Add KNN classification in ML

ML/Assignment3/KNN_From_Scratch_Sample_Dataset.ipynb

@@ -0,0 +1,101 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## KNN from scratch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def euclidean_distance(row1, row2):\n",
+    "    distance = 0.0\n",
+    "    for i in range(len(row1)-1):\n",
+    "        distance += (row1[i] - row2[i])**2\n",
+    "    return sqrt(distance)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_neighbors(train, test_row, num_neighbors):\n",
+    "    distances = list()\n",
+    "    for train_row in train:\n",
+    "        dist = euclidean_distance(train_row, test_row)\n",
+    "        distances.append((train_row, dist))\n",
+    "    distances.sort(key=lambda tup: tup[1])\n",
+    "    neighbors = list()\n",
+    "    for i in range(num_neighbors):\n",
+    "        neighbors.append(distances[i][0])\n",
+    "    return neighbors"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data point :  [6, 6]\n",
+      "Nearest Neighbors :  [[4, 6, 'Orange'], [6, 4, 'Orange'], [4, 4, 'Blue']]\n",
+      "Prediction :  Orange \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_data = [[2, 4, \"Orange\"], [4, 4, \"Blue\"], [4, 6, \"Orange\"], [4, 2, \"Orange\"], [6, 2, \"Blue\"], [6, 4, \"Orange\"]]\n",
+    "test_data = [[6, 6]]\n",
+    "\n",
+    "for item in test_data:\n",
+    "    print(\"Data point : \", item)\n",
+    "    neighbors = get_neighbors(train_data, item, 3)\n",
+    "    print(\"Nearest Neighbors : \", neighbors)\n",
+    "    output_values = [row[-1] for row in neighbors]\n",
+    "    prediction = max(set(output_values), key=output_values.count)\n",
+    "    print(\"Prediction : \", prediction, \"\\n\")"
+   ]
+  }
+ ],
+ "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": 2
+}