10. Decision Tree and Random Forest Regressor.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>bath</th>\n",
       "      <th>balcony</th>\n",
       "      <th>price</th>\n",
       "      <th>total_sqft_int</th>\n",
       "      <th>bhk</th>\n",
       "      <th>price_per_sqft</th>\n",
       "      <th>area_typeSuper built-up  Area</th>\n",
       "      <th>area_typeBuilt-up  Area</th>\n",
       "      <th>area_typePlot  Area</th>\n",
       "      <th>availability_Ready To Move</th>\n",
       "      <th>...</th>\n",
       "      <th>location_Kalena Agrahara</th>\n",
       "      <th>location_Horamavu Agara</th>\n",
       "      <th>location_Vidyaranyapura</th>\n",
       "      <th>location_BTM 2nd Stage</th>\n",
       "      <th>location_Hebbal Kempapura</th>\n",
       "      <th>location_Hosur Road</th>\n",
       "      <th>location_Horamavu Banaswadi</th>\n",
       "      <th>location_Domlur</th>\n",
       "      <th>location_Mahadevpura</th>\n",
       "      <th>location_Tumkur Road</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>2.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>1672.0</td>\n",
       "      <td>3</td>\n",
       "      <td>8971.291866</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>149.0</td>\n",
       "      <td>1750.0</td>\n",
       "      <td>3</td>\n",
       "      <td>8514.285714</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>2.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>1750.0</td>\n",
       "      <td>3</td>\n",
       "      <td>8571.428571</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>1250.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3200.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>1200.0</td>\n",
       "      <td>2</td>\n",
       "      <td>6916.666667</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 108 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   bath  balcony  price  total_sqft_int  bhk  price_per_sqft  \\\n",
       "0     3      2.0  150.0          1672.0    3     8971.291866   \n",
       "1     3      3.0  149.0          1750.0    3     8514.285714   \n",
       "2     3      2.0  150.0          1750.0    3     8571.428571   \n",
       "3     2      2.0   40.0          1250.0    2     3200.000000   \n",
       "4     2      2.0   83.0          1200.0    2     6916.666667   \n",
       "\n",
       "   area_typeSuper built-up  Area  area_typeBuilt-up  Area  \\\n",
       "0                              1                        0   \n",
       "1                              0                        1   \n",
       "2                              1                        0   \n",
       "3                              1                        0   \n",
       "4                              0                        0   \n",
       "\n",
       "   area_typePlot  Area  availability_Ready To Move  ...  \\\n",
       "0                    0                           1  ...   \n",
       "1                    0                           1  ...   \n",
       "2                    0                           1  ...   \n",
       "3                    0                           1  ...   \n",
       "4                    1                           1  ...   \n",
       "\n",
       "   location_Kalena Agrahara  location_Horamavu Agara  location_Vidyaranyapura  \\\n",
       "0                         0                        0                        0   \n",
       "1                         0                        0                        0   \n",
       "2                         0                        0                        0   \n",
       "3                         0                        0                        0   \n",
       "4                         0                        0                        0   \n",
       "\n",
       "   location_BTM 2nd Stage  location_Hebbal Kempapura  location_Hosur Road  \\\n",
       "0                       0                          0                    0   \n",
       "1                       0                          0                    0   \n",
       "2                       0                          0                    0   \n",
       "3                       0                          0                    0   \n",
       "4                       0                          0                    0   \n",
       "\n",
       "   location_Horamavu Banaswadi  location_Domlur  location_Mahadevpura  \\\n",
       "0                            0                0                     0   \n",
       "1                            0                0                     0   \n",
       "2                            0                0                     0   \n",
       "3                            0                0                     0   \n",
       "4                            0                0                     0   \n",
       "\n",
       "   location_Tumkur Road  \n",
       "0                     0  \n",
       "1                     0  \n",
       "2                     0  \n",
       "3                     0  \n",
       "4                     0  \n",
       "\n",
       "[5 rows x 108 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df=pd.read_csv('/Users/sudhanshukumar/Documents/Machine Learning/0 csv files/bangalore.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Random forest and Decision tree are of 2 types :\n",
    "\n",
    "**1.) Classifier: \n",
    "    Random forest Classifier and Decision tree Classifier\n",
    "   2.) Regression: \n",
    "      Random forest Regression and Decision tree Regression**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7120, 108)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df.drop('price',axis=1)\n",
    "y=df.price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeRegressor(ccp_alpha=0.0, criterion='mse', max_depth=None,\n",
       "                      max_features=None, max_leaf_nodes=None,\n",
       "                      min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                      min_samples_leaf=1, min_samples_split=2,\n",
       "                      min_weight_fraction_leaf=0.0, presort='deprecated',\n",
       "                      random_state=None, splitter='best')"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "DT_Model=DecisionTreeRegressor(criterion='mse')\n",
    "DT_Model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8941826314492822"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "DT_Model.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, ccp_alpha=0.0, criterion='mse',\n",
       "                      max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "                      max_samples=None, min_impurity_decrease=0.0,\n",
       "                      min_impurity_split=None, min_samples_leaf=1,\n",
       "                      min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "                      n_estimators=200, n_jobs=None, oob_score=False,\n",
       "                      random_state=None, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "RF_Model=RandomForestRegressor(criterion='mse',n_estimators=200)\n",
    "RF_Model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8829527034036628"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "RF_Model.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}