Added a few more implementations of algorithms

Data is yet to be added

Author: 13muskanp

BayesianClassifier.ipynb

@@ -0,0 +1,136 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "COLUMN\tVALUE\tOUTPUT\tPROBABILITY\n",
+      "Temp--->Hot--->Rainy--->0.4\n",
+      "Temp--->Mild--->Rainy--->0.4\n",
+      "Temp--->Cool--->Rainy--->0.2\n",
+      "Humidity--->High--->Rainy--->0.6\n",
+      "Humidity--->Normal--->Rainy--->0.4\n",
+      "Windy--->Low--->Rainy--->0.6\n",
+      "Windy--->High--->Rainy--->0.4\n",
+      "Cloudy--->Yes--->Rainy--->0.6\n",
+      "Cloudy--->No--->Rainy--->0.4\n",
+      "Temp--->Hot--->Overcast--->0.5\n",
+      "Temp--->Mild--->Overcast--->0.25\n",
+      "Temp--->Cool--->Overcast--->0.25\n",
+      "Humidity--->High--->Overcast--->0.5\n",
+      "Humidity--->Normal--->Overcast--->0.5\n",
+      "Windy--->Low--->Overcast--->0.5\n",
+      "Windy--->High--->Overcast--->0.5\n",
+      "Cloudy--->Yes--->Overcast--->0.5\n",
+      "Cloudy--->No--->Overcast--->0.5\n",
+      "Temp--->Hot--->Sunny--->0.0\n",
+      "Temp--->Mild--->Sunny--->0.6\n",
+      "Temp--->Cool--->Sunny--->0.4\n",
+      "Humidity--->High--->Sunny--->0.4\n",
+      "Humidity--->Normal--->Sunny--->0.6\n",
+      "Windy--->Low--->Sunny--->0.6\n",
+      "Windy--->High--->Sunny--->0.4\n",
+      "Cloudy--->Yes--->Sunny--->0.2\n",
+      "Cloudy--->No--->Sunny--->0.8\n",
+      "{'Rainy': 5, 'Overcast': 4, 'Sunny': 5}\n",
+      "{'Rainy': 0.6162624821683309, 'Overcast': 0.17831669044222537, 'Sunny': 0.20542082738944364}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "class BayesianClassifier:\n",
+    "\n",
+    "    def __init__(self, path, col):\n",
+    "        self.cols = {}\n",
+    "        self.op_cols = {}\n",
+    "        self.col = col\n",
+    "        self.data = pd.read_csv(path)\n",
+    "        self.dataM = self.data\n",
+    "        self.op = self.data[col]\n",
+    "        self.data = self.data.drop(col, axis=1)\n",
+    "        self.total = len(self.dataM)\n",
+    "    \n",
+    "    def get_probability_table(self):\n",
+    "        for i in self.op.unique():\n",
+    "            self.cols[i] = {}\n",
+    "            for j in self.data.columns:\n",
+    "                self.cols[i][j] = {}\n",
+    "                for k in self.data[j]:\n",
+    "                    if k not in self.cols[i][j]:\n",
+    "                        self.cols[i][j][k] = \"\"\n",
+    "        dfs = []\n",
+    "        for i in self.op.unique():\n",
+    "            for j in self.data.columns:\n",
+    "                for k in self.data[j].unique():\n",
+    "                    dfs.append(self.dataM[self.dataM[self.col] == i])\n",
+    "\n",
+    "                    \n",
+    "        print(\"COLUMN\\tVALUE\\tOUTPUT\\tPROBABILITY\")\n",
+    "        for x in self.cols:\n",
+    "            for y in self.cols[x]:\n",
+    "                for z in self.cols[x][y]:\n",
+    "                    self.op_cols[x] = len(self.dataM[self.dataM[self.col] == x])\n",
+    "                    total = len(self.dataM[(self.dataM[self.col] == x) & (self.dataM[y])])\n",
+    "                    p = len(self.dataM[(self.dataM[y] == z) & (self.dataM[self.col] == x)]) / total\n",
+    "                    self.cols[x][y][z] = p\n",
+    "                    print(\"{}--->{}--->{}--->{}\".format(y,z,x,p))\n",
+    "        print(self.op_cols)\n",
+    "                    \n",
+    "    def classify(self, values):\n",
+    "        p = {}\n",
+    "        tot = 0\n",
+    "        for i in self.op.unique():\n",
+    "            a = 1\n",
+    "            for key, value in values.items():\n",
+    "                a *= self.cols[i][key][value]\n",
+    "            p[i] = a*self.op_cols[i]/self.total\n",
+    "            tot += a*self.op_cols[i]/self.total\n",
+    "        \n",
+    "        for i in p:\n",
+    "            p[i] = p[i] / tot\n",
+    "        \n",
+    "        return p\n",
+    "            \n",
+    "b = BayesianClassifier(\"new.csv\", \"Weather\")\n",
+    "\n",
+    "b.get_probability_table()\n",
+    "print(b.classify({\"Temp\": 'Mild', \"Windy\": \"Low\", \"Humidity\": \"High\", \"Cloudy\": \"Yes\"}))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}