15th feb (1).ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "28c546c3",
   "metadata": {},
   "outputs": [],
   "source": [
    "#logistic registration \n",
    "#--> it is a statistical method used to model the relationaship between a binary dependent\n",
    "#  variable and one to more independent variables\n",
    "\n",
    "#In logiatic regression ,the dependent variable is binary ,meaning it can ony take on two value 0 and 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a8c598e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,confusion_matrix  #-->alg related func"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b5f9ccd6",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred=np.array([0.3,0.8,0.9,0.5,0.2,0.4,0.2,0.1,0.6,0.8,])\n",
    "y_true=np.array([1,0,1,1,0,0,1,0,1,0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "80668295",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Accuracy\n",
    "#accuracy measures the percentage of correctly classified instances out of all instances\n",
    "accuracy=accuracy_score(y_true,np.round(y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8cb8e599",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "18d9fdeb",
   "metadata": {},
   "outputs": [],
   "source": [
    "#precision\n",
    "#precision=true positive/all positive\n",
    "#-->it measured the proportion  of true positive out of all positive predictions\n",
    "precision=precision_score(y_true,np.round(y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a2257bfe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "precision"
   ]
  },
  {
   "cell_type": "raw",
   "id": "99a37ab8",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "afbf173e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Recall\n",
    "#Reacll=true positive/actual positive\n",
    "#it measures the proportion of true positive prediction out  of all actual poitice cases\n",
    "recall=recall_score(y_true,np.round(y_pred))\n",
    "recall        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0c6ade59",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4444444444444445"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#f1 score\n",
    "#-->it is the mean of precision and recall\n",
    "f1_score=f1_score(y_true,np.round(y_pred))\n",
    "f1_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "61e0a19e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[3, 2],\n",
       "       [3, 2]], dtype=int64)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#confusion matrix\n",
    "#it is a table that gives the performance of a classification model\n",
    "#it show true positive ,true negative,false positive,false negative\n",
    "matrix=confusion_matrix(y_true,np.round(y_pred))\n",
    "matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "8850cbf7",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Eg:1\n",
    "#logistic regression\n",
    "from sklearn.datasets import load_iris\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "4ba79488",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': array([[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",
       " 'target': array([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, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 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,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 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,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
       " 'frame': None,\n",
       " 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),\n",
       " 'DESCR': '.. _iris_dataset:\\n\\nIris plants dataset\\n--------------------\\n\\n**Data Set Characteristics:**\\n\\n    :Number of Instances: 150 (50 in each of three classes)\\n    :Number of Attributes: 4 numeric, predictive attributes and the class\\n    :Attribute Information:\\n        - sepal length in cm\\n        - sepal width in cm\\n        - petal length in cm\\n        - petal width in cm\\n        - class:\\n                - Iris-Setosa\\n                - Iris-Versicolour\\n                - Iris-Virginica\\n                \\n    :Summary Statistics:\\n\\n    ============== ==== ==== ======= ===== ====================\\n                    Min  Max   Mean    SD   Class Correlation\\n    ============== ==== ==== ======= ===== ====================\\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\\n    petal width:    0.1  2.5   1.20   0.76    0.9565  (high!)\\n    ============== ==== ==== ======= ===== ====================\\n\\n    :Missing Attribute Values: None\\n    :Class Distribution: 33.3% for each of 3 classes.\\n    :Creator: R.A. Fisher\\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n    :Date: July, 1988\\n\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature.  Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant.  One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\n.. topic:: References\\n\\n   - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n     Mathematical Statistics\" (John Wiley, NY, 1950).\\n   - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\\n   - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n     Structure and Classification Rule for Recognition in Partially Exposed\\n     Environments\".  IEEE Transactions on Pattern Analysis and Machine\\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n   - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\".  IEEE Transactions\\n     on Information Theory, May 1972, 431-433.\\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al\"s AUTOCLASS II\\n     conceptual clustering system finds 3 classes in the data.\\n   - Many, many more ...',\n",
       " 'feature_names': ['sepal length (cm)',\n",
       "  'sepal width (cm)',\n",
       "  'petal length (cm)',\n",
       "  'petal width (cm)'],\n",
       " 'filename': 'iris.csv',\n",
       " 'data_module': 'sklearn.datasets.data'}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris=load_iris()\n",
    "iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a149d12b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "iris_df=pd.DataFrame(data=iris.data,columns=iris.feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "6cab82a5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal length (cm)</th>\n",
       "      <th>sepal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>petal width (cm)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
       "0                  5.1               3.5                1.4               0.2\n",
       "1                  4.9               3.0                1.4               0.2\n",
       "2                  4.7               3.2                1.3               0.2\n",
       "3                  4.6               3.1                1.5               0.2\n",
       "4                  5.0               3.6                1.4               0.2\n",
       "..                 ...               ...                ...               ...\n",
       "145                6.7               3.0                5.2               2.3\n",
       "146                6.3               2.5                5.0               1.9\n",
       "147                6.5               3.0                5.2               2.0\n",
       "148                6.2               3.4                5.4               2.3\n",
       "149                5.9               3.0                5.1               1.8\n",
       "\n",
       "[150 rows x 4 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "5b58d856",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal length (cm)</th>\n",
       "      <th>sepal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>petal width (cm)</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
       "0                  5.1               3.5                1.4               0.2   \n",
       "1                  4.9               3.0                1.4               0.2   \n",
       "2                  4.7               3.2                1.3               0.2   \n",
       "3                  4.6               3.1                1.5               0.2   \n",
       "4                  5.0               3.6                1.4               0.2   \n",
       "..                 ...               ...                ...               ...   \n",
       "145                6.7               3.0                5.2               2.3   \n",
       "146                6.3               2.5                5.0               1.9   \n",
       "147                6.5               3.0                5.2               2.0   \n",
       "148                6.2               3.4                5.4               2.3   \n",
       "149                5.9               3.0                5.1               1.8   \n",
       "\n",
       "        target  \n",
       "0       setosa  \n",
       "1       setosa  \n",
       "2       setosa  \n",
       "3       setosa  \n",
       "4       setosa  \n",
       "..         ...  \n",
       "145  virginica  \n",
       "146  virginica  \n",
       "147  virginica  \n",
       "148  virginica  \n",
       "149  virginica  \n",
       "\n",
       "[150 rows x 5 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris_df['target']=iris.target_names[iris.target]\n",
    "iris_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "0f7c286e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[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]])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x=iris.data\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ac42b08d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([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, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 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,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 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,\n",
       "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y=iris.target\n",
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f1eebd72",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "8265deb1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(120, 4)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "f5342016",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(30, 4)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "524ca1eb",
   "metadata": {},
   "outputs": [],
   "source": [
    "clf= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "2c8d23be",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#to train the alogorithm\n",
    "clf.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ae87b18e",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred=clf.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "17366ed0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 2, 1, 2, 1, 1, 2, 0, 2, 0, 0, 2, 2, 1, 1, 1, 0, 2, 1, 0,\n",
       "       1, 1, 1, 1, 1, 2, 0, 0])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "34260f8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "accurac=accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "3a431a12",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "id": "b252d8a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gender</th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Index</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Male</td>\n",
       "      <td>174</td>\n",
       "      <td>96</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Male</td>\n",
       "      <td>189</td>\n",
       "      <td>87</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Female</td>\n",
       "      <td>185</td>\n",
       "      <td>110</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Female</td>\n",
       "      <td>195</td>\n",
       "      <td>104</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Male</td>\n",
       "      <td>149</td>\n",
       "      <td>61</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>495</th>\n",
       "      <td>Female</td>\n",
       "      <td>150</td>\n",
       "      <td>153</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>496</th>\n",
       "      <td>Female</td>\n",
       "      <td>184</td>\n",
       "      <td>121</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>497</th>\n",
       "      <td>Female</td>\n",
       "      <td>141</td>\n",
       "      <td>136</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>498</th>\n",
       "      <td>Male</td>\n",
       "      <td>150</td>\n",
       "      <td>95</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>499</th>\n",
       "      <td>Male</td>\n",
       "      <td>173</td>\n",
       "      <td>131</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>500 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Gender  Height  Weight  Index\n",
       "0      Male     174      96      4\n",
       "1      Male     189      87      2\n",
       "2    Female     185     110      4\n",
       "3    Female     195     104      3\n",
       "4      Male     149      61      3\n",
       "..      ...     ...     ...    ...\n",
       "495  Female     150     153      5\n",
       "496  Female     184     121      4\n",
       "497  Female     141     136      5\n",
       "498    Male     150      95      5\n",
       "499    Male     173     131      5\n",
       "\n",
       "[500 rows x 4 columns]"
      ]
     },
     "execution_count": 194,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df=pd.read_csv(\"C:\\\\Users\\\\prasa\\\\Desktop\\\\bmi.csv\")\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "id": "d381f654",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gender</th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Index</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Male</td>\n",
       "      <td>174</td>\n",
       "      <td>96</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Male</td>\n",
       "      <td>189</td>\n",
       "      <td>87</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Female</td>\n",
       "      <td>185</td>\n",
       "      <td>110</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Female</td>\n",
       "      <td>195</td>\n",
       "      <td>104</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Male</td>\n",
       "      <td>149</td>\n",
       "      <td>61</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Gender  Height  Weight  Index\n",
       "0    Male     174      96      4\n",
       "1    Male     189      87      2\n",
       "2  Female     185     110      4\n",
       "3  Female     195     104      3\n",
       "4    Male     149      61      3"
      ]
     },
     "execution_count": 195,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 196,
   "id": "6cfed1d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Female    255\n",
       "Male      245\n",
       "Name: Gender, dtype: int64"
      ]
     },
     "execution_count": 196,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Gender'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "id": "212e42a0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Index</th>\n",
       "      <th>Gender_Male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>174</td>\n",
       "      <td>96</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>189</td>\n",
       "      <td>87</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>185</td>\n",
       "      <td>110</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>195</td>\n",
       "      <td>104</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>149</td>\n",
       "      <td>61</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>495</th>\n",
       "      <td>150</td>\n",
       "      <td>153</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>496</th>\n",
       "      <td>184</td>\n",
       "      <td>121</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>497</th>\n",
       "      <td>141</td>\n",
       "      <td>136</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>498</th>\n",
       "      <td>150</td>\n",
       "      <td>95</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>499</th>\n",
       "      <td>173</td>\n",
       "      <td>131</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>500 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Height  Weight  Index  Gender_Male\n",
       "0       174      96      4            1\n",
       "1       189      87      2            1\n",
       "2       185     110      4            0\n",
       "3       195     104      3            0\n",
       "4       149      61      3            1\n",
       "..      ...     ...    ...          ...\n",
       "495     150     153      5            0\n",
       "496     184     121      4            0\n",
       "497     141     136      5            0\n",
       "498     150      95      5            1\n",
       "499     173     131      5            1\n",
       "\n",
       "[500 rows x 4 columns]"
      ]
     },
     "execution_count": 197,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=pd.get_dummies(df,columns=['Gender'],dtype=int,drop_first=True)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "id": "5f2e7d56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Gender_Male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>174</td>\n",
       "      <td>96</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>189</td>\n",
       "      <td>87</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>185</td>\n",
       "      <td>110</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>195</td>\n",
       "      <td>104</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>149</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>495</th>\n",
       "      <td>150</td>\n",
       "      <td>153</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>496</th>\n",
       "      <td>184</td>\n",
       "      <td>121</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>497</th>\n",
       "      <td>141</td>\n",
       "      <td>136</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>498</th>\n",
       "      <td>150</td>\n",
       "      <td>95</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>499</th>\n",
       "      <td>173</td>\n",
       "      <td>131</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>500 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Height  Weight  Gender_Male\n",
       "0       174      96            1\n",
       "1       189      87            1\n",
       "2       185     110            0\n",
       "3       195     104            0\n",
       "4       149      61            1\n",
       "..      ...     ...          ...\n",
       "495     150     153            0\n",
       "496     184     121            0\n",
       "497     141     136            0\n",
       "498     150      95            1\n",
       "499     173     131            1\n",
       "\n",
       "[500 rows x 3 columns]"
      ]
     },
     "execution_count": 214,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x=df.drop('Index',axis=1)\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "id": "c6fe19f3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      4\n",
       "1      2\n",
       "2      4\n",
       "3      3\n",
       "4      3\n",
       "      ..\n",
       "495    5\n",
       "496    4\n",
       "497    5\n",
       "498    5\n",
       "499    5\n",
       "Name: Index, Length: 500, dtype: int64"
      ]
     },
     "execution_count": 215,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y=df['Index']\n",
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "id": "5fe5455d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(500, 3)"
      ]
     },
     "execution_count": 216,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "9c633ecc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(500,)"
      ]
     },
     "execution_count": 217,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 227,
   "id": "964fe2da",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_trian,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 228,
   "id": "f21c0473",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 229,
   "id": "7967ee02",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 230,
   "id": "6f2379c2",
   "metadata": {},
   "outputs": [],
   "source": [
    "clf=LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 231,
   "id": "6a122aa6",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Found input variables with inconsistent numbers of samples: [120, 350]",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[231], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mclf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43my_train\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:1196\u001b[0m, in \u001b[0;36mLogisticRegression.fit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m   1193\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1194\u001b[0m     _dtype \u001b[38;5;241m=\u001b[39m [np\u001b[38;5;241m.\u001b[39mfloat64, np\u001b[38;5;241m.\u001b[39mfloat32]\n\u001b[1;32m-> 1196\u001b[0m X, y \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_data\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1197\u001b[0m \u001b[43m    \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1198\u001b[0m \u001b[43m    \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1199\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccept_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcsr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1200\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1201\u001b[0m \u001b[43m    \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mC\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1202\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccept_large_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msolver\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mliblinear\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msag\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msaga\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1203\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1204\u001b[0m check_classification_targets(y)\n\u001b[0;32m   1205\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclasses_ \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(y)\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\base.py:565\u001b[0m, in \u001b[0;36mBaseEstimator._validate_data\u001b[1;34m(self, X, y, reset, validate_separately, **check_params)\u001b[0m\n\u001b[0;32m    563\u001b[0m         y \u001b[38;5;241m=\u001b[39m check_array(y, input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_y_params)\n\u001b[0;32m    564\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 565\u001b[0m         X, y \u001b[38;5;241m=\u001b[39m check_X_y(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_params)\n\u001b[0;32m    566\u001b[0m     out \u001b[38;5;241m=\u001b[39m X, y\n\u001b[0;32m    568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m no_val_X \u001b[38;5;129;01mand\u001b[39;00m check_params\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mensure_2d\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mTrue\u001b[39;00m):\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:1124\u001b[0m, in \u001b[0;36mcheck_X_y\u001b[1;34m(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)\u001b[0m\n\u001b[0;32m   1106\u001b[0m X \u001b[38;5;241m=\u001b[39m check_array(\n\u001b[0;32m   1107\u001b[0m     X,\n\u001b[0;32m   1108\u001b[0m     accept_sparse\u001b[38;5;241m=\u001b[39maccept_sparse,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1119\u001b[0m     input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mX\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   1120\u001b[0m )\n\u001b[0;32m   1122\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_y(y, multi_output\u001b[38;5;241m=\u001b[39mmulti_output, y_numeric\u001b[38;5;241m=\u001b[39my_numeric, estimator\u001b[38;5;241m=\u001b[39mestimator)\n\u001b[1;32m-> 1124\u001b[0m \u001b[43mcheck_consistent_length\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m X, y\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:397\u001b[0m, in \u001b[0;36mcheck_consistent_length\u001b[1;34m(*arrays)\u001b[0m\n\u001b[0;32m    395\u001b[0m uniques \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(lengths)\n\u001b[0;32m    396\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(uniques) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m--> 397\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m    398\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFound input variables with inconsistent numbers of samples: \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    399\u001b[0m         \u001b[38;5;241m%\u001b[39m [\u001b[38;5;28mint\u001b[39m(l) \u001b[38;5;28;01mfor\u001b[39;00m l \u001b[38;5;129;01min\u001b[39;00m lengths]\n\u001b[0;32m    400\u001b[0m     )\n",
      "\u001b[1;31mValueError\u001b[0m: Found input variables with inconsistent numbers of samples: [120, 350]"
     ]
    }
   ],
   "source": [
    "clf.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "id": "8accfdfe",
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'DataFrame' object has no attribute 'predict'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[187], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m pred\u001b[38;5;241m=\u001b[39m\u001b[43mdf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m(x_test)\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\pandas\\core\\generic.py:5902\u001b[0m, in \u001b[0;36mNDFrame.__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m   5895\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[0;32m   5896\u001b[0m     name \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_internal_names_set\n\u001b[0;32m   5897\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m name \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_metadata\n\u001b[0;32m   5898\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m name \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_accessors\n\u001b[0;32m   5899\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_info_axis\u001b[38;5;241m.\u001b[39m_can_hold_identifiers_and_holds_name(name)\n\u001b[0;32m   5900\u001b[0m ):\n\u001b[0;32m   5901\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m[name]\n\u001b[1;32m-> 5902\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mobject\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__getattribute__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[1;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'predict'"
     ]
    }
   ],
   "source": [
    "pred=df.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "8ebb0228",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Index', ylabel='Height'>"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "x=df['Height']\n",
    "y=df['Index']\n",
    "sns.barplot(y='Height',x='Index',data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "d8cdc156",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_trian,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 192,
   "id": "20426ecc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(120, 4)"
      ]
     },
     "execution_count": 192,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "ca9c6151",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(100,)"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "2f69e58c",
   "metadata": {},
   "outputs": [],
   "source": [
    "clf=LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "60219b06",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Found input variables with inconsistent numbers of samples: [120, 400]",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[67], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mclf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43my_train\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:1196\u001b[0m, in \u001b[0;36mLogisticRegression.fit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m   1193\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1194\u001b[0m     _dtype \u001b[38;5;241m=\u001b[39m [np\u001b[38;5;241m.\u001b[39mfloat64, np\u001b[38;5;241m.\u001b[39mfloat32]\n\u001b[1;32m-> 1196\u001b[0m X, y \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_data\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1197\u001b[0m \u001b[43m    \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1198\u001b[0m \u001b[43m    \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1199\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccept_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcsr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1200\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1201\u001b[0m \u001b[43m    \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mC\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1202\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccept_large_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msolver\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mliblinear\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msag\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msaga\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1203\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1204\u001b[0m check_classification_targets(y)\n\u001b[0;32m   1205\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclasses_ \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(y)\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\base.py:565\u001b[0m, in \u001b[0;36mBaseEstimator._validate_data\u001b[1;34m(self, X, y, reset, validate_separately, **check_params)\u001b[0m\n\u001b[0;32m    563\u001b[0m         y \u001b[38;5;241m=\u001b[39m check_array(y, input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_y_params)\n\u001b[0;32m    564\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 565\u001b[0m         X, y \u001b[38;5;241m=\u001b[39m check_X_y(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_params)\n\u001b[0;32m    566\u001b[0m     out \u001b[38;5;241m=\u001b[39m X, y\n\u001b[0;32m    568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m no_val_X \u001b[38;5;129;01mand\u001b[39;00m check_params\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mensure_2d\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mTrue\u001b[39;00m):\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:1124\u001b[0m, in \u001b[0;36mcheck_X_y\u001b[1;34m(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)\u001b[0m\n\u001b[0;32m   1106\u001b[0m X \u001b[38;5;241m=\u001b[39m check_array(\n\u001b[0;32m   1107\u001b[0m     X,\n\u001b[0;32m   1108\u001b[0m     accept_sparse\u001b[38;5;241m=\u001b[39maccept_sparse,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1119\u001b[0m     input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mX\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   1120\u001b[0m )\n\u001b[0;32m   1122\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_y(y, multi_output\u001b[38;5;241m=\u001b[39mmulti_output, y_numeric\u001b[38;5;241m=\u001b[39my_numeric, estimator\u001b[38;5;241m=\u001b[39mestimator)\n\u001b[1;32m-> 1124\u001b[0m \u001b[43mcheck_consistent_length\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m X, y\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:397\u001b[0m, in \u001b[0;36mcheck_consistent_length\u001b[1;34m(*arrays)\u001b[0m\n\u001b[0;32m    395\u001b[0m uniques \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(lengths)\n\u001b[0;32m    396\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(uniques) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m--> 397\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m    398\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFound input variables with inconsistent numbers of samples: \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    399\u001b[0m         \u001b[38;5;241m%\u001b[39m [\u001b[38;5;28mint\u001b[39m(l) \u001b[38;5;28;01mfor\u001b[39;00m l \u001b[38;5;129;01min\u001b[39;00m lengths]\n\u001b[0;32m    400\u001b[0m     )\n",
      "\u001b[1;31mValueError\u001b[0m: Found input variables with inconsistent numbers of samples: [120, 400]"
     ]
    }
   ],
   "source": [
    "clf.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "53304c32",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5    198\n",
       "4    130\n",
       "2     69\n",
       "3     68\n",
       "1     22\n",
       "0     13\n",
       "Name: Index, dtype: int64"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Index'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "96d235c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>male</th>\n",
       "      <th>age</th>\n",
       "      <th>education</th>\n",
       "      <th>currentSmoker</th>\n",
       "      <th>cigsPerDay</th>\n",
       "      <th>BPMeds</th>\n",
       "      <th>prevalentStroke</th>\n",
       "      <th>prevalentHyp</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>totChol</th>\n",
       "      <th>sysBP</th>\n",
       "      <th>diaBP</th>\n",
       "      <th>BMI</th>\n",
       "      <th>heartRate</th>\n",
       "      <th>glucose</th>\n",
       "      <th>TenYearCHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>39</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>106.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>26.97</td>\n",
       "      <td>80.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>121.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>28.73</td>\n",
       "      <td>95.0</td>\n",
       "      <td>76.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>48</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>245.0</td>\n",
       "      <td>127.5</td>\n",
       "      <td>80.0</td>\n",
       "      <td>25.34</td>\n",
       "      <td>75.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>225.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>28.58</td>\n",
       "      <td>65.0</td>\n",
       "      <td>103.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>285.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>84.0</td>\n",
       "      <td>23.10</td>\n",
       "      <td>85.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4233</th>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>313.0</td>\n",
       "      <td>179.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>25.97</td>\n",
       "      <td>66.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4234</th>\n",
       "      <td>1</td>\n",
       "      <td>51</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>43.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>207.0</td>\n",
       "      <td>126.5</td>\n",
       "      <td>80.0</td>\n",
       "      <td>19.71</td>\n",
       "      <td>65.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4235</th>\n",
       "      <td>0</td>\n",
       "      <td>48</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "      <td>20.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>248.0</td>\n",
       "      <td>131.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>22.00</td>\n",
       "      <td>84.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4236</th>\n",
       "      <td>0</td>\n",
       "      <td>44</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>210.0</td>\n",
       "      <td>126.5</td>\n",
       "      <td>87.0</td>\n",
       "      <td>19.16</td>\n",
       "      <td>86.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4237</th>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>269.0</td>\n",
       "      <td>133.5</td>\n",
       "      <td>83.0</td>\n",
       "      <td>21.47</td>\n",
       "      <td>80.0</td>\n",
       "      <td>107.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4238 rows × 16 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      male  age  education  currentSmoker  cigsPerDay  BPMeds  \\\n",
       "0        1   39        4.0              0         0.0     0.0   \n",
       "1        0   46        2.0              0         0.0     0.0   \n",
       "2        1   48        1.0              1        20.0     0.0   \n",
       "3        0   61        3.0              1        30.0     0.0   \n",
       "4        0   46        3.0              1        23.0     0.0   \n",
       "...    ...  ...        ...            ...         ...     ...   \n",
       "4233     1   50        1.0              1         1.0     0.0   \n",
       "4234     1   51        3.0              1        43.0     0.0   \n",
       "4235     0   48        2.0              1        20.0     NaN   \n",
       "4236     0   44        1.0              1        15.0     0.0   \n",
       "4237     0   52        2.0              0         0.0     0.0   \n",
       "\n",
       "      prevalentStroke  prevalentHyp  diabetes  totChol  sysBP  diaBP    BMI  \\\n",
       "0                   0             0         0    195.0  106.0   70.0  26.97   \n",
       "1                   0             0         0    250.0  121.0   81.0  28.73   \n",
       "2                   0             0         0    245.0  127.5   80.0  25.34   \n",
       "3                   0             1         0    225.0  150.0   95.0  28.58   \n",
       "4                   0             0         0    285.0  130.0   84.0  23.10   \n",
       "...               ...           ...       ...      ...    ...    ...    ...   \n",
       "4233                0             1         0    313.0  179.0   92.0  25.97   \n",
       "4234                0             0         0    207.0  126.5   80.0  19.71   \n",
       "4235                0             0         0    248.0  131.0   72.0  22.00   \n",
       "4236                0             0         0    210.0  126.5   87.0  19.16   \n",
       "4237                0             0         0    269.0  133.5   83.0  21.47   \n",
       "\n",
       "      heartRate  glucose  TenYearCHD  \n",
       "0          80.0     77.0           0  \n",
       "1          95.0     76.0           0  \n",
       "2          75.0     70.0           0  \n",
       "3          65.0    103.0           1  \n",
       "4          85.0     85.0           0  \n",
       "...         ...      ...         ...  \n",
       "4233       66.0     86.0           1  \n",
       "4234       65.0     68.0           0  \n",
       "4235       84.0     86.0           0  \n",
       "4236       86.0      NaN           0  \n",
       "4237       80.0    107.0           0  \n",
       "\n",
       "[4238 rows x 16 columns]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=pd.read_csv(\"C:\\\\Users\\\\prasa\\\\Desktop\\\\framingham.csv\")\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "cccfdcef",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_trian,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "aa4922d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(500,)"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "852d187b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(500,)"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "ae24b162",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(120, 4)"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "384babca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(100, 3)"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "31787c88",
   "metadata": {},
   "outputs": [],
   "source": [
    "clf=LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "1c535d9a",
   "metadata": {},
   "outputs": [],
   "source": [
    "clf=LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "5c3b87ad",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Found input variables with inconsistent numbers of samples: [120, 400]",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[111], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mclf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43my_train\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:1196\u001b[0m, in \u001b[0;36mLogisticRegression.fit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m   1193\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1194\u001b[0m     _dtype \u001b[38;5;241m=\u001b[39m [np\u001b[38;5;241m.\u001b[39mfloat64, np\u001b[38;5;241m.\u001b[39mfloat32]\n\u001b[1;32m-> 1196\u001b[0m X, y \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_data\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1197\u001b[0m \u001b[43m    \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1198\u001b[0m \u001b[43m    \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1199\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccept_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcsr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1200\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1201\u001b[0m \u001b[43m    \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mC\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1202\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccept_large_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msolver\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mliblinear\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msag\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msaga\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1203\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1204\u001b[0m check_classification_targets(y)\n\u001b[0;32m   1205\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclasses_ \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(y)\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\base.py:565\u001b[0m, in \u001b[0;36mBaseEstimator._validate_data\u001b[1;34m(self, X, y, reset, validate_separately, **check_params)\u001b[0m\n\u001b[0;32m    563\u001b[0m         y \u001b[38;5;241m=\u001b[39m check_array(y, input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_y_params)\n\u001b[0;32m    564\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 565\u001b[0m         X, y \u001b[38;5;241m=\u001b[39m check_X_y(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_params)\n\u001b[0;32m    566\u001b[0m     out \u001b[38;5;241m=\u001b[39m X, y\n\u001b[0;32m    568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m no_val_X \u001b[38;5;129;01mand\u001b[39;00m check_params\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mensure_2d\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mTrue\u001b[39;00m):\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:1124\u001b[0m, in \u001b[0;36mcheck_X_y\u001b[1;34m(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)\u001b[0m\n\u001b[0;32m   1106\u001b[0m X \u001b[38;5;241m=\u001b[39m check_array(\n\u001b[0;32m   1107\u001b[0m     X,\n\u001b[0;32m   1108\u001b[0m     accept_sparse\u001b[38;5;241m=\u001b[39maccept_sparse,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1119\u001b[0m     input_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mX\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   1120\u001b[0m )\n\u001b[0;32m   1122\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_y(y, multi_output\u001b[38;5;241m=\u001b[39mmulti_output, y_numeric\u001b[38;5;241m=\u001b[39my_numeric, estimator\u001b[38;5;241m=\u001b[39mestimator)\n\u001b[1;32m-> 1124\u001b[0m \u001b[43mcheck_consistent_length\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m X, y\n",
      "File \u001b[1;32m~\\Contacts\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:397\u001b[0m, in \u001b[0;36mcheck_consistent_length\u001b[1;34m(*arrays)\u001b[0m\n\u001b[0;32m    395\u001b[0m uniques \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39munique(lengths)\n\u001b[0;32m    396\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(uniques) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m--> 397\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m    398\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFound input variables with inconsistent numbers of samples: \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    399\u001b[0m         \u001b[38;5;241m%\u001b[39m [\u001b[38;5;28mint\u001b[39m(l) \u001b[38;5;28;01mfor\u001b[39;00m l \u001b[38;5;129;01min\u001b[39;00m lengths]\n\u001b[0;32m    400\u001b[0m     )\n",
      "\u001b[1;31mValueError\u001b[0m: Found input variables with inconsistent numbers of samples: [120, 400]"
     ]
    }
   ],
   "source": [
    "clf.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "db6ab9eb",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a4f70d0a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a9e35ff5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}