ML_Deployment-House Prices.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1460 entries, 0 to 1459\n",
      "Data columns (total 81 columns):\n",
      " #   Column         Non-Null Count  Dtype  \n",
      "---  ------         --------------  -----  \n",
      " 0   Id             1460 non-null   int64  \n",
      " 1   MSSubClass     1460 non-null   int64  \n",
      " 2   MSZoning       1460 non-null   object \n",
      " 3   LotFrontage    1201 non-null   float64\n",
      " 4   LotArea        1460 non-null   int64  \n",
      " 5   Street         1460 non-null   object \n",
      " 6   Alley          91 non-null     object \n",
      " 7   LotShape       1460 non-null   object \n",
      " 8   LandContour    1460 non-null   object \n",
      " 9   Utilities      1460 non-null   object \n",
      " 10  LotConfig      1460 non-null   object \n",
      " 11  LandSlope      1460 non-null   object \n",
      " 12  Neighborhood   1460 non-null   object \n",
      " 13  Condition1     1460 non-null   object \n",
      " 14  Condition2     1460 non-null   object \n",
      " 15  BldgType       1460 non-null   object \n",
      " 16  HouseStyle     1460 non-null   object \n",
      " 17  OverallQual    1460 non-null   int64  \n",
      " 18  OverallCond    1460 non-null   int64  \n",
      " 19  YearBuilt      1460 non-null   int64  \n",
      " 20  YearRemodAdd   1460 non-null   int64  \n",
      " 21  RoofStyle      1460 non-null   object \n",
      " 22  RoofMatl       1460 non-null   object \n",
      " 23  Exterior1st    1460 non-null   object \n",
      " 24  Exterior2nd    1460 non-null   object \n",
      " 25  MasVnrType     1452 non-null   object \n",
      " 26  MasVnrArea     1452 non-null   float64\n",
      " 27  ExterQual      1460 non-null   object \n",
      " 28  ExterCond      1460 non-null   object \n",
      " 29  Foundation     1460 non-null   object \n",
      " 30  BsmtQual       1423 non-null   object \n",
      " 31  BsmtCond       1423 non-null   object \n",
      " 32  BsmtExposure   1422 non-null   object \n",
      " 33  BsmtFinType1   1423 non-null   object \n",
      " 34  BsmtFinSF1     1460 non-null   int64  \n",
      " 35  BsmtFinType2   1422 non-null   object \n",
      " 36  BsmtFinSF2     1460 non-null   int64  \n",
      " 37  BsmtUnfSF      1460 non-null   int64  \n",
      " 38  TotalBsmtSF    1460 non-null   int64  \n",
      " 39  Heating        1460 non-null   object \n",
      " 40  HeatingQC      1460 non-null   object \n",
      " 41  CentralAir     1460 non-null   object \n",
      " 42  Electrical     1459 non-null   object \n",
      " 43  1stFlrSF       1460 non-null   int64  \n",
      " 44  2ndFlrSF       1460 non-null   int64  \n",
      " 45  LowQualFinSF   1460 non-null   int64  \n",
      " 46  GrLivArea      1460 non-null   int64  \n",
      " 47  BsmtFullBath   1460 non-null   int64  \n",
      " 48  BsmtHalfBath   1460 non-null   int64  \n",
      " 49  FullBath       1460 non-null   int64  \n",
      " 50  HalfBath       1460 non-null   int64  \n",
      " 51  BedroomAbvGr   1460 non-null   int64  \n",
      " 52  KitchenAbvGr   1460 non-null   int64  \n",
      " 53  KitchenQual    1460 non-null   object \n",
      " 54  TotRmsAbvGrd   1460 non-null   int64  \n",
      " 55  Functional     1460 non-null   object \n",
      " 56  Fireplaces     1460 non-null   int64  \n",
      " 57  FireplaceQu    770 non-null    object \n",
      " 58  GarageType     1379 non-null   object \n",
      " 59  GarageYrBlt    1379 non-null   float64\n",
      " 60  GarageFinish   1379 non-null   object \n",
      " 61  GarageCars     1460 non-null   int64  \n",
      " 62  GarageArea     1460 non-null   int64  \n",
      " 63  GarageQual     1379 non-null   object \n",
      " 64  GarageCond     1379 non-null   object \n",
      " 65  PavedDrive     1460 non-null   object \n",
      " 66  WoodDeckSF     1460 non-null   int64  \n",
      " 67  OpenPorchSF    1460 non-null   int64  \n",
      " 68  EnclosedPorch  1460 non-null   int64  \n",
      " 69  3SsnPorch      1460 non-null   int64  \n",
      " 70  ScreenPorch    1460 non-null   int64  \n",
      " 71  PoolArea       1460 non-null   int64  \n",
      " 72  PoolQC         7 non-null      object \n",
      " 73  Fence          281 non-null    object \n",
      " 74  MiscFeature    54 non-null     object \n",
      " 75  MiscVal        1460 non-null   int64  \n",
      " 76  MoSold         1460 non-null   int64  \n",
      " 77  YrSold         1460 non-null   int64  \n",
      " 78  SaleType       1460 non-null   object \n",
      " 79  SaleCondition  1460 non-null   object \n",
      " 80  SalePrice      1460 non-null   int64  \n",
      "dtypes: float64(3), int64(35), object(43)\n",
      "memory usage: 924.0+ KB\n",
      "None\n",
      "(1460, 81)\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "\n",
    "train=pd.read_csv(\"train_hp.csv\", encoding=\"Latin-1\")\n",
    "#test=pd.read_csv(\"test_hp.csv\", encoding=\"Latin-1\")\n",
    "#sample_submission=pd.read_csv(\"hp_sample_submission.csv\", encoding=\"Latin-1\")\n",
    "\n",
    "print(train.info())\n",
    "#print(test.info())\n",
    "\n",
    "print(train.shape)\n",
    "\n",
    "#print(test.shape)\n",
    "\n",
    "#print(sample_submission.shape)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "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>Id</th>\n",
       "      <th>MSSubClass</th>\n",
       "      <th>MSZoning</th>\n",
       "      <th>LotFrontage</th>\n",
       "      <th>LotArea</th>\n",
       "      <th>Street</th>\n",
       "      <th>Alley</th>\n",
       "      <th>LotShape</th>\n",
       "      <th>LandContour</th>\n",
       "      <th>Utilities</th>\n",
       "      <th>...</th>\n",
       "      <th>PoolArea</th>\n",
       "      <th>PoolQC</th>\n",
       "      <th>Fence</th>\n",
       "      <th>MiscFeature</th>\n",
       "      <th>MiscVal</th>\n",
       "      <th>MoSold</th>\n",
       "      <th>YrSold</th>\n",
       "      <th>SaleType</th>\n",
       "      <th>SaleCondition</th>\n",
       "      <th>SalePrice</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>60</td>\n",
       "      <td>RL</td>\n",
       "      <td>65.0</td>\n",
       "      <td>8450</td>\n",
       "      <td>Pave</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Reg</td>\n",
       "      <td>Lvl</td>\n",
       "      <td>AllPub</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2008</td>\n",
       "      <td>WD</td>\n",
       "      <td>Normal</td>\n",
       "      <td>208500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>20</td>\n",
       "      <td>RL</td>\n",
       "      <td>80.0</td>\n",
       "      <td>9600</td>\n",
       "      <td>Pave</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Reg</td>\n",
       "      <td>Lvl</td>\n",
       "      <td>AllPub</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>2007</td>\n",
       "      <td>WD</td>\n",
       "      <td>Normal</td>\n",
       "      <td>181500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>60</td>\n",
       "      <td>RL</td>\n",
       "      <td>68.0</td>\n",
       "      <td>11250</td>\n",
       "      <td>Pave</td>\n",
       "      <td>NaN</td>\n",
       "      <td>IR1</td>\n",
       "      <td>Lvl</td>\n",
       "      <td>AllPub</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>2008</td>\n",
       "      <td>WD</td>\n",
       "      <td>Normal</td>\n",
       "      <td>223500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>70</td>\n",
       "      <td>RL</td>\n",
       "      <td>60.0</td>\n",
       "      <td>9550</td>\n",
       "      <td>Pave</td>\n",
       "      <td>NaN</td>\n",
       "      <td>IR1</td>\n",
       "      <td>Lvl</td>\n",
       "      <td>AllPub</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2006</td>\n",
       "      <td>WD</td>\n",
       "      <td>Abnorml</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>60</td>\n",
       "      <td>RL</td>\n",
       "      <td>84.0</td>\n",
       "      <td>14260</td>\n",
       "      <td>Pave</td>\n",
       "      <td>NaN</td>\n",
       "      <td>IR1</td>\n",
       "      <td>Lvl</td>\n",
       "      <td>AllPub</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>2008</td>\n",
       "      <td>WD</td>\n",
       "      <td>Normal</td>\n",
       "      <td>250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 81 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Id  MSSubClass MSZoning  LotFrontage  LotArea Street Alley LotShape  \\\n",
       "0   1          60       RL         65.0     8450   Pave   NaN      Reg   \n",
       "1   2          20       RL         80.0     9600   Pave   NaN      Reg   \n",
       "2   3          60       RL         68.0    11250   Pave   NaN      IR1   \n",
       "3   4          70       RL         60.0     9550   Pave   NaN      IR1   \n",
       "4   5          60       RL         84.0    14260   Pave   NaN      IR1   \n",
       "\n",
       "  LandContour Utilities  ... PoolArea PoolQC Fence MiscFeature MiscVal MoSold  \\\n",
       "0         Lvl    AllPub  ...        0    NaN   NaN         NaN       0      2   \n",
       "1         Lvl    AllPub  ...        0    NaN   NaN         NaN       0      5   \n",
       "2         Lvl    AllPub  ...        0    NaN   NaN         NaN       0      9   \n",
       "3         Lvl    AllPub  ...        0    NaN   NaN         NaN       0      2   \n",
       "4         Lvl    AllPub  ...        0    NaN   NaN         NaN       0     12   \n",
       "\n",
       "  YrSold  SaleType  SaleCondition  SalePrice  \n",
       "0   2008        WD         Normal     208500  \n",
       "1   2007        WD         Normal     181500  \n",
       "2   2008        WD         Normal     223500  \n",
       "3   2006        WD        Abnorml     140000  \n",
       "4   2008        WD         Normal     250000  \n",
       "\n",
       "[5 rows x 81 columns]"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: pycaret in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (1.0.0)\n",
      "Requirement already satisfied: ipywidgets in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (7.5.1)\n",
      "Requirement already satisfied: pandas-profiling==2.3.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (2.3.0)\n",
      "Requirement already satisfied: nltk in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (3.4.5)\n",
      "Requirement already satisfied: datefinder==0.7.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.7.0)\n",
      "Requirement already satisfied: matplotlib in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (3.1.3)\n",
      "Requirement already satisfied: joblib in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.14.1)\n",
      "Requirement already satisfied: datetime in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (4.3)\n",
      "Requirement already satisfied: scikit-learn==0.22 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.22)\n",
      "Requirement already satisfied: spacy in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (2.2.4)\n",
      "Requirement already satisfied: shap==0.32.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.32.1)\n",
      "Requirement already satisfied: numpy in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (1.18.1)\n",
      "Requirement already satisfied: catboost==0.20.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.20.2)\n",
      "Requirement already satisfied: seaborn in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.10.0)\n",
      "Requirement already satisfied: IPython in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (7.12.0)\n",
      "Requirement already satisfied: pandas in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (1.0.1)\n",
      "Requirement already satisfied: umap-learn in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.4.3)\n",
      "Requirement already satisfied: mlxtend in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.17.2)\n",
      "Requirement already satisfied: pyod in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.7.9)\n",
      "Requirement already satisfied: yellowbrick==1.0.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (1.0.1)\n",
      "Requirement already satisfied: wordcloud in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (1.7.0)\n",
      "Requirement already satisfied: pyLDAvis in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (2.1.2)\n",
      "Requirement already satisfied: plotly==4.4.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (4.4.1)\n",
      "Requirement already satisfied: awscli in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (1.18.66)\n",
      "Requirement already satisfied: gensim in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (3.8.3)\n",
      "Requirement already satisfied: xgboost==0.90 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.90)\n",
      "Requirement already satisfied: kmodes==0.10.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.10.1)\n",
      "Requirement already satisfied: lightgbm==2.3.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (2.3.1)\n",
      "Requirement already satisfied: textblob in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.15.3)\n",
      "Requirement already satisfied: cufflinks==0.17.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pycaret) (0.17.0)\n",
      "Requirement already satisfied: widgetsnbextension~=3.5.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from ipywidgets->pycaret) (3.5.1)\n",
      "Requirement already satisfied: traitlets>=4.3.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from ipywidgets->pycaret) (4.3.3)\n",
      "Requirement already satisfied: ipykernel>=4.5.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from ipywidgets->pycaret) (5.1.4)\n",
      "Requirement already satisfied: nbformat>=4.2.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from ipywidgets->pycaret) (5.0.4)\n",
      "Requirement already satisfied: jinja2>=2.8 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pandas-profiling==2.3.0->pycaret) (2.11.1)\n",
      "Requirement already satisfied: missingno>=0.4.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pandas-profiling==2.3.0->pycaret) (0.4.2)\n",
      "Requirement already satisfied: confuse>=1.0.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pandas-profiling==2.3.0->pycaret) (1.1.0)\n",
      "Requirement already satisfied: astropy in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pandas-profiling==2.3.0->pycaret) (4.0)\n",
      "Requirement already satisfied: htmlmin>=0.1.12 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pandas-profiling==2.3.0->pycaret) (0.1.12)\n",
      "Requirement already satisfied: phik>=0.9.8 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pandas-profiling==2.3.0->pycaret) (0.9.12)\n",
      "Requirement already satisfied: six in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nltk->pycaret) (1.14.0)\n",
      "Requirement already satisfied: python-dateutil>=2.4.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from datefinder==0.7.0->pycaret) (2.8.1)\n",
      "Requirement already satisfied: regex>=2017.02.08 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from datefinder==0.7.0->pycaret) (2020.5.14)\n",
      "Requirement already satisfied: pytz in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from datefinder==0.7.0->pycaret) (2019.3)\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from matplotlib->pycaret) (1.1.0)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from matplotlib->pycaret) (0.10.0)\n",
      "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from matplotlib->pycaret) (2.4.6)\n",
      "Requirement already satisfied: zope.interface in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from datetime->pycaret) (5.1.0)\n",
      "Requirement already satisfied: scipy>=0.17.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from scikit-learn==0.22->pycaret) (1.4.1)\n",
      "Requirement already satisfied: thinc==7.4.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (7.4.0)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (2.22.0)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (2.0.3)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (4.42.1)\n",
      "Requirement already satisfied: setuptools in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (45.2.0.post20200210)\n",
      "Requirement already satisfied: srsly<1.1.0,>=1.0.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (1.0.2)\n",
      "Requirement already satisfied: catalogue<1.1.0,>=0.0.7 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (1.0.0)\n",
      "Requirement already satisfied: wasabi<1.1.0,>=0.4.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (0.6.0)\n",
      "Requirement already satisfied: plac<1.2.0,>=0.9.6 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (1.1.3)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (3.0.2)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (1.0.2)\n",
      "Requirement already satisfied: blis<0.5.0,>=0.4.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from spacy->pycaret) (0.4.1)\n",
      "Requirement already satisfied: graphviz in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from catboost==0.20.2->pycaret) (0.14)\n",
      "Requirement already satisfied: backcall in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (0.1.0)\n",
      "Requirement already satisfied: decorator in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (4.4.1)\n",
      "Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (3.0.3)\n",
      "Requirement already satisfied: colorama; sys_platform == \"win32\" in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (0.4.3)\n",
      "Requirement already satisfied: jedi>=0.10 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (0.14.1)\n",
      "Requirement already satisfied: pygments in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (2.5.2)\n",
      "Requirement already satisfied: pickleshare in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from IPython->pycaret) (0.7.5)\n",
      "Requirement already satisfied: tbb in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from umap-learn->pycaret) (2019.0)\n",
      "Requirement already satisfied: numba!=0.47,>=0.46 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from umap-learn->pycaret) (0.48.0)\n",
      "Requirement already satisfied: suod in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyod->pycaret) (0.0.4)\n",
      "Requirement already satisfied: combo in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyod->pycaret) (0.1.0)\n",
      "Requirement already satisfied: pillow in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from wordcloud->pycaret) (7.0.0)\n",
      "Requirement already satisfied: future in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyLDAvis->pycaret) (0.18.2)\n",
      "Requirement already satisfied: numexpr in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyLDAvis->pycaret) (2.7.1)\n",
      "Requirement already satisfied: funcy in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyLDAvis->pycaret) (1.14)\n",
      "Requirement already satisfied: pytest in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyLDAvis->pycaret) (5.3.5)\n",
      "Requirement already satisfied: wheel>=0.23.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pyLDAvis->pycaret) (0.34.2)\n",
      "Requirement already satisfied: retrying>=1.3.3 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from plotly==4.4.1->pycaret) (1.3.3)\n",
      "Requirement already satisfied: s3transfer<0.4.0,>=0.3.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from awscli->pycaret) (0.3.3)\n",
      "Requirement already satisfied: rsa<=3.5.0,>=3.1.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from awscli->pycaret) (3.4.2)\n",
      "Requirement already satisfied: PyYAML<5.4,>=3.10; python_version != \"3.4\" in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from awscli->pycaret) (5.3)\n",
      "Requirement already satisfied: docutils<0.16,>=0.10 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from awscli->pycaret) (0.15.2)\n",
      "Requirement already satisfied: botocore==1.16.16 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from awscli->pycaret) (1.16.16)\n",
      "Requirement already satisfied: smart-open>=1.8.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from gensim->pycaret) (2.0.0)\n",
      "Requirement already satisfied: Cython==0.29.14 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from gensim->pycaret) (0.29.14)\n",
      "Requirement already satisfied: chart-studio>=1.0.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from cufflinks==0.17.0->pycaret) (1.1.0)\n",
      "Requirement already satisfied: colorlover>=0.2.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from cufflinks==0.17.0->pycaret) (0.3.0)\n",
      "Requirement already satisfied: notebook>=4.4.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from widgetsnbextension~=3.5.0->ipywidgets->pycaret) (6.0.3)\n",
      "Requirement already satisfied: ipython-genutils in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from traitlets>=4.3.1->ipywidgets->pycaret) (0.2.0)\n",
      "Requirement already satisfied: jupyter-client in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets->pycaret) (5.3.4)\n",
      "Requirement already satisfied: tornado>=4.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets->pycaret) (6.0.3)\n",
      "Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbformat>=4.2.0->ipywidgets->pycaret) (3.2.0)\n",
      "Requirement already satisfied: jupyter-core in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbformat>=4.2.0->ipywidgets->pycaret) (4.6.1)\n",
      "Requirement already satisfied: MarkupSafe>=0.23 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from jinja2>=2.8->pandas-profiling==2.3.0->pycaret) (1.1.1)\n",
      "Requirement already satisfied: idna<2.9,>=2.5 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy->pycaret) (2.8)\n",
      "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy->pycaret) (3.0.4)\n",
      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy->pycaret) (1.25.8)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy->pycaret) (2019.11.28)\n",
      "Requirement already satisfied: importlib-metadata>=0.20; python_version < \"3.8\" in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from catalogue<1.1.0,>=0.0.7->spacy->pycaret) (1.5.0)\n",
      "Requirement already satisfied: wcwidth in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->IPython->pycaret) (0.1.8)\n",
      "Requirement already satisfied: parso>=0.5.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from jedi>=0.10->IPython->pycaret) (0.5.2)\n",
      "Requirement already satisfied: llvmlite<0.32.0,>=0.31.0dev0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from numba!=0.47,>=0.46->umap-learn->pycaret) (0.31.0)\n",
      "Requirement already satisfied: py>=1.5.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pytest->pyLDAvis->pycaret) (1.8.1)\n",
      "Requirement already satisfied: packaging in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pytest->pyLDAvis->pycaret) (20.1)\n",
      "Requirement already satisfied: attrs>=17.4.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pytest->pyLDAvis->pycaret) (19.3.0)\n",
      "Requirement already satisfied: more-itertools>=4.0.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pytest->pyLDAvis->pycaret) (8.2.0)\n",
      "Requirement already satisfied: pluggy<1.0,>=0.12 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pytest->pyLDAvis->pycaret) (0.13.1)\n",
      "Requirement already satisfied: atomicwrites>=1.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from pytest->pyLDAvis->pycaret) (1.3.0)\n",
      "Requirement already satisfied: pyasn1>=0.1.3 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from rsa<=3.5.0,>=3.1.2->awscli->pycaret) (0.4.8)\n",
      "Requirement already satisfied: jmespath<1.0.0,>=0.7.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from botocore==1.16.16->awscli->pycaret) (0.10.0)\n",
      "Requirement already satisfied: boto in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from smart-open>=1.8.1->gensim->pycaret) (2.49.0)\n",
      "Requirement already satisfied: boto3 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from smart-open>=1.8.1->gensim->pycaret) (1.13.16)\n",
      "Requirement already satisfied: prometheus-client in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.7.1)\n",
      "Requirement already satisfied: nbconvert in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (5.6.1)\n",
      "Requirement already satisfied: terminado>=0.8.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.8.3)\n",
      "Requirement already satisfied: Send2Trash in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (1.5.0)\n",
      "Requirement already satisfied: pyzmq>=17 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (18.1.1)\n",
      "Requirement already satisfied: pywin32>=1.0; sys_platform == \"win32\" in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from jupyter-client->ipykernel>=4.5.1->ipywidgets->pycaret) (227)\n",
      "Requirement already satisfied: pyrsistent>=0.14.0 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets->pycaret) (0.15.7)\n",
      "Requirement already satisfied: zipp>=0.5 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from importlib-metadata>=0.20; python_version < \"3.8\"->catalogue<1.1.0,>=0.0.7->spacy->pycaret) (2.2.0)\n",
      "Requirement already satisfied: testpath in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.4.4)\n",
      "Requirement already satisfied: pandocfilters>=1.4.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (1.4.2)\n",
      "Requirement already satisfied: defusedxml in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.6.0)\n",
      "Requirement already satisfied: bleach in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (3.1.0)\n",
      "Requirement already satisfied: entrypoints>=0.2.2 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.3)\n",
      "Requirement already satisfied: mistune<2,>=0.8.1 in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.8.4)\n",
      "Requirement already satisfied: webencodings in c:\\users\\yvkch\\anaconda4\\lib\\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret) (0.5.1)\n"
     ]
    }
   ],
   "source": [
    "!pip install pycaret"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pycaret import regression\n",
    "from pycaret.regression import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "train['FirstFloorSF']=train['1stFlrSF']\n",
    "train['SecondFloorSF']=train['2ndFlrSF']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "train=train[['LotArea','GarageArea','FirstFloorSF','SecondFloorSF','PavedDrive','SaleCondition','FullBath','HalfBath','SalePrice']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>LotArea</th>\n",
       "      <th>GarageArea</th>\n",
       "      <th>FirstFloorSF</th>\n",
       "      <th>SecondFloorSF</th>\n",
       "      <th>PavedDrive</th>\n",
       "      <th>SaleCondition</th>\n",
       "      <th>FullBath</th>\n",
       "      <th>HalfBath</th>\n",
       "      <th>SalePrice</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8450</td>\n",
       "      <td>548</td>\n",
       "      <td>856</td>\n",
       "      <td>854</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>208500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9600</td>\n",
       "      <td>460</td>\n",
       "      <td>1262</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>181500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>11250</td>\n",
       "      <td>608</td>\n",
       "      <td>920</td>\n",
       "      <td>866</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>223500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9550</td>\n",
       "      <td>642</td>\n",
       "      <td>961</td>\n",
       "      <td>756</td>\n",
       "      <td>Y</td>\n",
       "      <td>Abnorml</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>14260</td>\n",
       "      <td>836</td>\n",
       "      <td>1145</td>\n",
       "      <td>1053</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   LotArea  GarageArea  FirstFloorSF  SecondFloorSF PavedDrive SaleCondition  \\\n",
       "0     8450         548           856            854          Y        Normal   \n",
       "1     9600         460          1262              0          Y        Normal   \n",
       "2    11250         608           920            866          Y        Normal   \n",
       "3     9550         642           961            756          Y       Abnorml   \n",
       "4    14260         836          1145           1053          Y        Normal   \n",
       "\n",
       "   FullBath  HalfBath  SalePrice  \n",
       "0         2         1     208500  \n",
       "1         2         0     181500  \n",
       "2         2         1     223500  \n",
       "3         1         0     140000  \n",
       "4         2         1     250000  "
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " \n",
      "Setup Succesfully Completed!\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "    #T_f5cd8798_c452_11ea_ad7e_30243236180brow15_col1 {\n",
       "            background-color:  lightgreen;\n",
       "        }</style><table id=\"T_f5cd8798_c452_11ea_ad7e_30243236180b\" ><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >Description</th>        <th class=\"col_heading level0 col1\" >Value</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow0_col0\" class=\"data row0 col0\" >session_id</td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow0_col1\" class=\"data row0 col1\" >5011</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow1_col0\" class=\"data row1 col0\" >Transform Target </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow1_col1\" class=\"data row1 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow2_col0\" class=\"data row2 col0\" >Transform Target Method</td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow2_col1\" class=\"data row2 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow3_col0\" class=\"data row3 col0\" >Original Data</td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow3_col1\" class=\"data row3 col1\" >(1460, 9)</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow4_col0\" class=\"data row4 col0\" >Missing Values </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow4_col1\" class=\"data row4 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow5_col0\" class=\"data row5 col0\" >Numeric Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow5_col1\" class=\"data row5 col1\" >4</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow6_col0\" class=\"data row6 col0\" >Categorical Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow6_col1\" class=\"data row6 col1\" >4</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow7_col0\" class=\"data row7 col0\" >Ordinal Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow7_col1\" class=\"data row7 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow8_col0\" class=\"data row8 col0\" >High Cardinality Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow8_col1\" class=\"data row8 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow9_col0\" class=\"data row9 col0\" >High Cardinality Method </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow9_col1\" class=\"data row9 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow10_col0\" class=\"data row10 col0\" >Sampled Data</td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow10_col1\" class=\"data row10 col1\" >(1460, 9)</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow11_col0\" class=\"data row11 col0\" >Transformed Train Set</td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow11_col1\" class=\"data row11 col1\" >(1021, 20)</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow12_col0\" class=\"data row12 col0\" >Transformed Test Set</td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow12_col1\" class=\"data row12 col1\" >(439, 20)</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow13_col0\" class=\"data row13 col0\" >Numeric Imputer </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow13_col1\" class=\"data row13 col1\" >mean</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow14_col0\" class=\"data row14 col0\" >Categorical Imputer </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow14_col1\" class=\"data row14 col1\" >constant</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow15_col0\" class=\"data row15 col0\" >Normalize </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow15_col1\" class=\"data row15 col1\" >True</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow16_col0\" class=\"data row16 col0\" >Normalize Method </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow16_col1\" class=\"data row16 col1\" >zscore</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow17_col0\" class=\"data row17 col0\" >Transformation </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow17_col1\" class=\"data row17 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow18_col0\" class=\"data row18 col0\" >Transformation Method </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow18_col1\" class=\"data row18 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow19_col0\" class=\"data row19 col0\" >PCA </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow19_col1\" class=\"data row19 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow20_col0\" class=\"data row20 col0\" >PCA Method </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow20_col1\" class=\"data row20 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row21\" class=\"row_heading level0 row21\" >21</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow21_col0\" class=\"data row21 col0\" >PCA Components </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow21_col1\" class=\"data row21 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row22\" class=\"row_heading level0 row22\" >22</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow22_col0\" class=\"data row22 col0\" >Ignore Low Variance </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow22_col1\" class=\"data row22 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row23\" class=\"row_heading level0 row23\" >23</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow23_col0\" class=\"data row23 col0\" >Combine Rare Levels </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow23_col1\" class=\"data row23 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row24\" class=\"row_heading level0 row24\" >24</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow24_col0\" class=\"data row24 col0\" >Rare Level Threshold </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow24_col1\" class=\"data row24 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row25\" class=\"row_heading level0 row25\" >25</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow25_col0\" class=\"data row25 col0\" >Numeric Binning </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow25_col1\" class=\"data row25 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row26\" class=\"row_heading level0 row26\" >26</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow26_col0\" class=\"data row26 col0\" >Remove Outliers </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow26_col1\" class=\"data row26 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row27\" class=\"row_heading level0 row27\" >27</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow27_col0\" class=\"data row27 col0\" >Outliers Threshold </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow27_col1\" class=\"data row27 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row28\" class=\"row_heading level0 row28\" >28</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow28_col0\" class=\"data row28 col0\" >Remove Multicollinearity </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow28_col1\" class=\"data row28 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row29\" class=\"row_heading level0 row29\" >29</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow29_col0\" class=\"data row29 col0\" >Multicollinearity Threshold </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow29_col1\" class=\"data row29 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row30\" class=\"row_heading level0 row30\" >30</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow30_col0\" class=\"data row30 col0\" >Clustering </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow30_col1\" class=\"data row30 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row31\" class=\"row_heading level0 row31\" >31</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow31_col0\" class=\"data row31 col0\" >Clustering Iteration </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow31_col1\" class=\"data row31 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row32\" class=\"row_heading level0 row32\" >32</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow32_col0\" class=\"data row32 col0\" >Polynomial Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow32_col1\" class=\"data row32 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row33\" class=\"row_heading level0 row33\" >33</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow33_col0\" class=\"data row33 col0\" >Polynomial Degree </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow33_col1\" class=\"data row33 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row34\" class=\"row_heading level0 row34\" >34</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow34_col0\" class=\"data row34 col0\" >Trignometry Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow34_col1\" class=\"data row34 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row35\" class=\"row_heading level0 row35\" >35</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow35_col0\" class=\"data row35 col0\" >Polynomial Threshold </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow35_col1\" class=\"data row35 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row36\" class=\"row_heading level0 row36\" >36</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow36_col0\" class=\"data row36 col0\" >Group Features </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow36_col1\" class=\"data row36 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row37\" class=\"row_heading level0 row37\" >37</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow37_col0\" class=\"data row37 col0\" >Feature Selection </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow37_col1\" class=\"data row37 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row38\" class=\"row_heading level0 row38\" >38</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow38_col0\" class=\"data row38 col0\" >Features Selection Threshold </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow38_col1\" class=\"data row38 col1\" >None</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row39\" class=\"row_heading level0 row39\" >39</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow39_col0\" class=\"data row39 col0\" >Feature Interaction </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow39_col1\" class=\"data row39 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row40\" class=\"row_heading level0 row40\" >40</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow40_col0\" class=\"data row40 col0\" >Feature Ratio </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow40_col1\" class=\"data row40 col1\" >False</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_f5cd8798_c452_11ea_ad7e_30243236180blevel0_row41\" class=\"row_heading level0 row41\" >41</th>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow41_col0\" class=\"data row41 col0\" >Interaction Threshold </td>\n",
       "                        <td id=\"T_f5cd8798_c452_11ea_ad7e_30243236180brow41_col1\" class=\"data row41 col1\" >None</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x26103192bc8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "reg = setup(data = train, \n",
    "             target = 'SalePrice',\n",
    "             numeric_imputation = 'mean',\n",
    "             categorical_features = ['PavedDrive','SaleCondition'] , \n",
    "             #ignore_features = ['Alley','PoolQC','MiscFeature','Fence','FireplaceQu','Utilities'],\n",
    "             normalize = True,\n",
    "             silent = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "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>LotArea</th>\n",
       "      <th>GarageArea</th>\n",
       "      <th>FirstFloorSF</th>\n",
       "      <th>SecondFloorSF</th>\n",
       "      <th>PavedDrive</th>\n",
       "      <th>SaleCondition</th>\n",
       "      <th>FullBath</th>\n",
       "      <th>HalfBath</th>\n",
       "      <th>SalePrice</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8450</td>\n",
       "      <td>548</td>\n",
       "      <td>856</td>\n",
       "      <td>854</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>208500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9600</td>\n",
       "      <td>460</td>\n",
       "      <td>1262</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>181500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>11250</td>\n",
       "      <td>608</td>\n",
       "      <td>920</td>\n",
       "      <td>866</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>223500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9550</td>\n",
       "      <td>642</td>\n",
       "      <td>961</td>\n",
       "      <td>756</td>\n",
       "      <td>Y</td>\n",
       "      <td>Abnorml</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>14260</td>\n",
       "      <td>836</td>\n",
       "      <td>1145</td>\n",
       "      <td>1053</td>\n",
       "      <td>Y</td>\n",
       "      <td>Normal</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   LotArea  GarageArea  FirstFloorSF  SecondFloorSF PavedDrive SaleCondition  \\\n",
       "0     8450         548           856            854          Y        Normal   \n",
       "1     9600         460          1262              0          Y        Normal   \n",
       "2    11250         608           920            866          Y        Normal   \n",
       "3     9550         642           961            756          Y       Abnorml   \n",
       "4    14260         836          1145           1053          Y        Normal   \n",
       "\n",
       "   FullBath  HalfBath  SalePrice  \n",
       "0         2         1     208500  \n",
       "1         2         0     181500  \n",
       "2         2         1     223500  \n",
       "3         1         0     140000  \n",
       "4         2         1     250000  "
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "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>MAE</th>\n",
       "      <th>MSE</th>\n",
       "      <th>RMSE</th>\n",
       "      <th>R2</th>\n",
       "      <th>RMSLE</th>\n",
       "      <th>MAPE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>30841.1699</td>\n",
       "      <td>2.902761e+09</td>\n",
       "      <td>53877.2774</td>\n",
       "      <td>0.4390</td>\n",
       "      <td>0.2631</td>\n",
       "      <td>0.1951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>32128.7820</td>\n",
       "      <td>2.493623e+09</td>\n",
       "      <td>49936.1872</td>\n",
       "      <td>0.6840</td>\n",
       "      <td>0.2509</td>\n",
       "      <td>0.1946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>25397.4716</td>\n",
       "      <td>1.269925e+09</td>\n",
       "      <td>35636.0138</td>\n",
       "      <td>0.7420</td>\n",
       "      <td>0.2012</td>\n",
       "      <td>0.1471</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>24852.1109</td>\n",
       "      <td>1.384674e+09</td>\n",
       "      <td>37211.2131</td>\n",
       "      <td>0.7054</td>\n",
       "      <td>0.2068</td>\n",
       "      <td>0.1540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>25679.7760</td>\n",
       "      <td>1.290991e+09</td>\n",
       "      <td>35930.3579</td>\n",
       "      <td>0.7122</td>\n",
       "      <td>0.2138</td>\n",
       "      <td>0.1685</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>29883.7629</td>\n",
       "      <td>1.736812e+09</td>\n",
       "      <td>41675.0790</td>\n",
       "      <td>0.7074</td>\n",
       "      <td>0.2189</td>\n",
       "      <td>0.1812</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>33172.4195</td>\n",
       "      <td>2.686363e+09</td>\n",
       "      <td>51830.1334</td>\n",
       "      <td>0.6956</td>\n",
       "      <td>0.2473</td>\n",
       "      <td>0.1889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>25078.3207</td>\n",
       "      <td>1.267248e+09</td>\n",
       "      <td>35598.4312</td>\n",
       "      <td>0.7965</td>\n",
       "      <td>0.1703</td>\n",
       "      <td>0.1357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>37559.1863</td>\n",
       "      <td>5.206433e+09</td>\n",
       "      <td>72155.6156</td>\n",
       "      <td>0.2510</td>\n",
       "      <td>0.2648</td>\n",
       "      <td>0.2104</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>30112.4513</td>\n",
       "      <td>1.797999e+09</td>\n",
       "      <td>42402.8140</td>\n",
       "      <td>0.6814</td>\n",
       "      <td>0.2314</td>\n",
       "      <td>0.1870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mean</th>\n",
       "      <td>29470.5451</td>\n",
       "      <td>2.203683e+09</td>\n",
       "      <td>45625.3123</td>\n",
       "      <td>0.6414</td>\n",
       "      <td>0.2269</td>\n",
       "      <td>0.1763</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SD</th>\n",
       "      <td>4002.9870</td>\n",
       "      <td>1.160061e+09</td>\n",
       "      <td>11045.9850</td>\n",
       "      <td>0.1573</td>\n",
       "      <td>0.0287</td>\n",
       "      <td>0.0228</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             MAE           MSE        RMSE      R2   RMSLE    MAPE\n",
       "0     30841.1699  2.902761e+09  53877.2774  0.4390  0.2631  0.1951\n",
       "1     32128.7820  2.493623e+09  49936.1872  0.6840  0.2509  0.1946\n",
       "2     25397.4716  1.269925e+09  35636.0138  0.7420  0.2012  0.1471\n",
       "3     24852.1109  1.384674e+09  37211.2131  0.7054  0.2068  0.1540\n",
       "4     25679.7760  1.290991e+09  35930.3579  0.7122  0.2138  0.1685\n",
       "5     29883.7629  1.736812e+09  41675.0790  0.7074  0.2189  0.1812\n",
       "6     33172.4195  2.686363e+09  51830.1334  0.6956  0.2473  0.1889\n",
       "7     25078.3207  1.267248e+09  35598.4312  0.7965  0.1703  0.1357\n",
       "8     37559.1863  5.206433e+09  72155.6156  0.2510  0.2648  0.2104\n",
       "9     30112.4513  1.797999e+09  42402.8140  0.6814  0.2314  0.1870\n",
       "Mean  29470.5451  2.203683e+09  45625.3123  0.6414  0.2269  0.1763\n",
       "SD     4002.9870  1.160061e+09  11045.9850  0.1573  0.0287  0.0228"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lr = create_model('lr')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Transformation Pipeline and Model Succesfully Saved\n"
     ]
    }
   ],
   "source": [
    "save_model(lr, 'hp_pyc_deployment_07122020')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Transformation Pipeline and Model Sucessfully Loaded\n"
     ]
    }
   ],
   "source": [
    "hp_pyc_deployment_07122020 = load_model('hp_pyc_deployment_07122020')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Pipeline(memory=None,\n",
       "          steps=[('dtypes',\n",
       "                  DataTypes_Auto_infer(categorical_features=['PavedDrive',\n",
       "                                                             'SaleCondition'],\n",
       "                                       display_types=False, features_todrop=[],\n",
       "                                       ml_usecase='regression',\n",
       "                                       numerical_features=[], target='SalePrice',\n",
       "                                       time_features=[])),\n",
       "                 ('imputer',\n",
       "                  Simple_Imputer(categorical_strategy='not_available',\n",
       "                                 numeric_strategy='mean',\n",
       "                                 target_variable=None)),\n",
       "                 ('new_...\n",
       "                                                   target='SalePrice')),\n",
       "                 ('P_transform', Empty()), ('pt_target', Empty()),\n",
       "                 ('binn', Empty()), ('rem_outliers', Empty()),\n",
       "                 ('cluster_all', Empty()),\n",
       "                 ('dummy', Dummify(target='SalePrice')),\n",
       "                 ('fix_perfect', Remove_100(target='SalePrice')),\n",
       "                 ('clean_names', Clean_Colum_Names()),\n",
       "                 ('feature_select', Empty()), ('fix_multi', Empty()),\n",
       "                 ('dfs', Empty()), ('pca', Empty())],\n",
       "          verbose=False),\n",
       " LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False),\n",
       " None]"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hp_pyc_deployment_07122020"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     8450\n",
       "1     9600\n",
       "2    11250\n",
       "3     9550\n",
       "4    14260\n",
       "Name: LotArea, dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Testing out the values to include in HTML file\n",
    "\n",
    "train['LotArea'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    548\n",
       "1    460\n",
       "2    608\n",
       "3    642\n",
       "4    836\n",
       "Name: GarageArea, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['GarageArea'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Gable      1141\n",
       "Hip         286\n",
       "Flat         13\n",
       "Gambrel      11\n",
       "Mansard       7\n",
       "Shed          2\n",
       "Name: RoofStyle, dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['RoofStyle'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2    768\n",
       "1    650\n",
       "3     33\n",
       "0      9\n",
       "Name: FullBath, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['FullBath'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    913\n",
       "1    535\n",
       "2     12\n",
       "Name: HalfBath, dtype: int64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['HalfBath'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Y    1340\n",
       "N      90\n",
       "P      30\n",
       "Name: PavedDrive, dtype: int64"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['PavedDrive'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Normal     1198\n",
       "Partial     125\n",
       "Abnorml     101\n",
       "Family       20\n",
       "Alloca       12\n",
       "AdjLand       4\n",
       "Name: SaleCondition, dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['SaleCondition'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}