preprocessing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#importing libraries\n",
    "import pandas as pd\n",
    "from datetime import datetime"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "#loads the dataset from a csv file\n",
    "file_data = pd.read_csv('housing_price_dataset.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   SquareFeet  Bedrooms  Bathrooms Neighborhood  YearBuilt          Price  Age\n",
      "0        2126         4          1        Rural       1969  215355.283618   54\n",
      "1        2459         3          2        Rural       1980  195014.221626   43\n",
      "2        1860         2          1       Suburb       1970  306891.012076   53\n",
      "3        2294         2          1        Urban       1996  206786.787153   27\n",
      "4        2130         5          2       Suburb       2001  272436.239065   22\n"
     ]
    }
   ],
   "source": [
    "#gets a snippet from the top of the dataset\n",
    "file_data.head()\n",
    "print(file_data.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(50000, 7)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#gets the shape of the dataset\n",
    "file_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<bound method DataFrame.info of        SquareFeet  Bedrooms  Bathrooms Neighborhood  YearBuilt          Price  \\\n",
       "0            2126         4          1        Rural       1969  215355.283618   \n",
       "1            2459         3          2        Rural       1980  195014.221626   \n",
       "2            1860         2          1       Suburb       1970  306891.012076   \n",
       "3            2294         2          1        Urban       1996  206786.787153   \n",
       "4            2130         5          2       Suburb       2001  272436.239065   \n",
       "...           ...       ...        ...          ...        ...            ...   \n",
       "49995        1282         5          3        Rural       1975  100080.865895   \n",
       "49996        2854         2          2       Suburb       1988  374507.656727   \n",
       "49997        2979         5          3       Suburb       1962  384110.555590   \n",
       "49998        2596         5          2        Rural       1984  380512.685957   \n",
       "49999        1572         5          3        Rural       2011  221618.583218   \n",
       "\n",
       "       Age  \n",
       "0       54  \n",
       "1       43  \n",
       "2       53  \n",
       "3       27  \n",
       "4       22  \n",
       "...    ...  \n",
       "49995   48  \n",
       "49996   35  \n",
       "49997   61  \n",
       "49998   39  \n",
       "49999   12  \n",
       "\n",
       "[50000 rows x 7 columns]>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#get information about the dataset\n",
    "file_data.info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SquareFeet      False\n",
       "Bedrooms        False\n",
       "Bathrooms       False\n",
       "Neighborhood    False\n",
       "YearBuilt       False\n",
       "Price           False\n",
       "Age             False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#finds if any of the values are null\n",
    "file_data.isnull().any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SquareFeet       2000\n",
       "Bedrooms            4\n",
       "Bathrooms           3\n",
       "Neighborhood        3\n",
       "YearBuilt          72\n",
       "Price           50000\n",
       "Age                72\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#finds the number of unique values per column\n",
    "file_data.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "#convert 'YearBuilt' to age\n",
    "current_year = int(datetime.now().strftime(\"%Y\"))\n",
    "file_data['Age'] = current_year - file_data['YearBuilt']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#exports processed data to new csv file\n",
    "processed_file_path = 'processed_data.csv'\n",
    "file_data.to_csv(processed_file_path, index=False)"
   ]
  }
 ],
 "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}