.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Linear Regression R²: 0.5517193889089222\n",
      "Random Forest R²: 0.5343406907435422\n",
      "Best model saved as 'best_model.pkl'\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "import pickle\n",
    "\n",
    "\n",
    "df = pd.read_csv(r'/teamspace/studios/this_studio/house_data.csv')\n",
    "\n",
    "\n",
    "columns = ['bedrooms', 'bathrooms', 'floors', 'yr_built', 'sqft_living', 'price']\n",
    "df = df[columns]\n",
    "\n",
    "\n",
    "X = df.iloc[:, 0:5]\n",
    "\n",
    "y = df.iloc[:, 5]\n",
    "\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)\n",
    "\n",
    "\n",
    "lr = LinearRegression()\n",
    "rf = RandomForestRegressor(random_state=42)\n",
    "\n",
    "\n",
    "lr.fit(X_train, y_train)\n",
    "rf.fit(X_train, y_train)\n",
    "\n",
    "\n",
    "lr_score = lr.score(X_test, y_test)\n",
    "rf_score = rf.score(X_test, y_test)\n",
    "\n",
    "print(\"Linear Regression R²:\", lr_score)\n",
    "print(\"Random Forest R²:\", rf_score)\n",
    "\n",
    "best_model = lr if lr_score >= rf_score else rf\n",
    "\n",
    "\n",
    "with open('best_model.pkl', 'wb') as file:\n",
    "    pickle.dump(best_model, file)\n",
    "\n",
    "print(\"Best model saved as 'best_model.pkl'\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}