{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6d3aac89-1910-4040-86b4-990f540e1657",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "cbea3a9b-aa44-45a9-9a5a-1f2804b343bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('Housing.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6a9d3b25-5a99-4205-8538-36735d63ab53",
   "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "93f8c2ae-24e8-4984-9e04-af1dd2ff478b",
   "metadata": {},
   "outputs": [],
   "source": [
    "missing_percentage = df.isnull().mean() * 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4dfb4ff9-1add-43c8-a9c3-d3ffd59d8690",
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_with_missing_30 = missing_percentage[missing_percentage > 30]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "93913f36-1c07-45b5-b1f4-4c139128e14f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Columns with more than 30% missing values:\n"
     ]
    }
   ],
   "source": [
    "print(\"Columns with more than 30% missing values:\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a8a462ff-0c49-4091-befd-5f9c7a7d57cc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Series([], dtype: float64)\n"
     ]
    }
   ],
   "source": [
    "print(columns_with_missing_30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "968b65e7-e711-470b-a26c-097c032aeeb2",
   "metadata": {},
   "outputs": [],
   "source": [
    "missing_percentage = df.isnull().mean() * 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e490392d-3da2-4ce7-8e7b-e0649209c177",
   "metadata": {},
   "outputs": [],
   "source": [
    "threshold = 30"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "cad62c69-8ce0-41ed-b403-719f6f052b3b",
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_to_drop = missing_percentage[missing_percentage > threshold].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4ad45dff-ed10-4b61-9bf7-48585f2e26a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_cleaned = df.drop(columns=columns_to_drop)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "bc06ccc6-8c40-4bf2-9c7e-0f8f62f7924e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Columns dropped: []\n",
      "Remaining columns: Index(['price', 'area', 'bedrooms', 'bathrooms', 'stories', 'mainroad',\n",
      "       'guestroom', 'basement', 'hotwaterheating', 'airconditioning',\n",
      "       'parking', 'prefarea', 'furnishingstatus'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(f\"Columns dropped: {list(columns_to_drop)}\")\n",
    "print(f\"Remaining columns: {df_cleaned.columns}\")"
   ]
  },
  {
   "cell_type": "raw",
   "id": "3c3d397f-8a06-4c5f-be24-cb14cd2573f7",
   "metadata": {},
   "source": [
    "data=df.copy()\n",
    "def replace_outliers_with_nan(column):\n",
    "Q1 = column.quantile(0.25)\n",
    "Q3 = column.quantile(0.75)\n",
    "IQR = Q3 - Q1\n",
    "lower_bound = Q1 - 1.5 * IQR\n",
    "upper_bound = Q3 + 1.5 * IQR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0e6f6928-66a9-4fc2-8c91-2cf96d723240",
   "metadata": {},
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "'return' outside function (624706388.py, line 1)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;36m  Cell \u001b[1;32mIn[1], line 1\u001b[1;36m\u001b[0m\n\u001b[1;33m    return column.where((column >= lower_bound) & (column <= upper_bound), np.nan)\u001b[0m\n\u001b[1;37m    ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m 'return' outside function\n"
     ]
    }
   ],
   "source": [
    "return column.where((column >= lower_bound) & (column <= upper_bound), np.nan)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "63a938e6-1fb6-4246-98e2-4e572117e675",
   "metadata": {},
   "outputs": [
    {
     "ename": "IndentationError",
     "evalue": "expected an indented block after 'for' statement on line 1 (900843858.py, line 2)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;36m  Cell \u001b[1;32mIn[2], line 2\u001b[1;36m\u001b[0m\n\u001b[1;33m    data[col] = replace_outliers_with_nan(data[col])\u001b[0m\n\u001b[1;37m    ^\u001b[0m\n\u001b[1;31mIndentationError\u001b[0m\u001b[1;31m:\u001b[0m expected an indented block after 'for' statement on line 1\n"
     ]
    }
   ],
   "source": [
    "for col in data.columns:\n",
    "data[col] = replace_outliers_with_nan(data[col])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "caf7da97-3af7-4b2a-9c35-db1e765c3c59",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'data' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[3], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m null_counts \u001b[38;5;241m=\u001b[39m data\u001b[38;5;241m.\u001b[39misnull()\u001b[38;5;241m.\u001b[39msum()\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSum of null values in each column:\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(null_counts)\n",
      "\u001b[1;31mNameError\u001b[0m: name 'data' is not defined"
     ]
    }
   ],
   "source": [
    "null_counts = data.isnull().sum()\n",
    "print(\"Sum of null values in each column:\")\n",
    "print(null_counts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "24fd8b2f-c28c-409d-b9d4-4ac845725afa",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "46596d49-7c6c-48e4-a748-3d4ab5ad8ff0",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c60767e1-9aa5-421c-a333-b5caa7e2d4ce",
   "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": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('Housing.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "de63c10d-6e29-4881-9c9c-b53dadc4265c",
   "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>parking</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5.450000e+02</td>\n",
       "      <td>545.000000</td>\n",
       "      <td>545.000000</td>\n",
       "      <td>545.000000</td>\n",
       "      <td>545.000000</td>\n",
       "      <td>545.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.766729e+06</td>\n",
       "      <td>5150.541284</td>\n",
       "      <td>2.965138</td>\n",
       "      <td>1.286239</td>\n",
       "      <td>1.805505</td>\n",
       "      <td>0.693578</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.870440e+06</td>\n",
       "      <td>2170.141023</td>\n",
       "      <td>0.738064</td>\n",
       "      <td>0.502470</td>\n",
       "      <td>0.867492</td>\n",
       "      <td>0.861586</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.750000e+06</td>\n",
       "      <td>1650.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>3.430000e+06</td>\n",
       "      <td>3600.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.340000e+06</td>\n",
       "      <td>4600.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>5.740000e+06</td>\n",
       "      <td>6360.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.330000e+07</td>\n",
       "      <td>16200.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price          area    bedrooms   bathrooms     stories  \\\n",
       "count  5.450000e+02    545.000000  545.000000  545.000000  545.000000   \n",
       "mean   4.766729e+06   5150.541284    2.965138    1.286239    1.805505   \n",
       "std    1.870440e+06   2170.141023    0.738064    0.502470    0.867492   \n",
       "min    1.750000e+06   1650.000000    1.000000    1.000000    1.000000   \n",
       "25%    3.430000e+06   3600.000000    2.000000    1.000000    1.000000   \n",
       "50%    4.340000e+06   4600.000000    3.000000    1.000000    2.000000   \n",
       "75%    5.740000e+06   6360.000000    3.000000    2.000000    2.000000   \n",
       "max    1.330000e+07  16200.000000    6.000000    4.000000    4.000000   \n",
       "\n",
       "          parking  \n",
       "count  545.000000  \n",
       "mean     0.693578  \n",
       "std      0.861586  \n",
       "min      0.000000  \n",
       "25%      0.000000  \n",
       "50%      0.000000  \n",
       "75%      1.000000  \n",
       "max      3.000000  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "397c351f-f7ca-412e-8fba-c00957407e46",
   "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": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}