Handling Missing Values.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2268dc50",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6122f71f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.datasets import fetch_california_housing\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a9a929d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': array([[   8.3252    ,   41.        ,    6.98412698, ...,    2.55555556,\n",
       "           37.88      , -122.23      ],\n",
       "        [   8.3014    ,   21.        ,    6.23813708, ...,    2.10984183,\n",
       "           37.86      , -122.22      ],\n",
       "        [   7.2574    ,   52.        ,    8.28813559, ...,    2.80225989,\n",
       "           37.85      , -122.24      ],\n",
       "        ...,\n",
       "        [   1.7       ,   17.        ,    5.20554273, ...,    2.3256351 ,\n",
       "           39.43      , -121.22      ],\n",
       "        [   1.8672    ,   18.        ,    5.32951289, ...,    2.12320917,\n",
       "           39.43      , -121.32      ],\n",
       "        [   2.3886    ,   16.        ,    5.25471698, ...,    2.61698113,\n",
       "           39.37      , -121.24      ]]),\n",
       " 'target': array([4.526, 3.585, 3.521, ..., 0.923, 0.847, 0.894]),\n",
       " 'frame': None,\n",
       " 'target_names': ['MedHouseVal'],\n",
       " 'feature_names': ['MedInc',\n",
       "  'HouseAge',\n",
       "  'AveRooms',\n",
       "  'AveBedrms',\n",
       "  'Population',\n",
       "  'AveOccup',\n",
       "  'Latitude',\n",
       "  'Longitude'],\n",
       " 'DESCR': '.. _california_housing_dataset:\\n\\nCalifornia Housing dataset\\n--------------------------\\n\\n**Data Set Characteristics:**\\n\\n    :Number of Instances: 20640\\n\\n    :Number of Attributes: 8 numeric, predictive attributes and the target\\n\\n    :Attribute Information:\\n        - MedInc        median income in block group\\n        - HouseAge      median house age in block group\\n        - AveRooms      average number of rooms per household\\n        - AveBedrms     average number of bedrooms per household\\n        - Population    block group population\\n        - AveOccup      average number of household members\\n        - Latitude      block group latitude\\n        - Longitude     block group longitude\\n\\n    :Missing Attribute Values: None\\n\\nThis dataset was obtained from the StatLib repository.\\nhttps://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html\\n\\nThe target variable is the median house value for California districts,\\nexpressed in hundreds of thousands of dollars ($100,000).\\n\\nThis dataset was derived from the 1990 U.S. census, using one row per census\\nblock group. A block group is the smallest geographical unit for which the U.S.\\nCensus Bureau publishes sample data (a block group typically has a population\\nof 600 to 3,000 people).\\n\\nA household is a group of people residing within a home. Since the average\\nnumber of rooms and bedrooms in this dataset are provided per household, these\\ncolumns may take surprisingly large values for block groups with few households\\nand many empty houses, such as vacation resorts.\\n\\nIt can be downloaded/loaded using the\\n:func:`sklearn.datasets.fetch_california_housing` function.\\n\\n.. topic:: References\\n\\n    - Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,\\n      Statistics and Probability Letters, 33 (1997) 291-297\\n'}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Data=fetch_california_housing()\n",
    "Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "35c0f7a6",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.DataFrame(Data.data,columns=Data.feature_names)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ca3e82a8",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.3252</td>\n",
       "      <td>41.0</td>\n",
       "      <td>6.984127</td>\n",
       "      <td>1.023810</td>\n",
       "      <td>322.0</td>\n",
       "      <td>2.555556</td>\n",
       "      <td>37.88</td>\n",
       "      <td>-122.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.3014</td>\n",
       "      <td>21.0</td>\n",
       "      <td>6.238137</td>\n",
       "      <td>0.971880</td>\n",
       "      <td>2401.0</td>\n",
       "      <td>2.109842</td>\n",
       "      <td>37.86</td>\n",
       "      <td>-122.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.2574</td>\n",
       "      <td>52.0</td>\n",
       "      <td>8.288136</td>\n",
       "      <td>1.073446</td>\n",
       "      <td>496.0</td>\n",
       "      <td>2.802260</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.6431</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.817352</td>\n",
       "      <td>1.073059</td>\n",
       "      <td>558.0</td>\n",
       "      <td>2.547945</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.8462</td>\n",
       "      <td>52.0</td>\n",
       "      <td>6.281853</td>\n",
       "      <td>1.081081</td>\n",
       "      <td>565.0</td>\n",
       "      <td>2.181467</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20635</th>\n",
       "      <td>1.5603</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.045455</td>\n",
       "      <td>1.133333</td>\n",
       "      <td>845.0</td>\n",
       "      <td>2.560606</td>\n",
       "      <td>39.48</td>\n",
       "      <td>-121.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20636</th>\n",
       "      <td>2.5568</td>\n",
       "      <td>18.0</td>\n",
       "      <td>6.114035</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>356.0</td>\n",
       "      <td>3.122807</td>\n",
       "      <td>39.49</td>\n",
       "      <td>-121.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20637</th>\n",
       "      <td>1.7000</td>\n",
       "      <td>17.0</td>\n",
       "      <td>5.205543</td>\n",
       "      <td>1.120092</td>\n",
       "      <td>1007.0</td>\n",
       "      <td>2.325635</td>\n",
       "      <td>39.43</td>\n",
       "      <td>-121.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20638</th>\n",
       "      <td>1.8672</td>\n",
       "      <td>18.0</td>\n",
       "      <td>5.329513</td>\n",
       "      <td>1.171920</td>\n",
       "      <td>741.0</td>\n",
       "      <td>2.123209</td>\n",
       "      <td>39.43</td>\n",
       "      <td>-121.32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20639</th>\n",
       "      <td>2.3886</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.254717</td>\n",
       "      <td>1.162264</td>\n",
       "      <td>1387.0</td>\n",
       "      <td>2.616981</td>\n",
       "      <td>39.37</td>\n",
       "      <td>-121.24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20640 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude   \n",
       "0      8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88  \\\n",
       "1      8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   \n",
       "2      7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   \n",
       "3      5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   \n",
       "4      3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   \n",
       "...       ...       ...       ...        ...         ...       ...       ...   \n",
       "20635  1.5603      25.0  5.045455   1.133333       845.0  2.560606     39.48   \n",
       "20636  2.5568      18.0  6.114035   1.315789       356.0  3.122807     39.49   \n",
       "20637  1.7000      17.0  5.205543   1.120092      1007.0  2.325635     39.43   \n",
       "20638  1.8672      18.0  5.329513   1.171920       741.0  2.123209     39.43   \n",
       "20639  2.3886      16.0  5.254717   1.162264      1387.0  2.616981     39.37   \n",
       "\n",
       "       Longitude  \n",
       "0        -122.23  \n",
       "1        -122.22  \n",
       "2        -122.24  \n",
       "3        -122.25  \n",
       "4        -122.25  \n",
       "...          ...  \n",
       "20635    -121.09  \n",
       "20636    -121.21  \n",
       "20637    -121.22  \n",
       "20638    -121.32  \n",
       "20639    -121.24  \n",
       "\n",
       "[20640 rows x 8 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d0d43415",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MedInc        0\n",
       "HouseAge      0\n",
       "AveRooms      0\n",
       "AveBedrms     0\n",
       "Population    0\n",
       "AveOccup      0\n",
       "Latitude      0\n",
       "Longitude     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b87e568e",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4c4eb4bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "y=Data.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ec661460",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([4.526, 3.585, 3.521, ..., 0.923, 0.847, 0.894])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "1335caa2",
   "metadata": {},
   "outputs": [],
   "source": [
    "y=pd.DataFrame(Data.target,columns=Data.target_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a60b5831",
   "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>MedHouseVal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4.526</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20635</th>\n",
       "      <td>0.781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20636</th>\n",
       "      <td>0.771</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20637</th>\n",
       "      <td>0.923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20638</th>\n",
       "      <td>0.847</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20639</th>\n",
       "      <td>0.894</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20640 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       MedHouseVal\n",
       "0            4.526\n",
       "1            3.585\n",
       "2            3.521\n",
       "3            3.413\n",
       "4            3.422\n",
       "...            ...\n",
       "20635        0.781\n",
       "20636        0.771\n",
       "20637        0.923\n",
       "20638        0.847\n",
       "20639        0.894\n",
       "\n",
       "[20640 rows x 1 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "e9222345",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Introducing Missing Values\n",
    "df.iloc[::10]=np.nan#Every 10th place introduced missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "211e3727",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MedInc        2064\n",
       "HouseAge      2064\n",
       "AveRooms      2064\n",
       "AveBedrms     2064\n",
       "Population    2064\n",
       "AveOccup      2064\n",
       "Latitude      2064\n",
       "Longitude     2064\n",
       "dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "6d8f05b9",
   "metadata": {},
   "outputs": [],
   "source": [
    "#1st Method is Deletion\n",
    "import pandas as pd\n",
    "from sklearn.datasets import load_iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "c8437d01",
   "metadata": {},
   "outputs": [],
   "source": [
    "data=load_iris()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "aa3ef02b",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.DataFrame(data.data,columns=data.feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c7f30799",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal length (cm)</th>\n",
       "      <th>sepal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>petal width (cm)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
       "0                  5.1               3.5                1.4               0.2\n",
       "1                  4.9               3.0                1.4               0.2\n",
       "2                  4.7               3.2                1.3               0.2\n",
       "3                  4.6               3.1                1.5               0.2\n",
       "4                  5.0               3.6                1.4               0.2\n",
       "..                 ...               ...                ...               ...\n",
       "145                6.7               3.0                5.2               2.3\n",
       "146                6.3               2.5                5.0               1.9\n",
       "147                6.5               3.0                5.2               2.0\n",
       "148                6.2               3.4                5.4               2.3\n",
       "149                5.9               3.0                5.1               1.8\n",
       "\n",
       "[150 rows x 4 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "602fb979",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.iloc[::10]=np.nan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "1f8a5e90",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sepal length (cm)    15\n",
       "sepal width (cm)     15\n",
       "petal length (cm)    15\n",
       "petal width (cm)     15\n",
       "dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "a674f24f",
   "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>sepal length (cm)</th>\n",
       "      <th>sepal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>petal width (cm)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5.4</td>\n",
       "      <td>3.9</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>4.4</td>\n",
       "      <td>2.9</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
       "0                NaN               NaN                NaN               NaN\n",
       "1                4.9               3.0                1.4               0.2\n",
       "2                4.7               3.2                1.3               0.2\n",
       "3                4.6               3.1                1.5               0.2\n",
       "4                5.0               3.6                1.4               0.2\n",
       "5                5.4               3.9                1.7               0.4\n",
       "6                4.6               3.4                1.4               0.3\n",
       "7                5.0               3.4                1.5               0.2\n",
       "8                4.4               2.9                1.4               0.2\n",
       "9                4.9               3.1                1.5               0.1"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "2b9795d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "df.dropna(axis=0,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "ebfbd121",
   "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>sepal length (cm)</th>\n",
       "      <th>sepal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>petal width (cm)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5.4</td>\n",
       "      <td>3.9</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>135 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
       "1                  4.9               3.0                1.4               0.2\n",
       "2                  4.7               3.2                1.3               0.2\n",
       "3                  4.6               3.1                1.5               0.2\n",
       "4                  5.0               3.6                1.4               0.2\n",
       "5                  5.4               3.9                1.7               0.4\n",
       "..                 ...               ...                ...               ...\n",
       "145                6.7               3.0                5.2               2.3\n",
       "146                6.3               2.5                5.0               1.9\n",
       "147                6.5               3.0                5.2               2.0\n",
       "148                6.2               3.4                5.4               2.3\n",
       "149                5.9               3.0                5.1               1.8\n",
       "\n",
       "[135 rows x 4 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "59d83600",
   "metadata": {},
   "outputs": [],
   "source": [
    "#2.Mean or Median Imputation Method\n",
    "from sklearn.datasets import fetch_california_housing\n",
    "from sklearn.impute import SimpleImputer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "0792cba6",
   "metadata": {},
   "outputs": [],
   "source": [
    "data=fetch_california_housing()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "10da6f7b",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.DataFrame(data.data,columns=data.feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "d1c7d845",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.iloc[::10]=np.nan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "204a533d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MedInc        2064\n",
       "HouseAge      2064\n",
       "AveRooms      2064\n",
       "AveBedrms     2064\n",
       "Population    2064\n",
       "AveOccup      2064\n",
       "Latitude      2064\n",
       "Longitude     2064\n",
       "dtype: int64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "98810b9e",
   "metadata": {},
   "outputs": [],
   "source": [
    "imp=SimpleImputer(strategy='mean')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "37c68e55",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_imputed=imp.fit_transform(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "c5b26c23",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[   3.87326599,   28.66316753,    5.42939584, ...,    3.0836242 ,\n",
       "          35.63219584, -119.56993109],\n",
       "       [   8.3014    ,   21.        ,    6.23813708, ...,    2.10984183,\n",
       "          37.86      , -122.22      ],\n",
       "       [   7.2574    ,   52.        ,    8.28813559, ...,    2.80225989,\n",
       "          37.85      , -122.24      ],\n",
       "       ...,\n",
       "       [   1.7       ,   17.        ,    5.20554273, ...,    2.3256351 ,\n",
       "          39.43      , -121.22      ],\n",
       "       [   1.8672    ,   18.        ,    5.32951289, ...,    2.12320917,\n",
       "          39.43      , -121.32      ],\n",
       "       [   2.3886    ,   16.        ,    5.25471698, ...,    2.61698113,\n",
       "          39.37      , -121.24      ]])"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_imputed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "98428493",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_imputed=pd.DataFrame(df_imputed,columns=df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "cc7a8b1f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=df.fillna(df.mean())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "2f392c0a",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.873266</td>\n",
       "      <td>28.663168</td>\n",
       "      <td>5.429396</td>\n",
       "      <td>1.096837</td>\n",
       "      <td>1424.137974</td>\n",
       "      <td>3.083624</td>\n",
       "      <td>35.632196</td>\n",
       "      <td>-119.569931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.301400</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>6.238137</td>\n",
       "      <td>0.971880</td>\n",
       "      <td>2401.000000</td>\n",
       "      <td>2.109842</td>\n",
       "      <td>37.860000</td>\n",
       "      <td>-122.220000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.257400</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>8.288136</td>\n",
       "      <td>1.073446</td>\n",
       "      <td>496.000000</td>\n",
       "      <td>2.802260</td>\n",
       "      <td>37.850000</td>\n",
       "      <td>-122.240000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.643100</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>5.817352</td>\n",
       "      <td>1.073059</td>\n",
       "      <td>558.000000</td>\n",
       "      <td>2.547945</td>\n",
       "      <td>37.850000</td>\n",
       "      <td>-122.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.846200</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>6.281853</td>\n",
       "      <td>1.081081</td>\n",
       "      <td>565.000000</td>\n",
       "      <td>2.181467</td>\n",
       "      <td>37.850000</td>\n",
       "      <td>-122.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20635</th>\n",
       "      <td>1.560300</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>5.045455</td>\n",
       "      <td>1.133333</td>\n",
       "      <td>845.000000</td>\n",
       "      <td>2.560606</td>\n",
       "      <td>39.480000</td>\n",
       "      <td>-121.090000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20636</th>\n",
       "      <td>2.556800</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>6.114035</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>356.000000</td>\n",
       "      <td>3.122807</td>\n",
       "      <td>39.490000</td>\n",
       "      <td>-121.210000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20637</th>\n",
       "      <td>1.700000</td>\n",
       "      <td>17.000000</td>\n",
       "      <td>5.205543</td>\n",
       "      <td>1.120092</td>\n",
       "      <td>1007.000000</td>\n",
       "      <td>2.325635</td>\n",
       "      <td>39.430000</td>\n",
       "      <td>-121.220000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20638</th>\n",
       "      <td>1.867200</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>5.329513</td>\n",
       "      <td>1.171920</td>\n",
       "      <td>741.000000</td>\n",
       "      <td>2.123209</td>\n",
       "      <td>39.430000</td>\n",
       "      <td>-121.320000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20639</th>\n",
       "      <td>2.388600</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>5.254717</td>\n",
       "      <td>1.162264</td>\n",
       "      <td>1387.000000</td>\n",
       "      <td>2.616981</td>\n",
       "      <td>39.370000</td>\n",
       "      <td>-121.240000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20640 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         MedInc   HouseAge  AveRooms  AveBedrms   Population  AveOccup   \n",
       "0      3.873266  28.663168  5.429396   1.096837  1424.137974  3.083624  \\\n",
       "1      8.301400  21.000000  6.238137   0.971880  2401.000000  2.109842   \n",
       "2      7.257400  52.000000  8.288136   1.073446   496.000000  2.802260   \n",
       "3      5.643100  52.000000  5.817352   1.073059   558.000000  2.547945   \n",
       "4      3.846200  52.000000  6.281853   1.081081   565.000000  2.181467   \n",
       "...         ...        ...       ...        ...          ...       ...   \n",
       "20635  1.560300  25.000000  5.045455   1.133333   845.000000  2.560606   \n",
       "20636  2.556800  18.000000  6.114035   1.315789   356.000000  3.122807   \n",
       "20637  1.700000  17.000000  5.205543   1.120092  1007.000000  2.325635   \n",
       "20638  1.867200  18.000000  5.329513   1.171920   741.000000  2.123209   \n",
       "20639  2.388600  16.000000  5.254717   1.162264  1387.000000  2.616981   \n",
       "\n",
       "        Latitude   Longitude  \n",
       "0      35.632196 -119.569931  \n",
       "1      37.860000 -122.220000  \n",
       "2      37.850000 -122.240000  \n",
       "3      37.850000 -122.250000  \n",
       "4      37.850000 -122.250000  \n",
       "...          ...         ...  \n",
       "20635  39.480000 -121.090000  \n",
       "20636  39.490000 -121.210000  \n",
       "20637  39.430000 -121.220000  \n",
       "20638  39.430000 -121.320000  \n",
       "20639  39.370000 -121.240000  \n",
       "\n",
       "[20640 rows x 8 columns]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "6933d28d",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.873266</td>\n",
       "      <td>28.663168</td>\n",
       "      <td>5.429396</td>\n",
       "      <td>1.096837</td>\n",
       "      <td>1424.137974</td>\n",
       "      <td>3.083624</td>\n",
       "      <td>35.632196</td>\n",
       "      <td>-119.569931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.301400</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>6.238137</td>\n",
       "      <td>0.971880</td>\n",
       "      <td>2401.000000</td>\n",
       "      <td>2.109842</td>\n",
       "      <td>37.860000</td>\n",
       "      <td>-122.220000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.257400</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>8.288136</td>\n",
       "      <td>1.073446</td>\n",
       "      <td>496.000000</td>\n",
       "      <td>2.802260</td>\n",
       "      <td>37.850000</td>\n",
       "      <td>-122.240000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.643100</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>5.817352</td>\n",
       "      <td>1.073059</td>\n",
       "      <td>558.000000</td>\n",
       "      <td>2.547945</td>\n",
       "      <td>37.850000</td>\n",
       "      <td>-122.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.846200</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>6.281853</td>\n",
       "      <td>1.081081</td>\n",
       "      <td>565.000000</td>\n",
       "      <td>2.181467</td>\n",
       "      <td>37.850000</td>\n",
       "      <td>-122.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20635</th>\n",
       "      <td>1.560300</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>5.045455</td>\n",
       "      <td>1.133333</td>\n",
       "      <td>845.000000</td>\n",
       "      <td>2.560606</td>\n",
       "      <td>39.480000</td>\n",
       "      <td>-121.090000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20636</th>\n",
       "      <td>2.556800</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>6.114035</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>356.000000</td>\n",
       "      <td>3.122807</td>\n",
       "      <td>39.490000</td>\n",
       "      <td>-121.210000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20637</th>\n",
       "      <td>1.700000</td>\n",
       "      <td>17.000000</td>\n",
       "      <td>5.205543</td>\n",
       "      <td>1.120092</td>\n",
       "      <td>1007.000000</td>\n",
       "      <td>2.325635</td>\n",
       "      <td>39.430000</td>\n",
       "      <td>-121.220000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20638</th>\n",
       "      <td>1.867200</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>5.329513</td>\n",
       "      <td>1.171920</td>\n",
       "      <td>741.000000</td>\n",
       "      <td>2.123209</td>\n",
       "      <td>39.430000</td>\n",
       "      <td>-121.320000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20639</th>\n",
       "      <td>2.388600</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>5.254717</td>\n",
       "      <td>1.162264</td>\n",
       "      <td>1387.000000</td>\n",
       "      <td>2.616981</td>\n",
       "      <td>39.370000</td>\n",
       "      <td>-121.240000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20640 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         MedInc   HouseAge  AveRooms  AveBedrms   Population  AveOccup   \n",
       "0      3.873266  28.663168  5.429396   1.096837  1424.137974  3.083624  \\\n",
       "1      8.301400  21.000000  6.238137   0.971880  2401.000000  2.109842   \n",
       "2      7.257400  52.000000  8.288136   1.073446   496.000000  2.802260   \n",
       "3      5.643100  52.000000  5.817352   1.073059   558.000000  2.547945   \n",
       "4      3.846200  52.000000  6.281853   1.081081   565.000000  2.181467   \n",
       "...         ...        ...       ...        ...          ...       ...   \n",
       "20635  1.560300  25.000000  5.045455   1.133333   845.000000  2.560606   \n",
       "20636  2.556800  18.000000  6.114035   1.315789   356.000000  3.122807   \n",
       "20637  1.700000  17.000000  5.205543   1.120092  1007.000000  2.325635   \n",
       "20638  1.867200  18.000000  5.329513   1.171920   741.000000  2.123209   \n",
       "20639  2.388600  16.000000  5.254717   1.162264  1387.000000  2.616981   \n",
       "\n",
       "        Latitude   Longitude  \n",
       "0      35.632196 -119.569931  \n",
       "1      37.860000 -122.220000  \n",
       "2      37.850000 -122.240000  \n",
       "3      37.850000 -122.250000  \n",
       "4      37.850000 -122.250000  \n",
       "...          ...         ...  \n",
       "20635  39.480000 -121.090000  \n",
       "20636  39.490000 -121.210000  \n",
       "20637  39.430000 -121.220000  \n",
       "20638  39.430000 -121.320000  \n",
       "20639  39.370000 -121.240000  \n",
       "\n",
       "[20640 rows x 8 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_imputed\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5f1d74ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "##3.Regression Imputation\n",
    "#Using Regression to predict the missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "f7807a71",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import fetch_california_housing\n",
    "from sklearn.linear_model import LinearRegression\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "1a805d81",
   "metadata": {},
   "outputs": [],
   "source": [
    "data=fetch_california_housing()\n",
    "df=pd.DataFrame(data.data,columns=data.feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "23810cf5",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.3252</td>\n",
       "      <td>41.0</td>\n",
       "      <td>6.984127</td>\n",
       "      <td>1.023810</td>\n",
       "      <td>322.0</td>\n",
       "      <td>2.555556</td>\n",
       "      <td>37.88</td>\n",
       "      <td>-122.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.3014</td>\n",
       "      <td>21.0</td>\n",
       "      <td>6.238137</td>\n",
       "      <td>0.971880</td>\n",
       "      <td>2401.0</td>\n",
       "      <td>2.109842</td>\n",
       "      <td>37.86</td>\n",
       "      <td>-122.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.2574</td>\n",
       "      <td>52.0</td>\n",
       "      <td>8.288136</td>\n",
       "      <td>1.073446</td>\n",
       "      <td>496.0</td>\n",
       "      <td>2.802260</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.6431</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.817352</td>\n",
       "      <td>1.073059</td>\n",
       "      <td>558.0</td>\n",
       "      <td>2.547945</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.8462</td>\n",
       "      <td>52.0</td>\n",
       "      <td>6.281853</td>\n",
       "      <td>1.081081</td>\n",
       "      <td>565.0</td>\n",
       "      <td>2.181467</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude   \n",
       "0  8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88  \\\n",
       "1  8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   \n",
       "2  7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   \n",
       "3  5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   \n",
       "4  3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   \n",
       "\n",
       "   Longitude  \n",
       "0    -122.23  \n",
       "1    -122.22  \n",
       "2    -122.24  \n",
       "3    -122.25  \n",
       "4    -122.25  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "cc42dd16",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.iloc[10:20,0]=np.nan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "d47c1c42",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.3252</td>\n",
       "      <td>41.0</td>\n",
       "      <td>6.984127</td>\n",
       "      <td>1.023810</td>\n",
       "      <td>322.0</td>\n",
       "      <td>2.555556</td>\n",
       "      <td>37.88</td>\n",
       "      <td>-122.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.3014</td>\n",
       "      <td>21.0</td>\n",
       "      <td>6.238137</td>\n",
       "      <td>0.971880</td>\n",
       "      <td>2401.0</td>\n",
       "      <td>2.109842</td>\n",
       "      <td>37.86</td>\n",
       "      <td>-122.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.2574</td>\n",
       "      <td>52.0</td>\n",
       "      <td>8.288136</td>\n",
       "      <td>1.073446</td>\n",
       "      <td>496.0</td>\n",
       "      <td>2.802260</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.6431</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.817352</td>\n",
       "      <td>1.073059</td>\n",
       "      <td>558.0</td>\n",
       "      <td>2.547945</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.8462</td>\n",
       "      <td>52.0</td>\n",
       "      <td>6.281853</td>\n",
       "      <td>1.081081</td>\n",
       "      <td>565.0</td>\n",
       "      <td>2.181467</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4.0368</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.761658</td>\n",
       "      <td>1.103627</td>\n",
       "      <td>413.0</td>\n",
       "      <td>2.139896</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3.6591</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.931907</td>\n",
       "      <td>0.951362</td>\n",
       "      <td>1094.0</td>\n",
       "      <td>2.128405</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>3.1200</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.797527</td>\n",
       "      <td>1.061824</td>\n",
       "      <td>1157.0</td>\n",
       "      <td>1.788253</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2.0804</td>\n",
       "      <td>42.0</td>\n",
       "      <td>4.294118</td>\n",
       "      <td>1.117647</td>\n",
       "      <td>1206.0</td>\n",
       "      <td>2.026891</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>3.6912</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.970588</td>\n",
       "      <td>0.990196</td>\n",
       "      <td>1551.0</td>\n",
       "      <td>2.172269</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.477612</td>\n",
       "      <td>1.079602</td>\n",
       "      <td>910.0</td>\n",
       "      <td>2.263682</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.772480</td>\n",
       "      <td>1.024523</td>\n",
       "      <td>1504.0</td>\n",
       "      <td>2.049046</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.322650</td>\n",
       "      <td>1.012821</td>\n",
       "      <td>1098.0</td>\n",
       "      <td>2.346154</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.097701</td>\n",
       "      <td>345.0</td>\n",
       "      <td>1.982759</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.262903</td>\n",
       "      <td>1.009677</td>\n",
       "      <td>1212.0</td>\n",
       "      <td>1.954839</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>NaN</td>\n",
       "      <td>50.0</td>\n",
       "      <td>4.242424</td>\n",
       "      <td>1.071970</td>\n",
       "      <td>697.0</td>\n",
       "      <td>2.640152</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.939577</td>\n",
       "      <td>1.048338</td>\n",
       "      <td>793.0</td>\n",
       "      <td>2.395770</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.052805</td>\n",
       "      <td>0.966997</td>\n",
       "      <td>648.0</td>\n",
       "      <td>2.138614</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>NaN</td>\n",
       "      <td>50.0</td>\n",
       "      <td>5.343675</td>\n",
       "      <td>1.085919</td>\n",
       "      <td>990.0</td>\n",
       "      <td>2.362768</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>NaN</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.465455</td>\n",
       "      <td>1.083636</td>\n",
       "      <td>690.0</td>\n",
       "      <td>2.509091</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>1.3578</td>\n",
       "      <td>40.0</td>\n",
       "      <td>4.524096</td>\n",
       "      <td>1.108434</td>\n",
       "      <td>409.0</td>\n",
       "      <td>2.463855</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.27</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude   \n",
       "0   8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88  \\\n",
       "1   8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   \n",
       "2   7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   \n",
       "3   5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   \n",
       "4   3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   \n",
       "5   4.0368      52.0  4.761658   1.103627       413.0  2.139896     37.85   \n",
       "6   3.6591      52.0  4.931907   0.951362      1094.0  2.128405     37.84   \n",
       "7   3.1200      52.0  4.797527   1.061824      1157.0  1.788253     37.84   \n",
       "8   2.0804      42.0  4.294118   1.117647      1206.0  2.026891     37.84   \n",
       "9   3.6912      52.0  4.970588   0.990196      1551.0  2.172269     37.84   \n",
       "10     NaN      52.0  5.477612   1.079602       910.0  2.263682     37.85   \n",
       "11     NaN      52.0  4.772480   1.024523      1504.0  2.049046     37.85   \n",
       "12     NaN      52.0  5.322650   1.012821      1098.0  2.346154     37.85   \n",
       "13     NaN      52.0  4.000000   1.097701       345.0  1.982759     37.84   \n",
       "14     NaN      52.0  4.262903   1.009677      1212.0  1.954839     37.85   \n",
       "15     NaN      50.0  4.242424   1.071970       697.0  2.640152     37.85   \n",
       "16     NaN      52.0  5.939577   1.048338       793.0  2.395770     37.85   \n",
       "17     NaN      52.0  4.052805   0.966997       648.0  2.138614     37.85   \n",
       "18     NaN      50.0  5.343675   1.085919       990.0  2.362768     37.84   \n",
       "19     NaN      52.0  5.465455   1.083636       690.0  2.509091     37.84   \n",
       "20  1.3578      40.0  4.524096   1.108434       409.0  2.463855     37.85   \n",
       "\n",
       "    Longitude  \n",
       "0     -122.23  \n",
       "1     -122.22  \n",
       "2     -122.24  \n",
       "3     -122.25  \n",
       "4     -122.25  \n",
       "5     -122.25  \n",
       "6     -122.25  \n",
       "7     -122.25  \n",
       "8     -122.26  \n",
       "9     -122.25  \n",
       "10    -122.26  \n",
       "11    -122.26  \n",
       "12    -122.26  \n",
       "13    -122.26  \n",
       "14    -122.26  \n",
       "15    -122.26  \n",
       "16    -122.27  \n",
       "17    -122.27  \n",
       "18    -122.26  \n",
       "19    -122.27  \n",
       "20    -122.27  "
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(21)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ce03a1c2",
   "metadata": {},
   "source": [
    "x_missing=df[df.isna().any(axis=1)]\n",
    "x_no_missing=df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "811ca4cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_missing=df[df.isna().any(axis=1)] \n",
    "x_no_missing=df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "b40bbc6c",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.3252</td>\n",
       "      <td>41.0</td>\n",
       "      <td>6.984127</td>\n",
       "      <td>1.023810</td>\n",
       "      <td>322.0</td>\n",
       "      <td>2.555556</td>\n",
       "      <td>37.88</td>\n",
       "      <td>-122.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.3014</td>\n",
       "      <td>21.0</td>\n",
       "      <td>6.238137</td>\n",
       "      <td>0.971880</td>\n",
       "      <td>2401.0</td>\n",
       "      <td>2.109842</td>\n",
       "      <td>37.86</td>\n",
       "      <td>-122.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.2574</td>\n",
       "      <td>52.0</td>\n",
       "      <td>8.288136</td>\n",
       "      <td>1.073446</td>\n",
       "      <td>496.0</td>\n",
       "      <td>2.802260</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.6431</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.817352</td>\n",
       "      <td>1.073059</td>\n",
       "      <td>558.0</td>\n",
       "      <td>2.547945</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.8462</td>\n",
       "      <td>52.0</td>\n",
       "      <td>6.281853</td>\n",
       "      <td>1.081081</td>\n",
       "      <td>565.0</td>\n",
       "      <td>2.181467</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20635</th>\n",
       "      <td>1.5603</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.045455</td>\n",
       "      <td>1.133333</td>\n",
       "      <td>845.0</td>\n",
       "      <td>2.560606</td>\n",
       "      <td>39.48</td>\n",
       "      <td>-121.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20636</th>\n",
       "      <td>2.5568</td>\n",
       "      <td>18.0</td>\n",
       "      <td>6.114035</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>356.0</td>\n",
       "      <td>3.122807</td>\n",
       "      <td>39.49</td>\n",
       "      <td>-121.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20637</th>\n",
       "      <td>1.7000</td>\n",
       "      <td>17.0</td>\n",
       "      <td>5.205543</td>\n",
       "      <td>1.120092</td>\n",
       "      <td>1007.0</td>\n",
       "      <td>2.325635</td>\n",
       "      <td>39.43</td>\n",
       "      <td>-121.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20638</th>\n",
       "      <td>1.8672</td>\n",
       "      <td>18.0</td>\n",
       "      <td>5.329513</td>\n",
       "      <td>1.171920</td>\n",
       "      <td>741.0</td>\n",
       "      <td>2.123209</td>\n",
       "      <td>39.43</td>\n",
       "      <td>-121.32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20639</th>\n",
       "      <td>2.3886</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.254717</td>\n",
       "      <td>1.162264</td>\n",
       "      <td>1387.0</td>\n",
       "      <td>2.616981</td>\n",
       "      <td>39.37</td>\n",
       "      <td>-121.24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20630 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude   \n",
       "0      8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88  \\\n",
       "1      8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   \n",
       "2      7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   \n",
       "3      5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   \n",
       "4      3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   \n",
       "...       ...       ...       ...        ...         ...       ...       ...   \n",
       "20635  1.5603      25.0  5.045455   1.133333       845.0  2.560606     39.48   \n",
       "20636  2.5568      18.0  6.114035   1.315789       356.0  3.122807     39.49   \n",
       "20637  1.7000      17.0  5.205543   1.120092      1007.0  2.325635     39.43   \n",
       "20638  1.8672      18.0  5.329513   1.171920       741.0  2.123209     39.43   \n",
       "20639  2.3886      16.0  5.254717   1.162264      1387.0  2.616981     39.37   \n",
       "\n",
       "       Longitude  \n",
       "0        -122.23  \n",
       "1        -122.22  \n",
       "2        -122.24  \n",
       "3        -122.25  \n",
       "4        -122.25  \n",
       "...          ...  \n",
       "20635    -121.09  \n",
       "20636    -121.21  \n",
       "20637    -121.22  \n",
       "20638    -121.32  \n",
       "20639    -121.24  \n",
       "\n",
       "[20630 rows x 8 columns]"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_no_missing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "cf9afda9",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train=x_no_missing.drop(columns=['MedInc'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "40bc40fd",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train=x_no_missing['MedInc']\n",
    "x_test=x_missing.drop(columns=['MedInc'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "9a06d14b",
   "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>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model=LinearRegression()\n",
    "model.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "3614e91b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_16987/2563625267.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  x_missing['MedInc']=model.predict(x_test)\n"
     ]
    }
   ],
   "source": [
    "x_missing['MedInc']=model.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "1fa71906",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_final = pd.concat([x_missing,x_no_missing],axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "ec450fc8",
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>3.985553</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.477612</td>\n",
       "      <td>1.079602</td>\n",
       "      <td>910.0</td>\n",
       "      <td>2.263682</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>3.490337</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.772480</td>\n",
       "      <td>1.024523</td>\n",
       "      <td>1504.0</td>\n",
       "      <td>2.049046</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>4.129700</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.322650</td>\n",
       "      <td>1.012821</td>\n",
       "      <td>1098.0</td>\n",
       "      <td>2.346154</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>2.374866</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.097701</td>\n",
       "      <td>345.0</td>\n",
       "      <td>1.982759</td>\n",
       "      <td>37.84</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>3.032323</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.262903</td>\n",
       "      <td>1.009677</td>\n",
       "      <td>1212.0</td>\n",
       "      <td>1.954839</td>\n",
       "      <td>37.85</td>\n",
       "      <td>-122.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20635</th>\n",
       "      <td>1.560300</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.045455</td>\n",
       "      <td>1.133333</td>\n",
       "      <td>845.0</td>\n",
       "      <td>2.560606</td>\n",
       "      <td>39.48</td>\n",
       "      <td>-121.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20636</th>\n",
       "      <td>2.556800</td>\n",
       "      <td>18.0</td>\n",
       "      <td>6.114035</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>356.0</td>\n",
       "      <td>3.122807</td>\n",
       "      <td>39.49</td>\n",
       "      <td>-121.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20637</th>\n",
       "      <td>1.700000</td>\n",
       "      <td>17.0</td>\n",
       "      <td>5.205543</td>\n",
       "      <td>1.120092</td>\n",
       "      <td>1007.0</td>\n",
       "      <td>2.325635</td>\n",
       "      <td>39.43</td>\n",
       "      <td>-121.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20638</th>\n",
       "      <td>1.867200</td>\n",
       "      <td>18.0</td>\n",
       "      <td>5.329513</td>\n",
       "      <td>1.171920</td>\n",
       "      <td>741.0</td>\n",
       "      <td>2.123209</td>\n",
       "      <td>39.43</td>\n",
       "      <td>-121.32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20639</th>\n",
       "      <td>2.388600</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.254717</td>\n",
       "      <td>1.162264</td>\n",
       "      <td>1387.0</td>\n",
       "      <td>2.616981</td>\n",
       "      <td>39.37</td>\n",
       "      <td>-121.24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20640 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup   \n",
       "10     3.985553      52.0  5.477612   1.079602       910.0  2.263682  \\\n",
       "11     3.490337      52.0  4.772480   1.024523      1504.0  2.049046   \n",
       "12     4.129700      52.0  5.322650   1.012821      1098.0  2.346154   \n",
       "13     2.374866      52.0  4.000000   1.097701       345.0  1.982759   \n",
       "14     3.032323      52.0  4.262903   1.009677      1212.0  1.954839   \n",
       "...         ...       ...       ...        ...         ...       ...   \n",
       "20635  1.560300      25.0  5.045455   1.133333       845.0  2.560606   \n",
       "20636  2.556800      18.0  6.114035   1.315789       356.0  3.122807   \n",
       "20637  1.700000      17.0  5.205543   1.120092      1007.0  2.325635   \n",
       "20638  1.867200      18.0  5.329513   1.171920       741.0  2.123209   \n",
       "20639  2.388600      16.0  5.254717   1.162264      1387.0  2.616981   \n",
       "\n",
       "       Latitude  Longitude  \n",
       "10        37.85    -122.26  \n",
       "11        37.85    -122.26  \n",
       "12        37.85    -122.26  \n",
       "13        37.84    -122.26  \n",
       "14        37.85    -122.26  \n",
       "...         ...        ...  \n",
       "20635     39.48    -121.09  \n",
       "20636     39.49    -121.21  \n",
       "20637     39.43    -121.22  \n",
       "20638     39.43    -121.32  \n",
       "20639     39.37    -121.24  \n",
       "\n",
       "[20640 rows x 8 columns]"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_final"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6607531a",
   "metadata": {},
   "source": [
    "# Another program cause im cool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "d079a07a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "from sklearn.linear_model import LinearRegression\n",
    "data = load_iris()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "d09e3997",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': array([[5.1, 3.5, 1.4, 0.2],\n",
       "        [4.9, 3. , 1.4, 0.2],\n",
       "        [4.7, 3.2, 1.3, 0.2],\n",
       "        [4.6, 3.1, 1.5, 0.2],\n",
       "        [5. , 3.6, 1.4, 0.2],\n",
       "        [5.4, 3.9, 1.7, 0.4],\n",
       "        [4.6, 3.4, 1.4, 0.3],\n",
       "        [5. , 3.4, 1.5, 0.2],\n",
       "        [4.4, 2.9, 1.4, 0.2],\n",
       "        [4.9, 3.1, 1.5, 0.1],\n",
       "        [5.4, 3.7, 1.5, 0.2],\n",
       "        [4.8, 3.4, 1.6, 0.2],\n",
       "        [4.8, 3. , 1.4, 0.1],\n",
       "        [4.3, 3. , 1.1, 0.1],\n",
       "        [5.8, 4. , 1.2, 0.2],\n",
       "        [5.7, 4.4, 1.5, 0.4],\n",
       "        [5.4, 3.9, 1.3, 0.4],\n",
       "        [5.1, 3.5, 1.4, 0.3],\n",
       "        [5.7, 3.8, 1.7, 0.3],\n",
       "        [5.1, 3.8, 1.5, 0.3],\n",
       "        [5.4, 3.4, 1.7, 0.2],\n",
       "        [5.1, 3.7, 1.5, 0.4],\n",
       "        [4.6, 3.6, 1. , 0.2],\n",
       "        [5.1, 3.3, 1.7, 0.5],\n",
       "        [4.8, 3.4, 1.9, 0.2],\n",
       "        [5. , 3. , 1.6, 0.2],\n",
       "        [5. , 3.4, 1.6, 0.4],\n",
       "        [5.2, 3.5, 1.5, 0.2],\n",
       "        [5.2, 3.4, 1.4, 0.2],\n",
       "        [4.7, 3.2, 1.6, 0.2],\n",
       "        [4.8, 3.1, 1.6, 0.2],\n",
       "        [5.4, 3.4, 1.5, 0.4],\n",
       "        [5.2, 4.1, 1.5, 0.1],\n",
       "        [5.5, 4.2, 1.4, 0.2],\n",
       "        [4.9, 3.1, 1.5, 0.2],\n",
       "        [5. , 3.2, 1.2, 0.2],\n",
       "        [5.5, 3.5, 1.3, 0.2],\n",
       "        [4.9, 3.6, 1.4, 0.1],\n",
       "        [4.4, 3. , 1.3, 0.2],\n",
       "        [5.1, 3.4, 1.5, 0.2],\n",
       "        [5. , 3.5, 1.3, 0.3],\n",
       "        [4.5, 2.3, 1.3, 0.3],\n",
       "        [4.4, 3.2, 1.3, 0.2],\n",
       "        [5. , 3.5, 1.6, 0.6],\n",
       "        [5.1, 3.8, 1.9, 0.4],\n",
       "        [4.8, 3. , 1.4, 0.3],\n",
       "        [5.1, 3.8, 1.6, 0.2],\n",
       "        [4.6, 3.2, 1.4, 0.2],\n",
       "        [5.3, 3.7, 1.5, 0.2],\n",
       "        [5. , 3.3, 1.4, 0.2],\n",
       "        [7. , 3.2, 4.7, 1.4],\n",
       "        [6.4, 3.2, 4.5, 1.5],\n",
       "        [6.9, 3.1, 4.9, 1.5],\n",
       "        [5.5, 2.3, 4. , 1.3],\n",
       "        [6.5, 2.8, 4.6, 1.5],\n",
       "        [5.7, 2.8, 4.5, 1.3],\n",
       "        [6.3, 3.3, 4.7, 1.6],\n",
       "        [4.9, 2.4, 3.3, 1. ],\n",
       "        [6.6, 2.9, 4.6, 1.3],\n",
       "        [5.2, 2.7, 3.9, 1.4],\n",
       "        [5. , 2. , 3.5, 1. ],\n",
       "        [5.9, 3. , 4.2, 1.5],\n",
       "        [6. , 2.2, 4. , 1. ],\n",
       "        [6.1, 2.9, 4.7, 1.4],\n",
       "        [5.6, 2.9, 3.6, 1.3],\n",
       "        [6.7, 3.1, 4.4, 1.4],\n",
       "        [5.6, 3. , 4.5, 1.5],\n",
       "        [5.8, 2.7, 4.1, 1. ],\n",
       "        [6.2, 2.2, 4.5, 1.5],\n",
       "        [5.6, 2.5, 3.9, 1.1],\n",
       "        [5.9, 3.2, 4.8, 1.8],\n",
       "        [6.1, 2.8, 4. , 1.3],\n",
       "        [6.3, 2.5, 4.9, 1.5],\n",
       "        [6.1, 2.8, 4.7, 1.2],\n",
       "        [6.4, 2.9, 4.3, 1.3],\n",
       "        [6.6, 3. , 4.4, 1.4],\n",
       "        [6.8, 2.8, 4.8, 1.4],\n",
       "        [6.7, 3. , 5. , 1.7],\n",
       "        [6. , 2.9, 4.5, 1.5],\n",
       "        [5.7, 2.6, 3.5, 1. ],\n",
       "        [5.5, 2.4, 3.8, 1.1],\n",
       "        [5.5, 2.4, 3.7, 1. ],\n",
       "        [5.8, 2.7, 3.9, 1.2],\n",
       "        [6. , 2.7, 5.1, 1.6],\n",
       "        [5.4, 3. , 4.5, 1.5],\n",
       "        [6. , 3.4, 4.5, 1.6],\n",
       "        [6.7, 3.1, 4.7, 1.5],\n",
       "        [6.3, 2.3, 4.4, 1.3],\n",
       "        [5.6, 3. , 4.1, 1.3],\n",
       "        [5.5, 2.5, 4. , 1.3],\n",
       "        [5.5, 2.6, 4.4, 1.2],\n",
       "        [6.1, 3. , 4.6, 1.4],\n",
       "        [5.8, 2.6, 4. , 1.2],\n",
       "        [5. , 2.3, 3.3, 1. ],\n",
       "        [5.6, 2.7, 4.2, 1.3],\n",
       "        [5.7, 3. , 4.2, 1.2],\n",
       "        [5.7, 2.9, 4.2, 1.3],\n",
       "        [6.2, 2.9, 4.3, 1.3],\n",
       "        [5.1, 2.5, 3. , 1.1],\n",
       "        [5.7, 2.8, 4.1, 1.3],\n",
       "        [6.3, 3.3, 6. , 2.5],\n",
       "        [5.8, 2.7, 5.1, 1.9],\n",
       "        [7.1, 3. , 5.9, 2.1],\n",
       "        [6.3, 2.9, 5.6, 1.8],\n",
       "        [6.5, 3. , 5.8, 2.2],\n",
       "        [7.6, 3. , 6.6, 2.1],\n",
       "        [4.9, 2.5, 4.5, 1.7],\n",
       "        [7.3, 2.9, 6.3, 1.8],\n",
       "        [6.7, 2.5, 5.8, 1.8],\n",
       "        [7.2, 3.6, 6.1, 2.5],\n",
       "        [6.5, 3.2, 5.1, 2. ],\n",
       "        [6.4, 2.7, 5.3, 1.9],\n",
       "        [6.8, 3. , 5.5, 2.1],\n",
       "        [5.7, 2.5, 5. , 2. ],\n",
       "        [5.8, 2.8, 5.1, 2.4],\n",
       "        [6.4, 3.2, 5.3, 2.3],\n",
       "        [6.5, 3. , 5.5, 1.8],\n",
       "        [7.7, 3.8, 6.7, 2.2],\n",
       "        [7.7, 2.6, 6.9, 2.3],\n",
       "        [6. , 2.2, 5. , 1.5],\n",
       "        [6.9, 3.2, 5.7, 2.3],\n",
       "        [5.6, 2.8, 4.9, 2. ],\n",
       "        [7.7, 2.8, 6.7, 2. ],\n",
       "        [6.3, 2.7, 4.9, 1.8],\n",
       "        [6.7, 3.3, 5.7, 2.1],\n",
       "        [7.2, 3.2, 6. , 1.8],\n",
       "        [6.2, 2.8, 4.8, 1.8],\n",
       "        [6.1, 3. , 4.9, 1.8],\n",
       "        [6.4, 2.8, 5.6, 2.1],\n",
       "        [7.2, 3. , 5.8, 1.6],\n",
       "        [7.4, 2.8, 6.1, 1.9],\n",
       "        [7.9, 3.8, 6.4, 2. ],\n",
       "        [6.4, 2.8, 5.6, 2.2],\n",
       "        [6.3, 2.8, 5.1, 1.5],\n",
       "        [6.1, 2.6, 5.6, 1.4],\n",
       "        [7.7, 3. , 6.1, 2.3],\n",
       "        [6.3, 3.4, 5.6, 2.4],\n",
       "        [6.4, 3.1, 5.5, 1.8],\n",
       "        [6. , 3. , 4.8, 1.8],\n",
       "        [6.9, 3.1, 5.4, 2.1],\n",
       "        [6.7, 3.1, 5.6, 2.4],\n",
       "        [6.9, 3.1, 5.1, 2.3],\n",
       "        [5.8, 2.7, 5.1, 1.9],\n",
       "        [6.8, 3.2, 5.9, 2.3],\n",
       "        [6.7, 3.3, 5.7, 2.5],\n",
       "        [6.7, 3. , 5.2, 2.3],\n",
       "        [6.3, 2.5, 5. , 1.9],\n",
       "        [6.5, 3. , 5.2, 2. ],\n",
       "        [6.2, 3.4, 5.4, 2.3],\n",
       "        [5.9, 3. , 5.1, 1.8]]),\n",
       " 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
       " 'frame': None,\n",
       " 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),\n",
       " 'DESCR': '.. _iris_dataset:\\n\\nIris plants dataset\\n--------------------\\n\\n**Data Set Characteristics:**\\n\\n    :Number of Instances: 150 (50 in each of three classes)\\n    :Number of Attributes: 4 numeric, predictive attributes and the class\\n    :Attribute Information:\\n        - sepal length in cm\\n        - sepal width in cm\\n        - petal length in cm\\n        - petal width in cm\\n        - class:\\n                - Iris-Setosa\\n                - Iris-Versicolour\\n                - Iris-Virginica\\n                \\n    :Summary Statistics:\\n\\n    ============== ==== ==== ======= ===== ====================\\n                    Min  Max   Mean    SD   Class Correlation\\n    ============== ==== ==== ======= ===== ====================\\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\\n    petal width:    0.1  2.5   1.20   0.76    0.9565  (high!)\\n    ============== ==== ==== ======= ===== ====================\\n\\n    :Missing Attribute Values: None\\n    :Class Distribution: 33.3% for each of 3 classes.\\n    :Creator: R.A. Fisher\\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n    :Date: July, 1988\\n\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature.  Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant.  One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\n.. topic:: References\\n\\n   - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n     Mathematical Statistics\" (John Wiley, NY, 1950).\\n   - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\\n   - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n     Structure and Classification Rule for Recognition in Partially Exposed\\n     Environments\".  IEEE Transactions on Pattern Analysis and Machine\\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n   - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\".  IEEE Transactions\\n     on Information Theory, May 1972, 431-433.\\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al\"s AUTOCLASS II\\n     conceptual clustering system finds 3 classes in the data.\\n   - Many, many more ...',\n",
       " 'feature_names': ['sepal length (cm)',\n",
       "  'sepal width (cm)',\n",
       "  'petal length (cm)',\n",
       "  'petal width (cm)'],\n",
       " 'filename': 'iris.csv',\n",
       " 'data_module': 'sklearn.datasets.data'}"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f73a3bad",
   "metadata": {},
   "source": [
    "# 4.Simple Interpolation method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "60766169",
   "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}