5 - K-NN & Naive Bayes/iris_NaiveBayes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#loading the dataset\n",
    "from sklearn.datasets import load_iris\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "iris_data=load_iris()\n",
    "# print(iris_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename'])\n"
     ]
    }
   ],
   "source": [
    "print(iris_data.keys())\n",
    "#keys of data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['setosa' 'versicolor' 'virginica']\n"
     ]
    }
   ],
   "source": [
    "print(iris_data['target_names'])\n",
    "#the value of the key target_names is an array of strings,\n",
    "#containing the  species of flowers which we want to predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']\n"
     ]
    }
   ],
   "source": [
    "print(iris_data['feature_names'])\n",
    "#The value of feature_names is a list of strings, giving the description of each feature:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[5.1 3.5 1.4 0.2]\n",
      " [4.9 3.  1.4 0.2]\n",
      " [4.7 3.2 1.3 0.2]\n",
      " [4.6 3.1 1.5 0.2]\n",
      " [5.  3.6 1.4 0.2]\n",
      " [5.4 3.9 1.7 0.4]\n",
      " [4.6 3.4 1.4 0.3]\n",
      " [5.  3.4 1.5 0.2]\n",
      " [4.4 2.9 1.4 0.2]\n",
      " [4.9 3.1 1.5 0.1]\n",
      " [5.4 3.7 1.5 0.2]\n",
      " [4.8 3.4 1.6 0.2]\n",
      " [4.8 3.  1.4 0.1]\n",
      " [4.3 3.  1.1 0.1]\n",
      " [5.8 4.  1.2 0.2]\n",
      " [5.7 4.4 1.5 0.4]\n",
      " [5.4 3.9 1.3 0.4]\n",
      " [5.1 3.5 1.4 0.3]\n",
      " [5.7 3.8 1.7 0.3]\n",
      " [5.1 3.8 1.5 0.3]\n",
      " [5.4 3.4 1.7 0.2]\n",
      " [5.1 3.7 1.5 0.4]\n",
      " [4.6 3.6 1.  0.2]\n",
      " [5.1 3.3 1.7 0.5]\n",
      " [4.8 3.4 1.9 0.2]\n",
      " [5.  3.  1.6 0.2]\n",
      " [5.  3.4 1.6 0.4]\n",
      " [5.2 3.5 1.5 0.2]\n",
      " [5.2 3.4 1.4 0.2]\n",
      " [4.7 3.2 1.6 0.2]\n",
      " [4.8 3.1 1.6 0.2]\n",
      " [5.4 3.4 1.5 0.4]\n",
      " [5.2 4.1 1.5 0.1]\n",
      " [5.5 4.2 1.4 0.2]\n",
      " [4.9 3.1 1.5 0.2]\n",
      " [5.  3.2 1.2 0.2]\n",
      " [5.5 3.5 1.3 0.2]\n",
      " [4.9 3.6 1.4 0.1]\n",
      " [4.4 3.  1.3 0.2]\n",
      " [5.1 3.4 1.5 0.2]\n",
      " [5.  3.5 1.3 0.3]\n",
      " [4.5 2.3 1.3 0.3]\n",
      " [4.4 3.2 1.3 0.2]\n",
      " [5.  3.5 1.6 0.6]\n",
      " [5.1 3.8 1.9 0.4]\n",
      " [4.8 3.  1.4 0.3]\n",
      " [5.1 3.8 1.6 0.2]\n",
      " [4.6 3.2 1.4 0.2]\n",
      " [5.3 3.7 1.5 0.2]\n",
      " [5.  3.3 1.4 0.2]\n",
      " [7.  3.2 4.7 1.4]\n",
      " [6.4 3.2 4.5 1.5]\n",
      " [6.9 3.1 4.9 1.5]\n",
      " [5.5 2.3 4.  1.3]\n",
      " [6.5 2.8 4.6 1.5]\n",
      " [5.7 2.8 4.5 1.3]\n",
      " [6.3 3.3 4.7 1.6]\n",
      " [4.9 2.4 3.3 1. ]\n",
      " [6.6 2.9 4.6 1.3]\n",
      " [5.2 2.7 3.9 1.4]\n",
      " [5.  2.  3.5 1. ]\n",
      " [5.9 3.  4.2 1.5]\n",
      " [6.  2.2 4.  1. ]\n",
      " [6.1 2.9 4.7 1.4]\n",
      " [5.6 2.9 3.6 1.3]\n",
      " [6.7 3.1 4.4 1.4]\n",
      " [5.6 3.  4.5 1.5]\n",
      " [5.8 2.7 4.1 1. ]\n",
      " [6.2 2.2 4.5 1.5]\n",
      " [5.6 2.5 3.9 1.1]\n",
      " [5.9 3.2 4.8 1.8]\n",
      " [6.1 2.8 4.  1.3]\n",
      " [6.3 2.5 4.9 1.5]\n",
      " [6.1 2.8 4.7 1.2]\n",
      " [6.4 2.9 4.3 1.3]\n",
      " [6.6 3.  4.4 1.4]\n",
      " [6.8 2.8 4.8 1.4]\n",
      " [6.7 3.  5.  1.7]\n",
      " [6.  2.9 4.5 1.5]\n",
      " [5.7 2.6 3.5 1. ]\n",
      " [5.5 2.4 3.8 1.1]\n",
      " [5.5 2.4 3.7 1. ]\n",
      " [5.8 2.7 3.9 1.2]\n",
      " [6.  2.7 5.1 1.6]\n",
      " [5.4 3.  4.5 1.5]\n",
      " [6.  3.4 4.5 1.6]\n",
      " [6.7 3.1 4.7 1.5]\n",
      " [6.3 2.3 4.4 1.3]\n",
      " [5.6 3.  4.1 1.3]\n",
      " [5.5 2.5 4.  1.3]\n",
      " [5.5 2.6 4.4 1.2]\n",
      " [6.1 3.  4.6 1.4]\n",
      " [5.8 2.6 4.  1.2]\n",
      " [5.  2.3 3.3 1. ]\n",
      " [5.6 2.7 4.2 1.3]\n",
      " [5.7 3.  4.2 1.2]\n",
      " [5.7 2.9 4.2 1.3]\n",
      " [6.2 2.9 4.3 1.3]\n",
      " [5.1 2.5 3.  1.1]\n",
      " [5.7 2.8 4.1 1.3]\n",
      " [6.3 3.3 6.  2.5]\n",
      " [5.8 2.7 5.1 1.9]\n",
      " [7.1 3.  5.9 2.1]\n",
      " [6.3 2.9 5.6 1.8]\n",
      " [6.5 3.  5.8 2.2]\n",
      " [7.6 3.  6.6 2.1]\n",
      " [4.9 2.5 4.5 1.7]\n",
      " [7.3 2.9 6.3 1.8]\n",
      " [6.7 2.5 5.8 1.8]\n",
      " [7.2 3.6 6.1 2.5]\n",
      " [6.5 3.2 5.1 2. ]\n",
      " [6.4 2.7 5.3 1.9]\n",
      " [6.8 3.  5.5 2.1]\n",
      " [5.7 2.5 5.  2. ]\n",
      " [5.8 2.8 5.1 2.4]\n",
      " [6.4 3.2 5.3 2.3]\n",
      " [6.5 3.  5.5 1.8]\n",
      " [7.7 3.8 6.7 2.2]\n",
      " [7.7 2.6 6.9 2.3]\n",
      " [6.  2.2 5.  1.5]\n",
      " [6.9 3.2 5.7 2.3]\n",
      " [5.6 2.8 4.9 2. ]\n",
      " [7.7 2.8 6.7 2. ]\n",
      " [6.3 2.7 4.9 1.8]\n",
      " [6.7 3.3 5.7 2.1]\n",
      " [7.2 3.2 6.  1.8]\n",
      " [6.2 2.8 4.8 1.8]\n",
      " [6.1 3.  4.9 1.8]\n",
      " [6.4 2.8 5.6 2.1]\n",
      " [7.2 3.  5.8 1.6]\n",
      " [7.4 2.8 6.1 1.9]\n",
      " [7.9 3.8 6.4 2. ]\n",
      " [6.4 2.8 5.6 2.2]\n",
      " [6.3 2.8 5.1 1.5]\n",
      " [6.1 2.6 5.6 1.4]\n",
      " [7.7 3.  6.1 2.3]\n",
      " [6.3 3.4 5.6 2.4]\n",
      " [6.4 3.1 5.5 1.8]\n",
      " [6.  3.  4.8 1.8]\n",
      " [6.9 3.1 5.4 2.1]\n",
      " [6.7 3.1 5.6 2.4]\n",
      " [6.9 3.1 5.1 2.3]\n",
      " [5.8 2.7 5.1 1.9]\n",
      " [6.8 3.2 5.9 2.3]\n",
      " [6.7 3.3 5.7 2.5]\n",
      " [6.7 3.  5.2 2.3]\n",
      " [6.3 2.5 5.  1.9]\n",
      " [6.5 3.  5.2 2. ]\n",
      " [6.2 3.4 5.4 2.3]\n",
      " [5.9 3.  5.1 1.8]]\n"
     ]
    }
   ],
   "source": [
    "X=iris_data['data']\n",
    "print(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
      " 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
      " 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2\n",
      " 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n",
      " 2 2]\n"
     ]
    }
   ],
   "source": [
    "y=iris_data['target']\n",
    "print(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(150, 4)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris_data['data'].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n",
    "#we have assigned random_state as 0 so that each time when we run this ,we get the same output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(112, 4)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(38, 4)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "gnb = GaussianNB()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GaussianNB()"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gnb.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Enter the sepel length- 2\n",
      "Enter the sepel width- 3\n",
      "Enter the petal length- 2\n",
      "Enter the petal width- 3\n"
     ]
    }
   ],
   "source": [
    "sepel_len=eval(input(\"Enter the sepel length- \"))\n",
    "sepel_wid=eval(input(\"Enter the sepel width- \"))\n",
    "petal_len=eval(input(\"Enter the petal length- \"))\n",
    "petal_wid=eval(input(\"Enter the petal width- \"))\n",
    "X_new = np.array([[sepel_len,sepel_wid,petal_len,petal_wid]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted target name ['virginica']\n"
     ]
    }
   ],
   "source": [
    "#calling predict method from knn for making prediction\n",
    "prediction = gnb.predict(X_new)\n",
    "print(\"Predicted target name\",iris_data['target_names'][prediction])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test set prediction:\n",
      " [2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0\n",
      " 1]\n"
     ]
    }
   ],
   "source": [
    "y_pred = gnb.predict(X_test)\n",
    "print(\"Test set prediction:\\n {}\".format(y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test score is: 1.00\n"
     ]
    }
   ],
   "source": [
    "#accuracy\n",
    "print('Test score is: {:.2f}'.format(gnb.score(X_test,y_test)))"
   ]
  },
  {
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}