Random Forest Classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "75f87c56",
   "metadata": {},
   "source": [
    "## Random forest classification"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6db5ca29",
   "metadata": {},
   "source": [
    "## Importing the Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7ed00c6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np \n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f76b11d0",
   "metadata": {},
   "source": [
    "## Loading the Data Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "05fc5c7d",
   "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>species</th>\n",
       "      <th>island</th>\n",
       "      <th>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "      <th>sex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.1</td>\n",
       "      <td>18.7</td>\n",
       "      <td>181.0</td>\n",
       "      <td>3750.0</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.5</td>\n",
       "      <td>17.4</td>\n",
       "      <td>186.0</td>\n",
       "      <td>3800.0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>40.3</td>\n",
       "      <td>18.0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>3250.0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>36.7</td>\n",
       "      <td>19.3</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3450.0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  species     island  bill_length_mm  bill_depth_mm  flipper_length_mm  \\\n",
       "0  Adelie  Torgersen            39.1           18.7              181.0   \n",
       "1  Adelie  Torgersen            39.5           17.4              186.0   \n",
       "2  Adelie  Torgersen            40.3           18.0              195.0   \n",
       "3  Adelie  Torgersen             NaN            NaN                NaN   \n",
       "4  Adelie  Torgersen            36.7           19.3              193.0   \n",
       "\n",
       "   body_mass_g     sex  \n",
       "0       3750.0    Male  \n",
       "1       3800.0  Female  \n",
       "2       3250.0  Female  \n",
       "3          NaN     NaN  \n",
       "4       3450.0  Female  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = sns.load_dataset('penguins')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4d7a78ac",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(344, 7)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "dda8335b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 344 entries, 0 to 343\n",
      "Data columns (total 7 columns):\n",
      " #   Column             Non-Null Count  Dtype  \n",
      "---  ------             --------------  -----  \n",
      " 0   species            344 non-null    object \n",
      " 1   island             344 non-null    object \n",
      " 2   bill_length_mm     342 non-null    float64\n",
      " 3   bill_depth_mm      342 non-null    float64\n",
      " 4   flipper_length_mm  342 non-null    float64\n",
      " 5   body_mass_g        342 non-null    float64\n",
      " 6   sex                333 non-null    object \n",
      "dtypes: float64(4), object(3)\n",
      "memory usage: 18.9+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b6aabf58",
   "metadata": {},
   "source": [
    "## Checking Null Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "7e460d03",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "species               0\n",
       "island                0\n",
       "bill_length_mm        2\n",
       "bill_depth_mm         2\n",
       "flipper_length_mm     2\n",
       "body_mass_g           2\n",
       "sex                  11\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9f9e0e46",
   "metadata": {},
   "source": [
    "## Removing NUll Value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "acd26084",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dropna(inplace=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c1679bab",
   "metadata": {},
   "source": [
    "## Checking the data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5f6451e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "species              0\n",
       "island               0\n",
       "bill_length_mm       0\n",
       "bill_depth_mm        0\n",
       "flipper_length_mm    0\n",
       "body_mass_g          0\n",
       "sex                  0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de5cc5cd",
   "metadata": {},
   "source": [
    "## Feature Engineering"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "996c5bc4",
   "metadata": {},
   "source": [
    "## One Hot Encoding Transformation categorical data into numeric"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "48745551",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Male', 'Female'], dtype=object)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sex.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "d83c2c1c",
   "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>Female</th>\n",
       "      <th>Male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Female  Male\n",
       "0       0     1\n",
       "1       1     0\n",
       "2       1     0\n",
       "4       1     0\n",
       "5       0     1"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df['sex']).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ca17692c",
   "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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Male\n",
       "0     1\n",
       "1     0\n",
       "2     0\n",
       "4     0\n",
       "5     1"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sex = pd.get_dummies(df['sex'], drop_first=True)\n",
    "sex.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd74dbcd",
   "metadata": {},
   "source": [
    "## Applying one-hot encoding to Island"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "6b6493e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Torgersen', 'Biscoe', 'Dream'], dtype=object)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " df.island.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a25df894",
   "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>Biscoe</th>\n",
       "      <th>Dream</th>\n",
       "      <th>Torgersen</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Biscoe  Dream  Torgersen\n",
       "0       0      0          1\n",
       "1       0      0          1\n",
       "2       0      0          1\n",
       "4       0      0          1\n",
       "5       0      0          1"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df['island']).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "19322d16",
   "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>Dream</th>\n",
       "      <th>Torgersen</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Dream  Torgersen\n",
       "0      0          1\n",
       "1      0          1\n",
       "2      0          1\n",
       "4      0          1\n",
       "5      0          1"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "island = pd.get_dummies(df['island'], drop_first = True)\n",
    "island.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "173ae210",
   "metadata": {},
   "source": [
    "## Concatenate the above data frames to the original df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "119ea71a",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_data = pd.concat([df, island, sex], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "c4ecacd4",
   "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>species</th>\n",
       "      <th>island</th>\n",
       "      <th>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "      <th>sex</th>\n",
       "      <th>Dream</th>\n",
       "      <th>Torgersen</th>\n",
       "      <th>Male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.1</td>\n",
       "      <td>18.7</td>\n",
       "      <td>181.0</td>\n",
       "      <td>3750.0</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.5</td>\n",
       "      <td>17.4</td>\n",
       "      <td>186.0</td>\n",
       "      <td>3800.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>40.3</td>\n",
       "      <td>18.0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>3250.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>36.7</td>\n",
       "      <td>19.3</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3450.0</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.3</td>\n",
       "      <td>20.6</td>\n",
       "      <td>190.0</td>\n",
       "      <td>3650.0</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  species     island  bill_length_mm  bill_depth_mm  flipper_length_mm  \\\n",
       "0  Adelie  Torgersen            39.1           18.7              181.0   \n",
       "1  Adelie  Torgersen            39.5           17.4              186.0   \n",
       "2  Adelie  Torgersen            40.3           18.0              195.0   \n",
       "4  Adelie  Torgersen            36.7           19.3              193.0   \n",
       "5  Adelie  Torgersen            39.3           20.6              190.0   \n",
       "\n",
       "   body_mass_g     sex  Dream  Torgersen  Male  \n",
       "0       3750.0    Male      0          1     1  \n",
       "1       3800.0  Female      0          1     0  \n",
       "2       3250.0  Female      0          1     0  \n",
       "4       3450.0  Female      0          1     0  \n",
       "5       3650.0    Male      0          1     1  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8f28783",
   "metadata": {},
   "source": [
    "## Drop the Repeated Columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "1c5e9956",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_data.drop(['sex', 'island'], axis=1, inplace=True);\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "4efc01df",
   "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>species</th>\n",
       "      <th>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "      <th>Dream</th>\n",
       "      <th>Torgersen</th>\n",
       "      <th>Male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>39.1</td>\n",
       "      <td>18.7</td>\n",
       "      <td>181.0</td>\n",
       "      <td>3750.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>39.5</td>\n",
       "      <td>17.4</td>\n",
       "      <td>186.0</td>\n",
       "      <td>3800.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>40.3</td>\n",
       "      <td>18.0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>3250.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>36.7</td>\n",
       "      <td>19.3</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3450.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>39.3</td>\n",
       "      <td>20.6</td>\n",
       "      <td>190.0</td>\n",
       "      <td>3650.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  species  bill_length_mm  bill_depth_mm  flipper_length_mm  body_mass_g  \\\n",
       "0  Adelie            39.1           18.7              181.0       3750.0   \n",
       "1  Adelie            39.5           17.4              186.0       3800.0   \n",
       "2  Adelie            40.3           18.0              195.0       3250.0   \n",
       "4  Adelie            36.7           19.3              193.0       3450.0   \n",
       "5  Adelie            39.3           20.6              190.0       3650.0   \n",
       "\n",
       "   Dream  Torgersen  Male  \n",
       "0      0          1     1  \n",
       "1      0          1     0  \n",
       "2      0          1     0  \n",
       "4      0          1     0  \n",
       "5      0          1     1  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3169138",
   "metadata": {},
   "source": [
    "## Creating Seperate target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "9628e81a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Adelie\n",
       "1    Adelie\n",
       "2    Adelie\n",
       "4    Adelie\n",
       "5    Adelie\n",
       "Name: species, dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y = new_data.species\n",
    "Y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "81130004",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Adelie', 'Chinstrap', 'Gentoo'], dtype=object)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y.unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "985b26ab",
   "metadata": {},
   "source": [
    "## Using the map function to convert categorical values into numeric"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "8a88b960",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0\n",
       "1    0\n",
       "2    0\n",
       "4    0\n",
       "5    0\n",
       "Name: species, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y=Y.map({'Adelie':0,'Chinstrap':1,'Gentoo':2})\n",
    "Y.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54fef6a3",
   "metadata": {},
   "source": [
    "## Dropping the Target Variable : Species"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "a835fc0c",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_data.drop('species', inplace = True, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "d404546b",
   "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>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "      <th>Dream</th>\n",
       "      <th>Torgersen</th>\n",
       "      <th>Male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39.1</td>\n",
       "      <td>18.7</td>\n",
       "      <td>181.0</td>\n",
       "      <td>3750.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>39.5</td>\n",
       "      <td>17.4</td>\n",
       "      <td>186.0</td>\n",
       "      <td>3800.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>40.3</td>\n",
       "      <td>18.0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>3250.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>36.7</td>\n",
       "      <td>19.3</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3450.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>39.3</td>\n",
       "      <td>20.6</td>\n",
       "      <td>190.0</td>\n",
       "      <td>3650.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   bill_length_mm  bill_depth_mm  flipper_length_mm  body_mass_g  Dream  \\\n",
       "0            39.1           18.7              181.0       3750.0      0   \n",
       "1            39.5           17.4              186.0       3800.0      0   \n",
       "2            40.3           18.0              195.0       3250.0      0   \n",
       "4            36.7           19.3              193.0       3450.0      0   \n",
       "5            39.3           20.6              190.0       3650.0      0   \n",
       "\n",
       "   Torgersen  Male  \n",
       "0          1     1  \n",
       "1          1     0  \n",
       "2          1     0  \n",
       "4          1     0  \n",
       "5          1     1  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "f8459076",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "X = new_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b9f973e",
   "metadata": {},
   "source": [
    "## Splitting the Data into Training and Test Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "470ebe71",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size=0.3, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "300b5f2b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train (233, 7)\n",
      "X_test (100, 7)\n",
      "Y_train (233,)\n",
      "Y_test (100,)\n"
     ]
    }
   ],
   "source": [
    "print('X_train', X_train.shape)\n",
    "print('X_test', X_test.shape)\n",
    "print('Y_train', Y_train.shape)\n",
    "print('Y_test', Y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69a3752b",
   "metadata": {},
   "source": [
    "## Training Random Forest Classification on Training Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "f805fcd8",
   "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>RandomForestClassifier(criterion=&#x27;entropy&#x27;, n_estimators=5, random_state=0)</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\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(criterion=&#x27;entropy&#x27;, n_estimators=5, random_state=0)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(criterion='entropy', n_estimators=5, random_state=0)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "classifier = RandomForestClassifier(n_estimators=5, criterion = 'entropy', random_state = 0)\n",
    "classifier.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "eb8538d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 2, 0, 0, 0, 1, 2, 2, 1, 2, 0, 0, 1, 0, 0, 2, 0, 1, 0, 0, 0,\n",
       "       2, 2, 2, 2, 0, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 0, 1, 0, 2, 2, 0, 0,\n",
       "       0, 0, 0, 0, 2, 0, 0, 0, 2, 2, 0, 0, 0, 0, 0, 2, 0, 1, 0, 2, 0, 0,\n",
       "       2, 2, 1, 2, 2, 1, 2, 1, 0, 2, 0, 2, 0, 2, 1, 2, 2, 2, 1, 2, 1, 0,\n",
       "       0, 2, 2, 0, 2, 0, 2, 0, 2, 0, 2, 2], dtype=int64)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_pred = classifier.predict(X_test)\n",
    "Y_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd8897ac",
   "metadata": {},
   "source": [
    "## Confusion matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "0ea37c75",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report, accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "d1e496df",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[48  0  0]\n",
      " [ 2 14  0]\n",
      " [ 0  0 36]]\n"
     ]
    }
   ],
   "source": [
    "cm = confusion_matrix(Y_test, Y_pred)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "a3b88218",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.98"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(Y_test, Y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "54f4e7f0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.96      1.00      0.98        48\n",
      "           1       1.00      0.88      0.93        16\n",
      "           2       1.00      1.00      1.00        36\n",
      "\n",
      "    accuracy                           0.98       100\n",
      "   macro avg       0.99      0.96      0.97       100\n",
      "weighted avg       0.98      0.98      0.98       100\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(Y_test, Y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b0f3b84b",
   "metadata": {},
   "source": [
    "## Try with Different number of trees and gini criteria"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "041bb3ba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 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-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 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-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 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-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 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-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=12, random_state=0)</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-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(n_estimators=12, random_state=0)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(n_estimators=12, random_state=0)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "classifier =  RandomForestClassifier(n_estimators=12, criterion = 'gini', random_state = 0)\n",
    "classifier.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "6211b7be",
   "metadata": {},
   "outputs": [],
   "source": [
    "Y_pred = classifier.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "6fa158c4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.98"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(Y_test, Y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b33feabf",
   "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
}