{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('iris_dataset.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 150 entries, 0 to 149\n",
      "Data columns (total 5 columns):\n",
      " #   Column        Non-Null Count  Dtype  \n",
      "---  ------        --------------  -----  \n",
      " 0   sepal_length  150 non-null    float64\n",
      " 1   sepal_width   150 non-null    float64\n",
      " 2   petal_length  150 non-null    float64\n",
      " 3   petal_width   150 non-null    float64\n",
      " 4   species       150 non-null    object \n",
      "dtypes: float64(4), object(1)\n",
      "memory usage: 6.0+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "feature = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']\n",
    "predection_class = ['species']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data[feature].values\n",
    "y = data[predection_class].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of X_test is (45, 4)\n",
      "Shape of X_train is (105, 4)\n",
      "Shape of Y_test is (45, 1)\n",
      "Shape of Y_train is (105, 1)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(X,y,test_size=0.30)\n",
    "print(f\"Shape of X_test is {X_test.shape}\")\n",
    "print(f\"Shape of X_train is {X_train.shape}\")\n",
    "print(f\"Shape of Y_test is {Y_test.shape}\")\n",
    "print(f\"Shape of Y_train is {Y_train.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\shubh\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\utils\\validation.py:1111: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.neighbors import NearestCentroid\n",
    "clf = NearestCentroid()\n",
    "clf.fit(X_train, Y_train)\n",
    "Y_pred = clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy 95.55555555555556\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "print(\"Accuracy\", metrics.accuracy_score(Y_test, Y_pred)*100)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.7"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}