house_prices_for_learn_users.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# [Kaggle] Housing Prices Competition for Kaggle Learn Users\n",
    "\n",
    "This notebook is to perform a simple decision tree to predict house prices in Iowa\n",
    "\n",
    "**Author: Han-Elliot Phan<br>Email: hanelliotphan@gmail.com**\n",
    "\n",
    "*Start date: July 10, 2023<br>End date: July 10, 2023*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import libraries\n",
    "\n",
    "import pandas as pd\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import mean_absolute_error\n",
    "from sklearn.impute import SimpleImputer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import train and test data\n",
    "\n",
    "train_data = pd.read_csv(\"datasets/train.csv\", index_col='Id')\n",
    "test_data = pd.read_csv(\"datasets/test.csv\", index_col='Id')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove rows with missing target, separate target from predictors\n",
    "\n",
    "train_data.dropna(axis=0, subset=['SalePrice'], inplace=True)\n",
    "y = train_data.SalePrice\n",
    "train_data.drop(['SalePrice'], axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select numerical predictors\n",
    "\n",
    "X = train_data.select_dtypes(exclude=['object'])\n",
    "X_test = test_data.select_dtypes(exclude=['object'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split train and test data\n",
    "\n",
    "X_train, X_valid, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<bound method NDFrame.head of       MSSubClass  LotFrontage  LotArea  OverallQual  OverallCond  YearBuilt  \\\n",
      "Id                                                                            \n",
      "619           20         90.0    11694            9            5       2007   \n",
      "871           20         60.0     6600            5            5       1962   \n",
      "93            30         80.0    13360            5            7       1921   \n",
      "818           20          NaN    13265            8            5       2002   \n",
      "303           20        118.0    13704            7            5       2001   \n",
      "...          ...          ...      ...          ...          ...        ...   \n",
      "764           60         82.0     9430            8            5       1999   \n",
      "836           20         60.0     9600            4            7       1950   \n",
      "1217          90         68.0     8930            6            5       1978   \n",
      "560          120          NaN     3196            7            5       2003   \n",
      "685           60         58.0    16770            7            5       1998   \n",
      "\n",
      "      YearRemodAdd  MasVnrArea  BsmtFinSF1  BsmtFinSF2  ...  GarageArea  \\\n",
      "Id                                                      ...               \n",
      "619           2007       452.0          48           0  ...         774   \n",
      "871           1962         0.0           0           0  ...         308   \n",
      "93            2006         0.0         713           0  ...         432   \n",
      "818           2002       148.0        1218           0  ...         857   \n",
      "303           2002       150.0           0           0  ...         843   \n",
      "...            ...         ...         ...         ...  ...         ...   \n",
      "764           1999       673.0        1163           0  ...         856   \n",
      "836           1995         0.0         442           0  ...         436   \n",
      "1217          1978         0.0           0           0  ...         539   \n",
      "560           2004        18.0           0           0  ...         420   \n",
      "685           1998        30.0           0           0  ...         486   \n",
      "\n",
      "      WoodDeckSF  OpenPorchSF  EnclosedPorch  3SsnPorch  ScreenPorch  \\\n",
      "Id                                                                     \n",
      "619            0          108              0          0          260   \n",
      "871            0            0              0          0            0   \n",
      "93             0            0             44          0            0   \n",
      "818          150           59              0          0            0   \n",
      "303          468           81              0          0            0   \n",
      "...          ...          ...            ...        ...          ...   \n",
      "764            0          128              0          0          180   \n",
      "836          290            0              0          0            0   \n",
      "1217           0            0              0          0            0   \n",
      "560          143           20              0          0            0   \n",
      "685            0           81              0          0            0   \n",
      "\n",
      "      PoolArea  MiscVal  MoSold  YrSold  \n",
      "Id                                       \n",
      "619          0        0       7    2007  \n",
      "871          0        0       8    2009  \n",
      "93           0        0       8    2009  \n",
      "818          0        0       7    2008  \n",
      "303          0        0       1    2006  \n",
      "...        ...      ...     ...     ...  \n",
      "764          0        0       7    2009  \n",
      "836          0        0       2    2010  \n",
      "1217         0        0       4    2010  \n",
      "560          0        0      10    2006  \n",
      "685          0        0       6    2010  \n",
      "\n",
      "[1168 rows x 36 columns]>\n",
      "(1168, 36)\n"
     ]
    }
   ],
   "source": [
    "# Display train data\n",
    "\n",
    "print(X_train.head)\n",
    "print(X_train.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LotFrontage    212\n",
      "MasVnrArea       6\n",
      "GarageYrBlt     58\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Check the number of missing values in each column of training data (if any)\n",
    "\n",
    "missing_val_count_by_column = (X_train.isnull().sum())\n",
    "print(missing_val_count_by_column[missing_val_count_by_column > 0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Since the data has missing values, perform imputation towards the train and test data\n",
    "\n",
    "final_imputer = SimpleImputer(strategy='constant', fill_value=0)\n",
    "final_X_train = pd.DataFrame(final_imputer.fit_transform(X_train))\n",
    "final_X_valid = pd.DataFrame(final_imputer.fit_transform(X_valid))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Develop data imputation\n",
    "\n",
    "imputer = SimpleImputer(strategy='constant', fill_value=0.0)\n",
    "final_X_train = pd.DataFrame(imputer.fit_transform(X_train))\n",
    "final_X_valid = pd.DataFrame(imputer.fit_transform(X_valid))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#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>RandomForestRegressor(random_state=0)</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\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(random_state=0)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestRegressor(random_state=0)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Define and fit the model\n",
    "\n",
    "model = RandomForestRegressor(n_estimators=100, random_state=0)\n",
    "model.fit(final_X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE (Your approach):\n",
      "18017.665970319635\n"
     ]
    }
   ],
   "source": [
    "# Get validation predictions and MAE\n",
    "\n",
    "preds_valid = model.predict(final_X_valid)\n",
    "print(\"MAE (Your approach):\")\n",
    "print(mean_absolute_error(y_valid, preds_valid))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Preprocess test data and get test predictions\n",
    "\n",
    "final_X_test = pd.DataFrame(final_imputer.transform(X_test))\n",
    "preds_test = model.predict(final_X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        Id  SalePrice\n",
      "0     1461  127436.50\n",
      "1     1462  159961.25\n",
      "2     1463  178998.25\n",
      "3     1464  184179.00\n",
      "4     1465  197855.00\n",
      "...    ...        ...\n",
      "1454  2915   85155.00\n",
      "1455  2916   87293.50\n",
      "1456  2917  155623.87\n",
      "1457  2918  106376.75\n",
      "1458  2919  230180.90\n",
      "\n",
      "[1459 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "# Get prediction results in dataframe\n",
    "\n",
    "result = pd.DataFrame({'Id': X_test.index, 'SalePrice': preds_test})\n",
    "print(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create submission file\n",
    "\n",
    "result.to_csv('datasets/submission.csv', 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": "3.9.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}