└── Krishnasinh_Jadeja.ipynb /Krishnasinh_Jadeja.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "provenance": [], 7 | "collapsed_sections": [] 8 | }, 9 | "kernelspec": { 10 | "name": "python3", 11 | "display_name": "Python 3" 12 | }, 13 | "language_info": { 14 | "name": "python" 15 | } 16 | }, 17 | "cells": [ 18 | { 19 | "cell_type": "code", 20 | "execution_count": null, 21 | "metadata": { 22 | "id": "mMecISboK9zi" 23 | }, 24 | "outputs": [], 25 | "source": [ 26 | "import numpy as np\n", 27 | "import pandas as pd\n", 28 | "import sklearn" 29 | ] 30 | }, 31 | { 32 | "cell_type": "code", 33 | "source": [ 34 | "from sklearn.datasets import load_boston\n", 35 | "df = load_boston()" 36 | ], 37 | "metadata": { 38 | "id": "smTCkcviLNvh" 39 | }, 40 | "execution_count": null, 41 | "outputs": [] 42 | }, 43 | { 44 | "cell_type": "code", 45 | "source": [ 46 | "df.keys()" 47 | ], 48 | "metadata": { 49 | "colab": { 50 | "base_uri": "https://localhost:8080/" 51 | }, 52 | "id": "gKRPllwILuaO", 53 | "outputId": "b66d9841-58fb-4195-cd8f-f73852d930d1" 54 | }, 55 | "execution_count": null, 56 | "outputs": [ 57 | { 58 | "output_type": "execute_result", 59 | "data": { 60 | "text/plain": [ 61 | "dict_keys(['data', 'target', 'feature_names', 'DESCR', 'filename', 'data_module'])" 62 | ] 63 | }, 64 | "metadata": {}, 65 | "execution_count": 4 66 | } 67 | ] 68 | }, 69 | { 70 | "cell_type": "code", 71 | "source": [ 72 | "boston = pd.DataFrame(df.data, columns=df.feature_names)\n", 73 | "boston.head()" 74 | ], 75 | "metadata": { 76 | "colab": { 77 | "base_uri": "https://localhost:8080/", 78 | "height": 270 79 | }, 80 | "id": "2YsiIIeZLweh", 81 | "outputId": "87a52019-e382-4c08-963f-218281f6fb61" 82 | }, 83 | "execution_count": null, 84 | "outputs": [ 85 | { 86 | "output_type": "execute_result", 87 | "data": { 88 | "text/plain": [ 89 | " CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX \\\n", 90 | "0 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.0900 1.0 296.0 \n", 91 | "1 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671 2.0 242.0 \n", 92 | "2 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671 2.0 242.0 \n", 93 | "3 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622 3.0 222.0 \n", 94 | "4 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 3.0 222.0 \n", 95 | "\n", 96 | " PTRATIO B LSTAT \n", 97 | "0 15.3 396.90 4.98 \n", 98 | "1 17.8 396.90 9.14 \n", 99 | "2 17.8 392.83 4.03 \n", 100 | "3 18.7 394.63 2.94 \n", 101 | "4 18.7 396.90 5.33 " 102 | ], 103 | "text/html": [ 104 | "\n", 105 | "
\n", 106 | "
\n", 107 | "
\n", 108 | "\n", 121 | "\n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | " \n", 210 | " \n", 211 | " \n", 212 | " \n", 213 | " \n", 214 | " \n", 215 | " \n", 216 | " \n", 217 | " \n", 218 | " \n", 219 | " \n", 220 | " \n", 221 | " \n", 222 | "
CRIMZNINDUSCHASNOXRMAGEDISRADTAXPTRATIOBLSTAT
00.0063218.02.310.00.5386.57565.24.09001.0296.015.3396.904.98
10.027310.07.070.00.4696.42178.94.96712.0242.017.8396.909.14
20.027290.07.070.00.4697.18561.14.96712.0242.017.8392.834.03
30.032370.02.180.00.4586.99845.86.06223.0222.018.7394.632.94
40.069050.02.180.00.4587.14754.26.06223.0222.018.7396.905.33
\n", 223 | "
\n", 224 | " \n", 234 | " \n", 235 | " \n", 272 | "\n", 273 | " \n", 297 | "
\n", 298 | "
\n", 299 | " " 300 | ] 301 | }, 302 | "metadata": {}, 303 | "execution_count": 5 304 | } 305 | ] 306 | }, 307 | { 308 | "cell_type": "code", 309 | "source": [ 310 | "boston['MEDV'] = df.target\n", 311 | "boston.head()" 312 | ], 313 | "metadata": { 314 | "colab": { 315 | "base_uri": "https://localhost:8080/", 316 | "height": 270 317 | }, 318 | "id": "zFTZlWH3MqLh", 319 | "outputId": "11cc9186-68cb-41ae-f671-73af59a1157b" 320 | }, 321 | "execution_count": null, 322 | "outputs": [ 323 | { 324 | "output_type": "execute_result", 325 | "data": { 326 | "text/plain": [ 327 | " CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX \\\n", 328 | "0 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.0900 1.0 296.0 \n", 329 | "1 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671 2.0 242.0 \n", 330 | "2 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671 2.0 242.0 \n", 331 | "3 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622 3.0 222.0 \n", 332 | "4 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 3.0 222.0 \n", 333 | "\n", 334 | " PTRATIO B LSTAT MEDV \n", 335 | "0 15.3 396.90 4.98 24.0 \n", 336 | "1 17.8 396.90 9.14 21.6 \n", 337 | "2 17.8 392.83 4.03 34.7 \n", 338 | "3 18.7 394.63 2.94 33.4 \n", 339 | "4 18.7 396.90 5.33 36.2 " 340 | ], 341 | "text/html": [ 342 | "\n", 343 | "
\n", 344 | "
\n", 345 | "
\n", 346 | "\n", 359 | "\n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | " \n", 370 | " \n", 371 | " \n", 372 | " \n", 373 | " \n", 374 | " \n", 375 | " \n", 376 | " \n", 377 | " \n", 378 | " \n", 379 | " \n", 380 | " \n", 381 | " \n", 382 | " \n", 383 | " \n", 384 | " \n", 385 | " \n", 386 | " \n", 387 | " \n", 388 | " \n", 389 | " \n", 390 | " \n", 391 | " \n", 392 | " \n", 393 | " \n", 394 | " \n", 395 | " \n", 396 | " \n", 397 | " \n", 398 | " \n", 399 | " \n", 400 | " \n", 401 | " \n", 402 | " \n", 403 | " \n", 404 | " \n", 405 | " \n", 406 | " \n", 407 | " \n", 408 | " \n", 409 | " \n", 410 | " \n", 411 | " \n", 412 | " \n", 413 | " \n", 414 | " \n", 415 | " \n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | "
CRIMZNINDUSCHASNOXRMAGEDISRADTAXPTRATIOBLSTATMEDV
00.0063218.02.310.00.5386.57565.24.09001.0296.015.3396.904.9824.0
10.027310.07.070.00.4696.42178.94.96712.0242.017.8396.909.1421.6
20.027290.07.070.00.4697.18561.14.96712.0242.017.8392.834.0334.7
30.032370.02.180.00.4586.99845.86.06223.0222.018.7394.632.9433.4
40.069050.02.180.00.4587.14754.26.06223.0222.018.7396.905.3336.2
\n", 467 | "
\n", 468 | " \n", 478 | " \n", 479 | " \n", 516 | "\n", 517 | " \n", 541 | "
\n", 542 | "
\n", 543 | " " 544 | ] 545 | }, 546 | "metadata": {}, 547 | "execution_count": 6 548 | } 549 | ] 550 | }, 551 | { 552 | "cell_type": "code", 553 | "source": [ 554 | " boston.isnull()" 555 | ], 556 | "metadata": { 557 | "colab": { 558 | "base_uri": "https://localhost:8080/", 559 | "height": 488 560 | }, 561 | "id": "xKdtTGCvM4ML", 562 | "outputId": "668ad76d-8a0c-466b-d89b-f2854b9af33c" 563 | }, 564 | "execution_count": null, 565 | "outputs": [ 566 | { 567 | "output_type": "execute_result", 568 | "data": { 569 | "text/plain": [ 570 | " CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX \\\n", 571 | "0 False False False False False False False False False False \n", 572 | "1 False False False False False False False False False False \n", 573 | "2 False False False False False False False False False False \n", 574 | "3 False False False False False False False False False False \n", 575 | "4 False False False False False False False False False False \n", 576 | ".. ... ... ... ... ... ... ... ... ... ... \n", 577 | "501 False False False False False False False False False False \n", 578 | "502 False False False False False False False False False False \n", 579 | "503 False False False False False False False False False False \n", 580 | "504 False False False False False False False False False False \n", 581 | "505 False False False False False False False False False False \n", 582 | "\n", 583 | " PTRATIO B LSTAT MEDV \n", 584 | "0 False False False False \n", 585 | "1 False False False False \n", 586 | "2 False False False False \n", 587 | "3 False False False False \n", 588 | "4 False False False False \n", 589 | ".. ... ... ... ... \n", 590 | "501 False False False False \n", 591 | "502 False False False False \n", 592 | "503 False False False False \n", 593 | "504 False False False False \n", 594 | "505 False False False False \n", 595 | "\n", 596 | "[506 rows x 14 columns]" 597 | ], 598 | "text/html": [ 599 | "\n", 600 | "
\n", 601 | "
\n", 602 | "
\n", 603 | "\n", 616 | "\n", 617 | " \n", 618 | " \n", 619 | " \n", 620 | " \n", 621 | " \n", 622 | " \n", 623 | " \n", 624 | " \n", 625 | " \n", 626 | " \n", 627 | " \n", 628 | " \n", 629 | " \n", 630 | " \n", 631 | " \n", 632 | " \n", 633 | " \n", 634 | " \n", 635 | " \n", 636 | " \n", 637 | " \n", 638 | " \n", 639 | " \n", 640 | " \n", 641 | " \n", 642 | " \n", 643 | " \n", 644 | " \n", 645 | " \n", 646 | " \n", 647 | " \n", 648 | " \n", 649 | " \n", 650 | " \n", 651 | " \n", 652 | " \n", 653 | " \n", 654 | " \n", 655 | " \n", 656 | " \n", 657 | " \n", 658 | " \n", 659 | " \n", 660 | " \n", 661 | " \n", 662 | " \n", 663 | " \n", 664 | " \n", 665 | " \n", 666 | " \n", 667 | " \n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | " \n", 700 | " \n", 701 | " \n", 702 | " \n", 703 | " \n", 704 | " \n", 705 | " \n", 706 | " \n", 707 | " \n", 708 | " \n", 709 | " \n", 710 | " \n", 711 | " \n", 712 | " \n", 713 | " \n", 714 | " \n", 715 | " \n", 716 | " \n", 717 | " \n", 718 | " \n", 719 | " \n", 720 | " \n", 721 | " \n", 722 | " \n", 723 | " \n", 724 | " \n", 725 | " \n", 726 | " \n", 727 | " \n", 728 | " \n", 729 | " \n", 730 | " \n", 731 | " \n", 732 | " \n", 733 | " \n", 734 | " \n", 735 | " \n", 736 | " \n", 737 | " \n", 738 | " \n", 739 | " \n", 740 | " \n", 741 | " \n", 742 | " \n", 743 | " \n", 744 | " \n", 745 | " \n", 746 | " \n", 747 | " \n", 748 | " \n", 749 | " \n", 750 | " \n", 751 | " \n", 752 | " \n", 753 | " \n", 754 | " \n", 755 | " \n", 756 | " \n", 757 | " \n", 758 | " \n", 759 | " \n", 760 | " \n", 761 | " \n", 762 | " \n", 763 | " \n", 764 | " \n", 765 | " \n", 766 | " \n", 767 | " \n", 768 | " \n", 769 | " \n", 770 | " \n", 771 | " \n", 772 | " \n", 773 | " \n", 774 | " \n", 775 | " \n", 776 | " \n", 777 | " \n", 778 | " \n", 779 | " \n", 780 | " \n", 781 | " \n", 782 | " \n", 783 | " \n", 784 | " \n", 785 | " \n", 786 | " \n", 787 | " \n", 788 | " \n", 789 | " \n", 790 | " \n", 791 | " \n", 792 | " \n", 793 | " \n", 794 | " \n", 795 | " \n", 796 | " \n", 797 | " \n", 798 | " \n", 799 | " \n", 800 | " \n", 801 | " \n", 802 | " \n", 803 | " \n", 804 | " \n", 805 | " \n", 806 | " \n", 807 | " \n", 808 | " \n", 809 | " \n", 810 | " \n", 811 | " \n", 812 | " \n", 813 | " \n", 814 | " \n", 815 | " \n", 816 | " \n", 817 | " \n", 818 | " \n", 819 | " \n", 820 | " \n", 821 | " \n", 822 | " \n", 823 | " \n", 824 | " \n", 825 | "
CRIMZNINDUSCHASNOXRMAGEDISRADTAXPTRATIOBLSTATMEDV
0FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
1FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
2FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
3FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
4FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
.............................................
501FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
502FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
503FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
504FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
505FalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalse
\n", 826 | "

506 rows × 14 columns

\n", 827 | "
\n", 828 | " \n", 838 | " \n", 839 | " \n", 876 | "\n", 877 | " \n", 901 | "
\n", 902 | "
\n", 903 | " " 904 | ] 905 | }, 906 | "metadata": {}, 907 | "execution_count": 7 908 | } 909 | ] 910 | }, 911 | { 912 | "cell_type": "code", 913 | "source": [ 914 | "boston.isnull().sum()" 915 | ], 916 | "metadata": { 917 | "colab": { 918 | "base_uri": "https://localhost:8080/" 919 | }, 920 | "id": "CUF2gciXNIh6", 921 | "outputId": "6bb7f1fa-c7a4-42a9-f782-1c7a179e65f0" 922 | }, 923 | "execution_count": null, 924 | "outputs": [ 925 | { 926 | "output_type": "execute_result", 927 | "data": { 928 | "text/plain": [ 929 | "CRIM 0\n", 930 | "ZN 0\n", 931 | "INDUS 0\n", 932 | "CHAS 0\n", 933 | "NOX 0\n", 934 | "RM 0\n", 935 | "AGE 0\n", 936 | "DIS 0\n", 937 | "RAD 0\n", 938 | "TAX 0\n", 939 | "PTRATIO 0\n", 940 | "B 0\n", 941 | "LSTAT 0\n", 942 | "MEDV 0\n", 943 | "dtype: int64" 944 | ] 945 | }, 946 | "metadata": {}, 947 | "execution_count": 8 948 | } 949 | ] 950 | }, 951 | { 952 | "cell_type": "code", 953 | "source": [ 954 | "from sklearn.model_selection import train_test_split\n", 955 | "\n", 956 | "X = boston.drop('MEDV', axis=1)\n", 957 | "Y = boston['MEDV']\n", 958 | "\n", 959 | "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.15, random_state=5)\n", 960 | "\n", 961 | "print(X_train.shape)\n", 962 | "print(X_test.shape)\n", 963 | "print(Y_train.shape)\n", 964 | "print(Y_test.shape)\n" 965 | ], 966 | "metadata": { 967 | "colab": { 968 | "base_uri": "https://localhost:8080/" 969 | }, 970 | "id": "2QWs8y2gNTcw", 971 | "outputId": "635fe221-7b8d-4433-e945-bc6a873b66a8" 972 | }, 973 | "execution_count": null, 974 | "outputs": [ 975 | { 976 | "output_type": "stream", 977 | "name": "stdout", 978 | "text": [ 979 | "(430, 13)\n", 980 | "(76, 13)\n", 981 | "(430,)\n", 982 | "(76,)\n" 983 | ] 984 | } 985 | ] 986 | }, 987 | { 988 | "cell_type": "code", 989 | "source": [ 990 | "from sklearn.linear_model import LinearRegression\n", 991 | "from sklearn.metrics import mean_squared_error" 992 | ], 993 | "metadata": { 994 | "id": "1kechGAXQrBm" 995 | }, 996 | "execution_count": null, 997 | "outputs": [] 998 | }, 999 | { 1000 | "cell_type": "code", 1001 | "source": [ 1002 | "lin_model = LinearRegression()\n", 1003 | "\n", 1004 | "lin_model.fit(X_train, Y_train)" 1005 | ], 1006 | "metadata": { 1007 | "colab": { 1008 | "base_uri": "https://localhost:8080/" 1009 | }, 1010 | "id": "Ve9Ify57Rf6I", 1011 | "outputId": "3df48a70-56f7-4c75-ff46-37fcc86ae523" 1012 | }, 1013 | "execution_count": null, 1014 | "outputs": [ 1015 | { 1016 | "output_type": "execute_result", 1017 | "data": { 1018 | "text/plain": [ 1019 | "LinearRegression()" 1020 | ] 1021 | }, 1022 | "metadata": {}, 1023 | "execution_count": 15 1024 | } 1025 | ] 1026 | }, 1027 | { 1028 | "cell_type": "code", 1029 | "source": [ 1030 | "y_train_predict = lin_model.predict(X_train)\n", 1031 | "rmse = (np.sqrt(mean_squared_error(Y_train, y_train_predict)))\n", 1032 | "\n", 1033 | "print(\"The model performance for training set\")\n", 1034 | "print('RMSE is {}'.format(rmse))\n", 1035 | "print(\"\\n\")\n", 1036 | "\n", 1037 | "y_test_predict = lin_model.predict(X_test)\n", 1038 | "rmse = (np.sqrt(mean_squared_error(Y_test, y_test_predict)))\n", 1039 | "\n", 1040 | "print(\"The model performance for testing set\")\n", 1041 | "print('RMSE is {}'.format(rmse))\n" 1042 | ], 1043 | "metadata": { 1044 | "colab": { 1045 | "base_uri": "https://localhost:8080/" 1046 | }, 1047 | "id": "SyMGsv20SJLn", 1048 | "outputId": "751c44aa-af9c-475b-ed4c-cb043c86c0f4" 1049 | }, 1050 | "execution_count": null, 1051 | "outputs": [ 1052 | { 1053 | "output_type": "stream", 1054 | "name": "stdout", 1055 | "text": [ 1056 | "The model performance for training set\n", 1057 | "RMSE is 4.710901797319796\n", 1058 | "\n", 1059 | "\n", 1060 | "The model performance for testing set\n", 1061 | "RMSE is 4.687543527902972\n" 1062 | ] 1063 | } 1064 | ] 1065 | }, 1066 | { 1067 | "cell_type": "code", 1068 | "source": [], 1069 | "metadata": { 1070 | "id": "_Ufz7oaIVIgM" 1071 | }, 1072 | "execution_count": null, 1073 | "outputs": [] 1074 | } 1075 | ] 1076 | } --------------------------------------------------------------------------------