The Algorithms logo
The Algorithms
Acerca deDonar

Price Prediction Model

H
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 158,
   "id": "e4ce5cb1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "id": "f9236408",
   "metadata": {},
   "outputs": [],
   "source": [
    "house = pd.read_csv(\"Housing.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "id": "1cbee77c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "price               0\n",
       "area                0\n",
       "bedrooms            0\n",
       "bathrooms           0\n",
       "stories             0\n",
       "mainroad            0\n",
       "guestroom           0\n",
       "basement            0\n",
       "hotwaterheating     0\n",
       "airconditioning     0\n",
       "parking             0\n",
       "prefarea            0\n",
       "furnishingstatus    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "house.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "id": "b5ddd0fa",
   "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>price</th>\n",
       "      <th>area</th>\n",
       "      <th>bedrooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>stories</th>\n",
       "      <th>mainroad</th>\n",
       "      <th>guestroom</th>\n",
       "      <th>basement</th>\n",
       "      <th>hotwaterheating</th>\n",
       "      <th>airconditioning</th>\n",
       "      <th>parking</th>\n",
       "      <th>prefarea</th>\n",
       "      <th>furnishingstatus</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13300000</td>\n",
       "      <td>7420</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12250000</td>\n",
       "      <td>8960</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12250000</td>\n",
       "      <td>9960</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>semi-furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>12215000</td>\n",
       "      <td>7500</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>3</td>\n",
       "      <td>yes</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>11410000</td>\n",
       "      <td>7420</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>10850000</td>\n",
       "      <td>7500</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>semi-furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>10150000</td>\n",
       "      <td>8580</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>semi-furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>10150000</td>\n",
       "      <td>16200</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>unfurnished</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      price   area  bedrooms  bathrooms  stories mainroad guestroom basement  \\\n",
       "0  13300000   7420         4          2        3      yes        no       no   \n",
       "1  12250000   8960         4          4        4      yes        no       no   \n",
       "2  12250000   9960         3          2        2      yes        no      yes   \n",
       "3  12215000   7500         4          2        2      yes        no      yes   \n",
       "4  11410000   7420         4          1        2      yes       yes      yes   \n",
       "5  10850000   7500         3          3        1      yes        no      yes   \n",
       "6  10150000   8580         4          3        4      yes        no       no   \n",
       "7  10150000  16200         5          3        2      yes        no       no   \n",
       "\n",
       "  hotwaterheating airconditioning  parking prefarea furnishingstatus  \n",
       "0              no             yes        2      yes        furnished  \n",
       "1              no             yes        3       no        furnished  \n",
       "2              no              no        2      yes   semi-furnished  \n",
       "3              no             yes        3      yes        furnished  \n",
       "4              no             yes        2       no        furnished  \n",
       "5              no             yes        2      yes   semi-furnished  \n",
       "6              no             yes        2      yes   semi-furnished  \n",
       "7              no              no        0       no      unfurnished  "
      ]
     },
     "execution_count": 226,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "house.head(8)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55ef0588",
   "metadata": {},
   "source": [
    "# Simple Regression \n",
    "- predict 'price' using 'area'\n",
    "- y  =  b0  +  b1 * x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "id": "1cf9d7a0",
   "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>price</th>\n",
       "      <th>area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13300000</td>\n",
       "      <td>7420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12250000</td>\n",
       "      <td>8960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12250000</td>\n",
       "      <td>9960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>12215000</td>\n",
       "      <td>7500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      price  area\n",
       "0  13300000  7420\n",
       "1  12250000  8960\n",
       "2  12250000  9960\n",
       "3  12215000  7500"
      ]
     },
     "execution_count": 162,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = house[['price','area']]\n",
    "data.head(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 227,
   "id": "6707b8bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(545,)"
      ]
     },
     "execution_count": 227,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = house['price'].to_numpy()\n",
    "x = house['area'].to_numpy()\n",
    "\n",
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "id": "fc666f54",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x12ffccee160>"
      ]
     },
     "execution_count": 232,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(x, y, color = \"b\",marker = \"*\", s = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "id": "022d38a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_mean = np.mean(y)\n",
    "x_mean = np.mean(x)\n",
    "\n",
    "num = 0   # numerator\n",
    "den = 0   # denominator\n",
    "\n",
    "n = np.size(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "id": "9e2db6a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2387308.482396433 461.9748942727828\n"
     ]
    }
   ],
   "source": [
    "for i in range(n):\n",
    "    num += (x[i] - x_mean) * (y[i] - y_mean)\n",
    "    den += (x[i] - x_mean)**2\n",
    "    \n",
    "b1 = num / den\n",
    "b0 = y_mean - b1*x_mean\n",
    "\n",
    "print(b0,b1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "id": "5b9e67b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "prediction = b0 + b1*x\n",
    "for i in range(n):\n",
    "    prediction[i] = prediction[i]//1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "id": "980808bf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x12ffccc0c40>]"
      ]
     },
     "execution_count": 167,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(x, y, color = \"r\",marker = \"o\", s = 10)\n",
    "plt.plot(x, prediction, color = \"b\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b8f1d05",
   "metadata": {},
   "source": [
    "# Multiple regression\n",
    "\n",
    "- y = b0 + b1 * x1 + b2 * x2 + ..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "id": "f0e76409",
   "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>price</th>\n",
       "      <th>area</th>\n",
       "      <th>bedrooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>stories</th>\n",
       "      <th>mainroad</th>\n",
       "      <th>guestroom</th>\n",
       "      <th>basement</th>\n",
       "      <th>hotwaterheating</th>\n",
       "      <th>airconditioning</th>\n",
       "      <th>parking</th>\n",
       "      <th>prefarea</th>\n",
       "      <th>furnishingstatus</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13300000</td>\n",
       "      <td>7420</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12250000</td>\n",
       "      <td>8960</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>12250000</td>\n",
       "      <td>9960</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>semi-furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>12215000</td>\n",
       "      <td>7500</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>3</td>\n",
       "      <td>yes</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>11410000</td>\n",
       "      <td>7420</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>furnished</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      price  area  bedrooms  bathrooms  stories mainroad guestroom basement  \\\n",
       "0  13300000  7420         4          2        3      yes        no       no   \n",
       "1  12250000  8960         4          4        4      yes        no       no   \n",
       "2  12250000  9960         3          2        2      yes        no      yes   \n",
       "3  12215000  7500         4          2        2      yes        no      yes   \n",
       "4  11410000  7420         4          1        2      yes       yes      yes   \n",
       "\n",
       "  hotwaterheating airconditioning  parking prefarea furnishingstatus  \n",
       "0              no             yes        2      yes        furnished  \n",
       "1              no             yes        3       no        furnished  \n",
       "2              no              no        2      yes   semi-furnished  \n",
       "3              no             yes        3      yes        furnished  \n",
       "4              no             yes        2       no        furnished  "
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "house.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "id": "70c757ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[7420,    4,    2,    3],\n",
       "       [8960,    4,    4,    4],\n",
       "       [9960,    3,    2,    2],\n",
       "       ...,\n",
       "       [3620,    2,    1,    1],\n",
       "       [2910,    3,    1,    1],\n",
       "       [3850,    3,    1,    2]], dtype=int64)"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dependent -> price\n",
    "y = house['price'].to_numpy()\n",
    "\n",
    "# -> independent variables\n",
    "x = house[['area','bedrooms','bathrooms','stories']].to_numpy()\n",
    "\n",
    "n = np.size(y)\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "id": "9ea64dd9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[5150.54128440367, 2.9651376146788992, 1.2862385321100918, 1.8055045871559634]"
      ]
     },
     "execution_count": 177,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_mean = np.mean(y)\n",
    "x_mean = [0,0,0,0]\n",
    "\n",
    "for i in range(n):\n",
    "    for j in range(4):\n",
    "        x_mean[j] += x[i][j]\n",
    "\n",
    "for i in range(4):\n",
    "    x_mean[i] /= n\n",
    "\n",
    "x_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "id": "b607bb0e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[461.9748942727828, 928788.1189320377, 1926558.8901060484, 907116.9031974602]"
      ]
     },
     "execution_count": 181,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b = []\n",
    "for j in range(4):\n",
    "    num = 0    # numerator\n",
    "    den = 0    # denominator\n",
    "    \n",
    "    for i in range(n):\n",
    "        num += (x[i][j] - x_mean[j]) * (y[i] - y_mean)\n",
    "        den += (x[i][j] - x_mean[j])**2\n",
    "    b.append(num / den)\n",
    "\n",
    "b"
   ]
  },
  
  {
   "cell_type": "code",
   "execution_count": 182,
   "id": "6ddbcb2a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-4482494.113759189"
      ]
     },
     "execution_count": 182,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# y = b0 + b1x1 + b2x2 + b3x3 + ...\n",
    "# finding b0\n",
    "\n",
    "b0 = y_mean\n",
    "for i in range(4):\n",
    "    b0 -= b[i]*x_mean[i]\n",
    "b0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 210,
   "id": "42ce8d7f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[9234980,\n",
       " 14706656,\n",
       " 8572491,\n",
       " 8364821,\n",
       " 6401304,\n",
       " 8455475,\n",
       " 12604547,\n",
       " 15239350,\n",
       " 6715447,\n",
       " 8441811,\n",
       " 8142731,\n",
       " 9598418,\n",
       " 7925945,\n",
       " 6516922,\n",
       " 7574626,\n",
       " 5745300,\n",
       " 7949044,\n",
       " 9712242,\n",
       " 6096306,\n",
       " 6937100,\n",
       " 4040394,\n",
       " 6369535,\n",
       " 4856443,\n",
       " 6077827,\n",
       " 8036600,\n",
       " 7921325,\n",
       " 8557305,\n",
       " 5237573,\n",
       " 9501498,\n",
       " 7440871,\n",
       " 9238717,\n",
       " 7092721,\n",
       " 7154447,\n",
       " 8651151,\n",
       " 7062147,\n",
       " 9019279,\n",
       " 8334834,\n",
       " 10872017,\n",
       " 6630746,\n",
       " 9486093,\n",
       " 5070598,\n",
       " 8723615,\n",
       " 8779052,\n",
       " 9486093,\n",
       " 9486093,\n",
       " 7650188,\n",
       " 8557305,\n",
       " 6907931,\n",
       " 5957713,\n",
       " 6501198,\n",
       " 9222548,\n",
       " 6780887,\n",
       " 9486093,\n",
       " 8164626,\n",
       " 6743071,\n",
       " 4816512,\n",
       " 8258443,\n",
       " 10872017,\n",
       " 10262210,\n",
       " 8557305,\n",
       " 6743071,\n",
       " 4311094,\n",
       " 7782733,\n",
       " 8745287,\n",
       " 6300115,\n",
       " 8073558,\n",
       " 6306826,\n",
       " 6621311,\n",
       " 3909395,\n",
       " 10485286,\n",
       " 5819121,\n",
       " 9486093,\n",
       " 6178010,\n",
       " 7905701,\n",
       " 3911041,\n",
       " 6868022,\n",
       " 7844217,\n",
       " 7881175,\n",
       " 3770802,\n",
       " 7650188,\n",
       " 4816512,\n",
       " 5819121,\n",
       " 7914841,\n",
       " 8557305,\n",
       " 3781688,\n",
       " 8689631,\n",
       " 6033152,\n",
       " 2966966,\n",
       " 4560780,\n",
       " 11719101,\n",
       " 4354537,\n",
       " 3327088,\n",
       " 8002935,\n",
       " 6390324,\n",
       " 9486093,\n",
       " 6772435,\n",
       " 5295320,\n",
       " 4094185,\n",
       " 7927373,\n",
       " 6652417,\n",
       " 6113139,\n",
       " 5492641,\n",
       " 8326317,\n",
       " 7811879,\n",
       " 5604966,\n",
       " 5937783,\n",
       " 6510656,\n",
       " 5917658,\n",
       " 5377366,\n",
       " 7955973,\n",
       " 4186580,\n",
       " 6819433,\n",
       " 8744078,\n",
       " 5581744,\n",
       " 3350187,\n",
       " 4833345,\n",
       " 6251731,\n",
       " 4682758,\n",
       " 4103424,\n",
       " 4380609,\n",
       " 4158861,\n",
       " 5385203,\n",
       " 6882084,\n",
       " 8281666,\n",
       " 8799841,\n",
       " 8344354,\n",
       " 4445286,\n",
       " 7881175,\n",
       " 5492641,\n",
       " 8246012,\n",
       " 3355025,\n",
       " 7480074,\n",
       " 5354049,\n",
       " 5169259,\n",
       " 4371370,\n",
       " 8557305,\n",
       " 7394674,\n",
       " 5117014,\n",
       " 5261654,\n",
       " 4075706,\n",
       " 8464910,\n",
       " 7976762,\n",
       " 9750746,\n",
       " 8953394,\n",
       " 5144733,\n",
       " 6168771,\n",
       " 5059494,\n",
       " 6512083,\n",
       " 5889940,\n",
       " 7041927,\n",
       " 4417365,\n",
       " 5006140,\n",
       " 6396903,\n",
       " 7422297,\n",
       " 5657430,\n",
       " 5882151,\n",
       " 4325172,\n",
       " 6201393,\n",
       " 4824105,\n",
       " 4519325,\n",
       " 7656548,\n",
       " 5769826,\n",
       " 7949044,\n",
       " 4290524,\n",
       " 7071073,\n",
       " 6043842,\n",
       " 4740950,\n",
       " 4260401,\n",
       " 4941464,\n",
       " 7921325,\n",
       " 5604966,\n",
       " 5881566,\n",
       " 5925252,\n",
       " 6441359,\n",
       " 3800167,\n",
       " 9427363,\n",
       " 5073572,\n",
       " 3932494,\n",
       " 4410638,\n",
       " 5440301,\n",
       " 6071780,\n",
       " 5370882,\n",
       " 3619997,\n",
       " 4824105,\n",
       " 5357146,\n",
       " 3430587,\n",
       " 6387008,\n",
       " 3955592,\n",
       " 3758371,\n",
       " 1844149,\n",
       " 6484460,\n",
       " 6987794,\n",
       " 4186580,\n",
       " 2426237,\n",
       " 6829200,\n",
       " 8863878,\n",
       " 4688285,\n",
       " 5264751,\n",
       " 4792489,\n",
       " 3984957,\n",
       " 4132789,\n",
       " 3936450,\n",
       " 2112094,\n",
       " 5468115,\n",
       " 3341166,\n",
       " 4047987,\n",
       " 2888212,\n",
       " 3430587,\n",
       " 4323845,\n",
       " 4242017,\n",
       " 4190998,\n",
       " 7097022,\n",
       " 6479964,\n",
       " 6300457,\n",
       " 2218348,\n",
       " 4873595,\n",
       " 3927874,\n",
       " 5214734,\n",
       " 2433167,\n",
       " 5278487,\n",
       " 8529681,\n",
       " 6479964,\n",
       " 4443219,\n",
       " 4964806,\n",
       " 4939380,\n",
       " 3183876,\n",
       " 6247306,\n",
       " 2980607,\n",
       " 3721631,\n",
       " 9365921,\n",
       " 3610539,\n",
       " 3133277,\n",
       " 3774758,\n",
       " 3059361,\n",
       " 5763684,\n",
       " 4668680,\n",
       " 2441742,\n",
       " 4359157,\n",
       " 6983516,\n",
       " 3892562,\n",
       " 3818646,\n",
       " 2874571,\n",
       " 3726251,\n",
       " 3222698,\n",
       " 4502369,\n",
       " 4520848,\n",
       " 2763697,\n",
       " 8668273,\n",
       " 4029413,\n",
       " 7205264,\n",
       " 4573311,\n",
       " 3638476,\n",
       " 5692618,\n",
       " 2742026,\n",
       " 5056957,\n",
       " 2927480,\n",
       " 3892562,\n",
       " 4948838,\n",
       " 3911041,\n",
       " 3146918,\n",
       " 3505427,\n",
       " 3666194,\n",
       " 1941163,\n",
       " 3877779,\n",
       " 3379551,\n",
       " 3375150,\n",
       " 3391983,\n",
       " 4317579,\n",
       " 5260226,\n",
       " 3846365,\n",
       " 6957225,\n",
       " 4782301,\n",
       " 3020093,\n",
       " 4590363,\n",
       " 5953189,\n",
       " 2071440,\n",
       " 2241447,\n",
       " 4994817,\n",
       " 3615377,\n",
       " 3146918,\n",
       " 4054035,\n",
       " 2287644,\n",
       " 3049458,\n",
       " 4987661,\n",
       " 3798302,\n",
       " 5116795,\n",
       " 2425070,\n",
       " 4585524,\n",
       " 4373016,\n",
       " 2911311,\n",
       " 8032323,\n",
       " 3408874,\n",
       " 6169054,\n",
       " 2246067,\n",
       " 6747909,\n",
       " 3118754,\n",
       " 6096306,\n",
       " 5652810,\n",
       " 3817000,\n",
       " 4371370,\n",
       " 4836175,\n",
       " 3670814,\n",
       " 3942715,\n",
       " 3216433,\n",
       " 4948838,\n",
       " 3638476,\n",
       " 4280621,\n",
       " 3929520,\n",
       " 3913813,\n",
       " 5113318,\n",
       " 3902465,\n",
       " 3008325,\n",
       " 2800655,\n",
       " 5671289,\n",
       " 2982253,\n",
       " 2795817,\n",
       " 7625661,\n",
       " 6277400,\n",
       " 3142517,\n",
       " 5266492,\n",
       " 4040394,\n",
       " 5648190,\n",
       " 4662538,\n",
       " 3632210,\n",
       " 4123549,\n",
       " 4571884,\n",
       " 3960431,\n",
       " 5038260,\n",
       " 6050108,\n",
       " 3874083,\n",
       " 2986873,\n",
       " 6418042,\n",
       " 5514312,\n",
       " 3430587,\n",
       " 1728655,\n",
       " 1971654,\n",
       " 4870303,\n",
       " 4983829,\n",
       " 2862139,\n",
       " 6369090,\n",
       " 8277265,\n",
       " 3604396,\n",
       " 5348707,\n",
       " 2093615,\n",
       " 1987361,\n",
       " 2975542,\n",
       " 2121132,\n",
       " 3592278,\n",
       " 3590537,\n",
       " 4271381,\n",
       " 2695828,\n",
       " 1871867,\n",
       " 2902071,\n",
       " 4271180,\n",
       " 4089347,\n",
       " 4948838,\n",
       " 6085857,\n",
       " 6174937,\n",
       " 1816430,\n",
       " 2800655,\n",
       " 2075136,\n",
       " 3918634,\n",
       " 2079756,\n",
       " 1864475,\n",
       " 3486024,\n",
       " 2726521,\n",
       " 1885726,\n",
       " 1885726,\n",
       " 2814296,\n",
       " 1871867,\n",
       " 2186010,\n",
       " 3693913,\n",
       " 3513743,\n",
       " 2501799,\n",
       " 3761468,\n",
       " 4798033,\n",
       " 5879178,\n",
       " 5287850,\n",
       " 4002772,\n",
       " 2763697,\n",
       " 2287644,\n",
       " 2056657,\n",
       " 3499883,\n",
       " 6978896,\n",
       " 2287644,\n",
       " 1890346,\n",
       " 2916149,\n",
       " 4003436,\n",
       " 3730871,\n",
       " 5098535,\n",
       " 4957538,\n",
       " 3447218,\n",
       " 3887942,\n",
       " 4567247,\n",
       " 2745218,\n",
       " 6494136,\n",
       " 1890346,\n",
       " 2934409,\n",
       " 3486024,\n",
       " 3604273,\n",
       " 1831213,\n",
       " 6433424,\n",
       " 2925170,\n",
       " 7117349,\n",
       " 4308339,\n",
       " 2551189,\n",
       " 2666464,\n",
       " 3942715,\n",
       " 2056657,\n",
       " 1680147,\n",
       " 2916149,\n",
       " 3942715,\n",
       " 3250417,\n",
       " 4872072,\n",
       " 2075136,\n",
       " 4255212,\n",
       " 2731359,\n",
       " 1890346,\n",
       " 4590363,\n",
       " 6171963,\n",
       " 3019211,\n",
       " 2403138,\n",
       " 1927304,\n",
       " 2869951,\n",
       " 3476785,\n",
       " 1680147,\n",
       " 2384878,\n",
       " 3035599,\n",
       " 2075136,\n",
       " 5179381,\n",
       " 1363695,\n",
       " 4442531,\n",
       " 3937113,\n",
       " 4581123,\n",
       " 4725259,\n",
       " 2075136,\n",
       " 3035599,\n",
       " 3853958,\n",
       " 2287644,\n",
       " 2024319,\n",
       " 4655039,\n",
       " 4063493,\n",
       " 1448698,\n",
       " 3133277,\n",
       " 3486024,\n",
       " 873783,\n",
       " 3976748,\n",
       " 1825670,\n",
       " 2100545,\n",
       " 2806921,\n",
       " 3638476,\n",
       " 3327088,\n",
       " 6202436,\n",
       " 1626558,\n",
       " 4123549,\n",
       " 3676098,\n",
       " 2245361,\n",
       " 2523470,\n",
       " 3823266,\n",
       " 1825670,\n",
       " 3950754,\n",
       " 2500153,\n",
       " 3042528,\n",
       " 1636260,\n",
       " 3194761,\n",
       " 1964262,\n",
       " 3472165,\n",
       " 3541461,\n",
       " 1518456,\n",
       " 2333842,\n",
       " 3482530,\n",
       " 3777068,\n",
       " 4650419,\n",
       " 3927655,\n",
       " 4983965,\n",
       " 2501799,\n",
       " 4747216,\n",
       " 2500153,\n",
       " 3707772,\n",
       " 4664279,\n",
       " 3652335,\n",
       " 1456090,\n",
       " 3499883,\n",
       " 5100626,\n",
       " 1613161,\n",
       " 1885726,\n",
       " 2980607,\n",
       " 5468115,\n",
       " 6282837,\n",
       " 3569180,\n",
       " 4054253,\n",
       " 1428371,\n",
       " 3268896,\n",
       " 2966966,\n",
       " 3350187,\n",
       " 3892562,\n",
       " 2056657,\n",
       " 2026167,\n",
       " 2039824,\n",
       " 7574749,\n",
       " 2431075,\n",
       " 2260145,\n",
       " 1816430,\n",
       " 2985445,\n",
       " 1680147,\n",
       " 3892562,\n",
       " 1553104,\n",
       " 1871867,\n",
       " 2241447,\n",
       " 4705543,\n",
       " 2468033,\n",
       " 2606626,\n",
       " 2501799,\n",
       " 4077352,\n",
       " 3430587,\n",
       " 3527602,\n",
       " 1705556,\n",
       " 1594682,\n",
       " 1825670,\n",
       " 3351833,\n",
       " 3765964,\n",
       " 1888036,\n",
       " 3188050,\n",
       " 6187533,\n",
       " 1716643,\n",
       " 1890346,\n",
       " 1677838,\n",
       " 1056943,\n",
       " 1114010,\n",
       " 3878703,\n",
       " 2038397,\n",
       " 3586012,\n",
       " 1594682,\n",
       " 3153402,\n",
       " 4359375,\n",
       " 1760993,\n",
       " 5482193,\n",
       " 2830020,\n",
       " 1894504,\n",
       " 1590062,\n",
       " 1594682,\n",
       " 2246285,\n",
       " 1881107,\n",
       " 2481892,\n",
       " 3823266]"
      ]
     },
     "execution_count": 210,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions = []\n",
    "for i in range(n):\n",
    "    predictions.append(int(b0 + b[0]*x[i][0] + b[1]*x[i][1] + b[2]*x[i][2] + b[3]*x[i][3]))\n",
    "\n",
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 211,
   "id": "d1c40144",
   "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>Predictions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9234980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14706656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8572491</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8364821</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6401304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>1594682</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>2246285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>1881107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>543</th>\n",
       "      <td>2481892</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>544</th>\n",
       "      <td>3823266</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>545 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Predictions\n",
       "0        9234980\n",
       "1       14706656\n",
       "2        8572491\n",
       "3        8364821\n",
       "4        6401304\n",
       "..           ...\n",
       "540      1594682\n",
       "541      2246285\n",
       "542      1881107\n",
       "543      2481892\n",
       "544      3823266\n",
       "\n",
       "[545 rows x 1 columns]"
      ]
     },
     "execution_count": 211,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions = pd.DataFrame(predictions)\n",
    "predictions.rename(columns={0:'Predictions'},inplace=True)\n",
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 212,
   "id": "eb9a0533",
   "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>Predictions</th>\n",
       "      <th>Original</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9234980</td>\n",
       "      <td>13300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14706656</td>\n",
       "      <td>12250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8572491</td>\n",
       "      <td>12250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8364821</td>\n",
       "      <td>12215000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6401304</td>\n",
       "      <td>11410000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>1594682</td>\n",
       "      <td>1820000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>2246285</td>\n",
       "      <td>1767150</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>1881107</td>\n",
       "      <td>1750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>543</th>\n",
       "      <td>2481892</td>\n",
       "      <td>1750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>544</th>\n",
       "      <td>3823266</td>\n",
       "      <td>1750000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>545 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Predictions  Original\n",
       "0        9234980  13300000\n",
       "1       14706656  12250000\n",
       "2        8572491  12250000\n",
       "3        8364821  12215000\n",
       "4        6401304  11410000\n",
       "..           ...       ...\n",
       "540      1594682   1820000\n",
       "541      2246285   1767150\n",
       "542      1881107   1750000\n",
       "543      2481892   1750000\n",
       "544      3823266   1750000\n",
       "\n",
       "[545 rows x 2 columns]"
      ]
     },
     "execution_count": 212,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions['Original'] = y\n",
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "id": "c543c7ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions['Difference'] = predictions['Original'] - predictions['Predictions']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "b4c98048",
   "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>Predictions</th>\n",
       "      <th>Original</th>\n",
       "      <th>Difference</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9234980</td>\n",
       "      <td>13300000</td>\n",
       "      <td>4065020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>14706656</td>\n",
       "      <td>12250000</td>\n",
       "      <td>-2456656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8572491</td>\n",
       "      <td>12250000</td>\n",
       "      <td>3677509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8364821</td>\n",
       "      <td>12215000</td>\n",
       "      <td>3850179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6401304</td>\n",
       "      <td>11410000</td>\n",
       "      <td>5008696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>1594682</td>\n",
       "      <td>1820000</td>\n",
       "      <td>225318</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>2246285</td>\n",
       "      <td>1767150</td>\n",
       "      <td>-479135</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>1881107</td>\n",
       "      <td>1750000</td>\n",
       "      <td>-131107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>543</th>\n",
       "      <td>2481892</td>\n",
       "      <td>1750000</td>\n",
       "      <td>-731892</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>544</th>\n",
       "      <td>3823266</td>\n",
       "      <td>1750000</td>\n",
       "      <td>-2073266</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>545 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Predictions  Original  Difference\n",
       "0        9234980  13300000     4065020\n",
       "1       14706656  12250000    -2456656\n",
       "2        8572491  12250000     3677509\n",
       "3        8364821  12215000     3850179\n",
       "4        6401304  11410000     5008696\n",
       "..           ...       ...         ...\n",
       "540      1594682   1820000      225318\n",
       "541      2246285   1767150     -479135\n",
       "542      1881107   1750000     -131107\n",
       "543      2481892   1750000     -731892\n",
       "544      3823266   1750000    -2073266\n",
       "\n",
       "[545 rows x 3 columns]"
      ]
     },
     "execution_count": 217,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 219,
   "id": "e6ebd934",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<bound method DataFrame.info of         price  area  bedrooms  bathrooms  stories mainroad guestroom basement  \\\n",
       "0    13300000  7420         4          2        3      yes        no       no   \n",
       "1    12250000  8960         4          4        4      yes        no       no   \n",
       "2    12250000  9960         3          2        2      yes        no      yes   \n",
       "3    12215000  7500         4          2        2      yes        no      yes   \n",
       "4    11410000  7420         4          1        2      yes       yes      yes   \n",
       "..        ...   ...       ...        ...      ...      ...       ...      ...   \n",
       "540   1820000  3000         2          1        1      yes        no      yes   \n",
       "541   1767150  2400         3          1        1       no        no       no   \n",
       "542   1750000  3620         2          1        1      yes        no       no   \n",
       "543   1750000  2910         3          1        1       no        no       no   \n",
       "544   1750000  3850         3          1        2      yes        no       no   \n",
       "\n",
       "    hotwaterheating airconditioning  parking prefarea furnishingstatus  \n",
       "0                no             yes        2      yes        furnished  \n",
       "1                no             yes        3       no        furnished  \n",
       "2                no              no        2      yes   semi-furnished  \n",
       "3                no             yes        3      yes        furnished  \n",
       "4                no             yes        2       no        furnished  \n",
       "..              ...             ...      ...      ...              ...  \n",
       "540              no              no        2       no      unfurnished  \n",
       "541              no              no        0       no   semi-furnished  \n",
       "542              no              no        0       no      unfurnished  \n",
       "543              no              no        0       no        furnished  \n",
       "544              no              no        0       no      unfurnished  \n",
       "\n",
       "[545 rows x 13 columns]>"
      ]
     },
     "execution_count": 219,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "house.info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 220,
   "id": "55e943e9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x12ffcbca6d0>"
      ]
     },
     "execution_count": 220,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x1080 with 42 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(house)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8d8b6836",
   "metadata": {},
   "source": [
    "Only viable pair is  AREA <-> PRICE  which best fits linear regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 225,
   "id": "1a40cc94",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x12ffe5ecb80>"
      ]
     },
     "execution_count": 225,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(house['area'], house['price'], color = \"black\",marker = \"*\", s = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d88325c9",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}
Acerca de este algoritmo
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
house = pd.read_csv("Housing.csv")
house.isnull().sum()
price               0
area                0
bedrooms            0
bathrooms           0
stories             0
mainroad            0
guestroom           0
basement            0
hotwaterheating     0
airconditioning     0
parking             0
prefarea            0
furnishingstatus    0
dtype: int64
house.head(8)
price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea furnishingstatus
0 13300000 7420 4 2 3 yes no no no yes 2 yes furnished
1 12250000 8960 4 4 4 yes no no no yes 3 no furnished
2 12250000 9960 3 2 2 yes no yes no no 2 yes semi-furnished
3 12215000 7500 4 2 2 yes no yes no yes 3 yes furnished
4 11410000 7420 4 1 2 yes yes yes no yes 2 no furnished
5 10850000 7500 3 3 1 yes no yes no yes 2 yes semi-furnished
6 10150000 8580 4 3 4 yes no no no yes 2 yes semi-furnished
7 10150000 16200 5 3 2 yes no no no no 0 no unfurnished

Simple Regression

  • predict 'price' using 'area'
  • y = b0 + b1 * x
data = house[['price','area']]
data.head(4)
price area
0 13300000 7420
1 12250000 8960
2 12250000 9960
3 12215000 7500
y = house['price'].to_numpy()
x = house['area'].to_numpy()

x.shape
(545,)
plt.scatter(x, y, color = "b",marker = "*", s = 10)
&lt;matplotlib.collections.PathCollection at 0x12ffccee160&gt;
y_mean = np.mean(y)
x_mean = np.mean(x)

num = 0   # numerator
den = 0   # denominator

n = np.size(y)
for i in range(n):
    num += (x[i] - x_mean) * (y[i] - y_mean)
    den += (x[i] - x_mean)**2
    
b1 = num / den
b0 = y_mean - b1*x_mean

print(b0,b1)
2387308.482396433 461.9748942727828
prediction = b0 + b1*x
for i in range(n):
    prediction[i] = prediction[i]//1
plt.scatter(x, y, color = "r",marker = "o", s = 10)
plt.plot(x, prediction, color = "b")
[&lt;matplotlib.lines.Line2D at 0x12ffccc0c40&gt;]

Multiple regression

  • y = b0 + b1 * x1 + b2 * x2 + ...
house.head(5)
price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea furnishingstatus
0 13300000 7420 4 2 3 yes no no no yes 2 yes furnished
1 12250000 8960 4 4 4 yes no no no yes 3 no furnished
2 12250000 9960 3 2 2 yes no yes no no 2 yes semi-furnished
3 12215000 7500 4 2 2 yes no yes no yes 3 yes furnished
4 11410000 7420 4 1 2 yes yes yes no yes 2 no furnished
# dependent -&gt; price
y = house['price'].to_numpy()

# -&gt; independent variables
x = house[['area','bedrooms','bathrooms','stories']].to_numpy()

n = np.size(y)
x
array([[7420,    4,    2,    3],
       [8960,    4,    4,    4],
       [9960,    3,    2,    2],
       ...,
       [3620,    2,    1,    1],
       [2910,    3,    1,    1],
       [3850,    3,    1,    2]], dtype=int64)
y_mean = np.mean(y)
x_mean = [0,0,0,0]

for i in range(n):
    for j in range(4):
        x_mean[j] += x[i][j]

for i in range(4):
    x_mean[i] /= n

x_mean
[5150.54128440367, 2.9651376146788992, 1.2862385321100918, 1.8055045871559634]
b = []
for j in range(4):
    num = 0    # numerator
    den = 0    # denominator
    
    for i in range(n):
        num += (x[i][j] - x_mean[j]) * (y[i] - y_mean)
        den += (x[i][j] - x_mean[j])**2
    b.append(num / den)

b
[461.9748942727828, 928788.1189320377, 1926558.8901060484, 907116.9031974602]
# y = b0 + b1x1 + b2x2 + b3x3 + ...
# finding b0

b0 = y_mean
for i in range(4):
    b0 -= b[i]*x_mean[i]
b0
-4482494.113759189
predictions = []
for i in range(n):
    predictions.append(int(b0 + b[0]*x[i][0] + b[1]*x[i][1] + b[2]*x[i][2] + b[3]*x[i][3]))

predictions
[9234980,
 14706656,
 8572491,
 8364821,
 6401304,
 8455475,
 12604547,
 15239350,
 6715447,
 8441811,
 8142731,
 9598418,
 7925945,
 6516922,
 7574626,
 5745300,
 7949044,
 9712242,
 6096306,
 6937100,
 4040394,
 6369535,
 4856443,
 6077827,
 8036600,
 7921325,
 8557305,
 5237573,
 9501498,
 7440871,
 9238717,
 7092721,
 7154447,
 8651151,
 7062147,
 9019279,
 8334834,
 10872017,
 6630746,
 9486093,
 5070598,
 8723615,
 8779052,
 9486093,
 9486093,
 7650188,
 8557305,
 6907931,
 5957713,
 6501198,
 9222548,
 6780887,
 9486093,
 8164626,
 6743071,
 4816512,
 8258443,
 10872017,
 10262210,
 8557305,
 6743071,
 4311094,
 7782733,
 8745287,
 6300115,
 8073558,
 6306826,
 6621311,
 3909395,
 10485286,
 5819121,
 9486093,
 6178010,
 7905701,
 3911041,
 6868022,
 7844217,
 7881175,
 3770802,
 7650188,
 4816512,
 5819121,
 7914841,
 8557305,
 3781688,
 8689631,
 6033152,
 2966966,
 4560780,
 11719101,
 4354537,
 3327088,
 8002935,
 6390324,
 9486093,
 6772435,
 5295320,
 4094185,
 7927373,
 6652417,
 6113139,
 5492641,
 8326317,
 7811879,
 5604966,
 5937783,
 6510656,
 5917658,
 5377366,
 7955973,
 4186580,
 6819433,
 8744078,
 5581744,
 3350187,
 4833345,
 6251731,
 4682758,
 4103424,
 4380609,
 4158861,
 5385203,
 6882084,
 8281666,
 8799841,
 8344354,
 4445286,
 7881175,
 5492641,
 8246012,
 3355025,
 7480074,
 5354049,
 5169259,
 4371370,
 8557305,
 7394674,
 5117014,
 5261654,
 4075706,
 8464910,
 7976762,
 9750746,
 8953394,
 5144733,
 6168771,
 5059494,
 6512083,
 5889940,
 7041927,
 4417365,
 5006140,
 6396903,
 7422297,
 5657430,
 5882151,
 4325172,
 6201393,
 4824105,
 4519325,
 7656548,
 5769826,
 7949044,
 4290524,
 7071073,
 6043842,
 4740950,
 4260401,
 4941464,
 7921325,
 5604966,
 5881566,
 5925252,
 6441359,
 3800167,
 9427363,
 5073572,
 3932494,
 4410638,
 5440301,
 6071780,
 5370882,
 3619997,
 4824105,
 5357146,
 3430587,
 6387008,
 3955592,
 3758371,
 1844149,
 6484460,
 6987794,
 4186580,
 2426237,
 6829200,
 8863878,
 4688285,
 5264751,
 4792489,
 3984957,
 4132789,
 3936450,
 2112094,
 5468115,
 3341166,
 4047987,
 2888212,
 3430587,
 4323845,
 4242017,
 4190998,
 7097022,
 6479964,
 6300457,
 2218348,
 4873595,
 3927874,
 5214734,
 2433167,
 5278487,
 8529681,
 6479964,
 4443219,
 4964806,
 4939380,
 3183876,
 6247306,
 2980607,
 3721631,
 9365921,
 3610539,
 3133277,
 3774758,
 3059361,
 5763684,
 4668680,
 2441742,
 4359157,
 6983516,
 3892562,
 3818646,
 2874571,
 3726251,
 3222698,
 4502369,
 4520848,
 2763697,
 8668273,
 4029413,
 7205264,
 4573311,
 3638476,
 5692618,
 2742026,
 5056957,
 2927480,
 3892562,
 4948838,
 3911041,
 3146918,
 3505427,
 3666194,
 1941163,
 3877779,
 3379551,
 3375150,
 3391983,
 4317579,
 5260226,
 3846365,
 6957225,
 4782301,
 3020093,
 4590363,
 5953189,
 2071440,
 2241447,
 4994817,
 3615377,
 3146918,
 4054035,
 2287644,
 3049458,
 4987661,
 3798302,
 5116795,
 2425070,
 4585524,
 4373016,
 2911311,
 8032323,
 3408874,
 6169054,
 2246067,
 6747909,
 3118754,
 6096306,
 5652810,
 3817000,
 4371370,
 4836175,
 3670814,
 3942715,
 3216433,
 4948838,
 3638476,
 4280621,
 3929520,
 3913813,
 5113318,
 3902465,
 3008325,
 2800655,
 5671289,
 2982253,
 2795817,
 7625661,
 6277400,
 3142517,
 5266492,
 4040394,
 5648190,
 4662538,
 3632210,
 4123549,
 4571884,
 3960431,
 5038260,
 6050108,
 3874083,
 2986873,
 6418042,
 5514312,
 3430587,
 1728655,
 1971654,
 4870303,
 4983829,
 2862139,
 6369090,
 8277265,
 3604396,
 5348707,
 2093615,
 1987361,
 2975542,
 2121132,
 3592278,
 3590537,
 4271381,
 2695828,
 1871867,
 2902071,
 4271180,
 4089347,
 4948838,
 6085857,
 6174937,
 1816430,
 2800655,
 2075136,
 3918634,
 2079756,
 1864475,
 3486024,
 2726521,
 1885726,
 1885726,
 2814296,
 1871867,
 2186010,
 3693913,
 3513743,
 2501799,
 3761468,
 4798033,
 5879178,
 5287850,
 4002772,
 2763697,
 2287644,
 2056657,
 3499883,
 6978896,
 2287644,
 1890346,
 2916149,
 4003436,
 3730871,
 5098535,
 4957538,
 3447218,
 3887942,
 4567247,
 2745218,
 6494136,
 1890346,
 2934409,
 3486024,
 3604273,
 1831213,
 6433424,
 2925170,
 7117349,
 4308339,
 2551189,
 2666464,
 3942715,
 2056657,
 1680147,
 2916149,
 3942715,
 3250417,
 4872072,
 2075136,
 4255212,
 2731359,
 1890346,
 4590363,
 6171963,
 3019211,
 2403138,
 1927304,
 2869951,
 3476785,
 1680147,
 2384878,
 3035599,
 2075136,
 5179381,
 1363695,
 4442531,
 3937113,
 4581123,
 4725259,
 2075136,
 3035599,
 3853958,
 2287644,
 2024319,
 4655039,
 4063493,
 1448698,
 3133277,
 3486024,
 873783,
 3976748,
 1825670,
 2100545,
 2806921,
 3638476,
 3327088,
 6202436,
 1626558,
 4123549,
 3676098,
 2245361,
 2523470,
 3823266,
 1825670,
 3950754,
 2500153,
 3042528,
 1636260,
 3194761,
 1964262,
 3472165,
 3541461,
 1518456,
 2333842,
 3482530,
 3777068,
 4650419,
 3927655,
 4983965,
 2501799,
 4747216,
 2500153,
 3707772,
 4664279,
 3652335,
 1456090,
 3499883,
 5100626,
 1613161,
 1885726,
 2980607,
 5468115,
 6282837,
 3569180,
 4054253,
 1428371,
 3268896,
 2966966,
 3350187,
 3892562,
 2056657,
 2026167,
 2039824,
 7574749,
 2431075,
 2260145,
 1816430,
 2985445,
 1680147,
 3892562,
 1553104,
 1871867,
 2241447,
 4705543,
 2468033,
 2606626,
 2501799,
 4077352,
 3430587,
 3527602,
 1705556,
 1594682,
 1825670,
 3351833,
 3765964,
 1888036,
 3188050,
 6187533,
 1716643,
 1890346,
 1677838,
 1056943,
 1114010,
 3878703,
 2038397,
 3586012,
 1594682,
 3153402,
 4359375,
 1760993,
 5482193,
 2830020,
 1894504,
 1590062,
 1594682,
 2246285,
 1881107,
 2481892,
 3823266]
predictions = pd.DataFrame(predictions)
predictions.rename(columns={0:'Predictions'},inplace=True)
predictions
Predictions
0 9234980
1 14706656
2 8572491
3 8364821
4 6401304
... ...
540 1594682
541 2246285
542 1881107
543 2481892
544 3823266

545 rows × 1 columns

predictions['Original'] = y
predictions
Predictions Original
0 9234980 13300000
1 14706656 12250000
2 8572491 12250000
3 8364821 12215000
4 6401304 11410000
... ... ...
540 1594682 1820000
541 2246285 1767150
542 1881107 1750000
543 2481892 1750000
544 3823266 1750000

545 rows × 2 columns

predictions['Difference'] = predictions['Original'] - predictions['Predictions']
predictions
Predictions Original Difference
0 9234980 13300000 4065020
1 14706656 12250000 -2456656
2 8572491 12250000 3677509
3 8364821 12215000 3850179
4 6401304 11410000 5008696
... ... ... ...
540 1594682 1820000 225318
541 2246285 1767150 -479135
542 1881107 1750000 -131107
543 2481892 1750000 -731892
544 3823266 1750000 -2073266

545 rows × 3 columns

house.info
&lt;bound method DataFrame.info of         price  area  bedrooms  bathrooms  stories mainroad guestroom basement  \
0    13300000  7420         4          2        3      yes        no       no   
1    12250000  8960         4          4        4      yes        no       no   
2    12250000  9960         3          2        2      yes        no      yes   
3    12215000  7500         4          2        2      yes        no      yes   
4    11410000  7420         4          1        2      yes       yes      yes   
..        ...   ...       ...        ...      ...      ...       ...      ...   
540   1820000  3000         2          1        1      yes        no      yes   
541   1767150  2400         3          1        1       no        no       no   
542   1750000  3620         2          1        1      yes        no       no   
543   1750000  2910         3          1        1       no        no       no   
544   1750000  3850         3          1        2      yes        no       no   

    hotwaterheating airconditioning  parking prefarea furnishingstatus  
0                no             yes        2      yes        furnished  
1                no             yes        3       no        furnished  
2                no              no        2      yes   semi-furnished  
3                no             yes        3      yes        furnished  
4                no             yes        2       no        furnished  
..              ...             ...      ...      ...              ...  
540              no              no        2       no      unfurnished  
541              no              no        0       no   semi-furnished  
542              no              no        0       no      unfurnished  
543              no              no        0       no        furnished  
544              no              no        0       no      unfurnished  

[545 rows x 13 columns]&gt;
sns.pairplot(house)
&lt;seaborn.axisgrid.PairGrid at 0x12ffcbca6d0&gt;

Only viable pair is AREA <-> PRICE which best fits linear regression

plt.scatter(house['area'], house['price'], color = "black",marker = "*", s = 10)
&lt;matplotlib.collections.PathCollection at 0x12ffe5ecb80&gt;