Classification modeling.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "d9035c80",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import necessary libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.model_selection import train_test_split, cross_val_score\n",
    "from sklearn.feature_selection import SelectKBest, f_classif\n",
    "import lazypredict\n",
    "from lazypredict.Supervised import LazyClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier\n",
    "import xgboost as xgb\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.metrics import classification_report, confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "598846ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "#load dataset\n",
    "df=pd.read_excel(\"C:\\\\Users\\\\ASUS\\\\Downloads\\\\clust.xlsx\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f9ede9d6",
   "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>Plant</th>\n",
       "      <th>CO2 Absorption Rate</th>\n",
       "      <th>Growth Habit</th>\n",
       "      <th>Leaf Surface Area</th>\n",
       "      <th>Leaf Structure</th>\n",
       "      <th>Tolerance to Pollution</th>\n",
       "      <th>Growth Rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Agave</td>\n",
       "      <td>9</td>\n",
       "      <td>Succulent</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Thick</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Moderate</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Common Ferns</td>\n",
       "      <td>7</td>\n",
       "      <td>Fern</td>\n",
       "      <td>High</td>\n",
       "      <td>Thin</td>\n",
       "      <td>High</td>\n",
       "      <td>Slow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Snake Plant</td>\n",
       "      <td>3</td>\n",
       "      <td>Succulent</td>\n",
       "      <td>Low</td>\n",
       "      <td>Thick</td>\n",
       "      <td>High</td>\n",
       "      <td>Slow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Peace Lily</td>\n",
       "      <td>1</td>\n",
       "      <td>Herbaceous</td>\n",
       "      <td>Low</td>\n",
       "      <td>Thin</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Slow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Spider Plant</td>\n",
       "      <td>3</td>\n",
       "      <td>Herbaceous</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Thin</td>\n",
       "      <td>High</td>\n",
       "      <td>Moderate</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Plant  CO2 Absorption Rate Growth Habit Leaf Surface Area  \\\n",
       "0         Agave                    9    Succulent          Moderate   \n",
       "1  Common Ferns                    7         Fern              High   \n",
       "2   Snake Plant                    3    Succulent               Low   \n",
       "3    Peace Lily                    1   Herbaceous               Low   \n",
       "4  Spider Plant                    3   Herbaceous          Moderate   \n",
       "\n",
       "  Leaf Structure Tolerance to Pollution Growth Rate  \n",
       "0          Thick               Moderate    Moderate  \n",
       "1           Thin                   High        Slow  \n",
       "2          Thick                   High        Slow  \n",
       "3           Thin               Moderate        Slow  \n",
       "4           Thin                   High    Moderate  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#load first five rows\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ed929e4b",
   "metadata": {
    "scrolled": true
   },
   "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>Plant</th>\n",
       "      <th>CO2 Absorption Rate</th>\n",
       "      <th>Growth Habit</th>\n",
       "      <th>Leaf Surface Area</th>\n",
       "      <th>Leaf Structure</th>\n",
       "      <th>Tolerance to Pollution</th>\n",
       "      <th>Growth Rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>Zebra Plant</td>\n",
       "      <td>2</td>\n",
       "      <td>Herbaceous</td>\n",
       "      <td>Low</td>\n",
       "      <td>Thin</td>\n",
       "      <td>High</td>\n",
       "      <td>Slow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>Delphinium</td>\n",
       "      <td>4</td>\n",
       "      <td>Herbaceous</td>\n",
       "      <td>High</td>\n",
       "      <td>Thin</td>\n",
       "      <td>High</td>\n",
       "      <td>Moderate</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>101</th>\n",
       "      <td>Heather</td>\n",
       "      <td>3</td>\n",
       "      <td>Shrub</td>\n",
       "      <td>Low</td>\n",
       "      <td>Thin</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Slow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>102</th>\n",
       "      <td>Baby Sun Rose</td>\n",
       "      <td>2</td>\n",
       "      <td>Herbaceous</td>\n",
       "      <td>Low</td>\n",
       "      <td>Thin</td>\n",
       "      <td>High</td>\n",
       "      <td>Slow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>103</th>\n",
       "      <td>Cosmos</td>\n",
       "      <td>4</td>\n",
       "      <td>Herbaceous</td>\n",
       "      <td>High</td>\n",
       "      <td>Thin</td>\n",
       "      <td>High</td>\n",
       "      <td>Moderate</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Plant  CO2 Absorption Rate Growth Habit Leaf Surface Area  \\\n",
       "99     Zebra Plant                    2   Herbaceous               Low   \n",
       "100     Delphinium                    4   Herbaceous              High   \n",
       "101        Heather                    3        Shrub               Low   \n",
       "102  Baby Sun Rose                    2   Herbaceous               Low   \n",
       "103         Cosmos                    4   Herbaceous              High   \n",
       "\n",
       "    Leaf Structure Tolerance to Pollution Growth Rate  \n",
       "99            Thin                   High        Slow  \n",
       "100           Thin                   High    Moderate  \n",
       "101           Thin               Moderate        Slow  \n",
       "102           Thin                   High        Slow  \n",
       "103           Thin                   High    Moderate  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#load last five rows\n",
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "dcbf8707",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(104, 7)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# rows, columns\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "763565ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "728"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# rows * columns\n",
    "df.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5764ed96",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Plant', 'CO2 Absorption Rate', 'Growth Habit', 'Leaf Surface Area',\n",
       "       'Leaf Structure', 'Tolerance to Pollution', 'Growth Rate'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# columns names\n",
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "db3fa6a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 104 entries, 0 to 103\n",
      "Data columns (total 7 columns):\n",
      " #   Column                  Non-Null Count  Dtype \n",
      "---  ------                  --------------  ----- \n",
      " 0   Plant                   104 non-null    object\n",
      " 1   CO2 Absorption Rate     104 non-null    int64 \n",
      " 2   Growth Habit            104 non-null    object\n",
      " 3   Leaf Surface Area       104 non-null    object\n",
      " 4   Leaf Structure          104 non-null    object\n",
      " 5   Tolerance to Pollution  104 non-null    object\n",
      " 6   Growth Rate             104 non-null    object\n",
      "dtypes: int64(1), object(6)\n",
      "memory usage: 5.8+ KB\n"
     ]
    }
   ],
   "source": [
    "# information about the data types of columns\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "fc212a2f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Plant                     0\n",
       "CO2 Absorption Rate       0\n",
       "Growth Habit              0\n",
       "Leaf Surface Area         0\n",
       "Leaf Structure            0\n",
       "Tolerance to Pollution    0\n",
       "Growth Rate               0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking null values\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5dbc9e1f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False    102\n",
       "True       2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking duplicate values\n",
    "df.duplicated().value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f8386ee4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# dropping duplicate values\n",
    "df.drop_duplicates(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "9c07f75d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(102, 7)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# confirming non-duplicates\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6ebe9b9b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# checking outliers\n",
    "df.boxplot('CO2 Absorption Rate')\n",
    "plt.title('Box plot of Numerical Columns')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "0d7f8c45",
   "metadata": {},
   "outputs": [],
   "source": [
    "# removing outliers\n",
    "df = df[(df['CO2 Absorption Rate'] >= 2) & (df['CO2 Absorption Rate'] <= 5)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "d8a5fd48",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# confirming outliers removal\n",
    "df.boxplot('CO2 Absorption Rate')\n",
    "plt.title('Box plot of Numerical Columns')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "c959350c",
   "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>CO2 Absorption Rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>86.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>3.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>5.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       CO2 Absorption Rate\n",
       "count                86.00\n",
       "mean                  3.31\n",
       "std                   0.97\n",
       "min                   2.00\n",
       "25%                   3.00\n",
       "50%                   3.00\n",
       "75%                   4.00\n",
       "max                   5.00"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get statistical summary\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "3d7c5f58",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Plant                     86\n",
       "CO2 Absorption Rate        4\n",
       "Growth Habit               8\n",
       "Leaf Surface Area          3\n",
       "Leaf Structure             3\n",
       "Tolerance to Pollution     2\n",
       "Growth Rate                3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking unique values in each column\n",
    "df.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "09e04547",
   "metadata": {},
   "outputs": [],
   "source": [
    "# resetting the numbering of index\n",
    "df.reset_index(drop=True, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "8cb70c92",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualizing co2 absorption rate\n",
    "df['CO2 Absorption Rate'].hist()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "40ddc979",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Unique values and their frequencies for Growth Habit :\n",
      "Herbaceous       65\n",
      "Shrub             7\n",
      "Herb              7\n",
      "Climbing Vine     3\n",
      "Succulent         1\n",
      "Fern              1\n",
      "Tree              1\n",
      "Moss              1\n",
      "Name: Growth Habit, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Unique values and their frequencies for Leaf Surface Area :\n",
      "Low         53\n",
      "High        19\n",
      "Moderate    14\n",
      "Name: Leaf Surface Area, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Unique values and their frequencies for Leaf Structure :\n",
      "Thin        75\n",
      "Thick        8\n",
      "Moderate     3\n",
      "Name: Leaf Structure, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Unique values and their frequencies for Tolerance to Pollution :\n",
      "High        57\n",
      "Moderate    29\n",
      "Name: Tolerance to Pollution, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Unique values and their frequencies for Growth Rate :\n",
      "Slow        53\n",
      "Moderate    22\n",
      "Fast        11\n",
      "Name: Growth Rate, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualizing columns such as growth habit, leaf surface area, leaf structure, tolerance to pollution and growth rate\n",
    "categorical_cols = ['Growth Habit', 'Leaf Surface Area', 'Leaf Structure', 'Tolerance to Pollution', 'Growth Rate']\n",
    "for col in categorical_cols:\n",
    "    print(\"\\nUnique values and their frequencies for\", col, \":\")\n",
    "    print(df[col].value_counts())\n",
    "\n",
    "    # Bar plot for categorical variables\n",
    "    plt.figure(figsize=(8, 6))\n",
    "    sns.countplot(x=col, data=df)\n",
    "    plt.xticks(rotation=45)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "f748b086",
   "metadata": {},
   "outputs": [],
   "source": [
    "# feature engineering\n",
    "# Identify the categorical columns\n",
    "categorical_cols = ['Plant', 'Growth Habit', 'Leaf Surface Area', 'Leaf Structure', 'Tolerance to Pollution', 'Growth Rate']\n",
    "\n",
    "# Label Encoding\n",
    "label_encoder = LabelEncoder()\n",
    "for col in categorical_cols:\n",
    "    df[col] = label_encoder.fit_transform(df[col])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "11869757",
   "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>Plant</th>\n",
       "      <th>CO2 Absorption Rate</th>\n",
       "      <th>Growth Habit</th>\n",
       "      <th>Leaf Surface Area</th>\n",
       "      <th>Leaf Structure</th>\n",
       "      <th>Tolerance to Pollution</th>\n",
       "      <th>Growth Rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>70</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>73</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>27</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>24</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81</th>\n",
       "      <td>84</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>23</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>34</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84</th>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>18</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>86 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Plant  CO2 Absorption Rate  Growth Habit  Leaf Surface Area  \\\n",
       "0      70                    3             6                  1   \n",
       "1      73                    3             3                  2   \n",
       "2      27                    5             0                  0   \n",
       "3       9                    5             1                  0   \n",
       "4      24                    5             7                  2   \n",
       "..    ...                  ...           ...                ...   \n",
       "81     84                    2             3                  1   \n",
       "82     23                    4             3                  0   \n",
       "83     34                    3             5                  1   \n",
       "84      3                    2             3                  1   \n",
       "85     18                    4             3                  0   \n",
       "\n",
       "    Leaf Structure  Tolerance to Pollution  Growth Rate  \n",
       "0                1                       0            2  \n",
       "1                2                       0            1  \n",
       "2                0                       0            0  \n",
       "3                2                       0            2  \n",
       "4                1                       0            0  \n",
       "..             ...                     ...          ...  \n",
       "81               2                       0            2  \n",
       "82               2                       0            1  \n",
       "83               2                       1            2  \n",
       "84               2                       0            2  \n",
       "85               2                       0            1  \n",
       "\n",
       "[86 rows x 7 columns]"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "2c185ddc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# splitting of dataset into X and y\n",
    "X = df.drop('Growth Rate', axis=1)\n",
    "y = df['Growth Rate']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "8b70afdc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Selected Features:\n",
      "Index(['CO2 Absorption Rate', 'Leaf Surface Area', 'Leaf Structure',\n",
      "       'Tolerance to Pollution'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "# Feature selection\n",
    "selector = SelectKBest(score_func=f_classif, k=4)  # Select top 4 features (adjust k as needed)\n",
    "X_selected = selector.fit_transform(X, y)\n",
    "\n",
    "# Get the indices of the selected features\n",
    "selected_feature_indices = selector.get_support(indices=True)\n",
    "\n",
    "# Get the column names of the selected features from the original dataset\n",
    "selected_feature_names = X.columns[selected_feature_indices]\n",
    "\n",
    "# Print the selected feature names\n",
    "print(\"Selected Features:\")\n",
    "print(selected_feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "e5dbc6d0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# splitting of dataset into train and test set\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_selected, y, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "64f78820",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████████████████████████████████████████████████████████████████████████████| 29/29 [00:01<00:00, 18.96it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                               Accuracy  Balanced Accuracy ROC AUC  F1 Score  \\\n",
      "Model                                                                          \n",
      "XGBClassifier                      0.78               0.70    None      0.76   \n",
      "RandomForestClassifier             0.78               0.70    None      0.76   \n",
      "ExtraTreesClassifier               0.78               0.70    None      0.76   \n",
      "AdaBoostClassifier                 0.72               0.66    None      0.72   \n",
      "DecisionTreeClassifier             0.72               0.66    None      0.72   \n",
      "ExtraTreeClassifier                0.72               0.66    None      0.72   \n",
      "LabelPropagation                   0.72               0.66    None      0.72   \n",
      "LabelSpreading                     0.72               0.66    None      0.72   \n",
      "Perceptron                         0.72               0.65    None      0.70   \n",
      "KNeighborsClassifier               0.72               0.62    None      0.68   \n",
      "BaggingClassifier                  0.67               0.60    None      0.65   \n",
      "SVC                                0.67               0.55    None      0.63   \n",
      "LinearSVC                          0.67               0.55    None      0.62   \n",
      "LinearDiscriminantAnalysis         0.67               0.55    None      0.62   \n",
      "GaussianNB                         0.56               0.54    None      0.57   \n",
      "RidgeClassifier                    0.67               0.53    None      0.58   \n",
      "RidgeClassifierCV                  0.67               0.53    None      0.58   \n",
      "BernoulliNB                        0.67               0.53    None      0.58   \n",
      "LGBMClassifier                     0.67               0.53    None      0.58   \n",
      "NearestCentroid                    0.61               0.51    None      0.59   \n",
      "PassiveAggressiveClassifier        0.61               0.51    None      0.58   \n",
      "LogisticRegression                 0.61               0.50    None      0.53   \n",
      "SGDClassifier                      0.56               0.42    None      0.45   \n",
      "CalibratedClassifierCV             0.56               0.40    None      0.44   \n",
      "QuadraticDiscriminantAnalysis      0.22               0.33    None      0.08   \n",
      "DummyClassifier                    0.50               0.33    None      0.33   \n",
      "\n",
      "                               Time Taken  \n",
      "Model                                      \n",
      "XGBClassifier                        0.17  \n",
      "RandomForestClassifier               0.32  \n",
      "ExtraTreesClassifier                 0.24  \n",
      "AdaBoostClassifier                   0.17  \n",
      "DecisionTreeClassifier               0.02  \n",
      "ExtraTreeClassifier                  0.02  \n",
      "LabelPropagation                     0.02  \n",
      "LabelSpreading                       0.02  \n",
      "Perceptron                           0.02  \n",
      "KNeighborsClassifier                 0.03  \n",
      "BaggingClassifier                    0.06  \n",
      "SVC                                  0.02  \n",
      "LinearSVC                            0.03  \n",
      "LinearDiscriminantAnalysis           0.01  \n",
      "GaussianNB                           0.02  \n",
      "RidgeClassifier                      0.02  \n",
      "RidgeClassifierCV                    0.02  \n",
      "BernoulliNB                          0.02  \n",
      "LGBMClassifier                       0.08  \n",
      "NearestCentroid                      0.02  \n",
      "PassiveAggressiveClassifier          0.02  \n",
      "LogisticRegression                   0.03  \n",
      "SGDClassifier                        0.03  \n",
      "CalibratedClassifierCV               0.09  \n",
      "QuadraticDiscriminantAnalysis        0.02  \n",
      "DummyClassifier                      0.01  \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# Create and train the LazyClassifier\n",
    "clf = LazyClassifier(verbose=0, ignore_warnings=True, custom_metric=None)\n",
    "models, predictions = clf.fit(X_train, X_test, y_train, y_test)\n",
    "\n",
    "# Print the model performance summary\n",
    "print(models)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "9a4cf483",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "XGBoost Classifier:\n",
      "[[2 1 1]\n",
      " [1 3 1]\n",
      " [0 0 9]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.67      0.50      0.57         4\n",
      "           1       0.75      0.60      0.67         5\n",
      "           2       0.82      1.00      0.90         9\n",
      "\n",
      "    accuracy                           0.78        18\n",
      "   macro avg       0.74      0.70      0.71        18\n",
      "weighted avg       0.77      0.78      0.76        18\n",
      "\n",
      "Random Forest Classifier:\n",
      "[[2 0 2]\n",
      " [1 2 2]\n",
      " [0 0 9]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.67      0.50      0.57         4\n",
      "           1       1.00      0.40      0.57         5\n",
      "           2       0.69      1.00      0.82         9\n",
      "\n",
      "    accuracy                           0.72        18\n",
      "   macro avg       0.79      0.63      0.65        18\n",
      "weighted avg       0.77      0.72      0.69        18\n",
      "\n",
      "Extra Trees Classifier:\n",
      "[[2 1 1]\n",
      " [1 3 1]\n",
      " [0 0 9]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.67      0.50      0.57         4\n",
      "           1       0.75      0.60      0.67         5\n",
      "           2       0.82      1.00      0.90         9\n",
      "\n",
      "    accuracy                           0.78        18\n",
      "   macro avg       0.74      0.70      0.71        18\n",
      "weighted avg       0.77      0.78      0.76        18\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# fitting the training set into top 3 classifiers: randomforest, xgboost and extratrees\n",
    "xgb_model = xgb.XGBClassifier()\n",
    "xgb_model.fit(X_train, y_train)\n",
    "\n",
    "rf_model = RandomForestClassifier()\n",
    "rf_model.fit(X_train, y_train)\n",
    "\n",
    "extra_trees_model = ExtraTreesClassifier()\n",
    "extra_trees_model.fit(X_train, y_train)\n",
    "\n",
    "xgb_y_pred = xgb_model.predict(X_test)\n",
    "rf_y_pred = rf_model.predict(X_test)\n",
    "extra_trees_y_pred = extra_trees_model.predict(X_test)\n",
    "\n",
    "# checking confusion matrix and classification report of all 3 classifiers\n",
    "print(\"XGBoost Classifier:\")\n",
    "xgb_cm = confusion_matrix(y_test, xgb_y_pred)\n",
    "print(xgb_cm)\n",
    "print(classification_report(y_test, xgb_y_pred))\n",
    "\n",
    "print(\"Random Forest Classifier:\")\n",
    "rf_cm = confusion_matrix(y_test, rf_y_pred)\n",
    "print(rf_cm)\n",
    "print(classification_report(y_test, rf_y_pred))\n",
    "\n",
    "print(\"Extra Trees Classifier:\")\n",
    "extra_trees_cm = confusion_matrix(y_test, extra_trees_y_pred)\n",
    "print(extra_trees_cm)\n",
    "print(classification_report(y_test, extra_trees_y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "11729e99",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x400 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualizing confusion matrix of all 3 top classifiers\n",
    "plt.figure(figsize=(12, 4))\n",
    "\n",
    "plt.subplot(141)\n",
    "sns.heatmap(rf_cm, annot=True, cmap='Blues', fmt='d', cbar=False)\n",
    "plt.title('Random Forest Classifier')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "\n",
    "plt.subplot(142)\n",
    "sns.heatmap(extra_trees_cm, annot=True, cmap='Blues', fmt='d', cbar=False)\n",
    "plt.title('Extra Trees Classifier')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "\n",
    "plt.subplot(143)\n",
    "sns.heatmap(xgb_cm, annot=True, cmap='Blues', fmt='d', cbar=False)\n",
    "plt.title('XGBoost Classifier')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "883152c4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Random Forest:\n",
      "Feature 0: 0.5469516134956479\n",
      "Feature 1: 0.24932797317571181\n",
      "Feature 2: 0.106955563974054\n",
      "Feature 3: 0.09676484935458637\n",
      "\n",
      "XGBoost:\n",
      "Feature 0: 0.6103460192680359\n",
      "Feature 1: 0.11636998504400253\n",
      "Feature 2: 0.10030073672533035\n",
      "Feature 3: 0.172983318567276\n",
      "\n",
      "Extra Trees:\n",
      "Feature 0: 0.20907050195780086\n",
      "Feature 1: 0.3780602630542599\n",
      "Feature 2: 0.08105326998268463\n",
      "Feature 3: 0.21614678537434875\n",
      "Feature 4: 0.05109476164794808\n",
      "Feature 5: 0.06457441798295786\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"Random Forest:\")\n",
    "# Feature importances\n",
    "importance = rf_model.feature_importances_\n",
    "for i in range(len(importance)):\n",
    "    print(f\"Feature {i}: {importance[i]}\")\n",
    "print()\n",
    "\n",
    "print(\"XGBoost:\")\n",
    "# Feature importances\n",
    "importance = xgb_model.feature_importances_\n",
    "for i in range(len(importance)):\n",
    "    print(f\"Feature {i}: {importance[i]}\")\n",
    "print()\n",
    "\n",
    "print(\"Extra Trees:\")\n",
    "# Feature importances\n",
    "importance = extra_trees_model.feature_importances_\n",
    "for i in range(len(importance)):\n",
    "    print(f\"Feature {i}: {importance[i]}\")\n",
    "print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "86acc968",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Feature importances for Random Forest\n",
    "rf_importances = [0.5469516134956479, 0.24932797317571181, 0.106955563974054, 0.09676484935458637]\n",
    "feature_names = ['Feature 0', 'Feature 1', 'Feature 2', 'Feature 3']\n",
    "\n",
    "plt.figure(figsize=(8, 6))\n",
    "plt.barh(feature_names, rf_importances, color='b', alpha=0.7)\n",
    "plt.xlabel('Feature Importance')\n",
    "plt.ylabel('Feature')\n",
    "plt.title('Random Forest Feature Importances')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "c88ffbe7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Feature importances for XGBoost\n",
    "xgb_importances = [0.6103460192680359, 0.11636998504400253, 0.10030073672533035, 0.172983318567276]\n",
    "feature_names = ['Feature 0', 'Feature 1', 'Feature 2', 'Feature 3']\n",
    "\n",
    "plt.figure(figsize=(8, 6))\n",
    "plt.barh(feature_names, xgb_importances, color='g', alpha=0.7)\n",
    "plt.xlabel('Feature Importance')\n",
    "plt.ylabel('Feature')\n",
    "plt.title('XGBoost Feature Importances')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "c52fa957",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Feature importances for Extra Trees\n",
    "et_importances = [0.20907050195780086, 0.3780602630542599, 0.08105326998268463, 0.21614678537434875, 0.05109476164794808, 0.06457441798295786]\n",
    "feature_names = ['Feature 0', 'Feature 1', 'Feature 2', 'Feature 3', 'Feature 4', 'Feature 5']\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.barh(feature_names, et_importances, color='r', alpha=0.7)\n",
    "plt.xlabel('Feature Importance')\n",
    "plt.ylabel('Feature')\n",
    "plt.title('Extra Trees Feature Importances')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "dcc10658",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Random Forest Classifier Accuracy: 0.8088\n",
      "XGBoost Classifier Accuracy: 0.8077\n",
      "Extra Trees Classifier Accuracy: 0.8516\n",
      "Best Model: ExtraTreesClassifier\n",
      "Test Accuracy: 0.7778\n"
     ]
    }
   ],
   "source": [
    "# determining the best out of 3 classifiers\n",
    "models = [\n",
    "    ('Random Forest Classifier', rf_model),\n",
    "    ('XGBoost Classifier', xgb_model),\n",
    "    ('Extra Trees Classifier', extra_trees_model)\n",
    "]\n",
    "\n",
    "best_model = None\n",
    "best_accuracy = 0.0\n",
    "\n",
    "for model_name, model in models:\n",
    "    # Perform cross-validation and compute accuracy\n",
    "    scores = cross_val_score(model, X_train, y_train, cv=5)\n",
    "    accuracy = scores.mean()\n",
    "\n",
    "    # Print the accuracy for the current model\n",
    "    print(f\"{model_name} Accuracy: {accuracy:.4f}\")\n",
    "\n",
    "    # Update the best model if the current model has higher accuracy\n",
    "    if accuracy > best_accuracy:\n",
    "        best_accuracy = accuracy\n",
    "        best_model = model\n",
    "\n",
    "# Step 6: Fit the best model on the full training set and evaluate on the test set\n",
    "best_model.fit(X_train, y_train)\n",
    "test_accuracy = best_model.score(X_test, y_test)\n",
    "print(f\"Best Model: {type(best_model).__name__}\")\n",
    "print(f\"Test Accuracy: {test_accuracy:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "53c834e9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Classifier names\n",
    "classifiers = ['Random Forest', 'XGBoost', 'Extra Trees']\n",
    "\n",
    "# Classifier accuracies\n",
    "accuracies = [0.8088, 0.8077, 0.8516]\n",
    "\n",
    "# Create a bar plot for classifier accuracies\n",
    "plt.bar(classifiers, accuracies, color='y', alpha=0.7)\n",
    "\n",
    "plt.xlabel('Classifier')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.title('Classifier Accuracies')\n",
    "\n",
    "plt.ylim(0, 1)  # Set the y-axis limits to better visualize the differences\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "5a8ddd73",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted classes:\n",
      "[0 2 2]\n"
     ]
    }
   ],
   "source": [
    "# example input\n",
    "new_data = [[12, 3, 4, 0, 2, 0], [23, 4, 3, 1, 1, 2], [70, 2, 1, 2, 0, 1]]\n",
    "predictions = best_model.predict(new_data)\n",
    "\n",
    "print(\"Predicted classes:\")\n",
    "print(predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e322044c",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}