1'}\n",
+      " Rule: ['I2'] -> ['I1'] \n",
+      " conf: 0.571   supp: 0.444   lift: 0.857  Freq. Itemset: {'I2', 'I1'}\n",
+      " Rule: ['I1'] -> ['I2'] \n",
+      " conf: 0.667   supp: 0.444   lift: 0.857  Freq. Itemset: {'I3', 'I1'}\n",
+      " Rule: ['I3'] -> ['I1'] \n",
+      " conf: 0.667   supp: 0.444   lift: 1.000  Freq. Itemset: {'I3', 'I1'}\n",
+      " Rule: ['I1'] -> ['I3'] \n",
+      " conf: 0.667   supp: 0.444   lift: 1.000  Freq. Itemset: {'I5', 'I1'}\n",
+      " Rule: ['I5'] -> ['I1'] \n",
+      " conf: 1.000   supp: 0.222   lift: 1.500  Freq. Itemset: {'I5', 'I1'}\n",
+      " Rule: ['I1'] -> ['I5'] \n",
+      " conf: 0.333   supp: 0.222   lift: 1.500  Freq. Itemset: {'I3', 'I2'}\n",
+      " Rule: ['I3'] -> ['I2'] \n",
+      " conf: 0.667   supp: 0.444   lift: 0.857  Freq. Itemset: {'I3', 'I2'}\n",
+      " Rule: ['I2'] -> ['I3'] \n",
+      " conf: 0.571   supp: 0.444   lift: 0.857  Freq. Itemset: {'I4', 'I2'}\n",
+      " Rule: ['I4'] -> ['I2'] \n",
+      " conf: 1.000   supp: 0.222   lift: 1.286  Freq. Itemset: {'I5', 'I2'}\n",
+      " Rule: ['I5'] -> ['I2'] \n",
+      " conf: 1.000   supp: 0.222   lift: 1.286  Freq. Itemset: {'I3', 'I2', 'I1'}\n",
+      " Rule: ['I3'] -> ['I2', 'I1'] \n",
+      " conf: 0.333   supp: 0.222   lift: 0.750  Freq. Itemset: {'I3', 'I2', 'I1'}\n",
+      " Rule: ['I1'] -> ['I3', 'I2'] \n",
+      " conf: 0.333   supp: 0.222   lift: 0.750  Freq. Itemset: {'I3', 'I2', 'I1'}\n",
+      " Rule: ['I3', 'I2'] -> ['I1'] \n",
+      " conf: 0.500   supp: 0.222   lift: 0.750  Freq. Itemset: {'I3', 'I2', 'I1'}\n",
+      " Rule: ['I3', 'I1'] -> ['I2'] \n",
+      " conf: 0.500   supp: 0.222   lift: 0.643  Freq. Itemset: {'I3', 'I2', 'I1'}\n",
+      " Rule: ['I2', 'I1'] -> ['I3'] \n",
+      " conf: 0.500   supp: 0.222   lift: 0.750  Freq. Itemset: {'I5', 'I2', 'I1'}\n",
+      " Rule: ['I5'] -> ['I2', 'I1'] \n",
+      " conf: 1.000   supp: 0.222   lift: 2.250  Freq. Itemset: {'I5', 'I2', 'I1'}\n",
+      " Rule: ['I1'] -> ['I5', 'I2'] \n",
+      " conf: 0.333   supp: 0.222   lift: 1.500  Freq. Itemset: {'I5', 'I2', 'I1'}\n",
+      " Rule: ['I5', 'I2'] -> ['I1'] \n",
+      " conf: 1.000   supp: 0.222   lift: 1.500  Freq. Itemset: {'I5', 'I2', 'I1'}\n",
+      " Rule: ['I5', 'I1'] -> ['I2'] \n",
+      " conf: 1.000   supp: 0.222   lift: 1.286  Freq. Itemset: {'I5', 'I2', 'I1'}\n",
+      " Rule: ['I2', 'I1'] -> ['I5'] \n",
+      " conf: 0.500   supp: 0.222   lift: 2.250  \n"
+     ]
+    }
+   ],
+   "source": [
+    "assoc_rules_str = \"\"\n",
+    "\n",
+    "for i in range(1, len(L)):\n",
+    "    for j in range (len(L[i])):\n",
+    "        s = powerset(set(L[i][j]))\n",
+    "        s.pop() #subset containing all the elements will be gotten rid of\n",
+    "        for z in s:\n",
+    "            S = set(z)\n",
+    "            X = set(L[i][j])\n",
+    "            X_S = set(X-S)\n",
+    "            sup_x = count_occurences(X, Transactions)\n",
+    "            sup_x_s = count_occurences(X_S, Transactions)\n",
+    "            conf = sup_x / count_occurences(S, Transactions)\n",
+    "            lift = conf / (sup_x_s/num_trans)\n",
+    "            if conf >= min_confidence and sup_x >= min_support:\n",
+    "                assoc_rules_str += write_rules(X, X_S, S, conf, sup_x, lift, num_trans)\n",
+    "\n",
+    "print(assoc_rules_str)"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

apriori.py

@@ -0,0 +1,79 @@
+import numpy as np
+from utils import *
+from functions import load_transaction_data, get_frequent,join_set_itemsets,count_occurences,write_rules,powerset
+
+
+path_to_data = 'Data.txt'
+min_support = 2/9
+min_confidence = 0.3 # 30 percent
+order = ['I' + str(i) for i in range(1,6)]
+#print(order)
+
+with open(path_to_data, "r") as file:
+    data = file.read()
+transactions = data.split("\n")
+num_trans = len(transactions)
+#print(num_trans)
+
+Transactions = load_transaction_data(path_to_data, order)
+
+#innitialization
+#for itemsets of 1
+C = {}
+L = {}
+itemset_size = 1
+Discarded = {itemset_size : []}
+C.update({itemset_size : [ [f] for f in order ]})
+
+#creating L1 (Frequent itemsets)
+supp_cnt_L = {}
+f, sup, new_discarded = get_frequent(C[itemset_size], Transactions, min_support, Discarded)
+Discarded.update({ itemset_size: new_discarded}) #real discarded itemsets from first iteration
+L.update({itemset_size : f})
+supp_cnt_L.update({itemset_size : sup})
+
+result = (L[1], supp_cnt_L[1])
+
+k = itemset_size + 1
+convergence = False
+while not  convergence:
+    C.update({k:join_set_itemsets(L[k-1], order)})
+    print("Result C{} \n".format(k))
+    tresult= C[k], [count_occurences(it, Transactions) for it in C[k]]
+    print (result)
+    print()
+    f, sup, new_discarded = get_frequent(C[k],Transactions, min_support, Discarded)
+    Discarded.update({k : new_discarded})
+    L.update({k : f})
+    supp_cnt_L.update({k : sup})
+    if len(L[k]) == 0:
+        convergence = True
+    else:
+        print("Table L{} \n".format(k))
+        result = L[k], supp_cnt_L[k]
+        print(result)
+        print()
+    k += 1
+
+#Generating association rules according to frequent itemsets above
+
+#starting from frequent sets of size 2 ie (k = 1), since frequent sets of size one can't produce significant rules
+
+assoc_rules_str = ""
+
+for i in range(1, len(L)):
+    for j in range (len(L[i])):
+        s = powerset(set(L[i][j]))
+        s.pop() #subset containing all the elements will be gotten rid of
+        for z in s:
+            S = set(z)
+            X = set(L[i][j])
+            X_S = set(X-S)
+            sup_x = count_occurences(X, Transactions)
+            sup_x_s = count_occurences(X_S, Transactions)
+            conf = sup_x / count_occurences(S, Transactions)
+            lift = conf / (sup_x_s/num_trans)
+            if conf >= min_confidence and sup_x >= min_support:
+                assoc_rules_str += write_rules(X, X_S, S, conf, sup_x, lift, num_trans)
+
+print(assoc_rules_str)