titanic using pipeline.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c14e02ea",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\numpy\\_distributor_init.py:30: UserWarning: loaded more than 1 DLL from .libs:\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\numpy\\.libs\\libopenblas.EL2C6PLE4ZYW3ECEVIV3OXXGRN2NRFM2.gfortran-win_amd64.dll\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\numpy\\.libs\\libopenblas.XWYDX2IKJW2NMTWSFYNGFUWKQU3LYTCZ.gfortran-win_amd64.dll\n",
      "  warnings.warn(\"loaded more than 1 DLL from .libs:\"\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.pipeline import Pipeline,make_pipeline\n",
    "from sklearn.feature_selection import SelectKBest,chi2\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "65abc34f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv(\"https://raw.githubusercontent.com/campusx-official/100-days-of-machine-learning/main/day29-sklearn-pipelines/train.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "76d19588",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>741</th>\n",
       "      <td>742</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Cavendish, Mr. Tyrell William</td>\n",
       "      <td>male</td>\n",
       "      <td>36.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>19877</td>\n",
       "      <td>78.8500</td>\n",
       "      <td>C46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>847</th>\n",
       "      <td>848</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Markoff, Mr. Marin</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>349213</td>\n",
       "      <td>7.8958</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>697</th>\n",
       "      <td>698</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Mullens, Miss. Katherine \"Katie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>35852</td>\n",
       "      <td>7.7333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>466</th>\n",
       "      <td>467</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Campbell, Mr. William</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>239853</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>261</th>\n",
       "      <td>262</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Asplund, Master. Edvin Rojj Felix</td>\n",
       "      <td>male</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>347077</td>\n",
       "      <td>31.3875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                               Name     Sex  \\\n",
       "741          742         0       1      Cavendish, Mr. Tyrell William    male   \n",
       "847          848         0       3                 Markoff, Mr. Marin    male   \n",
       "697          698         1       3   Mullens, Miss. Katherine \"Katie\"  female   \n",
       "466          467         0       2              Campbell, Mr. William    male   \n",
       "261          262         1       3  Asplund, Master. Edvin Rojj Felix    male   \n",
       "\n",
       "      Age  SibSp  Parch  Ticket     Fare Cabin Embarked  \n",
       "741  36.0      1      0   19877  78.8500   C46        S  \n",
       "847  35.0      0      0  349213   7.8958   NaN        C  \n",
       "697   NaN      0      0   35852   7.7333   NaN        Q  \n",
       "466   NaN      0      0  239853   0.0000   NaN        S  \n",
       "261   3.0      4      2  347077  31.3875   NaN        S  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0a8b7617",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop([\"PassengerId\",\"Name\",\"Ticket\",\"Cabin\"],axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fdc8ca33",
   "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>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Survived  Pclass     Sex   Age  SibSp  Parch     Fare Embarked\n",
       "0         0       3    male  22.0      1      0   7.2500        S\n",
       "1         1       1  female  38.0      1      0  71.2833        C\n",
       "2         1       3  female  26.0      0      0   7.9250        S\n",
       "3         1       1  female  35.0      1      0  53.1000        S\n",
       "4         0       3    male  35.0      0      0   8.0500        S"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ea1be20f",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=df.drop([\"Survived\"],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3a6d2c2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "y=df.Survived"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "64217ddf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0\n",
       "1    1\n",
       "2    1\n",
       "3    1\n",
       "4    0\n",
       "Name: Survived, dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c4f36e65",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=.2,random_state=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ac0233c4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "293    0\n",
       "617    0\n",
       "424    0\n",
       "888    0\n",
       "230    1\n",
       "Name: Survived, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "434b8cad",
   "metadata": {},
   "outputs": [],
   "source": [
    "trf1=ColumnTransformer([\n",
    "  (\"impute_age\",SimpleImputer(),[2]),\n",
    "  (\"impute_embarked\",SimpleImputer(strategy=\"most_frequent\"),[6])\n",
    "\n",
    "\n",
    "],remainder=\"passthrough\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "cffad684",
   "metadata": {},
   "outputs": [],
   "source": [
    "trf2=ColumnTransformer([\n",
    "    (\"ohe_sex_embarked\",OneHotEncoder(sparse=False,handle_unknown=\"ignore\"),[1,6])\n",
    "    \n",
    "    \n",
    "],remainder=\"passthrough\"\n",
    "\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "9ef031ab",
   "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>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                 OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                               sparse=False),\n",
       "                                 [1, 6])])</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 sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                 OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                               sparse=False),\n",
       "                                 [1, 6])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ohe_sex_embarked</label><div class=\"sk-toggleable__content\"><pre>[1, 6]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;, sparse=False)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre></pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "ColumnTransformer(remainder='passthrough',\n",
       "                  transformers=[('ohe_sex_embarked',\n",
       "                                 OneHotEncoder(handle_unknown='ignore',\n",
       "                                               sparse=False),\n",
       "                                 [1, 6])])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trf2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "0f545c65",
   "metadata": {},
   "outputs": [],
   "source": [
    "trf3=ColumnTransformer([\n",
    "    (\"scale\",MinMaxScaler(),slice(0,10)) #All columns has been scaled\n",
    " \n",
    "    \n",
    "    \n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4ae39713",
   "metadata": {},
   "outputs": [],
   "source": [
    "trf4=SelectKBest(score_func=chi2,k=8)#top 8 columns will be used"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6b7b899d",
   "metadata": {},
   "outputs": [],
   "source": [
    "trf5=DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "cf0f1695",
   "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>DecisionTreeClassifier()</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-6\" type=\"checkbox\" checked><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "DecisionTreeClassifier()"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trf5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "3eacb1de",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipe=Pipeline([\n",
    "    \n",
    "    (\"trf1\",trf1),\n",
    "    (\"trf2\",trf2),\n",
    "    (\"trf3\",trf3),\n",
    "    (\"trf4\",trf4),\n",
    "    (\"trf5\",trf5)\n",
    "    \n",
    "    \n",
    "])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1bedfd23",
   "metadata": {},
   "source": [
    "# Pipeline Vs make_pipeline\n",
    "Pipeline requires naming of steps, make_pipeline does not.\n",
    "\n",
    "(Same applies to ColumnTransformer vs make_column_transformer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "2ad05daf",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipe = make_pipeline(trf1,trf2,trf3,trf4,trf5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "bbdcfc98",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 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-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 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-3 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-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 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-3 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-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 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-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 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-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 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-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer-1&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;impute_age&#x27;, SimpleImputer(),\n",
       "                                                  [2]),\n",
       "                                                 (&#x27;impute_embarked&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                                  [6])])),\n",
       "                (&#x27;columntransformer-2&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                                                sparse=False),\n",
       "                                                  [1, 6])])),\n",
       "                (&#x27;columntransformer-3&#x27;,\n",
       "                 ColumnTransformer(transformers=[(&#x27;scale&#x27;, MinMaxScaler(),\n",
       "                                                  slice(0, 10, None))])),\n",
       "                (&#x27;selectkbest&#x27;,\n",
       "                 SelectKBest(k=8,\n",
       "                             score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)),\n",
       "                (&#x27;decisiontreeclassifier&#x27;, DecisionTreeClassifier())])</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 sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer-1&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;impute_age&#x27;, SimpleImputer(),\n",
       "                                                  [2]),\n",
       "                                                 (&#x27;impute_embarked&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                                  [6])])),\n",
       "                (&#x27;columntransformer-2&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                                                sparse=False),\n",
       "                                                  [1, 6])])),\n",
       "                (&#x27;columntransformer-3&#x27;,\n",
       "                 ColumnTransformer(transformers=[(&#x27;scale&#x27;, MinMaxScaler(),\n",
       "                                                  slice(0, 10, None))])),\n",
       "                (&#x27;selectkbest&#x27;,\n",
       "                 SelectKBest(k=8,\n",
       "                             score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)),\n",
       "                (&#x27;decisiontreeclassifier&#x27;, DecisionTreeClassifier())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer-1: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;impute_age&#x27;, SimpleImputer(), [2]),\n",
       "                                (&#x27;impute_embarked&#x27;,\n",
       "                                 SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                 [6])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">impute_age</label><div class=\"sk-toggleable__content\"><pre>[2]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer()</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">impute_embarked</label><div class=\"sk-toggleable__content\"><pre>[6]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;Pclass&#x27;, &#x27;Sex&#x27;, &#x27;SibSp&#x27;, &#x27;Parch&#x27;, &#x27;Fare&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" ><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer-2: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                 OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                               sparse=False),\n",
       "                                 [1, 6])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-16\" type=\"checkbox\" ><label for=\"sk-estimator-id-16\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ohe_sex_embarked</label><div class=\"sk-toggleable__content\"><pre>[1, 6]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-17\" type=\"checkbox\" ><label for=\"sk-estimator-id-17\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;, sparse=False)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-18\" type=\"checkbox\" ><label for=\"sk-estimator-id-18\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[0, 2, 3, 4, 5]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-19\" type=\"checkbox\" ><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-20\" type=\"checkbox\" ><label for=\"sk-estimator-id-20\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer-3: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[(&#x27;scale&#x27;, MinMaxScaler(), slice(0, 10, None))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-21\" type=\"checkbox\" ><label for=\"sk-estimator-id-21\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">scale</label><div class=\"sk-toggleable__content\"><pre>slice(0, 10, None)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-22\" type=\"checkbox\" ><label for=\"sk-estimator-id-22\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MinMaxScaler</label><div class=\"sk-toggleable__content\"><pre>MinMaxScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-23\" type=\"checkbox\" ><label for=\"sk-estimator-id-23\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SelectKBest</label><div class=\"sk-toggleable__content\"><pre>SelectKBest(k=8, score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-24\" type=\"checkbox\" ><label for=\"sk-estimator-id-24\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('columntransformer-1',\n",
       "                 ColumnTransformer(remainder='passthrough',\n",
       "                                   transformers=[('impute_age', SimpleImputer(),\n",
       "                                                  [2]),\n",
       "                                                 ('impute_embarked',\n",
       "                                                  SimpleImputer(strategy='most_frequent'),\n",
       "                                                  [6])])),\n",
       "                ('columntransformer-2',\n",
       "                 ColumnTransformer(remainder='passthrough',\n",
       "                                   transformers=[('ohe_sex_embarked',\n",
       "                                                  OneHotEncoder(handle_unknown='ignore',\n",
       "                                                                sparse=False),\n",
       "                                                  [1, 6])])),\n",
       "                ('columntransformer-3',\n",
       "                 ColumnTransformer(transformers=[('scale', MinMaxScaler(),\n",
       "                                                  slice(0, 10, None))])),\n",
       "                ('selectkbest',\n",
       "                 SelectKBest(k=8,\n",
       "                             score_func=<function chi2 at 0x000001B10D021EE0>)),\n",
       "                ('decisiontreeclassifier', DecisionTreeClassifier())])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# train we use pipeline not make_pipeline\n",
    "pipe.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "f2df65e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Display Pipeline\n",
    "\n",
    "from sklearn import set_config\n",
    "set_config(display='diagram')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "4a7e4120",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'columntransformer-1': ColumnTransformer(remainder='passthrough',\n",
       "                   transformers=[('impute_age', SimpleImputer(), [2]),\n",
       "                                 ('impute_embarked',\n",
       "                                  SimpleImputer(strategy='most_frequent'),\n",
       "                                  [6])]),\n",
       " 'columntransformer-2': ColumnTransformer(remainder='passthrough',\n",
       "                   transformers=[('ohe_sex_embarked',\n",
       "                                  OneHotEncoder(handle_unknown='ignore',\n",
       "                                                sparse=False),\n",
       "                                  [1, 6])]),\n",
       " 'columntransformer-3': ColumnTransformer(transformers=[('scale', MinMaxScaler(), slice(0, 10, None))]),\n",
       " 'selectkbest': SelectKBest(k=8, score_func=<function chi2 at 0x000001B10D021EE0>),\n",
       " 'decisiontreeclassifier': DecisionTreeClassifier()}"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe.named_steps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "ca56fa13",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('impute_age', SimpleImputer(), [2]),\n",
       " ('impute_embarked', SimpleImputer(strategy='most_frequent'), [6]),\n",
       " ('remainder', 'passthrough', [0, 1, 3, 4, 5])]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe.named_steps[\"trf1\"].transformers_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "da504e88",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Predict\n",
    "y_pred = pipe.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "62250ca9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,\n",
       "       1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1,\n",
       "       1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1,\n",
       "       0, 0, 0], dtype=int64)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "b0653c65",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6033519553072626"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f68730c7",
   "metadata": {},
   "source": [
    "# Cross Validation using Pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "45449ba3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.6446764503102531"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cross validation using cross_val_score\n",
    "from sklearn.model_selection import cross_val_score\n",
    "cross_val_score(pipe, x_train, y_train, cv=5, scoring='accuracy').mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54ca7398",
   "metadata": {},
   "source": [
    "# Gridsearch using pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "91271207",
   "metadata": {},
   "outputs": [],
   "source": [
    "# gridsearchcv\n",
    "params = {\n",
    "    'trf5__max_depth':[1,2,3,4,5,None]\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "d857e6f6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Abdur rahim nishad\\anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:828: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 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-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 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-4 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-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 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-4 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-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 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-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 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-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 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-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[(&#x27;trf1&#x27;,\n",
       "                                        ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                                          transformers=[(&#x27;impute_age&#x27;,\n",
       "                                                                         SimpleImputer(),\n",
       "                                                                         [2]),\n",
       "                                                                        (&#x27;impute_embarked&#x27;,\n",
       "                                                                         SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                                                         [6])])),\n",
       "                                       (&#x27;trf2&#x27;,\n",
       "                                        ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                                          transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                                                         OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                                                                       sparse=False),\n",
       "                                                                         [1,\n",
       "                                                                          6])])),\n",
       "                                       (&#x27;trf3&#x27;,\n",
       "                                        ColumnTransformer(transformers=[(&#x27;scale&#x27;,\n",
       "                                                                         MinMaxScaler(),\n",
       "                                                                         slice(0, 10, None))])),\n",
       "                                       (&#x27;trf4&#x27;,\n",
       "                                        SelectKBest(k=8,\n",
       "                                                    score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)),\n",
       "                                       (&#x27;trf5&#x27;, DecisionTreeClassifier())]),\n",
       "             param_grid={&#x27;trf5__max_depth&#x27;: [1, 2, 3, 4, 5, None]},\n",
       "             scoring=&#x27;accuracy&#x27;)</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 sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-25\" type=\"checkbox\" ><label for=\"sk-estimator-id-25\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[(&#x27;trf1&#x27;,\n",
       "                                        ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                                          transformers=[(&#x27;impute_age&#x27;,\n",
       "                                                                         SimpleImputer(),\n",
       "                                                                         [2]),\n",
       "                                                                        (&#x27;impute_embarked&#x27;,\n",
       "                                                                         SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                                                         [6])])),\n",
       "                                       (&#x27;trf2&#x27;,\n",
       "                                        ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                                          transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                                                         OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                                                                       sparse=False),\n",
       "                                                                         [1,\n",
       "                                                                          6])])),\n",
       "                                       (&#x27;trf3&#x27;,\n",
       "                                        ColumnTransformer(transformers=[(&#x27;scale&#x27;,\n",
       "                                                                         MinMaxScaler(),\n",
       "                                                                         slice(0, 10, None))])),\n",
       "                                       (&#x27;trf4&#x27;,\n",
       "                                        SelectKBest(k=8,\n",
       "                                                    score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)),\n",
       "                                       (&#x27;trf5&#x27;, DecisionTreeClassifier())]),\n",
       "             param_grid={&#x27;trf5__max_depth&#x27;: [1, 2, 3, 4, 5, None]},\n",
       "             scoring=&#x27;accuracy&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-26\" type=\"checkbox\" ><label for=\"sk-estimator-id-26\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;trf1&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;impute_age&#x27;, SimpleImputer(),\n",
       "                                                  [2]),\n",
       "                                                 (&#x27;impute_embarked&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                                  [6])])),\n",
       "                (&#x27;trf2&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                                                sparse=False),\n",
       "                                                  [1, 6])])),\n",
       "                (&#x27;trf3&#x27;,\n",
       "                 ColumnTransformer(transformers=[(&#x27;scale&#x27;, MinMaxScaler(),\n",
       "                                                  slice(0, 10, None))])),\n",
       "                (&#x27;trf4&#x27;,\n",
       "                 SelectKBest(k=8,\n",
       "                             score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)),\n",
       "                (&#x27;trf5&#x27;, DecisionTreeClassifier())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-27\" type=\"checkbox\" ><label for=\"sk-estimator-id-27\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">trf1: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;impute_age&#x27;, SimpleImputer(), [2]),\n",
       "                                (&#x27;impute_embarked&#x27;,\n",
       "                                 SimpleImputer(strategy=&#x27;most_frequent&#x27;),\n",
       "                                 [6])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-28\" type=\"checkbox\" ><label for=\"sk-estimator-id-28\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">impute_age</label><div class=\"sk-toggleable__content\"><pre>[2]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-29\" type=\"checkbox\" ><label for=\"sk-estimator-id-29\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer()</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-30\" type=\"checkbox\" ><label for=\"sk-estimator-id-30\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">impute_embarked</label><div class=\"sk-toggleable__content\"><pre>[6]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-31\" type=\"checkbox\" ><label for=\"sk-estimator-id-31\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-32\" type=\"checkbox\" ><label for=\"sk-estimator-id-32\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;Pclass&#x27;, &#x27;Sex&#x27;, &#x27;SibSp&#x27;, &#x27;Parch&#x27;, &#x27;Fare&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-33\" type=\"checkbox\" ><label for=\"sk-estimator-id-33\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-34\" type=\"checkbox\" ><label for=\"sk-estimator-id-34\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">trf2: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;ohe_sex_embarked&#x27;,\n",
       "                                 OneHotEncoder(handle_unknown=&#x27;ignore&#x27;,\n",
       "                                               sparse=False),\n",
       "                                 [1, 6])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-35\" type=\"checkbox\" ><label for=\"sk-estimator-id-35\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ohe_sex_embarked</label><div class=\"sk-toggleable__content\"><pre>[1, 6]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-36\" type=\"checkbox\" ><label for=\"sk-estimator-id-36\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;, sparse=False)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-37\" type=\"checkbox\" ><label for=\"sk-estimator-id-37\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[0, 2, 3, 4, 5]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-38\" type=\"checkbox\" ><label for=\"sk-estimator-id-38\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-39\" type=\"checkbox\" ><label for=\"sk-estimator-id-39\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">trf3: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[(&#x27;scale&#x27;, MinMaxScaler(), slice(0, 10, None))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-40\" type=\"checkbox\" ><label for=\"sk-estimator-id-40\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">scale</label><div class=\"sk-toggleable__content\"><pre>slice(0, 10, None)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-41\" type=\"checkbox\" ><label for=\"sk-estimator-id-41\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MinMaxScaler</label><div class=\"sk-toggleable__content\"><pre>MinMaxScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-42\" type=\"checkbox\" ><label for=\"sk-estimator-id-42\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SelectKBest</label><div class=\"sk-toggleable__content\"><pre>SelectKBest(k=8, score_func=&lt;function chi2 at 0x000001B10D021EE0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-43\" type=\"checkbox\" ><label for=\"sk-estimator-id-43\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[('trf1',\n",
       "                                        ColumnTransformer(remainder='passthrough',\n",
       "                                                          transformers=[('impute_age',\n",
       "                                                                         SimpleImputer(),\n",
       "                                                                         [2]),\n",
       "                                                                        ('impute_embarked',\n",
       "                                                                         SimpleImputer(strategy='most_frequent'),\n",
       "                                                                         [6])])),\n",
       "                                       ('trf2',\n",
       "                                        ColumnTransformer(remainder='passthrough',\n",
       "                                                          transformers=[('ohe_sex_embarked',\n",
       "                                                                         OneHotEncoder(handle_unknown='ignore',\n",
       "                                                                                       sparse=False),\n",
       "                                                                         [1,\n",
       "                                                                          6])])),\n",
       "                                       ('trf3',\n",
       "                                        ColumnTransformer(transformers=[('scale',\n",
       "                                                                         MinMaxScaler(),\n",
       "                                                                         slice(0, 10, None))])),\n",
       "                                       ('trf4',\n",
       "                                        SelectKBest(k=8,\n",
       "                                                    score_func=<function chi2 at 0x000001B10D021EE0>)),\n",
       "                                       ('trf5', DecisionTreeClassifier())]),\n",
       "             param_grid={'trf5__max_depth': [1, 2, 3, 4, 5, None]},\n",
       "             scoring='accuracy')"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "grid = GridSearchCV(pipe, params, cv=5, scoring='accuracy')\n",
    "grid.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "704e2c9f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6446764503102531"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "grid.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "6637c003",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'trf5__max_depth': 3}"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "e2b2561c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# export \n",
    "import pickle\n",
    "pickle.dump(pipe,open('pipe.pkl','wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "ce4dda5c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,\n",
       "       1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1,\n",
       "       1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1,\n",
       "       0, 0, 0], dtype=int64)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da85a585",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}