Add files via upload

ML algorithms from scratch/Naive Bayes from scratch.ipynb

@@ -0,0 +1,214 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Naive Bayes from scratch.ipynb.ipynb",
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "\n",
+        "\n",
+        "## Naive Bayes \n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "ZPIkyYBagucI"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "32VI1xFQgtIP"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "class NaiveBayes:\n",
+        "  def fit(self,X,y):\n",
+        "    no_samples, no_features = X.shape\n",
+        "    self.no_classes = len(np.unique(y))\n",
+        "    self.mean = np.zeros((self.no_classes, no_features))\n",
+        "    self.var = np.zeros((self.no_classes, no_features))\n",
+        "    self.priors = np.zeros(self.no_classes)\n",
+        "    for c in range(self.no_classes):\n",
+        "      x_class = X[y==c]\n",
+        "      \n",
+        "      self.mean[c,:] = np.mean(x_class, axis = 0)\n",
+        "      self.var[c,:] = np.mean(x_class, axis = 0)\n",
+        "      self.priors[c] = x_class.shape[0] / float(no_features) \n",
+        "  \n",
+        "  def gaus_class_probability(self,x):\n",
+        "    posteriors = []\n",
+        "\n",
+        "    for c in range(self.no_classes):\n",
+        "      mean = self.mean[c]\n",
+        "      var = self.var[c]\n",
+        "      prior = np.log(self.priors[c])\n",
+        "\n",
+        "      conditional_prob = np.sum(np.log(self.gaussian_density(x,mean,var)))\n",
+        "      posterior  = prior + conditional_prob\n",
+        "\n",
+        "      posteriors.append(posterior)\n",
+        "    #return the index of the highest class probability\n",
+        "    return np.argmax(posteriors)\n",
+        "  def gaussian_density(self,x,mean,var):\n",
+        "    constant = 1 / np.sqrt(var *2 * np.pi)\n",
+        "\n",
+        "    probability = np.exp(-0.5 * ((x - mean)**2 / var))\n",
+        "\n",
+        "    gaus = constant * probability\n",
+        "    \n",
+        "    return gaus\n",
+        "  def gaus_predict(self,X):\n",
+        "    y_pred = [self.gaus_class_probability(x) for x in X]\n",
+        "    return np.array(y_pred)\n",
+        "\n",
+        "\n",
+        "\n",
+        "\n",
+        "  # def pdf_class_probability(self,x):\n",
+        "  #   posteriors = []\n",
+        "\n",
+        "  #   for c in range(self.no_classes):\n",
+        "  #     mean = self.mean[c]\n",
+        "  #     var = self.var[c]\n",
+        "  #     prior = np.log(self.priors[c])\n",
+        "\n",
+        "  #     conditional_prob = np.sum(np.log(self.pdf(c,x)))\n",
+        "  #     posterior = prior + conditional_prob\n",
+        "  #     posteriors.append(posterior)\n",
+        "  #   #return the index of the highest class probability\n",
+        "  #   return np.argmax(posteriors)\n",
+        "  # def pdf_predict(self,X):\n",
+        "  #   y_pred = [self.gaus_class_probability(x) for x in X]\n",
+        "  #   return np.array(y_pred)\n",
+        "  \n",
+        "  \n",
+        "  \n",
+        "  # def pdf(self,class_idx, x):\n",
+        "  #   mean = self.mean[class_idx]\n",
+        "  #   var = self.var[class_idx]\n",
+        "  #   constant = 1 / np.sqrt(2 * np.pi * (var**2))\n",
+        "  #   probability = np.exp(-((x-mean)**2)/(2*(var**2)))\n",
+        "    \n",
+        "  #   pdf = constant * probability\n",
+        "\n",
+        "  #   return pdf"
+      ],
+      "metadata": {
+        "id": "0Q_4TZqssUx0"
+      },
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sklearn import datasets\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "# load iris dataset\n",
+        "iris = datasets.load_iris()\n",
+        "X = iris.data\n",
+        "y = iris.target\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "OQgYd2yNBH9H"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "nb_gaus = NaiveBayes()\n",
+        "nb_gaus.fit(X_train, y_train)\n",
+        "gaus_predictions = nb_gaus.gaus_predict(X_test)\n",
+        "\n",
+        "# helper function to calculate accuracy\n",
+        "def get_accuracy(y_true, y_hat):\n",
+        "    return np.sum(y_true==y_hat) / len(y_true)\n",
+        "  \n",
+        "# print results\n",
+        "print('Naive Bayes Accuracy: ', get_accuracy(y_test, gaus_predictions))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "voX5B2-OCasD",
+        "outputId": "5efef2bc-670a-4479-9808-74028835bf69"
+      },
+      "execution_count": 8,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Naive Bayes Accuracy:  0.9666666666666667\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# instantiate, train and predict Naive Bayes Classifier\n",
+        "nb_pdf = NaiveBayes()\n",
+        "nb_pdf.fit(X_train, y_train)\n",
+        "pdf_predictions = nb_pdf.pdf_predict(X_test)\n",
+        "\n",
+        "# print results\n",
+        "print('Naive Bayes Accuracy: ', get_accuracy(y_test, pdf_predictions))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "LSp4eD66Cw8e",
+        "outputId": "dc03dcf9-f375-492c-e4ca-bb5cba0a2f62"
+      },
+      "execution_count": 10,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Naive Bayes Accuracy:  0.9666666666666667\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        ""
+      ],
+      "metadata": {
+        "id": "w0Mvy4JDG9VF"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}