├── README.md
└── Pune house price prediction.ipynb


/README.md:
--------------------------------------------------------------------------------
1 | # Machine-Learning-Project- Pune House Price Prediction
2 | This repository consists House Prices Prediction in Pune. Datasets are provided in each of the folders above, and also the solution to the problem statements have been provided.
3 | 
4 | Please do ⭐ the repository, if it helped you in anyway.
5 | 


--------------------------------------------------------------------------------
/Pune house price prediction.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 244,
   6 |    "metadata": {},
   7 |    "outputs": [],
   8 |    "source": [
   9 |     "# Importing essential libraries\n",
  10 |     "import numpy as np\n",
  11 |     "import pandas as pd\n",
  12 |     "from matplotlib import pyplot as plt\n",
  13 |     "from matplotlib import rcParams as rcP\n",
  14 |     "%matplotlib inline"
  15 |    ]
  16 |   },
  17 |   {
  18 |    "cell_type": "code",
  19 |    "execution_count": 245,
  20 |    "metadata": {},
  21 |    "outputs": [
  22 |     {
  23 |      "data": {
  24 |       "text/html": [
  25 |        "<div>\n",
  26 |        "<style scoped>\n",
  27 |        "    .dataframe tbody tr th:only-of-type {\n",
  28 |        "        vertical-align: middle;\n",
  29 |        "    }\n",
  30 |        "\n",
  31 |        "    .dataframe tbody tr th {\n",
  32 |        "        vertical-align: top;\n",
  33 |        "    }\n",
  34 |        "\n",
  35 |        "    .dataframe thead th {\n",
  36 |        "        text-align: right;\n",
  37 |        "    }\n",
  38 |        "</style>\n",
  39 |        "<table border=\"1\" class=\"dataframe\">\n",
  40 |        "  <thead>\n",
  41 |        "    <tr style=\"text-align: right;\">\n",
  42 |        "      <th></th>\n",
  43 |        "      <th>area_type</th>\n",
  44 |        "      <th>availability</th>\n",
  45 |        "      <th>size</th>\n",
  46 |        "      <th>society</th>\n",
  47 |        "      <th>total_sqft</th>\n",
  48 |        "      <th>bath</th>\n",
  49 |        "      <th>balcony</th>\n",
  50 |        "      <th>price</th>\n",
  51 |        "      <th>site_location</th>\n",
  52 |        "    </tr>\n",
  53 |        "  </thead>\n",
  54 |        "  <tbody>\n",
  55 |        "    <tr>\n",
  56 |        "      <td>0</td>\n",
  57 |        "      <td>Super built-up  Area</td>\n",
  58 |        "      <td>19-Dec</td>\n",
  59 |        "      <td>2 BHK</td>\n",
  60 |        "      <td>Coomee</td>\n",
  61 |        "      <td>1056</td>\n",
  62 |        "      <td>2.0</td>\n",
  63 |        "      <td>1.0</td>\n",
  64 |        "      <td>39.07</td>\n",
  65 |        "      <td>Alandi Road</td>\n",
  66 |        "    </tr>\n",
  67 |        "    <tr>\n",
  68 |        "      <td>1</td>\n",
  69 |        "      <td>Plot  Area</td>\n",
  70 |        "      <td>Ready To Move</td>\n",
  71 |        "      <td>4 Bedroom</td>\n",
  72 |        "      <td>Theanmp</td>\n",
  73 |        "      <td>2600</td>\n",
  74 |        "      <td>5.0</td>\n",
  75 |        "      <td>3.0</td>\n",
  76 |        "      <td>120.00</td>\n",
  77 |        "      <td>Ambegaon Budruk</td>\n",
  78 |        "    </tr>\n",
  79 |        "    <tr>\n",
  80 |        "      <td>2</td>\n",
  81 |        "      <td>Built-up  Area</td>\n",
  82 |        "      <td>Ready To Move</td>\n",
  83 |        "      <td>3 BHK</td>\n",
  84 |        "      <td>NaN</td>\n",
  85 |        "      <td>1440</td>\n",
  86 |        "      <td>2.0</td>\n",
  87 |        "      <td>3.0</td>\n",
  88 |        "      <td>62.00</td>\n",
  89 |        "      <td>Anandnagar</td>\n",
  90 |        "    </tr>\n",
  91 |        "    <tr>\n",
  92 |        "      <td>3</td>\n",
  93 |        "      <td>Super built-up  Area</td>\n",
  94 |        "      <td>Ready To Move</td>\n",
  95 |        "      <td>3 BHK</td>\n",
  96 |        "      <td>Soiewre</td>\n",
  97 |        "      <td>1521</td>\n",
  98 |        "      <td>3.0</td>\n",
  99 |        "      <td>1.0</td>\n",
 100 |        "      <td>95.00</td>\n",
 101 |        "      <td>Aundh</td>\n",
 102 |        "    </tr>\n",
 103 |        "    <tr>\n",
 104 |        "      <td>4</td>\n",
 105 |        "      <td>Super built-up  Area</td>\n",
 106 |        "      <td>Ready To Move</td>\n",
 107 |        "      <td>2 BHK</td>\n",
 108 |        "      <td>NaN</td>\n",
 109 |        "      <td>1200</td>\n",
 110 |        "      <td>2.0</td>\n",
 111 |        "      <td>1.0</td>\n",
 112 |        "      <td>51.00</td>\n",
 113 |        "      <td>Aundh Road</td>\n",
 114 |        "    </tr>\n",
 115 |        "  </tbody>\n",
 116 |        "</table>\n",
 117 |        "</div>"
 118 |       ],
 119 |       "text/plain": [
 120 |        "              area_type   availability       size  society total_sqft  bath  \\\n",
 121 |        "0  Super built-up  Area         19-Dec      2 BHK  Coomee        1056   2.0   \n",
 122 |        "1            Plot  Area  Ready To Move  4 Bedroom  Theanmp       2600   5.0   \n",
 123 |        "2        Built-up  Area  Ready To Move      3 BHK      NaN       1440   2.0   \n",
 124 |        "3  Super built-up  Area  Ready To Move      3 BHK  Soiewre       1521   3.0   \n",
 125 |        "4  Super built-up  Area  Ready To Move      2 BHK      NaN       1200   2.0   \n",
 126 |        "\n",
 127 |        "   balcony   price    site_location  \n",
 128 |        "0      1.0   39.07      Alandi Road  \n",
 129 |        "1      3.0  120.00  Ambegaon Budruk  \n",
 130 |        "2      3.0   62.00       Anandnagar  \n",
 131 |        "3      1.0   95.00            Aundh  \n",
 132 |        "4      1.0   51.00       Aundh Road  "
 133 |       ]
 134 |      },
 135 |      "execution_count": 245,
 136 |      "metadata": {},
 137 |      "output_type": "execute_result"
 138 |     }
 139 |    ],
 140 |    "source": [
 141 |     "# Loading the dataset\n",
 142 |     "df = pd.read_csv('pune_House_Data.csv')\n",
 143 |     "df.head()"
 144 |    ]
 145 |   },
 146 |   {
 147 |    "cell_type": "code",
 148 |    "execution_count": 246,
 149 |    "metadata": {},
 150 |    "outputs": [
 151 |     {
 152 |      "data": {
 153 |       "text/plain": [
 154 |        "(13320, 9)"
 155 |       ]
 156 |      },
 157 |      "execution_count": 246,
 158 |      "metadata": {},
 159 |      "output_type": "execute_result"
 160 |     }
 161 |    ],
 162 |    "source": [
 163 |     "# Exploring the dataset\n",
 164 |     "df.shape"
 165 |    ]
 166 |   },
 167 |   {
 168 |    "cell_type": "code",
 169 |    "execution_count": 247,
 170 |    "metadata": {
 171 |     "scrolled": true
 172 |    },
 173 |    "outputs": [
 174 |     {
 175 |      "data": {
 176 |       "text/plain": [
 177 |        "area_type\n",
 178 |        "Built-up  Area          2418\n",
 179 |        "Carpet  Area              87\n",
 180 |        "Plot  Area              2025\n",
 181 |        "Super built-up  Area    8790\n",
 182 |        "Name: area_type, dtype: int64"
 183 |       ]
 184 |      },
 185 |      "execution_count": 247,
 186 |      "metadata": {},
 187 |      "output_type": "execute_result"
 188 |     }
 189 |    ],
 190 |    "source": [
 191 |     "# Exploring the dataset\n",
 192 |     "df.groupby('area_type')['area_type'].agg('count')"
 193 |    ]
 194 |   },
 195 |   {
 196 |    "cell_type": "code",
 197 |    "execution_count": 248,
 198 |    "metadata": {
 199 |     "scrolled": true
 200 |    },
 201 |    "outputs": [
 202 |     {
 203 |      "data": {
 204 |       "text/plain": [
 205 |        "availability\n",
 206 |        "14-Jul                      1\n",
 207 |        "14-Nov                      1\n",
 208 |        "15-Aug                      1\n",
 209 |        "15-Dec                      1\n",
 210 |        "15-Jun                      1\n",
 211 |        "                        ...  \n",
 212 |        "22-Mar                      3\n",
 213 |        "22-May                     10\n",
 214 |        "22-Nov                      2\n",
 215 |        "Immediate Possession       16\n",
 216 |        "Ready To Move           10581\n",
 217 |        "Name: availability, Length: 81, dtype: int64"
 218 |       ]
 219 |      },
 220 |      "execution_count": 248,
 221 |      "metadata": {},
 222 |      "output_type": "execute_result"
 223 |     }
 224 |    ],
 225 |    "source": [
 226 |     "# Exploring the dataset\n",
 227 |     "df.groupby('availability')['availability'].agg('count')"
 228 |    ]
 229 |   },
 230 |   {
 231 |    "cell_type": "code",
 232 |    "execution_count": 249,
 233 |    "metadata": {
 234 |     "scrolled": true
 235 |    },
 236 |    "outputs": [
 237 |     {
 238 |      "data": {
 239 |       "text/plain": [
 240 |        "size\n",
 241 |        "1 BHK          538\n",
 242 |        "1 Bedroom      105\n",
 243 |        "1 RK            13\n",
 244 |        "10 BHK           2\n",
 245 |        "10 Bedroom      12\n",
 246 |        "11 BHK           2\n",
 247 |        "11 Bedroom       2\n",
 248 |        "12 Bedroom       1\n",
 249 |        "13 BHK           1\n",
 250 |        "14 BHK           1\n",
 251 |        "16 BHK           1\n",
 252 |        "18 Bedroom       1\n",
 253 |        "19 BHK           1\n",
 254 |        "2 BHK         5199\n",
 255 |        "2 Bedroom      329\n",
 256 |        "27 BHK           1\n",
 257 |        "3 BHK         4310\n",
 258 |        "3 Bedroom      547\n",
 259 |        "4 BHK          591\n",
 260 |        "4 Bedroom      826\n",
 261 |        "43 Bedroom       1\n",
 262 |        "5 BHK           59\n",
 263 |        "5 Bedroom      297\n",
 264 |        "6 BHK           30\n",
 265 |        "6 Bedroom      191\n",
 266 |        "7 BHK           17\n",
 267 |        "7 Bedroom       83\n",
 268 |        "8 BHK            5\n",
 269 |        "8 Bedroom       84\n",
 270 |        "9 BHK            8\n",
 271 |        "9 Bedroom       46\n",
 272 |        "Name: size, dtype: int64"
 273 |       ]
 274 |      },
 275 |      "execution_count": 249,
 276 |      "metadata": {},
 277 |      "output_type": "execute_result"
 278 |     }
 279 |    ],
 280 |    "source": [
 281 |     "# Exploring the dataset\n",
 282 |     "df.groupby('size')['size'].agg('count')"
 283 |    ]
 284 |   },
 285 |   {
 286 |    "cell_type": "code",
 287 |    "execution_count": 250,
 288 |    "metadata": {},
 289 |    "outputs": [
 290 |     {
 291 |      "data": {
 292 |       "text/plain": [
 293 |        "site_location\n",
 294 |        "Alandi Road        139\n",
 295 |        "Ambegaon Budruk    139\n",
 296 |        "Anandnagar         139\n",
 297 |        "Aundh              139\n",
 298 |        "Aundh Road         139\n",
 299 |        "                  ... \n",
 300 |        "Wakadewadi         138\n",
 301 |        "Wanowrie           138\n",
 302 |        "Warje              138\n",
 303 |        "Yerawada           138\n",
 304 |        "other                1\n",
 305 |        "Name: site_location, Length: 97, dtype: int64"
 306 |       ]
 307 |      },
 308 |      "execution_count": 250,
 309 |      "metadata": {},
 310 |      "output_type": "execute_result"
 311 |     }
 312 |    ],
 313 |    "source": [
 314 |     "# Exploring the dataset\n",
 315 |     "df.groupby('site_location')['site_location'].agg('count')"
 316 |    ]
 317 |   },
 318 |   {
 319 |    "cell_type": "code",
 320 |    "execution_count": 251,
 321 |    "metadata": {},
 322 |    "outputs": [
 323 |     {
 324 |      "data": {
 325 |       "text/html": [
 326 |        "<div>\n",
 327 |        "<style scoped>\n",
 328 |        "    .dataframe tbody tr th:only-of-type {\n",
 329 |        "        vertical-align: middle;\n",
 330 |        "    }\n",
 331 |        "\n",
 332 |        "    .dataframe tbody tr th {\n",
 333 |        "        vertical-align: top;\n",
 334 |        "    }\n",
 335 |        "\n",
 336 |        "    .dataframe thead th {\n",
 337 |        "        text-align: right;\n",
 338 |        "    }\n",
 339 |        "</style>\n",
 340 |        "<table border=\"1\" class=\"dataframe\">\n",
 341 |        "  <thead>\n",
 342 |        "    <tr style=\"text-align: right;\">\n",
 343 |        "      <th></th>\n",
 344 |        "      <th>area_type</th>\n",
 345 |        "      <th>availability</th>\n",
 346 |        "      <th>size</th>\n",
 347 |        "      <th>total_sqft</th>\n",
 348 |        "      <th>bath</th>\n",
 349 |        "      <th>balcony</th>\n",
 350 |        "      <th>price</th>\n",
 351 |        "      <th>site_location</th>\n",
 352 |        "    </tr>\n",
 353 |        "  </thead>\n",
 354 |        "  <tbody>\n",
 355 |        "    <tr>\n",
 356 |        "      <td>0</td>\n",
 357 |        "      <td>Super built-up  Area</td>\n",
 358 |        "      <td>19-Dec</td>\n",
 359 |        "      <td>2 BHK</td>\n",
 360 |        "      <td>1056</td>\n",
 361 |        "      <td>2.0</td>\n",
 362 |        "      <td>1.0</td>\n",
 363 |        "      <td>39.07</td>\n",
 364 |        "      <td>Alandi Road</td>\n",
 365 |        "    </tr>\n",
 366 |        "    <tr>\n",
 367 |        "      <td>1</td>\n",
 368 |        "      <td>Plot  Area</td>\n",
 369 |        "      <td>Ready To Move</td>\n",
 370 |        "      <td>4 Bedroom</td>\n",
 371 |        "      <td>2600</td>\n",
 372 |        "      <td>5.0</td>\n",
 373 |        "      <td>3.0</td>\n",
 374 |        "      <td>120.00</td>\n",
 375 |        "      <td>Ambegaon Budruk</td>\n",
 376 |        "    </tr>\n",
 377 |        "    <tr>\n",
 378 |        "      <td>2</td>\n",
 379 |        "      <td>Built-up  Area</td>\n",
 380 |        "      <td>Ready To Move</td>\n",
 381 |        "      <td>3 BHK</td>\n",
 382 |        "      <td>1440</td>\n",
 383 |        "      <td>2.0</td>\n",
 384 |        "      <td>3.0</td>\n",
 385 |        "      <td>62.00</td>\n",
 386 |        "      <td>Anandnagar</td>\n",
 387 |        "    </tr>\n",
 388 |        "    <tr>\n",
 389 |        "      <td>3</td>\n",
 390 |        "      <td>Super built-up  Area</td>\n",
 391 |        "      <td>Ready To Move</td>\n",
 392 |        "      <td>3 BHK</td>\n",
 393 |        "      <td>1521</td>\n",
 394 |        "      <td>3.0</td>\n",
 395 |        "      <td>1.0</td>\n",
 396 |        "      <td>95.00</td>\n",
 397 |        "      <td>Aundh</td>\n",
 398 |        "    </tr>\n",
 399 |        "    <tr>\n",
 400 |        "      <td>4</td>\n",
 401 |        "      <td>Super built-up  Area</td>\n",
 402 |        "      <td>Ready To Move</td>\n",
 403 |        "      <td>2 BHK</td>\n",
 404 |        "      <td>1200</td>\n",
 405 |        "      <td>2.0</td>\n",
 406 |        "      <td>1.0</td>\n",
 407 |        "      <td>51.00</td>\n",
 408 |        "      <td>Aundh Road</td>\n",
 409 |        "    </tr>\n",
 410 |        "  </tbody>\n",
 411 |        "</table>\n",
 412 |        "</div>"
 413 |       ],
 414 |       "text/plain": [
 415 |        "              area_type   availability       size total_sqft  bath  balcony  \\\n",
 416 |        "0  Super built-up  Area         19-Dec      2 BHK       1056   2.0      1.0   \n",
 417 |        "1            Plot  Area  Ready To Move  4 Bedroom       2600   5.0      3.0   \n",
 418 |        "2        Built-up  Area  Ready To Move      3 BHK       1440   2.0      3.0   \n",
 419 |        "3  Super built-up  Area  Ready To Move      3 BHK       1521   3.0      1.0   \n",
 420 |        "4  Super built-up  Area  Ready To Move      2 BHK       1200   2.0      1.0   \n",
 421 |        "\n",
 422 |        "    price    site_location  \n",
 423 |        "0   39.07      Alandi Road  \n",
 424 |        "1  120.00  Ambegaon Budruk  \n",
 425 |        "2   62.00       Anandnagar  \n",
 426 |        "3   95.00            Aundh  \n",
 427 |        "4   51.00       Aundh Road  "
 428 |       ]
 429 |      },
 430 |      "execution_count": 251,
 431 |      "metadata": {},
 432 |      "output_type": "execute_result"
 433 |     }
 434 |    ],
 435 |    "source": [
 436 |     "# Removing the columns of society\n",
 437 |     "df = df.drop('society', axis='columns')\n",
 438 |     "df.head()"
 439 |    ]
 440 |   },
 441 |   {
 442 |    "cell_type": "markdown",
 443 |    "metadata": {},
 444 |    "source": [
 445 |     "## Data Cleaning Process"
 446 |    ]
 447 |   },
 448 |   {
 449 |    "cell_type": "code",
 450 |    "execution_count": 252,
 451 |    "metadata": {},
 452 |    "outputs": [
 453 |     {
 454 |      "data": {
 455 |       "text/plain": [
 456 |        "area_type          0\n",
 457 |        "availability       0\n",
 458 |        "size              16\n",
 459 |        "total_sqft         0\n",
 460 |        "bath              73\n",
 461 |        "balcony          609\n",
 462 |        "price              0\n",
 463 |        "site_location      1\n",
 464 |        "dtype: int64"
 465 |       ]
 466 |      },
 467 |      "execution_count": 252,
 468 |      "metadata": {},
 469 |      "output_type": "execute_result"
 470 |     }
 471 |    ],
 472 |    "source": [
 473 |     "# Data Cleaning\n",
 474 |     "# Checking the null values in the dataset\n",
 475 |     "df.isnull().sum()"
 476 |    ]
 477 |   },
 478 |   {
 479 |    "cell_type": "code",
 480 |    "execution_count": 253,
 481 |    "metadata": {},
 482 |    "outputs": [],
 483 |    "source": [
 484 |     "# Applying median to the balcony and bath column\n",
 485 |     "from math import floor\n",
 486 |     "\n",
 487 |     "balcony_median = float(floor(df.balcony.median()))\n",
 488 |     "bath_median = float(floor(df.bath.median()))\n",
 489 |     "\n",
 490 |     "df.balcony = df.balcony.fillna(balcony_median)\n",
 491 |     "df.bath = df.bath.fillna(bath_median)"
 492 |    ]
 493 |   },
 494 |   {
 495 |    "cell_type": "code",
 496 |    "execution_count": 254,
 497 |    "metadata": {},
 498 |    "outputs": [
 499 |     {
 500 |      "data": {
 501 |       "text/plain": [
 502 |        "area_type         0\n",
 503 |        "availability      0\n",
 504 |        "size             16\n",
 505 |        "total_sqft        0\n",
 506 |        "bath              0\n",
 507 |        "balcony           0\n",
 508 |        "price             0\n",
 509 |        "site_location     1\n",
 510 |        "dtype: int64"
 511 |       ]
 512 |      },
 513 |      "execution_count": 254,
 514 |      "metadata": {},
 515 |      "output_type": "execute_result"
 516 |     }
 517 |    ],
 518 |    "source": [
 519 |     "# Checking the null values in the dataset again\n",
 520 |     "df.isnull().sum()"
 521 |    ]
 522 |   },
 523 |   {
 524 |    "cell_type": "code",
 525 |    "execution_count": 255,
 526 |    "metadata": {},
 527 |    "outputs": [
 528 |     {
 529 |      "data": {
 530 |       "text/plain": [
 531 |        "area_type        0\n",
 532 |        "availability     0\n",
 533 |        "size             0\n",
 534 |        "total_sqft       0\n",
 535 |        "bath             0\n",
 536 |        "balcony          0\n",
 537 |        "price            0\n",
 538 |        "site_location    0\n",
 539 |        "dtype: int64"
 540 |       ]
 541 |      },
 542 |      "execution_count": 255,
 543 |      "metadata": {},
 544 |      "output_type": "execute_result"
 545 |     }
 546 |    ],
 547 |    "source": [
 548 |     "# Dropping the rows with null values because the dataset is huge as compared to null values.\n",
 549 |     "df = df.dropna()\n",
 550 |     "df.isnull().sum()"
 551 |    ]
 552 |   },
 553 |   {
 554 |    "cell_type": "code",
 555 |    "execution_count": 256,
 556 |    "metadata": {
 557 |     "scrolled": true
 558 |    },
 559 |    "outputs": [
 560 |     {
 561 |      "data": {
 562 |       "text/plain": [
 563 |        "bhk\n",
 564 |        "1      656\n",
 565 |        "2     5527\n",
 566 |        "3     4857\n",
 567 |        "4     1417\n",
 568 |        "5      356\n",
 569 |        "6      221\n",
 570 |        "7      100\n",
 571 |        "8       89\n",
 572 |        "9       54\n",
 573 |        "10      14\n",
 574 |        "11       4\n",
 575 |        "12       1\n",
 576 |        "13       1\n",
 577 |        "14       1\n",
 578 |        "16       1\n",
 579 |        "18       1\n",
 580 |        "19       1\n",
 581 |        "27       1\n",
 582 |        "43       1\n",
 583 |        "Name: bhk, dtype: int64"
 584 |       ]
 585 |      },
 586 |      "execution_count": 256,
 587 |      "metadata": {},
 588 |      "output_type": "execute_result"
 589 |     }
 590 |    ],
 591 |    "source": [
 592 |     "# Converting the size column to bhk\n",
 593 |     "df['bhk'] = df['size'].apply(lambda x: int(x.split(' ')[0]))\n",
 594 |     "df = df.drop('size', axis='columns')\n",
 595 |     "df.groupby('bhk')['bhk'].agg('count')"
 596 |    ]
 597 |   },
 598 |   {
 599 |    "cell_type": "code",
 600 |    "execution_count": 257,
 601 |    "metadata": {
 602 |     "scrolled": true
 603 |    },
 604 |    "outputs": [
 605 |     {
 606 |      "data": {
 607 |       "text/plain": [
 608 |        "array(['1056', '2600', '1440', ..., '1133 - 1384', '774', '4689'],\n",
 609 |        "      dtype=object)"
 610 |       ]
 611 |      },
 612 |      "execution_count": 257,
 613 |      "metadata": {},
 614 |      "output_type": "execute_result"
 615 |     }
 616 |    ],
 617 |    "source": [
 618 |     "# Exploring the total_sqft column\n",
 619 |     "df.total_sqft.unique()"
 620 |    ]
 621 |   },
 622 |   {
 623 |    "cell_type": "code",
 624 |    "execution_count": 258,
 625 |    "metadata": {},
 626 |    "outputs": [],
 627 |    "source": [
 628 |     "# Since the total_sqft contains range values such as 1133-1384, lets filter out these values\n",
 629 |     "def isFloat(x):\n",
 630 |     "    try:\n",
 631 |     "        float(x)\n",
 632 |     "    except:\n",
 633 |     "        return False\n",
 634 |     "    return True"
 635 |    ]
 636 |   },
 637 |   {
 638 |    "cell_type": "code",
 639 |    "execution_count": 259,
 640 |    "metadata": {},
 641 |    "outputs": [
 642 |     {
 643 |      "data": {
 644 |       "text/html": [
 645 |        "<div>\n",
 646 |        "<style scoped>\n",
 647 |        "    .dataframe tbody tr th:only-of-type {\n",
 648 |        "        vertical-align: middle;\n",
 649 |        "    }\n",
 650 |        "\n",
 651 |        "    .dataframe tbody tr th {\n",
 652 |        "        vertical-align: top;\n",
 653 |        "    }\n",
 654 |        "\n",
 655 |        "    .dataframe thead th {\n",
 656 |        "        text-align: right;\n",
 657 |        "    }\n",
 658 |        "</style>\n",
 659 |        "<table border=\"1\" class=\"dataframe\">\n",
 660 |        "  <thead>\n",
 661 |        "    <tr style=\"text-align: right;\">\n",
 662 |        "      <th></th>\n",
 663 |        "      <th>area_type</th>\n",
 664 |        "      <th>availability</th>\n",
 665 |        "      <th>total_sqft</th>\n",
 666 |        "      <th>bath</th>\n",
 667 |        "      <th>balcony</th>\n",
 668 |        "      <th>price</th>\n",
 669 |        "      <th>site_location</th>\n",
 670 |        "      <th>bhk</th>\n",
 671 |        "    </tr>\n",
 672 |        "  </thead>\n",
 673 |        "  <tbody>\n",
 674 |        "    <tr>\n",
 675 |        "      <td>30</td>\n",
 676 |        "      <td>Super built-up  Area</td>\n",
 677 |        "      <td>19-Dec</td>\n",
 678 |        "      <td>2100 - 2850</td>\n",
 679 |        "      <td>4.0</td>\n",
 680 |        "      <td>0.0</td>\n",
 681 |        "      <td>186.000</td>\n",
 682 |        "      <td>Gultekdi</td>\n",
 683 |        "      <td>4</td>\n",
 684 |        "    </tr>\n",
 685 |        "    <tr>\n",
 686 |        "      <td>56</td>\n",
 687 |        "      <td>Built-up  Area</td>\n",
 688 |        "      <td>20-Feb</td>\n",
 689 |        "      <td>3010 - 3410</td>\n",
 690 |        "      <td>2.0</td>\n",
 691 |        "      <td>2.0</td>\n",
 692 |        "      <td>192.000</td>\n",
 693 |        "      <td>Model colony</td>\n",
 694 |        "      <td>4</td>\n",
 695 |        "    </tr>\n",
 696 |        "    <tr>\n",
 697 |        "      <td>81</td>\n",
 698 |        "      <td>Built-up  Area</td>\n",
 699 |        "      <td>18-Oct</td>\n",
 700 |        "      <td>2957 - 3450</td>\n",
 701 |        "      <td>2.0</td>\n",
 702 |        "      <td>2.0</td>\n",
 703 |        "      <td>224.500</td>\n",
 704 |        "      <td>Shukrawar Peth</td>\n",
 705 |        "      <td>4</td>\n",
 706 |        "    </tr>\n",
 707 |        "    <tr>\n",
 708 |        "      <td>122</td>\n",
 709 |        "      <td>Super built-up  Area</td>\n",
 710 |        "      <td>18-Mar</td>\n",
 711 |        "      <td>3067 - 8156</td>\n",
 712 |        "      <td>4.0</td>\n",
 713 |        "      <td>0.0</td>\n",
 714 |        "      <td>477.000</td>\n",
 715 |        "      <td>Ganeshkhind</td>\n",
 716 |        "      <td>4</td>\n",
 717 |        "    </tr>\n",
 718 |        "    <tr>\n",
 719 |        "      <td>137</td>\n",
 720 |        "      <td>Super built-up  Area</td>\n",
 721 |        "      <td>19-Mar</td>\n",
 722 |        "      <td>1042 - 1105</td>\n",
 723 |        "      <td>2.0</td>\n",
 724 |        "      <td>0.0</td>\n",
 725 |        "      <td>54.005</td>\n",
 726 |        "      <td>Khadaki</td>\n",
 727 |        "      <td>2</td>\n",
 728 |        "    </tr>\n",
 729 |        "    <tr>\n",
 730 |        "      <td>...</td>\n",
 731 |        "      <td>...</td>\n",
 732 |        "      <td>...</td>\n",
 733 |        "      <td>...</td>\n",
 734 |        "      <td>...</td>\n",
 735 |        "      <td>...</td>\n",
 736 |        "      <td>...</td>\n",
 737 |        "      <td>...</td>\n",
 738 |        "      <td>...</td>\n",
 739 |        "    </tr>\n",
 740 |        "    <tr>\n",
 741 |        "      <td>12990</td>\n",
 742 |        "      <td>Super built-up  Area</td>\n",
 743 |        "      <td>18-May</td>\n",
 744 |        "      <td>1804 - 2273</td>\n",
 745 |        "      <td>3.0</td>\n",
 746 |        "      <td>0.0</td>\n",
 747 |        "      <td>122.000</td>\n",
 748 |        "      <td>Gokhale Nagar</td>\n",
 749 |        "      <td>3</td>\n",
 750 |        "    </tr>\n",
 751 |        "    <tr>\n",
 752 |        "      <td>13059</td>\n",
 753 |        "      <td>Super built-up  Area</td>\n",
 754 |        "      <td>Ready To Move</td>\n",
 755 |        "      <td>1200 - 1470</td>\n",
 756 |        "      <td>2.0</td>\n",
 757 |        "      <td>0.0</td>\n",
 758 |        "      <td>72.760</td>\n",
 759 |        "      <td>Anandnagar</td>\n",
 760 |        "      <td>2</td>\n",
 761 |        "    </tr>\n",
 762 |        "    <tr>\n",
 763 |        "      <td>13240</td>\n",
 764 |        "      <td>Super built-up  Area</td>\n",
 765 |        "      <td>Ready To Move</td>\n",
 766 |        "      <td>1020 - 1130</td>\n",
 767 |        "      <td>2.0</td>\n",
 768 |        "      <td>2.0</td>\n",
 769 |        "      <td>52.570</td>\n",
 770 |        "      <td>Vadgaon Budruk</td>\n",
 771 |        "      <td>1</td>\n",
 772 |        "    </tr>\n",
 773 |        "    <tr>\n",
 774 |        "      <td>13265</td>\n",
 775 |        "      <td>Super built-up  Area</td>\n",
 776 |        "      <td>20-Sep</td>\n",
 777 |        "      <td>1133 - 1384</td>\n",
 778 |        "      <td>2.0</td>\n",
 779 |        "      <td>0.0</td>\n",
 780 |        "      <td>59.135</td>\n",
 781 |        "      <td>Dapodi</td>\n",
 782 |        "      <td>2</td>\n",
 783 |        "    </tr>\n",
 784 |        "    <tr>\n",
 785 |        "      <td>13299</td>\n",
 786 |        "      <td>Super built-up  Area</td>\n",
 787 |        "      <td>18-Dec</td>\n",
 788 |        "      <td>2830 - 2882</td>\n",
 789 |        "      <td>5.0</td>\n",
 790 |        "      <td>0.0</td>\n",
 791 |        "      <td>154.500</td>\n",
 792 |        "      <td>Laxmi Road</td>\n",
 793 |        "      <td>4</td>\n",
 794 |        "    </tr>\n",
 795 |        "  </tbody>\n",
 796 |        "</table>\n",
 797 |        "<p>239 rows × 8 columns</p>\n",
 798 |        "</div>"
 799 |       ],
 800 |       "text/plain": [
 801 |        "                  area_type   availability   total_sqft  bath  balcony  \\\n",
 802 |        "30     Super built-up  Area         19-Dec  2100 - 2850   4.0      0.0   \n",
 803 |        "56           Built-up  Area         20-Feb  3010 - 3410   2.0      2.0   \n",
 804 |        "81           Built-up  Area         18-Oct  2957 - 3450   2.0      2.0   \n",
 805 |        "122    Super built-up  Area         18-Mar  3067 - 8156   4.0      0.0   \n",
 806 |        "137    Super built-up  Area         19-Mar  1042 - 1105   2.0      0.0   \n",
 807 |        "...                     ...            ...          ...   ...      ...   \n",
 808 |        "12990  Super built-up  Area         18-May  1804 - 2273   3.0      0.0   \n",
 809 |        "13059  Super built-up  Area  Ready To Move  1200 - 1470   2.0      0.0   \n",
 810 |        "13240  Super built-up  Area  Ready To Move  1020 - 1130   2.0      2.0   \n",
 811 |        "13265  Super built-up  Area         20-Sep  1133 - 1384   2.0      0.0   \n",
 812 |        "13299  Super built-up  Area         18-Dec  2830 - 2882   5.0      0.0   \n",
 813 |        "\n",
 814 |        "         price   site_location  bhk  \n",
 815 |        "30     186.000        Gultekdi    4  \n",
 816 |        "56     192.000    Model colony    4  \n",
 817 |        "81     224.500  Shukrawar Peth    4  \n",
 818 |        "122    477.000     Ganeshkhind    4  \n",
 819 |        "137     54.005         Khadaki    2  \n",
 820 |        "...        ...             ...  ...  \n",
 821 |        "12990  122.000   Gokhale Nagar    3  \n",
 822 |        "13059   72.760      Anandnagar    2  \n",
 823 |        "13240   52.570  Vadgaon Budruk    1  \n",
 824 |        "13265   59.135          Dapodi    2  \n",
 825 |        "13299  154.500      Laxmi Road    4  \n",
 826 |        "\n",
 827 |        "[239 rows x 8 columns]"
 828 |       ]
 829 |      },
 830 |      "execution_count": 259,
 831 |      "metadata": {},
 832 |      "output_type": "execute_result"
 833 |     }
 834 |    ],
 835 |    "source": [
 836 |     "# Displaying all the rows that are not integers\n",
 837 |     "df[~df['total_sqft'].apply(isFloat)]"
 838 |    ]
 839 |   },
 840 |   {
 841 |    "cell_type": "code",
 842 |    "execution_count": 260,
 843 |    "metadata": {},
 844 |    "outputs": [],
 845 |    "source": [
 846 |     "# Converting the range values to integer values and removing other types of error\n",
 847 |     "def convert_sqft_to_num(x):\n",
 848 |     "    tokens = x.split('-')\n",
 849 |     "    if len(tokens) == 2:\n",
 850 |     "        return (float(tokens[0])+float(tokens[1]))/2\n",
 851 |     "    try:\n",
 852 |     "        return float(x)\n",
 853 |     "    except:\n",
 854 |     "        return None"
 855 |    ]
 856 |   },
 857 |   {
 858 |    "cell_type": "code",
 859 |    "execution_count": 261,
 860 |    "metadata": {
 861 |     "scrolled": false
 862 |    },
 863 |    "outputs": [
 864 |     {
 865 |      "data": {
 866 |       "text/html": [
 867 |        "<div>\n",
 868 |        "<style scoped>\n",
 869 |        "    .dataframe tbody tr th:only-of-type {\n",
 870 |        "        vertical-align: middle;\n",
 871 |        "    }\n",
 872 |        "\n",
 873 |        "    .dataframe tbody tr th {\n",
 874 |        "        vertical-align: top;\n",
 875 |        "    }\n",
 876 |        "\n",
 877 |        "    .dataframe thead th {\n",
 878 |        "        text-align: right;\n",
 879 |        "    }\n",
 880 |        "</style>\n",
 881 |        "<table border=\"1\" class=\"dataframe\">\n",
 882 |        "  <thead>\n",
 883 |        "    <tr style=\"text-align: right;\">\n",
 884 |        "      <th></th>\n",
 885 |        "      <th>area_type</th>\n",
 886 |        "      <th>availability</th>\n",
 887 |        "      <th>bath</th>\n",
 888 |        "      <th>balcony</th>\n",
 889 |        "      <th>price</th>\n",
 890 |        "      <th>site_location</th>\n",
 891 |        "      <th>bhk</th>\n",
 892 |        "      <th>new_total_sqft</th>\n",
 893 |        "    </tr>\n",
 894 |        "  </thead>\n",
 895 |        "  <tbody>\n",
 896 |        "    <tr>\n",
 897 |        "      <td>0</td>\n",
 898 |        "      <td>Super built-up  Area</td>\n",
 899 |        "      <td>19-Dec</td>\n",
 900 |        "      <td>2.0</td>\n",
 901 |        "      <td>1.0</td>\n",
 902 |        "      <td>39.07</td>\n",
 903 |        "      <td>Alandi Road</td>\n",
 904 |        "      <td>2</td>\n",
 905 |        "      <td>1056.0</td>\n",
 906 |        "    </tr>\n",
 907 |        "    <tr>\n",
 908 |        "      <td>1</td>\n",
 909 |        "      <td>Plot  Area</td>\n",
 910 |        "      <td>Ready To Move</td>\n",
 911 |        "      <td>5.0</td>\n",
 912 |        "      <td>3.0</td>\n",
 913 |        "      <td>120.00</td>\n",
 914 |        "      <td>Ambegaon Budruk</td>\n",
 915 |        "      <td>4</td>\n",
 916 |        "      <td>2600.0</td>\n",
 917 |        "    </tr>\n",
 918 |        "    <tr>\n",
 919 |        "      <td>2</td>\n",
 920 |        "      <td>Built-up  Area</td>\n",
 921 |        "      <td>Ready To Move</td>\n",
 922 |        "      <td>2.0</td>\n",
 923 |        "      <td>3.0</td>\n",
 924 |        "      <td>62.00</td>\n",
 925 |        "      <td>Anandnagar</td>\n",
 926 |        "      <td>3</td>\n",
 927 |        "      <td>1440.0</td>\n",
 928 |        "    </tr>\n",
 929 |        "    <tr>\n",
 930 |        "      <td>3</td>\n",
 931 |        "      <td>Super built-up  Area</td>\n",
 932 |        "      <td>Ready To Move</td>\n",
 933 |        "      <td>3.0</td>\n",
 934 |        "      <td>1.0</td>\n",
 935 |        "      <td>95.00</td>\n",
 936 |        "      <td>Aundh</td>\n",
 937 |        "      <td>3</td>\n",
 938 |        "      <td>1521.0</td>\n",
 939 |        "    </tr>\n",
 940 |        "    <tr>\n",
 941 |        "      <td>4</td>\n",
 942 |        "      <td>Super built-up  Area</td>\n",
 943 |        "      <td>Ready To Move</td>\n",
 944 |        "      <td>2.0</td>\n",
 945 |        "      <td>1.0</td>\n",
 946 |        "      <td>51.00</td>\n",
 947 |        "      <td>Aundh Road</td>\n",
 948 |        "      <td>2</td>\n",
 949 |        "      <td>1200.0</td>\n",
 950 |        "    </tr>\n",
 951 |        "  </tbody>\n",
 952 |        "</table>\n",
 953 |        "</div>"
 954 |       ],
 955 |       "text/plain": [
 956 |        "              area_type   availability  bath  balcony   price  \\\n",
 957 |        "0  Super built-up  Area         19-Dec   2.0      1.0   39.07   \n",
 958 |        "1            Plot  Area  Ready To Move   5.0      3.0  120.00   \n",
 959 |        "2        Built-up  Area  Ready To Move   2.0      3.0   62.00   \n",
 960 |        "3  Super built-up  Area  Ready To Move   3.0      1.0   95.00   \n",
 961 |        "4  Super built-up  Area  Ready To Move   2.0      1.0   51.00   \n",
 962 |        "\n",
 963 |        "     site_location  bhk  new_total_sqft  \n",
 964 |        "0      Alandi Road    2          1056.0  \n",
 965 |        "1  Ambegaon Budruk    4          2600.0  \n",
 966 |        "2       Anandnagar    3          1440.0  \n",
 967 |        "3            Aundh    3          1521.0  \n",
 968 |        "4       Aundh Road    2          1200.0  "
 969 |       ]
 970 |      },
 971 |      "execution_count": 261,
 972 |      "metadata": {},
 973 |      "output_type": "execute_result"
 974 |     }
 975 |    ],
 976 |    "source": [
 977 |     "df['new_total_sqft'] = df.total_sqft.apply(convert_sqft_to_num)\n",
 978 |     "df = df.drop('total_sqft', axis='columns')\n",
 979 |     "df.head()"
 980 |    ]
 981 |   },
 982 |   {
 983 |    "cell_type": "code",
 984 |    "execution_count": 262,
 985 |    "metadata": {},
 986 |    "outputs": [
 987 |     {
 988 |      "data": {
 989 |       "text/plain": [
 990 |        "area_type          0\n",
 991 |        "availability       0\n",
 992 |        "bath               0\n",
 993 |        "balcony            0\n",
 994 |        "price              0\n",
 995 |        "site_location      0\n",
 996 |        "bhk                0\n",
 997 |        "new_total_sqft    46\n",
 998 |        "dtype: int64"
 999 |       ]
1000 |      },
1001 |      "execution_count": 262,
1002 |      "metadata": {},
1003 |      "output_type": "execute_result"
1004 |     }
1005 |    ],
1006 |    "source": [
1007 |     "# Removing the rows in new_total_sqft column that hase None values\n",
1008 |     "df.isna().sum()"
1009 |    ]
1010 |   },
1011 |   {
1012 |    "cell_type": "code",
1013 |    "execution_count": 263,
1014 |    "metadata": {},
1015 |    "outputs": [
1016 |     {
1017 |      "data": {
1018 |       "text/plain": [
1019 |        "area_type         0\n",
1020 |        "availability      0\n",
1021 |        "bath              0\n",
1022 |        "balcony           0\n",
1023 |        "price             0\n",
1024 |        "site_location     0\n",
1025 |        "bhk               0\n",
1026 |        "new_total_sqft    0\n",
1027 |        "dtype: int64"
1028 |       ]
1029 |      },
1030 |      "execution_count": 263,
1031 |      "metadata": {},
1032 |      "output_type": "execute_result"
1033 |     }
1034 |    ],
1035 |    "source": [
1036 |     "# Removing the rows in new_total_sqft column that hase None values\n",
1037 |     "df = df.dropna()\n",
1038 |     "df.isna().sum()"
1039 |    ]
1040 |   },
1041 |   {
1042 |    "cell_type": "markdown",
1043 |    "metadata": {},
1044 |    "source": [
1045 |     "## Feature Engineering"
1046 |    ]
1047 |   },
1048 |   {
1049 |    "cell_type": "code",
1050 |    "execution_count": 264,
1051 |    "metadata": {
1052 |     "scrolled": true
1053 |    },
1054 |    "outputs": [
1055 |     {
1056 |      "data": {
1057 |       "text/html": [
1058 |        "<div>\n",
1059 |        "<style scoped>\n",
1060 |        "    .dataframe tbody tr th:only-of-type {\n",
1061 |        "        vertical-align: middle;\n",
1062 |        "    }\n",
1063 |        "\n",
1064 |        "    .dataframe tbody tr th {\n",
1065 |        "        vertical-align: top;\n",
1066 |        "    }\n",
1067 |        "\n",
1068 |        "    .dataframe thead th {\n",
1069 |        "        text-align: right;\n",
1070 |        "    }\n",
1071 |        "</style>\n",
1072 |        "<table border=\"1\" class=\"dataframe\">\n",
1073 |        "  <thead>\n",
1074 |        "    <tr style=\"text-align: right;\">\n",
1075 |        "      <th></th>\n",
1076 |        "      <th>area_type</th>\n",
1077 |        "      <th>availability</th>\n",
1078 |        "      <th>bath</th>\n",
1079 |        "      <th>balcony</th>\n",
1080 |        "      <th>price</th>\n",
1081 |        "      <th>site_location</th>\n",
1082 |        "      <th>bhk</th>\n",
1083 |        "      <th>new_total_sqft</th>\n",
1084 |        "      <th>price_per_sqft</th>\n",
1085 |        "    </tr>\n",
1086 |        "  </thead>\n",
1087 |        "  <tbody>\n",
1088 |        "    <tr>\n",
1089 |        "      <td>0</td>\n",
1090 |        "      <td>Super built-up  Area</td>\n",
1091 |        "      <td>19-Dec</td>\n",
1092 |        "      <td>2.0</td>\n",
1093 |        "      <td>1.0</td>\n",
1094 |        "      <td>39.07</td>\n",
1095 |        "      <td>Alandi Road</td>\n",
1096 |        "      <td>2</td>\n",
1097 |        "      <td>1056.0</td>\n",
1098 |        "      <td>3699.810606</td>\n",
1099 |        "    </tr>\n",
1100 |        "    <tr>\n",
1101 |        "      <td>1</td>\n",
1102 |        "      <td>Plot  Area</td>\n",
1103 |        "      <td>Ready To Move</td>\n",
1104 |        "      <td>5.0</td>\n",
1105 |        "      <td>3.0</td>\n",
1106 |        "      <td>120.00</td>\n",
1107 |        "      <td>Ambegaon Budruk</td>\n",
1108 |        "      <td>4</td>\n",
1109 |        "      <td>2600.0</td>\n",
1110 |        "      <td>4615.384615</td>\n",
1111 |        "    </tr>\n",
1112 |        "    <tr>\n",
1113 |        "      <td>2</td>\n",
1114 |        "      <td>Built-up  Area</td>\n",
1115 |        "      <td>Ready To Move</td>\n",
1116 |        "      <td>2.0</td>\n",
1117 |        "      <td>3.0</td>\n",
1118 |        "      <td>62.00</td>\n",
1119 |        "      <td>Anandnagar</td>\n",
1120 |        "      <td>3</td>\n",
1121 |        "      <td>1440.0</td>\n",
1122 |        "      <td>4305.555556</td>\n",
1123 |        "    </tr>\n",
1124 |        "    <tr>\n",
1125 |        "      <td>3</td>\n",
1126 |        "      <td>Super built-up  Area</td>\n",
1127 |        "      <td>Ready To Move</td>\n",
1128 |        "      <td>3.0</td>\n",
1129 |        "      <td>1.0</td>\n",
1130 |        "      <td>95.00</td>\n",
1131 |        "      <td>Aundh</td>\n",
1132 |        "      <td>3</td>\n",
1133 |        "      <td>1521.0</td>\n",
1134 |        "      <td>6245.890861</td>\n",
1135 |        "    </tr>\n",
1136 |        "    <tr>\n",
1137 |        "      <td>4</td>\n",
1138 |        "      <td>Super built-up  Area</td>\n",
1139 |        "      <td>Ready To Move</td>\n",
1140 |        "      <td>2.0</td>\n",
1141 |        "      <td>1.0</td>\n",
1142 |        "      <td>51.00</td>\n",
1143 |        "      <td>Aundh Road</td>\n",
1144 |        "      <td>2</td>\n",
1145 |        "      <td>1200.0</td>\n",
1146 |        "      <td>4250.000000</td>\n",
1147 |        "    </tr>\n",
1148 |        "  </tbody>\n",
1149 |        "</table>\n",
1150 |        "</div>"
1151 |       ],
1152 |       "text/plain": [
1153 |        "              area_type   availability  bath  balcony   price  \\\n",
1154 |        "0  Super built-up  Area         19-Dec   2.0      1.0   39.07   \n",
1155 |        "1            Plot  Area  Ready To Move   5.0      3.0  120.00   \n",
1156 |        "2        Built-up  Area  Ready To Move   2.0      3.0   62.00   \n",
1157 |        "3  Super built-up  Area  Ready To Move   3.0      1.0   95.00   \n",
1158 |        "4  Super built-up  Area  Ready To Move   2.0      1.0   51.00   \n",
1159 |        "\n",
1160 |        "     site_location  bhk  new_total_sqft  price_per_sqft  \n",
1161 |        "0      Alandi Road    2          1056.0     3699.810606  \n",
1162 |        "1  Ambegaon Budruk    4          2600.0     4615.384615  \n",
1163 |        "2       Anandnagar    3          1440.0     4305.555556  \n",
1164 |        "3            Aundh    3          1521.0     6245.890861  \n",
1165 |        "4       Aundh Road    2          1200.0     4250.000000  "
1166 |       ]
1167 |      },
1168 |      "execution_count": 264,
1169 |      "metadata": {},
1170 |      "output_type": "execute_result"
1171 |     }
1172 |    ],
1173 |    "source": [
1174 |     "# Adding a new column of price_per_sqft\n",
1175 |     "df1 = df.copy()\n",
1176 |     "\n",
1177 |     "# In our dataset the price column is in Lakhs\n",
1178 |     "df1['price_per_sqft'] = (df1['price']*100000)/df1['new_total_sqft']\n",
1179 |     "df1.head()"
1180 |    ]
1181 |   },
1182 |   {
1183 |    "cell_type": "code",
1184 |    "execution_count": 265,
1185 |    "metadata": {
1186 |     "scrolled": true
1187 |    },
1188 |    "outputs": [
1189 |     {
1190 |      "name": "stdout",
1191 |      "output_type": "stream",
1192 |      "text": [
1193 |       "97\n"
1194 |      ]
1195 |     }
1196 |    ],
1197 |    "source": [
1198 |     "# Checking unique values of 'location' column\n",
1199 |     "locations = list(df['site_location'].unique())\n",
1200 |     "print(len(locations))"
1201 |    ]
1202 |   },
1203 |   {
1204 |    "cell_type": "code",
1205 |    "execution_count": 266,
1206 |    "metadata": {
1207 |     "scrolled": false
1208 |    },
1209 |    "outputs": [
1210 |     {
1211 |      "data": {
1212 |       "text/plain": [
1213 |        "site_location\n",
1214 |        "Pune Railway Station    139\n",
1215 |        "Paud Road               139\n",
1216 |        "Ganesh Peth             139\n",
1217 |        "Mangalwar peth          139\n",
1218 |        "Manik Bagh              139\n",
1219 |        "                       ... \n",
1220 |        "Nagar Road              136\n",
1221 |        "Narayangaon             136\n",
1222 |        "Fatima Nagar            136\n",
1223 |        "Camp                    136\n",
1224 |        "other                     1\n",
1225 |        "Name: site_location, Length: 97, dtype: int64"
1226 |       ]
1227 |      },
1228 |      "execution_count": 266,
1229 |      "metadata": {},
1230 |      "output_type": "execute_result"
1231 |     }
1232 |    ],
1233 |    "source": [
1234 |     "# Removing the extra spaces at the end\n",
1235 |     "df1.site_location = df1.site_location.apply(lambda x: x.strip())\n",
1236 |     "\n",
1237 |     "# Calulating all the unqiue values in 'site_location' column\n",
1238 |     "location_stats = df1.groupby('site_location')['site_location'].agg('count').sort_values(ascending=False)\n",
1239 |     "location_stats"
1240 |    ]
1241 |   },
1242 |   {
1243 |    "cell_type": "code",
1244 |    "execution_count": 267,
1245 |    "metadata": {
1246 |     "scrolled": false
1247 |    },
1248 |    "outputs": [
1249 |     {
1250 |      "name": "stdout",
1251 |      "output_type": "stream",
1252 |      "text": [
1253 |       "1 97\n"
1254 |      ]
1255 |     }
1256 |    ],
1257 |    "source": [
1258 |     "# Checking locations with less than 10 values\n",
1259 |     "print(len(location_stats[location_stats<=10]), len(df1.site_location.unique()))"
1260 |    ]
1261 |   },
1262 |   {
1263 |    "cell_type": "code",
1264 |    "execution_count": 268,
1265 |    "metadata": {},
1266 |    "outputs": [
1267 |     {
1268 |      "data": {
1269 |       "text/html": [
1270 |        "<div>\n",
1271 |        "<style scoped>\n",
1272 |        "    .dataframe tbody tr th:only-of-type {\n",
1273 |        "        vertical-align: middle;\n",
1274 |        "    }\n",
1275 |        "\n",
1276 |        "    .dataframe tbody tr th {\n",
1277 |        "        vertical-align: top;\n",
1278 |        "    }\n",
1279 |        "\n",
1280 |        "    .dataframe thead th {\n",
1281 |        "        text-align: right;\n",
1282 |        "    }\n",
1283 |        "</style>\n",
1284 |        "<table border=\"1\" class=\"dataframe\">\n",
1285 |        "  <thead>\n",
1286 |        "    <tr style=\"text-align: right;\">\n",
1287 |        "      <th></th>\n",
1288 |        "      <th>area_type</th>\n",
1289 |        "      <th>availability</th>\n",
1290 |        "      <th>bath</th>\n",
1291 |        "      <th>balcony</th>\n",
1292 |        "      <th>price</th>\n",
1293 |        "      <th>site_location</th>\n",
1294 |        "      <th>bhk</th>\n",
1295 |        "      <th>new_total_sqft</th>\n",
1296 |        "      <th>price_per_sqft</th>\n",
1297 |        "    </tr>\n",
1298 |        "  </thead>\n",
1299 |        "  <tbody>\n",
1300 |        "    <tr>\n",
1301 |        "      <td>0</td>\n",
1302 |        "      <td>Super built-up  Area</td>\n",
1303 |        "      <td>19-Dec</td>\n",
1304 |        "      <td>2.0</td>\n",
1305 |        "      <td>1.0</td>\n",
1306 |        "      <td>39.07</td>\n",
1307 |        "      <td>Alandi Road</td>\n",
1308 |        "      <td>2</td>\n",
1309 |        "      <td>1056.0</td>\n",
1310 |        "      <td>3699.810606</td>\n",
1311 |        "    </tr>\n",
1312 |        "    <tr>\n",
1313 |        "      <td>1</td>\n",
1314 |        "      <td>Plot  Area</td>\n",
1315 |        "      <td>Ready To Move</td>\n",
1316 |        "      <td>5.0</td>\n",
1317 |        "      <td>3.0</td>\n",
1318 |        "      <td>120.00</td>\n",
1319 |        "      <td>Ambegaon Budruk</td>\n",
1320 |        "      <td>4</td>\n",
1321 |        "      <td>2600.0</td>\n",
1322 |        "      <td>4615.384615</td>\n",
1323 |        "    </tr>\n",
1324 |        "    <tr>\n",
1325 |        "      <td>2</td>\n",
1326 |        "      <td>Built-up  Area</td>\n",
1327 |        "      <td>Ready To Move</td>\n",
1328 |        "      <td>2.0</td>\n",
1329 |        "      <td>3.0</td>\n",
1330 |        "      <td>62.00</td>\n",
1331 |        "      <td>Anandnagar</td>\n",
1332 |        "      <td>3</td>\n",
1333 |        "      <td>1440.0</td>\n",
1334 |        "      <td>4305.555556</td>\n",
1335 |        "    </tr>\n",
1336 |        "    <tr>\n",
1337 |        "      <td>3</td>\n",
1338 |        "      <td>Super built-up  Area</td>\n",
1339 |        "      <td>Ready To Move</td>\n",
1340 |        "      <td>3.0</td>\n",
1341 |        "      <td>1.0</td>\n",
1342 |        "      <td>95.00</td>\n",
1343 |        "      <td>Aundh</td>\n",
1344 |        "      <td>3</td>\n",
1345 |        "      <td>1521.0</td>\n",
1346 |        "      <td>6245.890861</td>\n",
1347 |        "    </tr>\n",
1348 |        "    <tr>\n",
1349 |        "      <td>4</td>\n",
1350 |        "      <td>Super built-up  Area</td>\n",
1351 |        "      <td>Ready To Move</td>\n",
1352 |        "      <td>2.0</td>\n",
1353 |        "      <td>1.0</td>\n",
1354 |        "      <td>51.00</td>\n",
1355 |        "      <td>Aundh Road</td>\n",
1356 |        "      <td>2</td>\n",
1357 |        "      <td>1200.0</td>\n",
1358 |        "      <td>4250.000000</td>\n",
1359 |        "    </tr>\n",
1360 |        "  </tbody>\n",
1361 |        "</table>\n",
1362 |        "</div>"
1363 |       ],
1364 |       "text/plain": [
1365 |        "              area_type   availability  bath  balcony   price  \\\n",
1366 |        "0  Super built-up  Area         19-Dec   2.0      1.0   39.07   \n",
1367 |        "1            Plot  Area  Ready To Move   5.0      3.0  120.00   \n",
1368 |        "2        Built-up  Area  Ready To Move   2.0      3.0   62.00   \n",
1369 |        "3  Super built-up  Area  Ready To Move   3.0      1.0   95.00   \n",
1370 |        "4  Super built-up  Area  Ready To Move   2.0      1.0   51.00   \n",
1371 |        "\n",
1372 |        "     site_location  bhk  new_total_sqft  price_per_sqft  \n",
1373 |        "0      Alandi Road    2          1056.0     3699.810606  \n",
1374 |        "1  Ambegaon Budruk    4          2600.0     4615.384615  \n",
1375 |        "2       Anandnagar    3          1440.0     4305.555556  \n",
1376 |        "3            Aundh    3          1521.0     6245.890861  \n",
1377 |        "4       Aundh Road    2          1200.0     4250.000000  "
1378 |       ]
1379 |      },
1380 |      "execution_count": 268,
1381 |      "metadata": {},
1382 |      "output_type": "execute_result"
1383 |     }
1384 |    ],
1385 |    "source": [
1386 |     "df1.head()"
1387 |    ]
1388 |   },
1389 |   {
1390 |    "cell_type": "code",
1391 |    "execution_count": 269,
1392 |    "metadata": {
1393 |     "scrolled": true
1394 |    },
1395 |    "outputs": [
1396 |     {
1397 |      "data": {
1398 |       "text/plain": [
1399 |        "97"
1400 |       ]
1401 |      },
1402 |      "execution_count": 269,
1403 |      "metadata": {},
1404 |      "output_type": "execute_result"
1405 |     }
1406 |    ],
1407 |    "source": [
1408 |     "# Labelling the locations with less than or equal to 10 occurences to 'other'\n",
1409 |     "locations_less_than_10 = location_stats[location_stats<=10]\n",
1410 |     "\n",
1411 |     "df1.site_location = df1.site_location.apply(lambda x: 'other' if x in locations_less_than_10 else x)\n",
1412 |     "len(df1.site_location.unique())"
1413 |    ]
1414 |   },
1415 |   {
1416 |    "cell_type": "code",
1417 |    "execution_count": 270,
1418 |    "metadata": {},
1419 |    "outputs": [
1420 |     {
1421 |      "data": {
1422 |       "text/plain": [
1423 |        "availability\n",
1424 |        "Ready To Move    10541\n",
1425 |        "18-Dec             306\n",
1426 |        "18-May             294\n",
1427 |        "18-Apr             271\n",
1428 |        "18-Aug             199\n",
1429 |        "                 ...  \n",
1430 |        "15-Jun               1\n",
1431 |        "15-Dec               1\n",
1432 |        "15-Aug               1\n",
1433 |        "14-Nov               1\n",
1434 |        "14-Jul               1\n",
1435 |        "Name: availability, Length: 80, dtype: int64"
1436 |       ]
1437 |      },
1438 |      "execution_count": 270,
1439 |      "metadata": {},
1440 |      "output_type": "execute_result"
1441 |     }
1442 |    ],
1443 |    "source": [
1444 |     "# Checking the unique values in 'availability column'\n",
1445 |     "df1.groupby('availability')['availability'].agg('count').sort_values(ascending=False)"
1446 |    ]
1447 |   },
1448 |   {
1449 |    "cell_type": "code",
1450 |    "execution_count": 271,
1451 |    "metadata": {},
1452 |    "outputs": [
1453 |     {
1454 |      "data": {
1455 |       "text/plain": [
1456 |        "2"
1457 |       ]
1458 |      },
1459 |      "execution_count": 271,
1460 |      "metadata": {},
1461 |      "output_type": "execute_result"
1462 |     }
1463 |    ],
1464 |    "source": [
1465 |     "# Labelling the dates into Not Ready\n",
1466 |     "dates = df1.groupby('availability')['availability'].agg('count').sort_values(ascending=False)\n",
1467 |     "\n",
1468 |     "dates_not_ready = dates[dates<10000]\n",
1469 |     "df1.availability = df1.availability.apply(lambda x: 'Not Ready' if x in dates_not_ready else x)\n",
1470 |     "\n",
1471 |     "len(df1.availability.unique())"
1472 |    ]
1473 |   },
1474 |   {
1475 |    "cell_type": "code",
1476 |    "execution_count": 272,
1477 |    "metadata": {},
1478 |    "outputs": [
1479 |     {
1480 |      "data": {
1481 |       "text/html": [
1482 |        "<div>\n",
1483 |        "<style scoped>\n",
1484 |        "    .dataframe tbody tr th:only-of-type {\n",
1485 |        "        vertical-align: middle;\n",
1486 |        "    }\n",
1487 |        "\n",
1488 |        "    .dataframe tbody tr th {\n",
1489 |        "        vertical-align: top;\n",
1490 |        "    }\n",
1491 |        "\n",
1492 |        "    .dataframe thead th {\n",
1493 |        "        text-align: right;\n",
1494 |        "    }\n",
1495 |        "</style>\n",
1496 |        "<table border=\"1\" class=\"dataframe\">\n",
1497 |        "  <thead>\n",
1498 |        "    <tr style=\"text-align: right;\">\n",
1499 |        "      <th></th>\n",
1500 |        "      <th>area_type</th>\n",
1501 |        "      <th>availability</th>\n",
1502 |        "      <th>bath</th>\n",
1503 |        "      <th>balcony</th>\n",
1504 |        "      <th>price</th>\n",
1505 |        "      <th>site_location</th>\n",
1506 |        "      <th>bhk</th>\n",
1507 |        "      <th>new_total_sqft</th>\n",
1508 |        "      <th>price_per_sqft</th>\n",
1509 |        "    </tr>\n",
1510 |        "  </thead>\n",
1511 |        "  <tbody>\n",
1512 |        "    <tr>\n",
1513 |        "      <td>0</td>\n",
1514 |        "      <td>Super built-up  Area</td>\n",
1515 |        "      <td>Not Ready</td>\n",
1516 |        "      <td>2.0</td>\n",
1517 |        "      <td>1.0</td>\n",
1518 |        "      <td>39.07</td>\n",
1519 |        "      <td>Alandi Road</td>\n",
1520 |        "      <td>2</td>\n",
1521 |        "      <td>1056.0</td>\n",
1522 |        "      <td>3699.810606</td>\n",
1523 |        "    </tr>\n",
1524 |        "    <tr>\n",
1525 |        "      <td>1</td>\n",
1526 |        "      <td>Plot  Area</td>\n",
1527 |        "      <td>Ready To Move</td>\n",
1528 |        "      <td>5.0</td>\n",
1529 |        "      <td>3.0</td>\n",
1530 |        "      <td>120.00</td>\n",
1531 |        "      <td>Ambegaon Budruk</td>\n",
1532 |        "      <td>4</td>\n",
1533 |        "      <td>2600.0</td>\n",
1534 |        "      <td>4615.384615</td>\n",
1535 |        "    </tr>\n",
1536 |        "    <tr>\n",
1537 |        "      <td>2</td>\n",
1538 |        "      <td>Built-up  Area</td>\n",
1539 |        "      <td>Ready To Move</td>\n",
1540 |        "      <td>2.0</td>\n",
1541 |        "      <td>3.0</td>\n",
1542 |        "      <td>62.00</td>\n",
1543 |        "      <td>Anandnagar</td>\n",
1544 |        "      <td>3</td>\n",
1545 |        "      <td>1440.0</td>\n",
1546 |        "      <td>4305.555556</td>\n",
1547 |        "    </tr>\n",
1548 |        "    <tr>\n",
1549 |        "      <td>3</td>\n",
1550 |        "      <td>Super built-up  Area</td>\n",
1551 |        "      <td>Ready To Move</td>\n",
1552 |        "      <td>3.0</td>\n",
1553 |        "      <td>1.0</td>\n",
1554 |        "      <td>95.00</td>\n",
1555 |        "      <td>Aundh</td>\n",
1556 |        "      <td>3</td>\n",
1557 |        "      <td>1521.0</td>\n",
1558 |        "      <td>6245.890861</td>\n",
1559 |        "    </tr>\n",
1560 |        "    <tr>\n",
1561 |        "      <td>4</td>\n",
1562 |        "      <td>Super built-up  Area</td>\n",
1563 |        "      <td>Ready To Move</td>\n",
1564 |        "      <td>2.0</td>\n",
1565 |        "      <td>1.0</td>\n",
1566 |        "      <td>51.00</td>\n",
1567 |        "      <td>Aundh Road</td>\n",
1568 |        "      <td>2</td>\n",
1569 |        "      <td>1200.0</td>\n",
1570 |        "      <td>4250.000000</td>\n",
1571 |        "    </tr>\n",
1572 |        "  </tbody>\n",
1573 |        "</table>\n",
1574 |        "</div>"
1575 |       ],
1576 |       "text/plain": [
1577 |        "              area_type   availability  bath  balcony   price  \\\n",
1578 |        "0  Super built-up  Area      Not Ready   2.0      1.0   39.07   \n",
1579 |        "1            Plot  Area  Ready To Move   5.0      3.0  120.00   \n",
1580 |        "2        Built-up  Area  Ready To Move   2.0      3.0   62.00   \n",
1581 |        "3  Super built-up  Area  Ready To Move   3.0      1.0   95.00   \n",
1582 |        "4  Super built-up  Area  Ready To Move   2.0      1.0   51.00   \n",
1583 |        "\n",
1584 |        "     site_location  bhk  new_total_sqft  price_per_sqft  \n",
1585 |        "0      Alandi Road    2          1056.0     3699.810606  \n",
1586 |        "1  Ambegaon Budruk    4          2600.0     4615.384615  \n",
1587 |        "2       Anandnagar    3          1440.0     4305.555556  \n",
1588 |        "3            Aundh    3          1521.0     6245.890861  \n",
1589 |        "4       Aundh Road    2          1200.0     4250.000000  "
1590 |       ]
1591 |      },
1592 |      "execution_count": 272,
1593 |      "metadata": {},
1594 |      "output_type": "execute_result"
1595 |     }
1596 |    ],
1597 |    "source": [
1598 |     "df1.head()"
1599 |    ]
1600 |   },
1601 |   {
1602 |    "cell_type": "code",
1603 |    "execution_count": 273,
1604 |    "metadata": {},
1605 |    "outputs": [
1606 |     {
1607 |      "data": {
1608 |       "text/plain": [
1609 |        "area_type\n",
1610 |        "Super built-up  Area    8778\n",
1611 |        "Built-up  Area          2402\n",
1612 |        "Plot  Area              1991\n",
1613 |        "Carpet  Area              86\n",
1614 |        "Name: area_type, dtype: int64"
1615 |       ]
1616 |      },
1617 |      "execution_count": 273,
1618 |      "metadata": {},
1619 |      "output_type": "execute_result"
1620 |     }
1621 |    ],
1622 |    "source": [
1623 |     "# Checking the unique values in 'area_type' column\n",
1624 |     "df1.groupby('area_type')['area_type'].agg('count').sort_values(ascending=False)\n",
1625 |     "\n",
1626 |     "# Since the column has only few unique values, we don't perform any operation"
1627 |    ]
1628 |   },
1629 |   {
1630 |    "cell_type": "markdown",
1631 |    "metadata": {},
1632 |    "source": [
1633 |     "## Removing Outliers"
1634 |    ]
1635 |   },
1636 |   {
1637 |    "cell_type": "code",
1638 |    "execution_count": 274,
1639 |    "metadata": {},
1640 |    "outputs": [
1641 |     {
1642 |      "name": "stdout",
1643 |      "output_type": "stream",
1644 |      "text": [
1645 |       "12513 13257\n"
1646 |      ]
1647 |     }
1648 |    ],
1649 |    "source": [
1650 |     "# Removing the rows that have 1 Room for less than 300sqft\n",
1651 |     "\n",
1652 |     "df2 = df1[~(df1.new_total_sqft/df1.bhk<300)]\n",
1653 |     "print(len(df2), len(df1))"
1654 |    ]
1655 |   },
1656 |   {
1657 |    "cell_type": "code",
1658 |    "execution_count": 275,
1659 |    "metadata": {},
1660 |    "outputs": [
1661 |     {
1662 |      "data": {
1663 |       "text/plain": [
1664 |        "count     12513.000000\n",
1665 |        "mean       6307.567166\n",
1666 |        "std        4160.879784\n",
1667 |        "min         267.829813\n",
1668 |        "25%        4211.469534\n",
1669 |        "50%        5295.138889\n",
1670 |        "75%        6916.666667\n",
1671 |        "max      176470.588235\n",
1672 |        "Name: price_per_sqft, dtype: float64"
1673 |       ]
1674 |      },
1675 |      "execution_count": 275,
1676 |      "metadata": {},
1677 |      "output_type": "execute_result"
1678 |     }
1679 |    ],
1680 |    "source": [
1681 |     "df2.price_per_sqft.describe()"
1682 |    ]
1683 |   },
1684 |   {
1685 |    "cell_type": "code",
1686 |    "execution_count": 276,
1687 |    "metadata": {},
1688 |    "outputs": [
1689 |     {
1690 |      "name": "stdout",
1691 |      "output_type": "stream",
1692 |      "text": [
1693 |       "12513 10937\n"
1694 |      ]
1695 |     }
1696 |    ],
1697 |    "source": [
1698 |     "# Since there is a wide range for 'price_per_sqft' column with min = Rs.267/sqft till max = Rs. 127470/sqft, we remove the extreme ends using the SD\n",
1699 |     "def remove_pps_outliers(df):\n",
1700 |     "    \n",
1701 |     "    df_out = pd.DataFrame()\n",
1702 |     "    \n",
1703 |     "    for key, sub_df in df.groupby('site_location'):\n",
1704 |     "        m = np.mean(sub_df.price_per_sqft)\n",
1705 |     "        sd = np.std(sub_df.price_per_sqft)\n",
1706 |     "        reduce_df = sub_df[(sub_df.price_per_sqft>(m-sd)) & (sub_df.price_per_sqft<(m+sd))]\n",
1707 |     "        df_out = pd.concat([df_out, reduce_df], ignore_index=True)\n",
1708 |     "    \n",
1709 |     "    return df_out\n",
1710 |     "\n",
1711 |     "df3 = remove_pps_outliers(df2)\n",
1712 |     "print(len(df2), len(df3))"
1713 |    ]
1714 |   },
1715 |   {
1716 |    "cell_type": "code",
1717 |    "execution_count": 277,
1718 |    "metadata": {},
1719 |    "outputs": [
1720 |     {
1721 |      "data": {
1722 |       "image/png": "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\n",
1723 |       "text/plain": [
1724 |        "<Figure size 1080x720 with 1 Axes>"
1725 |       ]
1726 |      },
1727 |      "metadata": {
1728 |       "needs_background": "light"
1729 |      },
1730 |      "output_type": "display_data"
1731 |     }
1732 |    ],
1733 |    "source": [
1734 |     "def plot_scatter_chart(df, site_location):\n",
1735 |     "    bhk2 = df[(df.site_location == site_location) & (df.bhk == 2)]\n",
1736 |     "    bhk3 = df[(df.site_location == site_location) & (df.bhk == 3)]\n",
1737 |     "    rcP['figure.figsize'] = (15,10)\n",
1738 |     "    plt.scatter(bhk2.new_total_sqft, bhk2.price, color='blue', label='2 BHK', s=50)\n",
1739 |     "    plt.scatter(bhk3.new_total_sqft, bhk3.price, color='green', marker='+', label='3 BHK', s=50)\n",
1740 |     "    plt.xlabel('Total Square Feet Area')\n",
1741 |     "    plt.ylabel('Price (in Lakhs)')\n",
1742 |     "    plt.title(site_location)\n",
1743 |     "    plt.legend()\n",
1744 |     "    \n",
1745 |     "plot_scatter_chart(df3, 'Hadapsar')"
1746 |    ]
1747 |   },
1748 |   {
1749 |    "cell_type": "code",
1750 |    "execution_count": 278,
1751 |    "metadata": {},
1752 |    "outputs": [
1753 |     {
1754 |      "name": "stdout",
1755 |      "output_type": "stream",
1756 |      "text": [
1757 |       "10937 7459\n"
1758 |      ]
1759 |     }
1760 |    ],
1761 |    "source": [
1762 |     "# Here we observe that 3 BHK cost that same as 2 BHK in 'Hebbal' location hence removing such outliers is necessary\n",
1763 |     "def remove_bhk_outliers(df):\n",
1764 |     "    exclude_indices = np.array([])\n",
1765 |     "    \n",
1766 |     "    for site_location, site_location_df in df.groupby('site_location'):\n",
1767 |     "        bhk_stats = {}\n",
1768 |     "        \n",
1769 |     "        for bhk, bhk_df in site_location_df.groupby('bhk'):\n",
1770 |     "            bhk_stats[bhk] = {\n",
1771 |     "                'mean': np.mean(bhk_df.price_per_sqft),\n",
1772 |     "                'std': np.std(bhk_df.price_per_sqft),\n",
1773 |     "                'count': bhk_df.shape[0]\n",
1774 |     "            }\n",
1775 |     "        \n",
1776 |     "        for bhk, bhk_df in site_location_df.groupby('bhk'):\n",
1777 |     "            stats = bhk_stats.get(bhk-1)\n",
1778 |     "            if stats and stats['count']>5:\n",
1779 |     "                exclude_indices = np.append(exclude_indices, bhk_df[bhk_df.price_per_sqft<(stats['mean'])].index.values)\n",
1780 |     "    \n",
1781 |     "    return df.drop(exclude_indices, axis='index')\n",
1782 |     "\n",
1783 |     "df4 = remove_bhk_outliers(df3)\n",
1784 |     "print(len(df3), len(df4))"
1785 |    ]
1786 |   },
1787 |   {
1788 |    "cell_type": "code",
1789 |    "execution_count": 279,
1790 |    "metadata": {},
1791 |    "outputs": [
1792 |     {
1793 |      "data": {
1794 |       "image/png": "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\n",
1795 |       "text/plain": [
1796 |        "<Figure size 1080x720 with 1 Axes>"
1797 |       ]
1798 |      },
1799 |      "metadata": {
1800 |       "needs_background": "light"
1801 |      },
1802 |      "output_type": "display_data"
1803 |     }
1804 |    ],
1805 |    "source": [
1806 |     "plot_scatter_chart(df4, 'Hadapsar')"
1807 |    ]
1808 |   },
1809 |   {
1810 |    "cell_type": "code",
1811 |    "execution_count": 280,
1812 |    "metadata": {},
1813 |    "outputs": [
1814 |     {
1815 |      "data": {
1816 |       "text/plain": [
1817 |        "Text(0, 0.5, 'Count')"
1818 |       ]
1819 |      },
1820 |      "execution_count": 280,
1821 |      "metadata": {},
1822 |      "output_type": "execute_result"
1823 |     },
1824 |     {
1825 |      "data": {
1826 |       "image/png": "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\n",
1827 |       "text/plain": [
1828 |        "<Figure size 1080x720 with 1 Axes>"
1829 |       ]
1830 |      },
1831 |      "metadata": {
1832 |       "needs_background": "light"
1833 |      },
1834 |      "output_type": "display_data"
1835 |     }
1836 |    ],
1837 |    "source": [
1838 |     "plt.hist(df4.price_per_sqft, rwidth=0.5)\n",
1839 |     "plt.xlabel('Price Per Square Feet')\n",
1840 |     "plt.ylabel('Count')"
1841 |    ]
1842 |   },
1843 |   {
1844 |    "cell_type": "code",
1845 |    "execution_count": 281,
1846 |    "metadata": {},
1847 |    "outputs": [
1848 |     {
1849 |      "data": {
1850 |       "text/plain": [
1851 |        "Text(0, 0.5, 'Count')"
1852 |       ]
1853 |      },
1854 |      "execution_count": 281,
1855 |      "metadata": {},
1856 |      "output_type": "execute_result"
1857 |     },
1858 |     {
1859 |      "data": {
1860 |       "image/png": "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\n",
1861 |       "text/plain": [
1862 |        "<Figure size 1080x720 with 1 Axes>"
1863 |       ]
1864 |      },
1865 |      "metadata": {
1866 |       "needs_background": "light"
1867 |      },
1868 |      "output_type": "display_data"
1869 |     }
1870 |    ],
1871 |    "source": [
1872 |     "plt.hist(df4.bath, rwidth=0.5)\n",
1873 |     "plt.xlabel('Number of Bathrooms')\n",
1874 |     "plt.ylabel('Count')"
1875 |    ]
1876 |   },
1877 |   {
1878 |    "cell_type": "code",
1879 |    "execution_count": 282,
1880 |    "metadata": {
1881 |     "scrolled": true
1882 |    },
1883 |    "outputs": [
1884 |     {
1885 |      "name": "stdout",
1886 |      "output_type": "stream",
1887 |      "text": [
1888 |       "7459 7395\n"
1889 |      ]
1890 |     }
1891 |    ],
1892 |    "source": [
1893 |     "# Removing the rows that have 'bath' greater than 'bhk'+2\n",
1894 |     "df5 = df4[df4.bath<(df4.bhk+2)]\n",
1895 |     "print(len(df4), len(df5))"
1896 |    ]
1897 |   },
1898 |   {
1899 |    "cell_type": "code",
1900 |    "execution_count": 283,
1901 |    "metadata": {},
1902 |    "outputs": [
1903 |     {
1904 |      "data": {
1905 |       "text/html": [
1906 |        "<div>\n",
1907 |        "<style scoped>\n",
1908 |        "    .dataframe tbody tr th:only-of-type {\n",
1909 |        "        vertical-align: middle;\n",
1910 |        "    }\n",
1911 |        "\n",
1912 |        "    .dataframe tbody tr th {\n",
1913 |        "        vertical-align: top;\n",
1914 |        "    }\n",
1915 |        "\n",
1916 |        "    .dataframe thead th {\n",
1917 |        "        text-align: right;\n",
1918 |        "    }\n",
1919 |        "</style>\n",
1920 |        "<table border=\"1\" class=\"dataframe\">\n",
1921 |        "  <thead>\n",
1922 |        "    <tr style=\"text-align: right;\">\n",
1923 |        "      <th></th>\n",
1924 |        "      <th>area_type</th>\n",
1925 |        "      <th>availability</th>\n",
1926 |        "      <th>bath</th>\n",
1927 |        "      <th>balcony</th>\n",
1928 |        "      <th>price</th>\n",
1929 |        "      <th>site_location</th>\n",
1930 |        "      <th>bhk</th>\n",
1931 |        "      <th>new_total_sqft</th>\n",
1932 |        "      <th>price_per_sqft</th>\n",
1933 |        "    </tr>\n",
1934 |        "  </thead>\n",
1935 |        "  <tbody>\n",
1936 |        "    <tr>\n",
1937 |        "      <td>10923</td>\n",
1938 |        "      <td>Super built-up  Area</td>\n",
1939 |        "      <td>Not Ready</td>\n",
1940 |        "      <td>2.0</td>\n",
1941 |        "      <td>1.0</td>\n",
1942 |        "      <td>67.0</td>\n",
1943 |        "      <td>Yerawada</td>\n",
1944 |        "      <td>2</td>\n",
1945 |        "      <td>1165.0</td>\n",
1946 |        "      <td>5751.072961</td>\n",
1947 |        "    </tr>\n",
1948 |        "    <tr>\n",
1949 |        "      <td>10928</td>\n",
1950 |        "      <td>Built-up  Area</td>\n",
1951 |        "      <td>Ready To Move</td>\n",
1952 |        "      <td>6.0</td>\n",
1953 |        "      <td>2.0</td>\n",
1954 |        "      <td>115.0</td>\n",
1955 |        "      <td>Yerawada</td>\n",
1956 |        "      <td>6</td>\n",
1957 |        "      <td>3500.0</td>\n",
1958 |        "      <td>3285.714286</td>\n",
1959 |        "    </tr>\n",
1960 |        "    <tr>\n",
1961 |        "      <td>10931</td>\n",
1962 |        "      <td>Built-up  Area</td>\n",
1963 |        "      <td>Not Ready</td>\n",
1964 |        "      <td>2.0</td>\n",
1965 |        "      <td>2.0</td>\n",
1966 |        "      <td>353.0</td>\n",
1967 |        "      <td>Yerawada</td>\n",
1968 |        "      <td>5</td>\n",
1969 |        "      <td>3210.0</td>\n",
1970 |        "      <td>10996.884735</td>\n",
1971 |        "    </tr>\n",
1972 |        "    <tr>\n",
1973 |        "      <td>10932</td>\n",
1974 |        "      <td>Super built-up  Area</td>\n",
1975 |        "      <td>Ready To Move</td>\n",
1976 |        "      <td>2.0</td>\n",
1977 |        "      <td>2.0</td>\n",
1978 |        "      <td>54.0</td>\n",
1979 |        "      <td>Yerawada</td>\n",
1980 |        "      <td>2</td>\n",
1981 |        "      <td>1050.0</td>\n",
1982 |        "      <td>5142.857143</td>\n",
1983 |        "    </tr>\n",
1984 |        "    <tr>\n",
1985 |        "      <td>10936</td>\n",
1986 |        "      <td>Super built-up  Area</td>\n",
1987 |        "      <td>Not Ready</td>\n",
1988 |        "      <td>2.0</td>\n",
1989 |        "      <td>1.0</td>\n",
1990 |        "      <td>70.0</td>\n",
1991 |        "      <td>Yerawada</td>\n",
1992 |        "      <td>2</td>\n",
1993 |        "      <td>1132.0</td>\n",
1994 |        "      <td>6183.745583</td>\n",
1995 |        "    </tr>\n",
1996 |        "  </tbody>\n",
1997 |        "</table>\n",
1998 |        "</div>"
1999 |       ],
2000 |       "text/plain": [
2001 |        "                  area_type   availability  bath  balcony  price  \\\n",
2002 |        "10923  Super built-up  Area      Not Ready   2.0      1.0   67.0   \n",
2003 |        "10928        Built-up  Area  Ready To Move   6.0      2.0  115.0   \n",
2004 |        "10931        Built-up  Area      Not Ready   2.0      2.0  353.0   \n",
2005 |        "10932  Super built-up  Area  Ready To Move   2.0      2.0   54.0   \n",
2006 |        "10936  Super built-up  Area      Not Ready   2.0      1.0   70.0   \n",
2007 |        "\n",
2008 |        "      site_location  bhk  new_total_sqft  price_per_sqft  \n",
2009 |        "10923      Yerawada    2          1165.0     5751.072961  \n",
2010 |        "10928      Yerawada    6          3500.0     3285.714286  \n",
2011 |        "10931      Yerawada    5          3210.0    10996.884735  \n",
2012 |        "10932      Yerawada    2          1050.0     5142.857143  \n",
2013 |        "10936      Yerawada    2          1132.0     6183.745583  "
2014 |       ]
2015 |      },
2016 |      "execution_count": 283,
2017 |      "metadata": {},
2018 |      "output_type": "execute_result"
2019 |     }
2020 |    ],
2021 |    "source": [
2022 |     "df5.tail()"
2023 |    ]
2024 |   },
2025 |   {
2026 |    "cell_type": "markdown",
2027 |    "metadata": {},
2028 |    "source": [
2029 |     "## Model Building"
2030 |    ]
2031 |   },
2032 |   {
2033 |    "cell_type": "code",
2034 |    "execution_count": 284,
2035 |    "metadata": {},
2036 |    "outputs": [],
2037 |    "source": [
2038 |     "# Removing the unnecessary columns (columns that were added only for removing the outliers)\n",
2039 |     "df6 = df5.copy()\n",
2040 |     "df6 = df6.drop('price_per_sqft', axis='columns')"
2041 |    ]
2042 |   },
2043 |   {
2044 |    "cell_type": "code",
2045 |    "execution_count": 285,
2046 |    "metadata": {},
2047 |    "outputs": [
2048 |     {
2049 |      "data": {
2050 |       "text/html": [
2051 |        "<div>\n",
2052 |        "<style scoped>\n",
2053 |        "    .dataframe tbody tr th:only-of-type {\n",
2054 |        "        vertical-align: middle;\n",
2055 |        "    }\n",
2056 |        "\n",
2057 |        "    .dataframe tbody tr th {\n",
2058 |        "        vertical-align: top;\n",
2059 |        "    }\n",
2060 |        "\n",
2061 |        "    .dataframe thead th {\n",
2062 |        "        text-align: right;\n",
2063 |        "    }\n",
2064 |        "</style>\n",
2065 |        "<table border=\"1\" class=\"dataframe\">\n",
2066 |        "  <thead>\n",
2067 |        "    <tr style=\"text-align: right;\">\n",
2068 |        "      <th></th>\n",
2069 |        "      <th>area_type</th>\n",
2070 |        "      <th>availability</th>\n",
2071 |        "      <th>bath</th>\n",
2072 |        "      <th>balcony</th>\n",
2073 |        "      <th>price</th>\n",
2074 |        "      <th>site_location</th>\n",
2075 |        "      <th>bhk</th>\n",
2076 |        "      <th>new_total_sqft</th>\n",
2077 |        "    </tr>\n",
2078 |        "  </thead>\n",
2079 |        "  <tbody>\n",
2080 |        "    <tr>\n",
2081 |        "      <td>0</td>\n",
2082 |        "      <td>Super built-up  Area</td>\n",
2083 |        "      <td>Not Ready</td>\n",
2084 |        "      <td>2.0</td>\n",
2085 |        "      <td>1.0</td>\n",
2086 |        "      <td>39.07</td>\n",
2087 |        "      <td>Alandi Road</td>\n",
2088 |        "      <td>2</td>\n",
2089 |        "      <td>1056.0</td>\n",
2090 |        "    </tr>\n",
2091 |        "    <tr>\n",
2092 |        "      <td>1</td>\n",
2093 |        "      <td>Plot  Area</td>\n",
2094 |        "      <td>Ready To Move</td>\n",
2095 |        "      <td>4.0</td>\n",
2096 |        "      <td>1.0</td>\n",
2097 |        "      <td>245.00</td>\n",
2098 |        "      <td>Alandi Road</td>\n",
2099 |        "      <td>4</td>\n",
2100 |        "      <td>2894.0</td>\n",
2101 |        "    </tr>\n",
2102 |        "    <tr>\n",
2103 |        "      <td>2</td>\n",
2104 |        "      <td>Super built-up  Area</td>\n",
2105 |        "      <td>Ready To Move</td>\n",
2106 |        "      <td>2.0</td>\n",
2107 |        "      <td>2.0</td>\n",
2108 |        "      <td>50.00</td>\n",
2109 |        "      <td>Alandi Road</td>\n",
2110 |        "      <td>2</td>\n",
2111 |        "      <td>1084.0</td>\n",
2112 |        "    </tr>\n",
2113 |        "    <tr>\n",
2114 |        "      <td>3</td>\n",
2115 |        "      <td>Super built-up  Area</td>\n",
2116 |        "      <td>Ready To Move</td>\n",
2117 |        "      <td>2.0</td>\n",
2118 |        "      <td>2.0</td>\n",
2119 |        "      <td>80.00</td>\n",
2120 |        "      <td>Alandi Road</td>\n",
2121 |        "      <td>2</td>\n",
2122 |        "      <td>1230.0</td>\n",
2123 |        "    </tr>\n",
2124 |        "    <tr>\n",
2125 |        "      <td>4</td>\n",
2126 |        "      <td>Super built-up  Area</td>\n",
2127 |        "      <td>Ready To Move</td>\n",
2128 |        "      <td>3.0</td>\n",
2129 |        "      <td>2.0</td>\n",
2130 |        "      <td>130.00</td>\n",
2131 |        "      <td>Alandi Road</td>\n",
2132 |        "      <td>3</td>\n",
2133 |        "      <td>1750.0</td>\n",
2134 |        "    </tr>\n",
2135 |        "  </tbody>\n",
2136 |        "</table>\n",
2137 |        "</div>"
2138 |       ],
2139 |       "text/plain": [
2140 |        "              area_type   availability  bath  balcony   price site_location  \\\n",
2141 |        "0  Super built-up  Area      Not Ready   2.0      1.0   39.07   Alandi Road   \n",
2142 |        "1            Plot  Area  Ready To Move   4.0      1.0  245.00   Alandi Road   \n",
2143 |        "2  Super built-up  Area  Ready To Move   2.0      2.0   50.00   Alandi Road   \n",
2144 |        "3  Super built-up  Area  Ready To Move   2.0      2.0   80.00   Alandi Road   \n",
2145 |        "4  Super built-up  Area  Ready To Move   3.0      2.0  130.00   Alandi Road   \n",
2146 |        "\n",
2147 |        "   bhk  new_total_sqft  \n",
2148 |        "0    2          1056.0  \n",
2149 |        "1    4          2894.0  \n",
2150 |        "2    2          1084.0  \n",
2151 |        "3    2          1230.0  \n",
2152 |        "4    3          1750.0  "
2153 |       ]
2154 |      },
2155 |      "execution_count": 285,
2156 |      "metadata": {},
2157 |      "output_type": "execute_result"
2158 |     }
2159 |    ],
2160 |    "source": [
2161 |     "df6.head()"
2162 |    ]
2163 |   },
2164 |   {
2165 |    "cell_type": "code",
2166 |    "execution_count": 286,
2167 |    "metadata": {},
2168 |    "outputs": [],
2169 |    "source": [
2170 |     "# Converting the categorical_value into numerical_values using get_dummies method\n",
2171 |     "dummy_cols = pd.get_dummies(df6.site_location)\n",
2172 |     "df6 = pd.concat([df6,dummy_cols], axis='columns')"
2173 |    ]
2174 |   },
2175 |   {
2176 |    "cell_type": "code",
2177 |    "execution_count": 287,
2178 |    "metadata": {},
2179 |    "outputs": [],
2180 |    "source": [
2181 |     "# Converting the categorical_value into numerical_values using get_dummies method\n",
2182 |     "dummy_cols = pd.get_dummies(df6.availability).drop('Not Ready', axis='columns')\n",
2183 |     "df6 = pd.concat([df6,dummy_cols], axis='columns')"
2184 |    ]
2185 |   },
2186 |   {
2187 |    "cell_type": "code",
2188 |    "execution_count": 288,
2189 |    "metadata": {},
2190 |    "outputs": [],
2191 |    "source": [
2192 |     "# Converting the categorical_value into numerical_values using get_dummies method\n",
2193 |     "dummy_cols = pd.get_dummies(df6.area_type).drop('Super built-up  Area', axis='columns')\n",
2194 |     "df6 = pd.concat([df6,dummy_cols], axis='columns')"
2195 |    ]
2196 |   },
2197 |   {
2198 |    "cell_type": "code",
2199 |    "execution_count": 289,
2200 |    "metadata": {
2201 |     "scrolled": false
2202 |    },
2203 |    "outputs": [
2204 |     {
2205 |      "data": {
2206 |       "text/html": [
2207 |        "<div>\n",
2208 |        "<style scoped>\n",
2209 |        "    .dataframe tbody tr th:only-of-type {\n",
2210 |        "        vertical-align: middle;\n",
2211 |        "    }\n",
2212 |        "\n",
2213 |        "    .dataframe tbody tr th {\n",
2214 |        "        vertical-align: top;\n",
2215 |        "    }\n",
2216 |        "\n",
2217 |        "    .dataframe thead th {\n",
2218 |        "        text-align: right;\n",
2219 |        "    }\n",
2220 |        "</style>\n",
2221 |        "<table border=\"1\" class=\"dataframe\">\n",
2222 |        "  <thead>\n",
2223 |        "    <tr style=\"text-align: right;\">\n",
2224 |        "      <th></th>\n",
2225 |        "      <th>bath</th>\n",
2226 |        "      <th>balcony</th>\n",
2227 |        "      <th>price</th>\n",
2228 |        "      <th>bhk</th>\n",
2229 |        "      <th>new_total_sqft</th>\n",
2230 |        "      <th>Alandi Road</th>\n",
2231 |        "      <th>Ambegaon Budruk</th>\n",
2232 |        "      <th>Anandnagar</th>\n",
2233 |        "      <th>Aundh</th>\n",
2234 |        "      <th>Aundh Road</th>\n",
2235 |        "      <th>...</th>\n",
2236 |        "      <th>Wadgaon Sheri</th>\n",
2237 |        "      <th>Wagholi</th>\n",
2238 |        "      <th>Wakadewadi</th>\n",
2239 |        "      <th>Wanowrie</th>\n",
2240 |        "      <th>Warje</th>\n",
2241 |        "      <th>Yerawada</th>\n",
2242 |        "      <th>Ready To Move</th>\n",
2243 |        "      <th>Built-up  Area</th>\n",
2244 |        "      <th>Carpet  Area</th>\n",
2245 |        "      <th>Plot  Area</th>\n",
2246 |        "    </tr>\n",
2247 |        "  </thead>\n",
2248 |        "  <tbody>\n",
2249 |        "    <tr>\n",
2250 |        "      <td>0</td>\n",
2251 |        "      <td>2.0</td>\n",
2252 |        "      <td>1.0</td>\n",
2253 |        "      <td>39.07</td>\n",
2254 |        "      <td>2</td>\n",
2255 |        "      <td>1056.0</td>\n",
2256 |        "      <td>1</td>\n",
2257 |        "      <td>0</td>\n",
2258 |        "      <td>0</td>\n",
2259 |        "      <td>0</td>\n",
2260 |        "      <td>0</td>\n",
2261 |        "      <td>...</td>\n",
2262 |        "      <td>0</td>\n",
2263 |        "      <td>0</td>\n",
2264 |        "      <td>0</td>\n",
2265 |        "      <td>0</td>\n",
2266 |        "      <td>0</td>\n",
2267 |        "      <td>0</td>\n",
2268 |        "      <td>0</td>\n",
2269 |        "      <td>0</td>\n",
2270 |        "      <td>0</td>\n",
2271 |        "      <td>0</td>\n",
2272 |        "    </tr>\n",
2273 |        "    <tr>\n",
2274 |        "      <td>1</td>\n",
2275 |        "      <td>4.0</td>\n",
2276 |        "      <td>1.0</td>\n",
2277 |        "      <td>245.00</td>\n",
2278 |        "      <td>4</td>\n",
2279 |        "      <td>2894.0</td>\n",
2280 |        "      <td>1</td>\n",
2281 |        "      <td>0</td>\n",
2282 |        "      <td>0</td>\n",
2283 |        "      <td>0</td>\n",
2284 |        "      <td>0</td>\n",
2285 |        "      <td>...</td>\n",
2286 |        "      <td>0</td>\n",
2287 |        "      <td>0</td>\n",
2288 |        "      <td>0</td>\n",
2289 |        "      <td>0</td>\n",
2290 |        "      <td>0</td>\n",
2291 |        "      <td>0</td>\n",
2292 |        "      <td>1</td>\n",
2293 |        "      <td>0</td>\n",
2294 |        "      <td>0</td>\n",
2295 |        "      <td>1</td>\n",
2296 |        "    </tr>\n",
2297 |        "    <tr>\n",
2298 |        "      <td>2</td>\n",
2299 |        "      <td>2.0</td>\n",
2300 |        "      <td>2.0</td>\n",
2301 |        "      <td>50.00</td>\n",
2302 |        "      <td>2</td>\n",
2303 |        "      <td>1084.0</td>\n",
2304 |        "      <td>1</td>\n",
2305 |        "      <td>0</td>\n",
2306 |        "      <td>0</td>\n",
2307 |        "      <td>0</td>\n",
2308 |        "      <td>0</td>\n",
2309 |        "      <td>...</td>\n",
2310 |        "      <td>0</td>\n",
2311 |        "      <td>0</td>\n",
2312 |        "      <td>0</td>\n",
2313 |        "      <td>0</td>\n",
2314 |        "      <td>0</td>\n",
2315 |        "      <td>0</td>\n",
2316 |        "      <td>1</td>\n",
2317 |        "      <td>0</td>\n",
2318 |        "      <td>0</td>\n",
2319 |        "      <td>0</td>\n",
2320 |        "    </tr>\n",
2321 |        "    <tr>\n",
2322 |        "      <td>3</td>\n",
2323 |        "      <td>2.0</td>\n",
2324 |        "      <td>2.0</td>\n",
2325 |        "      <td>80.00</td>\n",
2326 |        "      <td>2</td>\n",
2327 |        "      <td>1230.0</td>\n",
2328 |        "      <td>1</td>\n",
2329 |        "      <td>0</td>\n",
2330 |        "      <td>0</td>\n",
2331 |        "      <td>0</td>\n",
2332 |        "      <td>0</td>\n",
2333 |        "      <td>...</td>\n",
2334 |        "      <td>0</td>\n",
2335 |        "      <td>0</td>\n",
2336 |        "      <td>0</td>\n",
2337 |        "      <td>0</td>\n",
2338 |        "      <td>0</td>\n",
2339 |        "      <td>0</td>\n",
2340 |        "      <td>1</td>\n",
2341 |        "      <td>0</td>\n",
2342 |        "      <td>0</td>\n",
2343 |        "      <td>0</td>\n",
2344 |        "    </tr>\n",
2345 |        "    <tr>\n",
2346 |        "      <td>4</td>\n",
2347 |        "      <td>3.0</td>\n",
2348 |        "      <td>2.0</td>\n",
2349 |        "      <td>130.00</td>\n",
2350 |        "      <td>3</td>\n",
2351 |        "      <td>1750.0</td>\n",
2352 |        "      <td>1</td>\n",
2353 |        "      <td>0</td>\n",
2354 |        "      <td>0</td>\n",
2355 |        "      <td>0</td>\n",
2356 |        "      <td>0</td>\n",
2357 |        "      <td>...</td>\n",
2358 |        "      <td>0</td>\n",
2359 |        "      <td>0</td>\n",
2360 |        "      <td>0</td>\n",
2361 |        "      <td>0</td>\n",
2362 |        "      <td>0</td>\n",
2363 |        "      <td>0</td>\n",
2364 |        "      <td>1</td>\n",
2365 |        "      <td>0</td>\n",
2366 |        "      <td>0</td>\n",
2367 |        "      <td>0</td>\n",
2368 |        "    </tr>\n",
2369 |        "    <tr>\n",
2370 |        "      <td>5</td>\n",
2371 |        "      <td>2.0</td>\n",
2372 |        "      <td>1.0</td>\n",
2373 |        "      <td>41.00</td>\n",
2374 |        "      <td>2</td>\n",
2375 |        "      <td>995.0</td>\n",
2376 |        "      <td>1</td>\n",
2377 |        "      <td>0</td>\n",
2378 |        "      <td>0</td>\n",
2379 |        "      <td>0</td>\n",
2380 |        "      <td>0</td>\n",
2381 |        "      <td>...</td>\n",
2382 |        "      <td>0</td>\n",
2383 |        "      <td>0</td>\n",
2384 |        "      <td>0</td>\n",
2385 |        "      <td>0</td>\n",
2386 |        "      <td>0</td>\n",
2387 |        "      <td>0</td>\n",
2388 |        "      <td>1</td>\n",
2389 |        "      <td>1</td>\n",
2390 |        "      <td>0</td>\n",
2391 |        "      <td>0</td>\n",
2392 |        "    </tr>\n",
2393 |        "    <tr>\n",
2394 |        "      <td>8</td>\n",
2395 |        "      <td>2.0</td>\n",
2396 |        "      <td>1.0</td>\n",
2397 |        "      <td>95.00</td>\n",
2398 |        "      <td>2</td>\n",
2399 |        "      <td>1360.0</td>\n",
2400 |        "      <td>1</td>\n",
2401 |        "      <td>0</td>\n",
2402 |        "      <td>0</td>\n",
2403 |        "      <td>0</td>\n",
2404 |        "      <td>0</td>\n",
2405 |        "      <td>...</td>\n",
2406 |        "      <td>0</td>\n",
2407 |        "      <td>0</td>\n",
2408 |        "      <td>0</td>\n",
2409 |        "      <td>0</td>\n",
2410 |        "      <td>0</td>\n",
2411 |        "      <td>0</td>\n",
2412 |        "      <td>1</td>\n",
2413 |        "      <td>0</td>\n",
2414 |        "      <td>0</td>\n",
2415 |        "      <td>0</td>\n",
2416 |        "    </tr>\n",
2417 |        "    <tr>\n",
2418 |        "      <td>9</td>\n",
2419 |        "      <td>2.0</td>\n",
2420 |        "      <td>2.0</td>\n",
2421 |        "      <td>50.00</td>\n",
2422 |        "      <td>2</td>\n",
2423 |        "      <td>1040.0</td>\n",
2424 |        "      <td>1</td>\n",
2425 |        "      <td>0</td>\n",
2426 |        "      <td>0</td>\n",
2427 |        "      <td>0</td>\n",
2428 |        "      <td>0</td>\n",
2429 |        "      <td>...</td>\n",
2430 |        "      <td>0</td>\n",
2431 |        "      <td>0</td>\n",
2432 |        "      <td>0</td>\n",
2433 |        "      <td>0</td>\n",
2434 |        "      <td>0</td>\n",
2435 |        "      <td>0</td>\n",
2436 |        "      <td>1</td>\n",
2437 |        "      <td>1</td>\n",
2438 |        "      <td>0</td>\n",
2439 |        "      <td>0</td>\n",
2440 |        "    </tr>\n",
2441 |        "    <tr>\n",
2442 |        "      <td>10</td>\n",
2443 |        "      <td>3.0</td>\n",
2444 |        "      <td>2.0</td>\n",
2445 |        "      <td>86.06</td>\n",
2446 |        "      <td>3</td>\n",
2447 |        "      <td>1655.0</td>\n",
2448 |        "      <td>1</td>\n",
2449 |        "      <td>0</td>\n",
2450 |        "      <td>0</td>\n",
2451 |        "      <td>0</td>\n",
2452 |        "      <td>0</td>\n",
2453 |        "      <td>...</td>\n",
2454 |        "      <td>0</td>\n",
2455 |        "      <td>0</td>\n",
2456 |        "      <td>0</td>\n",
2457 |        "      <td>0</td>\n",
2458 |        "      <td>0</td>\n",
2459 |        "      <td>0</td>\n",
2460 |        "      <td>1</td>\n",
2461 |        "      <td>0</td>\n",
2462 |        "      <td>0</td>\n",
2463 |        "      <td>0</td>\n",
2464 |        "    </tr>\n",
2465 |        "    <tr>\n",
2466 |        "      <td>12</td>\n",
2467 |        "      <td>5.0</td>\n",
2468 |        "      <td>3.0</td>\n",
2469 |        "      <td>198.00</td>\n",
2470 |        "      <td>4</td>\n",
2471 |        "      <td>2790.0</td>\n",
2472 |        "      <td>1</td>\n",
2473 |        "      <td>0</td>\n",
2474 |        "      <td>0</td>\n",
2475 |        "      <td>0</td>\n",
2476 |        "      <td>0</td>\n",
2477 |        "      <td>...</td>\n",
2478 |        "      <td>0</td>\n",
2479 |        "      <td>0</td>\n",
2480 |        "      <td>0</td>\n",
2481 |        "      <td>0</td>\n",
2482 |        "      <td>0</td>\n",
2483 |        "      <td>0</td>\n",
2484 |        "      <td>0</td>\n",
2485 |        "      <td>0</td>\n",
2486 |        "      <td>0</td>\n",
2487 |        "      <td>0</td>\n",
2488 |        "    </tr>\n",
2489 |        "  </tbody>\n",
2490 |        "</table>\n",
2491 |        "<p>10 rows × 105 columns</p>\n",
2492 |        "</div>"
2493 |       ],
2494 |       "text/plain": [
2495 |        "    bath  balcony   price  bhk  new_total_sqft  Alandi Road  Ambegaon Budruk  \\\n",
2496 |        "0    2.0      1.0   39.07    2          1056.0            1                0   \n",
2497 |        "1    4.0      1.0  245.00    4          2894.0            1                0   \n",
2498 |        "2    2.0      2.0   50.00    2          1084.0            1                0   \n",
2499 |        "3    2.0      2.0   80.00    2          1230.0            1                0   \n",
2500 |        "4    3.0      2.0  130.00    3          1750.0            1                0   \n",
2501 |        "5    2.0      1.0   41.00    2           995.0            1                0   \n",
2502 |        "8    2.0      1.0   95.00    2          1360.0            1                0   \n",
2503 |        "9    2.0      2.0   50.00    2          1040.0            1                0   \n",
2504 |        "10   3.0      2.0   86.06    3          1655.0            1                0   \n",
2505 |        "12   5.0      3.0  198.00    4          2790.0            1                0   \n",
2506 |        "\n",
2507 |        "    Anandnagar  Aundh  Aundh Road  ...  Wadgaon Sheri  Wagholi  Wakadewadi  \\\n",
2508 |        "0            0      0           0  ...              0        0           0   \n",
2509 |        "1            0      0           0  ...              0        0           0   \n",
2510 |        "2            0      0           0  ...              0        0           0   \n",
2511 |        "3            0      0           0  ...              0        0           0   \n",
2512 |        "4            0      0           0  ...              0        0           0   \n",
2513 |        "5            0      0           0  ...              0        0           0   \n",
2514 |        "8            0      0           0  ...              0        0           0   \n",
2515 |        "9            0      0           0  ...              0        0           0   \n",
2516 |        "10           0      0           0  ...              0        0           0   \n",
2517 |        "12           0      0           0  ...              0        0           0   \n",
2518 |        "\n",
2519 |        "    Wanowrie  Warje  Yerawada  Ready To Move  Built-up  Area  Carpet  Area  \\\n",
2520 |        "0          0      0         0              0               0             0   \n",
2521 |        "1          0      0         0              1               0             0   \n",
2522 |        "2          0      0         0              1               0             0   \n",
2523 |        "3          0      0         0              1               0             0   \n",
2524 |        "4          0      0         0              1               0             0   \n",
2525 |        "5          0      0         0              1               1             0   \n",
2526 |        "8          0      0         0              1               0             0   \n",
2527 |        "9          0      0         0              1               1             0   \n",
2528 |        "10         0      0         0              1               0             0   \n",
2529 |        "12         0      0         0              0               0             0   \n",
2530 |        "\n",
2531 |        "    Plot  Area  \n",
2532 |        "0            0  \n",
2533 |        "1            1  \n",
2534 |        "2            0  \n",
2535 |        "3            0  \n",
2536 |        "4            0  \n",
2537 |        "5            0  \n",
2538 |        "8            0  \n",
2539 |        "9            0  \n",
2540 |        "10           0  \n",
2541 |        "12           0  \n",
2542 |        "\n",
2543 |        "[10 rows x 105 columns]"
2544 |       ]
2545 |      },
2546 |      "execution_count": 289,
2547 |      "metadata": {},
2548 |      "output_type": "execute_result"
2549 |     }
2550 |    ],
2551 |    "source": [
2552 |     "df6.drop(['area_type','availability','site_location'], axis='columns', inplace=True)\n",
2553 |     "df6.head(10)"
2554 |    ]
2555 |   },
2556 |   {
2557 |    "cell_type": "code",
2558 |    "execution_count": 290,
2559 |    "metadata": {},
2560 |    "outputs": [
2561 |     {
2562 |      "data": {
2563 |       "text/plain": [
2564 |        "(7395, 105)"
2565 |       ]
2566 |      },
2567 |      "execution_count": 290,
2568 |      "metadata": {},
2569 |      "output_type": "execute_result"
2570 |     }
2571 |    ],
2572 |    "source": [
2573 |     "# Size of the dataset\n",
2574 |     "df6.shape"
2575 |    ]
2576 |   },
2577 |   {
2578 |    "cell_type": "code",
2579 |    "execution_count": 291,
2580 |    "metadata": {},
2581 |    "outputs": [],
2582 |    "source": [
2583 |     "# Splitting the dataset into features and label\n",
2584 |     "X = df6.drop('price', axis='columns')\n",
2585 |     "y = df6['price']"
2586 |    ]
2587 |   },
2588 |   {
2589 |    "cell_type": "code",
2590 |    "execution_count": 292,
2591 |    "metadata": {},
2592 |    "outputs": [],
2593 |    "source": [
2594 |     "# Using GridSearchCV to find the best algorithm for this problem\n",
2595 |     "from sklearn.model_selection import GridSearchCV\n",
2596 |     "from sklearn.model_selection import ShuffleSplit\n",
2597 |     "from sklearn.linear_model import LinearRegression\n",
2598 |     "from sklearn.linear_model import Lasso\n",
2599 |     "from sklearn.tree import DecisionTreeRegressor"
2600 |    ]
2601 |   },
2602 |   {
2603 |    "cell_type": "code",
2604 |    "execution_count": 293,
2605 |    "metadata": {},
2606 |    "outputs": [
2607 |     {
2608 |      "data": {
2609 |       "text/html": [
2610 |        "<div>\n",
2611 |        "<style scoped>\n",
2612 |        "    .dataframe tbody tr th:only-of-type {\n",
2613 |        "        vertical-align: middle;\n",
2614 |        "    }\n",
2615 |        "\n",
2616 |        "    .dataframe tbody tr th {\n",
2617 |        "        vertical-align: top;\n",
2618 |        "    }\n",
2619 |        "\n",
2620 |        "    .dataframe thead th {\n",
2621 |        "        text-align: right;\n",
2622 |        "    }\n",
2623 |        "</style>\n",
2624 |        "<table border=\"1\" class=\"dataframe\">\n",
2625 |        "  <thead>\n",
2626 |        "    <tr style=\"text-align: right;\">\n",
2627 |        "      <th></th>\n",
2628 |        "      <th>model</th>\n",
2629 |        "      <th>best_parameters</th>\n",
2630 |        "      <th>accuracy</th>\n",
2631 |        "    </tr>\n",
2632 |        "  </thead>\n",
2633 |        "  <tbody>\n",
2634 |        "    <tr>\n",
2635 |        "      <td>0</td>\n",
2636 |        "      <td>linear_regression</td>\n",
2637 |        "      <td>{'normalize': True}</td>\n",
2638 |        "      <td>0.835475</td>\n",
2639 |        "    </tr>\n",
2640 |        "    <tr>\n",
2641 |        "      <td>1</td>\n",
2642 |        "      <td>lasso</td>\n",
2643 |        "      <td>{'alpha': 2, 'selection': 'random'}</td>\n",
2644 |        "      <td>0.829241</td>\n",
2645 |        "    </tr>\n",
2646 |        "    <tr>\n",
2647 |        "      <td>2</td>\n",
2648 |        "      <td>decision_tree</td>\n",
2649 |        "      <td>{'criterion': 'mse', 'splitter': 'best'}</td>\n",
2650 |        "      <td>0.781004</td>\n",
2651 |        "    </tr>\n",
2652 |        "  </tbody>\n",
2653 |        "</table>\n",
2654 |        "</div>"
2655 |       ],
2656 |       "text/plain": [
2657 |        "               model                           best_parameters  accuracy\n",
2658 |        "0  linear_regression                       {'normalize': True}  0.835475\n",
2659 |        "1              lasso       {'alpha': 2, 'selection': 'random'}  0.829241\n",
2660 |        "2      decision_tree  {'criterion': 'mse', 'splitter': 'best'}  0.781004"
2661 |       ]
2662 |      },
2663 |      "execution_count": 293,
2664 |      "metadata": {},
2665 |      "output_type": "execute_result"
2666 |     }
2667 |    ],
2668 |    "source": [
2669 |     "# Creating a function for GridSearchCV\n",
2670 |     "\n",
2671 |     "def find_best_model(X, y):\n",
2672 |     "    models = {\n",
2673 |     "        'linear_regression': {\n",
2674 |     "            'model': LinearRegression(),\n",
2675 |     "            'parameters': {\n",
2676 |     "                'normalize': [True,False]\n",
2677 |     "            }\n",
2678 |     "        },\n",
2679 |     "        \n",
2680 |     "        'lasso': {\n",
2681 |     "            'model': Lasso(),\n",
2682 |     "            'parameters': {\n",
2683 |     "                'alpha': [1,2],\n",
2684 |     "                'selection': ['random', 'cyclic']\n",
2685 |     "            }\n",
2686 |     "        },\n",
2687 |     "        \n",
2688 |     "        'decision_tree': {\n",
2689 |     "            'model': DecisionTreeRegressor(),\n",
2690 |     "            'parameters': {\n",
2691 |     "                'criterion': ['mse', 'friedman_mse'],\n",
2692 |     "                'splitter': ['best', 'random']\n",
2693 |     "            }\n",
2694 |     "        }\n",
2695 |     "    }\n",
2696 |     "    \n",
2697 |     "    scores = []\n",
2698 |     "    cv_X_y = ShuffleSplit(n_splits=5, test_size=0.20, random_state=0)\n",
2699 |     "    \n",
2700 |     "    for model_name, model_params in models.items():\n",
2701 |     "        gs = GridSearchCV(model_params['model'], model_params['parameters'], cv=cv_X_y, return_train_score=False)\n",
2702 |     "        gs.fit(X, y)\n",
2703 |     "        scores.append({\n",
2704 |     "            'model': model_name,\n",
2705 |     "            'best_parameters': gs.best_params_,\n",
2706 |     "            'accuracy': gs.best_score_\n",
2707 |     "        })\n",
2708 |     "        \n",
2709 |     "    return pd.DataFrame(scores, columns=['model', 'best_parameters', 'accuracy'])\n",
2710 |     "\n",
2711 |     "find_best_model(X, y)"
2712 |    ]
2713 |   },
2714 |   {
2715 |    "cell_type": "markdown",
2716 |    "metadata": {},
2717 |    "source": [
2718 |     "#### Since the Linear Regression has the highest accuracy, the model selected for this problem is Linear Regression"
2719 |    ]
2720 |   },
2721 |   {
2722 |    "cell_type": "code",
2723 |    "execution_count": 294,
2724 |    "metadata": {},
2725 |    "outputs": [],
2726 |    "source": [
2727 |     "# Splitting the dataset into train and test set\n",
2728 |     "from sklearn.model_selection import train_test_split\n",
2729 |     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=20)"
2730 |    ]
2731 |   },
2732 |   {
2733 |    "cell_type": "code",
2734 |    "execution_count": 295,
2735 |    "metadata": {},
2736 |    "outputs": [
2737 |     {
2738 |      "data": {
2739 |       "text/plain": [
2740 |        "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=True)"
2741 |       ]
2742 |      },
2743 |      "execution_count": 295,
2744 |      "metadata": {},
2745 |      "output_type": "execute_result"
2746 |     }
2747 |    ],
2748 |    "source": [
2749 |     "# Creating Linear Regression Model\n",
2750 |     "from sklearn.linear_model import LinearRegression\n",
2751 |     "model = LinearRegression(normalize=True)\n",
2752 |     "model.fit(X_train, y_train)"
2753 |    ]
2754 |   },
2755 |   {
2756 |    "cell_type": "code",
2757 |    "execution_count": 296,
2758 |    "metadata": {},
2759 |    "outputs": [
2760 |     {
2761 |      "data": {
2762 |       "text/plain": [
2763 |        "0.8180571987758956"
2764 |       ]
2765 |      },
2766 |      "execution_count": 296,
2767 |      "metadata": {},
2768 |      "output_type": "execute_result"
2769 |     }
2770 |    ],
2771 |    "source": [
2772 |     "model.score(X_test, y_test)"
2773 |    ]
2774 |   },
2775 |   {
2776 |    "cell_type": "markdown",
2777 |    "metadata": {},
2778 |    "source": [
2779 |     "#### Predicting the values using our trained model"
2780 |    ]
2781 |   },
2782 |   {
2783 |    "cell_type": "code",
2784 |    "execution_count": 297,
2785 |    "metadata": {},
2786 |    "outputs": [
2787 |     {
2788 |      "data": {
2789 |       "text/plain": [
2790 |        "Index(['bath', 'balcony', 'bhk', 'new_total_sqft', 'Alandi Road',\n",
2791 |        "       'Ambegaon Budruk', 'Anandnagar', 'Aundh', 'Aundh Road', 'Balaji Nagar',\n",
2792 |        "       ...\n",
2793 |        "       'Wadgaon Sheri', 'Wagholi', 'Wakadewadi', 'Wanowrie', 'Warje',\n",
2794 |        "       'Yerawada', 'Ready To Move', 'Built-up  Area', 'Carpet  Area',\n",
2795 |        "       'Plot  Area'],\n",
2796 |        "      dtype='object', length=104)"
2797 |       ]
2798 |      },
2799 |      "execution_count": 297,
2800 |      "metadata": {},
2801 |      "output_type": "execute_result"
2802 |     }
2803 |    ],
2804 |    "source": [
2805 |     "X.columns"
2806 |    ]
2807 |   },
2808 |   {
2809 |    "cell_type": "code",
2810 |    "execution_count": 298,
2811 |    "metadata": {},
2812 |    "outputs": [
2813 |     {
2814 |      "data": {
2815 |       "text/plain": [
2816 |        "9"
2817 |       ]
2818 |      },
2819 |      "execution_count": 298,
2820 |      "metadata": {},
2821 |      "output_type": "execute_result"
2822 |     }
2823 |    ],
2824 |    "source": [
2825 |     "# For finding the appropriate location\n",
2826 |     "np.where(X.columns=='Balaji Nagar')[0][0]"
2827 |    ]
2828 |   },
2829 |   {
2830 |    "cell_type": "code",
2831 |    "execution_count": 299,
2832 |    "metadata": {},
2833 |    "outputs": [
2834 |     {
2835 |      "data": {
2836 |       "text/plain": [
2837 |        "101"
2838 |       ]
2839 |      },
2840 |      "execution_count": 299,
2841 |      "metadata": {},
2842 |      "output_type": "execute_result"
2843 |     }
2844 |    ],
2845 |    "source": [
2846 |     "# For finding the appropriate area_type\n",
2847 |     "np.where(X.columns=='Built-up  Area')[0][0]"
2848 |    ]
2849 |   },
2850 |   {
2851 |    "cell_type": "code",
2852 |    "execution_count": 300,
2853 |    "metadata": {},
2854 |    "outputs": [
2855 |     {
2856 |      "data": {
2857 |       "text/plain": [
2858 |        "100"
2859 |       ]
2860 |      },
2861 |      "execution_count": 300,
2862 |      "metadata": {},
2863 |      "output_type": "execute_result"
2864 |     }
2865 |    ],
2866 |    "source": [
2867 |     "# For finding the appropriate availability\n",
2868 |     "np.where(X.columns=='Ready To Move')[0][0]"
2869 |    ]
2870 |   },
2871 |   {
2872 |    "cell_type": "code",
2873 |    "execution_count": 301,
2874 |    "metadata": {},
2875 |    "outputs": [],
2876 |    "source": [
2877 |     "# Creating a fuction to predict values\n",
2878 |     "def prediction(location, bhk, bath, balcony, sqft, area_type, availability):\n",
2879 |     "    \n",
2880 |     "    loc_index, area_index, avail_index = -1,-1,-1\n",
2881 |     "        \n",
2882 |     "    if location!='other':\n",
2883 |     "        loc_index = int(np.where(X.columns==location)[0][0])\n",
2884 |     "    \n",
2885 |     "    if area_type!='Super built-up  Area':\n",
2886 |     "        area_index = np.where(X.columns==area_type)[0][0]\n",
2887 |     "        \n",
2888 |     "    if availability!='Not Ready':        \n",
2889 |     "        avail_index = np.where(X.columns==availability)[0][0]\n",
2890 |     "            \n",
2891 |     "    x = np.zeros(len(X.columns))\n",
2892 |     "    x[0] = bath\n",
2893 |     "    x[1] = balcony\n",
2894 |     "    x[2] = bhk\n",
2895 |     "    x[3] = sqft\n",
2896 |     "    \n",
2897 |     "    if loc_index >= 0:\n",
2898 |     "        x[loc_index] = 1\n",
2899 |     "    if area_index >= 0:\n",
2900 |     "        x[area_index] = 1\n",
2901 |     "    if avail_index >= 0:\n",
2902 |     "        x[avail_index] = 1\n",
2903 |     "        \n",
2904 |     "    return model.predict([x])[0]"
2905 |    ]
2906 |   },
2907 |   {
2908 |    "cell_type": "code",
2909 |    "execution_count": 302,
2910 |    "metadata": {},
2911 |    "outputs": [
2912 |     {
2913 |      "data": {
2914 |       "text/plain": [
2915 |        "52.17049124040433"
2916 |       ]
2917 |      },
2918 |      "execution_count": 302,
2919 |      "metadata": {},
2920 |      "output_type": "execute_result"
2921 |     }
2922 |    ],
2923 |    "source": [
2924 |     "# Prediction 1\n",
2925 |     "# Input in the form : Location, BHK, Bath, Balcony, Sqft, area_type, availability.\n",
2926 |     "prediction('Balaji Nagar', 2, 2, 2, 1000, 'Built-up  Area', 'Ready To Move')"
2927 |    ]
2928 |   },
2929 |   {
2930 |    "cell_type": "code",
2931 |    "execution_count": 303,
2932 |    "metadata": {},
2933 |    "outputs": [
2934 |     {
2935 |      "data": {
2936 |       "text/plain": [
2937 |        "52.09543340931981"
2938 |       ]
2939 |      },
2940 |      "execution_count": 303,
2941 |      "metadata": {},
2942 |      "output_type": "execute_result"
2943 |     }
2944 |    ],
2945 |    "source": [
2946 |     "# Prediction 2\n",
2947 |     "# Input in the form : Location, BHK, Bath, Balcony, Sqft, area_type, availability.\n",
2948 |     "prediction('Hadapsar', 2, 2, 2, 1000, 'Super built-up  Area', 'Ready To Move')"
2949 |    ]
2950 |   },
2951 |   {
2952 |    "cell_type": "code",
2953 |    "execution_count": 304,
2954 |    "metadata": {},
2955 |    "outputs": [
2956 |     {
2957 |      "data": {
2958 |       "text/plain": [
2959 |        "140.1821349541965"
2960 |       ]
2961 |      },
2962 |      "execution_count": 304,
2963 |      "metadata": {},
2964 |      "output_type": "execute_result"
2965 |     }
2966 |    ],
2967 |    "source": [
2968 |     "# Prediction 3\n",
2969 |     "# Input in the form : Location, BHK, Bath, Balcony, Sqft, area_type, availability.\n",
2970 |     "prediction('Camp', 2, 3, 2, 2000, 'Plot  Area', 'Not Ready')"
2971 |    ]
2972 |   },
2973 |   {
2974 |    "cell_type": "code",
2975 |    "execution_count": 305,
2976 |    "metadata": {},
2977 |    "outputs": [
2978 |     {
2979 |      "data": {
2980 |       "text/plain": [
2981 |        "140.2386444110721"
2982 |       ]
2983 |      },
2984 |      "execution_count": 305,
2985 |      "metadata": {},
2986 |      "output_type": "execute_result"
2987 |     }
2988 |    ],
2989 |    "source": [
2990 |     "# Prediction 4\n",
2991 |     "# Input in the form : Location, BHK, Bath, Balcony, Sqft, area_type, availability.\n",
2992 |     "prediction('Baner', 2, 3, 2, 2000, 'Plot  Area', 'Not Ready')"
2993 |    ]
2994 |   }
2995 |  ],
2996 |  "metadata": {
2997 |   "kernelspec": {
2998 |    "display_name": "Python 3",
2999 |    "language": "python",
3000 |    "name": "python3"
3001 |   },
3002 |   "language_info": {
3003 |    "codemirror_mode": {
3004 |     "name": "ipython",
3005 |     "version": 3
3006 |    },
3007 |    "file_extension": ".py",
3008 |    "mimetype": "text/x-python",
3009 |    "name": "python",
3010 |    "nbconvert_exporter": "python",
3011 |    "pygments_lexer": "ipython3",
3012 |    "version": "3.7.4"
3013 |   }
3014 |  },
3015 |  "nbformat": 4,
3016 |  "nbformat_minor": 2
3017 | }
3018 | 


--------------------------------------------------------------------------------