Skip to content

P
projs
Switch branch/tag
Find file
Normal viewHistoryPermalink
douban_starter_torch.ipynb 88.9 KB
Newer Older
new file: project1-douban/.idea/.gitignore
03548cc6
 
20220116006 committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "### 豆瓣评分的预测\n",
    "\n",
    "在这个项目中，我们要预测一部电影的评分，这个问题实际上就是一个分类问题。给定的输入为一段文本，输出为具体的评分。 在这个项目中，我们需要做：\n",
    "- 文本的预处理，如停用词的过滤，低频词的过滤，特殊符号的过滤等\n",
    "- 文本转化成向量，将使用三种方式，分别为tf-idf, word2vec以及BERT向量。 \n",
    "- 训练逻辑回归和朴素贝叶斯模型，并做交叉验证\n",
    "- 评估模型的准确率\n",
    "\n",
    "在具体标记为``TODO``的部分填写相应的代码。 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#导入数据处理的基础包\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "#导入用于计数的包\n",
    "from collections import Counter\n",
    "\n",
    "#导入tf-idf相关的包\n",
    "from sklearn.feature_extraction.text import TfidfTransformer    \n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "\n",
    "#导入模型评估的包\n",
    "from sklearn import metrics\n",
    "\n",
    "#导入与word2vec相关的包\n",
    "from gensim.models import KeyedVectors\n",
    "\n",
    "\n",
    "#包tqdm是用来对可迭代对象执行时生成一个进度条用以监视程序运行过程\n",
    "from tqdm import tqdm\n",
    "\n",
    "#导入其他一些功能包\n",
    "import requests\n",
    "import os\n",
    "\n",
    "import re"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "### 1. 读取数据并做文本的处理\n",
    "你需要完成以下几步操作：\n",
    "- 去掉无用的字符如！&，可自行定义\n",
    "- 中文分词\n",
    "- 去掉低频词"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>Movie_Name_EN</th>\n",
       "      <th>Movie_Name_CN</th>\n",
       "      <th>Crawl_Date</th>\n",
       "      <th>Number</th>\n",
       "      <th>Username</th>\n",
       "      <th>Date</th>\n",
       "      <th>Star</th>\n",
       "      <th>Comment</th>\n",
       "      <th>Like</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Avengers Age of Ultron</td>\n",
       "      <td>复仇者联盟2</td>\n",
       "      <td>2017-01-22</td>\n",
       "      <td>1</td>\n",
       "      <td>然潘</td>\n",
       "      <td>2015-05-13</td>\n",
       "      <td>3</td>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>2404</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10</td>\n",
       "      <td>Avengers Age of Ultron</td>\n",
       "      <td>复仇者联盟2</td>\n",
       "      <td>2017-01-22</td>\n",
       "      <td>11</td>\n",
       "      <td>影志</td>\n",
       "      <td>2015-04-30</td>\n",
       "      <td>4</td>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20</td>\n",
       "      <td>Avengers Age of Ultron</td>\n",
       "      <td>复仇者联盟2</td>\n",
       "      <td>2017-01-22</td>\n",
       "      <td>21</td>\n",
       "      <td>随时流感</td>\n",
       "      <td>2015-04-28</td>\n",
       "      <td>2</td>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>30</td>\n",
       "      <td>Avengers Age of Ultron</td>\n",
       "      <td>复仇者联盟2</td>\n",
       "      <td>2017-01-22</td>\n",
       "      <td>31</td>\n",
       "      <td>乌鸦火堂</td>\n",
       "      <td>2015-05-08</td>\n",
       "      <td>4</td>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>40</td>\n",
       "      <td>Avengers Age of Ultron</td>\n",
       "      <td>复仇者联盟2</td>\n",
       "      <td>2017-01-22</td>\n",
       "      <td>41</td>\n",
       "      <td>办公室甜心</td>\n",
       "      <td>2015-05-10</td>\n",
       "      <td>5</td>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ID           Movie_Name_EN Movie_Name_CN  Crawl_Date  Number Username  \\\n",
       "0   0  Avengers Age of Ultron        复仇者联盟2  2017-01-22       1       然潘   \n",
       "1  10  Avengers Age of Ultron        复仇者联盟2  2017-01-22      11       影志   \n",
       "2  20  Avengers Age of Ultron        复仇者联盟2  2017-01-22      21     随时流感   \n",
       "3  30  Avengers Age of Ultron        复仇者联盟2  2017-01-22      31     乌鸦火堂   \n",
       "4  40  Avengers Age of Ultron        复仇者联盟2  2017-01-22      41    办公室甜心   \n",
       "\n",
       "         Date  Star                                            Comment  Like  \n",
       "0  2015-05-13     3                                      连奥创都知道整容要去韩国。  2404  \n",
       "1  2015-04-30     4   “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...   381  \n",
       "2  2015-04-28     2                                 奥创弱爆了弱爆了弱爆了啊！！！！！！   120  \n",
       "3  2015-05-08     4   与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...    30  \n",
       "4  2015-05-10     5   看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...    16  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#读取数据\n",
    "data = pd.read_csv('data/DMSC.csv')\n",
    "#观察数据格式\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 212506 entries, 0 to 212505\n",
      "Data columns (total 10 columns):\n",
      " #   Column         Non-Null Count   Dtype \n",
      "---  ------         --------------   ----- \n",
      " 0   ID             212506 non-null  int64 \n",
      " 1   Movie_Name_EN  212506 non-null  object\n",
      " 2   Movie_Name_CN  212506 non-null  object\n",
      " 3   Crawl_Date     212506 non-null  object\n",
      " 4   Number         212506 non-null  int64 \n",
      " 5   Username       212496 non-null  object\n",
      " 6   Date           212506 non-null  object\n",
      " 7   Star           212506 non-null  int64 \n",
      " 8   Comment        212506 non-null  object\n",
      " 9   Like           212506 non-null  int64 \n",
      "dtypes: int64(4), object(6)\n",
      "memory usage: 16.2+ MB\n"
     ]
    }
   ],
   "source": [
    "#输出数据的一些相关信息\n",
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comment</th>\n",
       "      <th>Star</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Comment  Star\n",
       "0                                      连奥创都知道整容要去韩国。     3\n",
       "1   “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...     4\n",
       "2                                 奥创弱爆了弱爆了弱爆了啊！！！！！！     2\n",
       "3   与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...     4\n",
       "4   看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...     5"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#只保留数据中我们需要的两列：Comment列和Star列\n",
    "data = data[['Comment','Star']]\n",
    "#观察新的数据的格式\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comment</th>\n",
       "      <th>Star</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>avengers1睡着1次 avengers2睡着两次。。。</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>谁再喊我看这种电影我和谁急！实在是接受无能。。。</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Long takes, no stakes. 最后大战灾难性得乱 olsen到底什么能力完...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>视觉效果的极限是视觉疲劳</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>感觉有略黑暗了点，不过还是萌点满满，但是一想到就要完结了又心碎了一地，，，，</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>妇联成员都只会讲不好笑的笑话，唯一加分的是朱莉·德培</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>只算還OK的商業片。現在這類片型第一品牌就是漫威了，熱鬧打鬥大場面，人神機甲齊飛，各型超級...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>好看！好看！好看！</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>难看一笔</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>6/10。第一部精准的节奏、巧妙的悬念和清楚的内心戏不见了，或许导演不想把超级英雄打造成战...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>欧洲竟然真的是最早上映啊＝ ＝法国比美国还早一周……没怎么看懂的我想找科普说明都不容易！嘛...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>我是美队的忠实脑！残！粉！！！！！！！！！</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              Comment  Star\n",
       "0                                       连奥创都知道整容要去韩国。     1\n",
       "1    “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...     1\n",
       "2                                  奥创弱爆了弱爆了弱爆了啊！！！！！！     0\n",
       "3    与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...     1\n",
       "4    看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...     1\n",
       "5                                   绝逼不质疑尾灯的导演和编剧水平       1\n",
       "6                      avengers1睡着1次 avengers2睡着两次。。。     0\n",
       "7                            谁再喊我看这种电影我和谁急！实在是接受无能。。。     0\n",
       "8    超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...     1\n",
       "9    观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...     1\n",
       "10   Long takes, no stakes. 最后大战灾难性得乱 olsen到底什么能力完...     1\n",
       "11                                       视觉效果的极限是视觉疲劳     1\n",
       "12             感觉有略黑暗了点，不过还是萌点满满，但是一想到就要完结了又心碎了一地，，，，     1\n",
       "13                         妇联成员都只会讲不好笑的笑话，唯一加分的是朱莉·德培     0\n",
       "14   只算還OK的商業片。現在這類片型第一品牌就是漫威了，熱鬧打鬥大場面，人神機甲齊飛，各型超級...     1\n",
       "15                                          好看！好看！好看！     1\n",
       "16                                               难看一笔     0\n",
       "17   6/10。第一部精准的节奏、巧妙的悬念和清楚的内心戏不见了，或许导演不想把超级英雄打造成战...     1\n",
       "18   欧洲竟然真的是最早上映啊＝ ＝法国比美国还早一周……没怎么看懂的我想找科普说明都不容易！嘛...     1\n",
       "19                              我是美队的忠实脑！残！粉！！！！！！！！！     1"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 这里的star代表具体的评分。但在这个项目中，我们要预测的是正面还是负面。我们把评分为1和2的看作是负面，把评分为3，4，5的作为正面\n",
    "data['Star']=(data.Star/3).astype(int)\n",
    "data.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务1： 去掉一些无用的字符"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comment</th>\n",
       "      <th>Star</th>\n",
       "      <th>comment_clean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>1</td>\n",
       "      <td>连奥创都知道整容要去韩国</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>1</td>\n",
       "      <td>一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>0</td>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>1</td>\n",
       "      <td>与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>1</td>\n",
       "      <td>看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "      <td>1</td>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>avengers1睡着1次 avengers2睡着两次。。。</td>\n",
       "      <td>0</td>\n",
       "      <td>睡着 次 睡着两次</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>谁再喊我看这种电影我和谁急！实在是接受无能。。。</td>\n",
       "      <td>0</td>\n",
       "      <td>谁再喊我看这种电影我和谁急 实在是接受无能</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...</td>\n",
       "      <td>1</td>\n",
       "      <td>超愉悦以及超满足 在历经了第一阶段比漫画更普世的设定融合之后 发展到   居然出现了不少传统...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...</td>\n",
       "      <td>1</td>\n",
       "      <td>观影过程中 耳边一直有一种突突突突突的声音 我还感慨电影为了让奥创给观众带来紧张感 声音上真...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Long takes, no stakes. 最后大战灾难性得乱 olsen到底什么能力完...</td>\n",
       "      <td>1</td>\n",
       "      <td>最后大战灾难性得乱 到底什么能力完全没明白 是巴菲里的   其实剧本没那么差 美国例外论的主...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>视觉效果的极限是视觉疲劳</td>\n",
       "      <td>1</td>\n",
       "      <td>视觉效果的极限是视觉疲劳</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>感觉有略黑暗了点，不过还是萌点满满，但是一想到就要完结了又心碎了一地，，，，</td>\n",
       "      <td>1</td>\n",
       "      <td>感觉有略黑暗了点 不过还是萌点满满 但是一想到就要完结了又心碎了一地</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>妇联成员都只会讲不好笑的笑话，唯一加分的是朱莉·德培</td>\n",
       "      <td>0</td>\n",
       "      <td>妇联成员都只会讲不好笑的笑话 唯一加分的是朱莉 德培</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>只算還OK的商業片。現在這類片型第一品牌就是漫威了，熱鬧打鬥大場面，人神機甲齊飛，各型超級...</td>\n",
       "      <td>1</td>\n",
       "      <td>只算還 的商業片 現在這類片型第一品牌就是漫威了 熱鬧打鬥大場面 人神機甲齊飛 各型超級英雄...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>好看！好看！好看！</td>\n",
       "      <td>1</td>\n",
       "      <td>好看 好看 好看</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>难看一笔</td>\n",
       "      <td>0</td>\n",
       "      <td>难看一笔</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>6/10。第一部精准的节奏、巧妙的悬念和清楚的内心戏不见了，或许导演不想把超级英雄打造成战...</td>\n",
       "      <td>1</td>\n",
       "      <td>第一部精准的节奏 巧妙的悬念和清楚的内心戏不见了 或许导演不想把超级英雄打造成战斗机器 所以...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>欧洲竟然真的是最早上映啊＝ ＝法国比美国还早一周……没怎么看懂的我想找科普说明都不容易！嘛...</td>\n",
       "      <td>1</td>\n",
       "      <td>欧洲竟然真的是最早上映啊   法国比美国还早一周 没怎么看懂的我想找科普说明都不容易 嘛 我...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>我是美队的忠实脑！残！粉！！！！！！！！！</td>\n",
       "      <td>1</td>\n",
       "      <td>我是美队的忠实脑 残 粉</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              Comment  Star  \\\n",
       "0                                       连奥创都知道整容要去韩国。     1   \n",
       "1    “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...     1   \n",
       "2                                  奥创弱爆了弱爆了弱爆了啊！！！！！！     0   \n",
       "3    与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...     1   \n",
       "4    看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...     1   \n",
       "5                                   绝逼不质疑尾灯的导演和编剧水平       1   \n",
       "6                      avengers1睡着1次 avengers2睡着两次。。。     0   \n",
       "7                            谁再喊我看这种电影我和谁急！实在是接受无能。。。     0   \n",
       "8    超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...     1   \n",
       "9    观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...     1   \n",
       "10   Long takes, no stakes. 最后大战灾难性得乱 olsen到底什么能力完...     1   \n",
       "11                                       视觉效果的极限是视觉疲劳     1   \n",
       "12             感觉有略黑暗了点，不过还是萌点满满，但是一想到就要完结了又心碎了一地，，，，     1   \n",
       "13                         妇联成员都只会讲不好笑的笑话，唯一加分的是朱莉·德培     0   \n",
       "14   只算還OK的商業片。現在這類片型第一品牌就是漫威了，熱鬧打鬥大場面，人神機甲齊飛，各型超級...     1   \n",
       "15                                          好看！好看！好看！     1   \n",
       "16                                               难看一笔     0   \n",
       "17   6/10。第一部精准的节奏、巧妙的悬念和清楚的内心戏不见了，或许导演不想把超级英雄打造成战...     1   \n",
       "18   欧洲竟然真的是最早上映啊＝ ＝法国比美国还早一周……没怎么看懂的我想找科普说明都不容易！嘛...     1   \n",
       "19                              我是美队的忠实脑！残！粉！！！！！！！！！     1   \n",
       "\n",
       "                                        comment_clean  \n",
       "0                                        连奥创都知道整容要去韩国  \n",
       "1   一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...  \n",
       "2                                        奥创弱爆了弱爆了弱爆了啊  \n",
       "3   与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...  \n",
       "4   看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...  \n",
       "5                                     绝逼不质疑尾灯的导演和编剧水平  \n",
       "6                                           睡着 次 睡着两次  \n",
       "7                               谁再喊我看这种电影我和谁急 实在是接受无能  \n",
       "8   超愉悦以及超满足 在历经了第一阶段比漫画更普世的设定融合之后 发展到   居然出现了不少传统...  \n",
       "9   观影过程中 耳边一直有一种突突突突突的声音 我还感慨电影为了让奥创给观众带来紧张感 声音上真...  \n",
       "10  最后大战灾难性得乱 到底什么能力完全没明白 是巴菲里的   其实剧本没那么差 美国例外论的主...  \n",
       "11                                       视觉效果的极限是视觉疲劳  \n",
       "12                 感觉有略黑暗了点 不过还是萌点满满 但是一想到就要完结了又心碎了一地  \n",
       "13                         妇联成员都只会讲不好笑的笑话 唯一加分的是朱莉 德培  \n",
       "14  只算還 的商業片 現在這類片型第一品牌就是漫威了 熱鬧打鬥大場面 人神機甲齊飛 各型超級英雄...  \n",
       "15                                           好看 好看 好看  \n",
       "16                                               难看一笔  \n",
       "17  第一部精准的节奏 巧妙的悬念和清楚的内心戏不见了 或许导演不想把超级英雄打造成战斗机器 所以...  \n",
       "18  欧洲竟然真的是最早上映啊   法国比美国还早一周 没怎么看懂的我想找科普说明都不容易 嘛 我...  \n",
       "19                                       我是美队的忠实脑 残 粉  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# TODO1: 去掉一些无用的字符，自行定一个字符几何，并从文本中去掉\n",
    "def pre_process(input_str):\n",
    "    # input_str = re.sub('[0-9]+', 'DIG', input_str)\n",
    "    # 去除标点符号\n",
    "    # input_str = re.sub(r\"[{}]+\".format(punc), \" \", input_str)\n",
    "    \n",
    "    input_str = re.sub(\n",
    "        \"[0-9a-zA-Z\\-\\s+\\.\\!\\/_,$%^*\\(\\)\\+(+\\\"\\')]+|[+——！，。？、~@#￥%……&*（）<>\\[\\]:：★◆【】《》;；=?？]+\", \" \", input_str)\n",
    "    # 其他非中文字符\n",
    "    input_str = re.sub(r\"[^\\u4e00-\\u9fff]\", \" \", input_str)\n",
    "    return input_str.strip()\n",
    "\n",
    "# 正则去除标点符号\n",
    "data['comment_clean'] = data['Comment'].apply(pre_process)\n",
    "data.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务2：使用结巴分词对文本做分词"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "apply:   0%|                                                                                | 0/212506 [00:00<?, ?it/s]Building prefix dict from the default dictionary ...\n",
      "Loading model from cache C:\\Users\\avaws\\AppData\\Local\\Temp\\jieba.cache\n",
      "Loading model cost 0.587 seconds.\n",
      "Prefix dict has been built successfully.\n",
      "apply: 100%|█████████████████████████████████████████████████████████████████| 212506/212506 [00:35<00:00, 6040.35it/s]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comment</th>\n",
       "      <th>Star</th>\n",
       "      <th>comment_clean</th>\n",
       "      <th>comment_processed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>1</td>\n",
       "      <td>连奥创都知道整容要去韩国</td>\n",
       "      <td>连 奥创 都 知道 整容 要 去 韩国</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>1</td>\n",
       "      <td>一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...</td>\n",
       "      <td>一个 没有 黑暗面 的 人 不 值得 信任       第二部 剥去 冗长 的 铺垫   开...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>0</td>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊</td>\n",
       "      <td>奥创 弱 爆 了 弱 爆 了 弱 爆 了 啊</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>1</td>\n",
       "      <td>与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...</td>\n",
       "      <td>与 第一集 不同   承上启下   阴郁 严肃   但 也 不会 不 好看 啊   除非 本...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>1</td>\n",
       "      <td>看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...</td>\n",
       "      <td>看毕   我 激动 地 对 友人 说   等等 奥创 要 来 毁灭 台北 怎么办 厚   她...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Comment  Star  \\\n",
       "0                                      连奥创都知道整容要去韩国。     1   \n",
       "1   “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...     1   \n",
       "2                                 奥创弱爆了弱爆了弱爆了啊！！！！！！     0   \n",
       "3   与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...     1   \n",
       "4   看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...     1   \n",
       "\n",
       "                                       comment_clean  \\\n",
       "0                                       连奥创都知道整容要去韩国   \n",
       "1  一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...   \n",
       "2                                       奥创弱爆了弱爆了弱爆了啊   \n",
       "3  与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...   \n",
       "4  看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...   \n",
       "\n",
       "                                   comment_processed  \n",
       "0                                连 奥创 都 知道 整容 要 去 韩国  \n",
       "1  一个 没有 黑暗面 的 人 不 值得 信任       第二部 剥去 冗长 的 铺垫   开...  \n",
       "2                             奥创 弱 爆 了 弱 爆 了 弱 爆 了 啊  \n",
       "3  与 第一集 不同   承上启下   阴郁 严肃   但 也 不会 不 好看 啊   除非 本...  \n",
       "4  看毕   我 激动 地 对 友人 说   等等 奥创 要 来 毁灭 台北 怎么办 厚   她...  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# TODO2: 导入中文分词包jieba, 并用jieba对原始文本做分词\n",
    "import jieba\n",
    "def comment_cut(content):\n",
    "    # TODO: 使用结巴完成对每一个comment的分词\n",
    "    # 分词并过滤空字符串\n",
    "    return ' '.join([w for w in jieba.lcut(content.strip()) if len(w) > 0])\n",
    "\n",
    "# 输出进度条\n",
    "tqdm.pandas(desc='apply')\n",
    "data['comment_processed'] = data['comment_clean'].progress_apply(comment_cut)\n",
    "\n",
    "# 观察新的数据的格式\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务3：设定停用词并去掉停用词"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "apply: 100%|█████████████████████████████████████████████████████████████████| 212506/212506 [00:34<00:00, 6213.38it/s]\n"
     ]
    }
   ],
   "source": [
    "# TODO3: 设定停用词并从文本中去掉停用词\n",
    "\n",
    "# 下载中文停用词表至data/stopWord.json中，下载地址:https://github.com/goto456/stopwords/\n",
    "if not os.path.exists('./data/stopWord.json'):\n",
    "    stopWord = requests.get(\"https://raw.githubusercontent.com/goto456/stopwords/master/cn_stopwords.txt\")\n",
    "    with open(\"./data/stopWord.json\", \"wb\") as f:\n",
    "         f.write(stopWord.content)\n",
    "\n",
    "# 读取下载的停用词表，并保存在列表中\n",
    "with open(\"./data/stopWord.json\",\"r\", encoding=\"utf-8\") as f:\n",
    "    stopWords = f.read().split(\"\\n\")  \n",
    "    \n",
    "    \n",
    "# 去除停用词\n",
    "def rm_stop_word(input_str):\n",
    "    # your code, remove stop words\n",
    "    # TODO\n",
    "    return [w for w in input_str.split() if w not in stopWords]\n",
    "\n",
    "#这行代码中.progress_apply()函数的作用等同于.apply()函数的作用，只是写成.progress_apply()函数才能被tqdm包监控从而输出进度条。\n",
    "data['comment_processed'] = data['comment_processed'].progress_apply(rm_stop_word)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comment</th>\n",
       "      <th>Star</th>\n",
       "      <th>comment_clean</th>\n",
       "      <th>comment_processed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>1</td>\n",
       "      <td>连奥创都知道整容要去韩国</td>\n",
       "      <td>[奥创, 知道, 整容, 韩国]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>1</td>\n",
       "      <td>一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...</td>\n",
       "      <td>[一个, 没有, 黑暗面, 值得, 信任, 第二部, 剥去, 冗长, 铺垫, 开场, 高潮,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>0</td>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊</td>\n",
       "      <td>[奥创, 弱, 爆, 弱, 爆, 弱, 爆]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>1</td>\n",
       "      <td>与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...</td>\n",
       "      <td>[第一集, 不同, 承上启下, 阴郁, 严肃, 不会, 好看, 本来, 喜欢, 漫威, 电影...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>1</td>\n",
       "      <td>看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...</td>\n",
       "      <td>[看毕, 激动, 友人, 说, 奥创, 毁灭, 台北, 厚, 拍了拍, 肩膀, 没事, 反正...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "      <td>1</td>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "      <td>[绝逼, 质疑, 尾灯, 导演, 编剧, 水平]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>avengers1睡着1次 avengers2睡着两次。。。</td>\n",
       "      <td>0</td>\n",
       "      <td>睡着 次 睡着两次</td>\n",
       "      <td>[睡着, 次, 睡着, 两次]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>谁再喊我看这种电影我和谁急！实在是接受无能。。。</td>\n",
       "      <td>0</td>\n",
       "      <td>谁再喊我看这种电影我和谁急 实在是接受无能</td>\n",
       "      <td>[喊, 这种, 电影, 急, 实在, 接受, 无能]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...</td>\n",
       "      <td>1</td>\n",
       "      <td>超愉悦以及超满足 在历经了第一阶段比漫画更普世的设定融合之后 发展到   居然出现了不少传统...</td>\n",
       "      <td>[超, 愉悦, 超, 满足, 历经, 第一阶段, 漫画, 更普世, 设定, 融合, 之后, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...</td>\n",
       "      <td>1</td>\n",
       "      <td>观影过程中 耳边一直有一种突突突突突的声音 我还感慨电影为了让奥创给观众带来紧张感 声音上真...</td>\n",
       "      <td>[观影, 过程, 中, 耳边, 一直, 一种, 突突突, 突突, 声音, 感慨, 电影, 奥...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Long takes, no stakes. 最后大战灾难性得乱 olsen到底什么能力完...</td>\n",
       "      <td>1</td>\n",
       "      <td>最后大战灾难性得乱 到底什么能力完全没明白 是巴菲里的   其实剧本没那么差 美国例外论的主...</td>\n",
       "      <td>[最后, 大战, 灾难性, 得乱, 到底, 能力, 完全, 没, 明白, 巴菲, 里, 其实...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>视觉效果的极限是视觉疲劳</td>\n",
       "      <td>1</td>\n",
       "      <td>视觉效果的极限是视觉疲劳</td>\n",
       "      <td>[视觉效果, 极限, 视觉, 疲劳]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>感觉有略黑暗了点，不过还是萌点满满，但是一想到就要完结了又心碎了一地，，，，</td>\n",
       "      <td>1</td>\n",
       "      <td>感觉有略黑暗了点 不过还是萌点满满 但是一想到就要完结了又心碎了一地</td>\n",
       "      <td>[感觉, 有略, 黑暗, 点, 萌点, 满满, 想到, 完结, 心碎, 一地]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>妇联成员都只会讲不好笑的笑话，唯一加分的是朱莉·德培</td>\n",
       "      <td>0</td>\n",
       "      <td>妇联成员都只会讲不好笑的笑话 唯一加分的是朱莉 德培</td>\n",
       "      <td>[妇联, 成员, 只会, 讲, 不好, 笑, 笑话, 唯一, 加分, 朱莉, 德培]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>只算還OK的商業片。現在這類片型第一品牌就是漫威了，熱鬧打鬥大場面，人神機甲齊飛，各型超級...</td>\n",
       "      <td>1</td>\n",
       "      <td>只算還 的商業片 現在這類片型第一品牌就是漫威了 熱鬧打鬥大場面 人神機甲齊飛 各型超級英雄...</td>\n",
       "      <td>[只算還, 商業片, 現在, 這類, 片型, 第一, 品牌, 漫威, 熱鬧, 打鬥大場, 面...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>好看！好看！好看！</td>\n",
       "      <td>1</td>\n",
       "      <td>好看 好看 好看</td>\n",
       "      <td>[好看, 好看, 好看]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>难看一笔</td>\n",
       "      <td>0</td>\n",
       "      <td>难看一笔</td>\n",
       "      <td>[难看, 一笔]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>6/10。第一部精准的节奏、巧妙的悬念和清楚的内心戏不见了，或许导演不想把超级英雄打造成战...</td>\n",
       "      <td>1</td>\n",
       "      <td>第一部精准的节奏 巧妙的悬念和清楚的内心戏不见了 或许导演不想把超级英雄打造成战斗机器 所以...</td>\n",
       "      <td>[第一部, 精准, 节奏, 巧妙, 悬念, 清楚, 内心, 戏, 不见, 或许, 导演, 不...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>欧洲竟然真的是最早上映啊＝ ＝法国比美国还早一周……没怎么看懂的我想找科普说明都不容易！嘛...</td>\n",
       "      <td>1</td>\n",
       "      <td>欧洲竟然真的是最早上映啊   法国比美国还早一周 没怎么看懂的我想找科普说明都不容易 嘛 我...</td>\n",
       "      <td>[欧洲, 竟然, 真的, 最早, 上映, 法国, 美国, 早, 一周, 没, 懂, 想, 找...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>我是美队的忠实脑！残！粉！！！！！！！！！</td>\n",
       "      <td>1</td>\n",
       "      <td>我是美队的忠实脑 残 粉</td>\n",
       "      <td>[美队, 忠实, 脑, 残, 粉]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              Comment  Star  \\\n",
       "0                                       连奥创都知道整容要去韩国。     1   \n",
       "1    “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...     1   \n",
       "2                                  奥创弱爆了弱爆了弱爆了啊！！！！！！     0   \n",
       "3    与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...     1   \n",
       "4    看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...     1   \n",
       "5                                   绝逼不质疑尾灯的导演和编剧水平       1   \n",
       "6                      avengers1睡着1次 avengers2睡着两次。。。     0   \n",
       "7                            谁再喊我看这种电影我和谁急！实在是接受无能。。。     0   \n",
       "8    超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...     1   \n",
       "9    观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...     1   \n",
       "10   Long takes, no stakes. 最后大战灾难性得乱 olsen到底什么能力完...     1   \n",
       "11                                       视觉效果的极限是视觉疲劳     1   \n",
       "12             感觉有略黑暗了点，不过还是萌点满满，但是一想到就要完结了又心碎了一地，，，，     1   \n",
       "13                         妇联成员都只会讲不好笑的笑话，唯一加分的是朱莉·德培     0   \n",
       "14   只算還OK的商業片。現在這類片型第一品牌就是漫威了，熱鬧打鬥大場面，人神機甲齊飛，各型超級...     1   \n",
       "15                                          好看！好看！好看！     1   \n",
       "16                                               难看一笔     0   \n",
       "17   6/10。第一部精准的节奏、巧妙的悬念和清楚的内心戏不见了，或许导演不想把超级英雄打造成战...     1   \n",
       "18   欧洲竟然真的是最早上映啊＝ ＝法国比美国还早一周……没怎么看懂的我想找科普说明都不容易！嘛...     1   \n",
       "19                              我是美队的忠实脑！残！粉！！！！！！！！！     1   \n",
       "\n",
       "                                        comment_clean  \\\n",
       "0                                        连奥创都知道整容要去韩国   \n",
       "1   一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...   \n",
       "2                                        奥创弱爆了弱爆了弱爆了啊   \n",
       "3   与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...   \n",
       "4   看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...   \n",
       "5                                     绝逼不质疑尾灯的导演和编剧水平   \n",
       "6                                           睡着 次 睡着两次   \n",
       "7                               谁再喊我看这种电影我和谁急 实在是接受无能   \n",
       "8   超愉悦以及超满足 在历经了第一阶段比漫画更普世的设定融合之后 发展到   居然出现了不少传统...   \n",
       "9   观影过程中 耳边一直有一种突突突突突的声音 我还感慨电影为了让奥创给观众带来紧张感 声音上真...   \n",
       "10  最后大战灾难性得乱 到底什么能力完全没明白 是巴菲里的   其实剧本没那么差 美国例外论的主...   \n",
       "11                                       视觉效果的极限是视觉疲劳   \n",
       "12                 感觉有略黑暗了点 不过还是萌点满满 但是一想到就要完结了又心碎了一地   \n",
       "13                         妇联成员都只会讲不好笑的笑话 唯一加分的是朱莉 德培   \n",
       "14  只算還 的商業片 現在這類片型第一品牌就是漫威了 熱鬧打鬥大場面 人神機甲齊飛 各型超級英雄...   \n",
       "15                                           好看 好看 好看   \n",
       "16                                               难看一笔   \n",
       "17  第一部精准的节奏 巧妙的悬念和清楚的内心戏不见了 或许导演不想把超级英雄打造成战斗机器 所以...   \n",
       "18  欧洲竟然真的是最早上映啊   法国比美国还早一周 没怎么看懂的我想找科普说明都不容易 嘛 我...   \n",
       "19                                       我是美队的忠实脑 残 粉   \n",
       "\n",
       "                                    comment_processed  \n",
       "0                                    [奥创, 知道, 整容, 韩国]  \n",
       "1   [一个, 没有, 黑暗面, 值得, 信任, 第二部, 剥去, 冗长, 铺垫, 开场, 高潮,...  \n",
       "2                              [奥创, 弱, 爆, 弱, 爆, 弱, 爆]  \n",
       "3   [第一集, 不同, 承上启下, 阴郁, 严肃, 不会, 好看, 本来, 喜欢, 漫威, 电影...  \n",
       "4   [看毕, 激动, 友人, 说, 奥创, 毁灭, 台北, 厚, 拍了拍, 肩膀, 没事, 反正...  \n",
       "5                            [绝逼, 质疑, 尾灯, 导演, 编剧, 水平]  \n",
       "6                                     [睡着, 次, 睡着, 两次]  \n",
       "7                          [喊, 这种, 电影, 急, 实在, 接受, 无能]  \n",
       "8   [超, 愉悦, 超, 满足, 历经, 第一阶段, 漫画, 更普世, 设定, 融合, 之后, ...  \n",
       "9   [观影, 过程, 中, 耳边, 一直, 一种, 突突突, 突突, 声音, 感慨, 电影, 奥...  \n",
       "10  [最后, 大战, 灾难性, 得乱, 到底, 能力, 完全, 没, 明白, 巴菲, 里, 其实...  \n",
       "11                                 [视觉效果, 极限, 视觉, 疲劳]  \n",
       "12            [感觉, 有略, 黑暗, 点, 萌点, 满满, 想到, 完结, 心碎, 一地]  \n",
       "13         [妇联, 成员, 只会, 讲, 不好, 笑, 笑话, 唯一, 加分, 朱莉, 德培]  \n",
       "14  [只算還, 商業片, 現在, 這類, 片型, 第一, 品牌, 漫威, 熱鬧, 打鬥大場, 面...  \n",
       "15                                       [好看, 好看, 好看]  \n",
       "16                                           [难看, 一笔]  \n",
       "17  [第一部, 精准, 节奏, 巧妙, 悬念, 清楚, 内心, 戏, 不见, 或许, 导演, 不...  \n",
       "18  [欧洲, 竟然, 真的, 最早, 上映, 法国, 美国, 早, 一周, 没, 懂, 想, 找...  \n",
       "19                                  [美队, 忠实, 脑, 残, 粉]  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务4：去掉低频词，出现次数少于10次的词去掉"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "apply: 100%|███████████████████████████████████████████████████████████████| 212506/212506 [00:00<00:00, 231161.84it/s]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comment</th>\n",
       "      <th>Star</th>\n",
       "      <th>comment_clean</th>\n",
       "      <th>comment_processed</th>\n",
       "      <th>comment_processed_str</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>连奥创都知道整容要去韩国。</td>\n",
       "      <td>1</td>\n",
       "      <td>连奥创都知道整容要去韩国</td>\n",
       "      <td>[奥创, 知道, 整容, 韩国]</td>\n",
       "      <td>奥创 知道 整容 韩国</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>“一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...</td>\n",
       "      <td>1</td>\n",
       "      <td>一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...</td>\n",
       "      <td>[一个, 没有, 黑暗面, 值得, 信任, 第二部, 冗长, 铺垫, 开场, 高潮, 一直,...</td>\n",
       "      <td>一个 没有 黑暗面 值得 信任 第二部 冗长 铺垫 开场 高潮 一直 结束 会 有人 觉得 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊！！！！！！</td>\n",
       "      <td>0</td>\n",
       "      <td>奥创弱爆了弱爆了弱爆了啊</td>\n",
       "      <td>[奥创, 弱, 爆, 弱, 爆, 弱, 爆]</td>\n",
       "      <td>奥创 弱 爆 弱 爆 弱 爆</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...</td>\n",
       "      <td>1</td>\n",
       "      <td>与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...</td>\n",
       "      <td>[第一集, 不同, 承上启下, 阴郁, 严肃, 不会, 好看, 本来, 喜欢, 漫威, 电影...</td>\n",
       "      <td>第一集 不同 承上启下 阴郁 严肃 不会 好看 本来 喜欢 漫威 电影 场面 更加 宏大 团...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...</td>\n",
       "      <td>1</td>\n",
       "      <td>看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...</td>\n",
       "      <td>[激动, 友人, 说, 奥创, 毁灭, 台北, 厚, 肩膀, 没事, 反正, 买, 两份, ...</td>\n",
       "      <td>激动 友人 说 奥创 毁灭 台北 厚 肩膀 没事 反正 买 两份 旅行 惹</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "      <td>1</td>\n",
       "      <td>绝逼不质疑尾灯的导演和编剧水平</td>\n",
       "      <td>[绝逼, 质疑, 尾灯, 导演, 编剧, 水平]</td>\n",
       "      <td>绝逼 质疑 尾灯 导演 编剧 水平</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>avengers1睡着1次 avengers2睡着两次。。。</td>\n",
       "      <td>0</td>\n",
       "      <td>睡着 次 睡着两次</td>\n",
       "      <td>[睡着, 次, 睡着, 两次]</td>\n",
       "      <td>睡着 次 睡着 两次</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>谁再喊我看这种电影我和谁急！实在是接受无能。。。</td>\n",
       "      <td>0</td>\n",
       "      <td>谁再喊我看这种电影我和谁急 实在是接受无能</td>\n",
       "      <td>[喊, 这种, 电影, 急, 实在, 接受, 无能]</td>\n",
       "      <td>喊 这种 电影 急 实在 接受 无能</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...</td>\n",
       "      <td>1</td>\n",
       "      <td>超愉悦以及超满足 在历经了第一阶段比漫画更普世的设定融合之后 发展到   居然出现了不少传统...</td>\n",
       "      <td>[超, 愉悦, 超, 满足, 历经, 漫画, 设定, 融合, 之后, 发展, 居然, 出现,...</td>\n",
       "      <td>超 愉悦 超 满足 历经 漫画 设定 融合 之后 发展 居然 出现 不少 传统 科幻 尾灯 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...</td>\n",
       "      <td>1</td>\n",
       "      <td>观影过程中 耳边一直有一种突突突突突的声音 我还感慨电影为了让奥创给观众带来紧张感 声音上真...</td>\n",
       "      <td>[观影, 过程, 中, 耳边, 一直, 一种, 突突突, 声音, 感慨, 电影, 奥创, 观...</td>\n",
       "      <td>观影 过程 中 耳边 一直 一种 突突突 声音 感慨 电影 奥创 观众 带来 紧张感 声音 ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Comment  Star  \\\n",
       "0                                      连奥创都知道整容要去韩国。     1   \n",
       "1   “一个没有黑暗面的人不值得信任。” 第二部剥去冗长的铺垫，开场即高潮、一直到结束，会有人觉...     1   \n",
       "2                                 奥创弱爆了弱爆了弱爆了啊！！！！！！     0   \n",
       "3   与第一集不同，承上启下，阴郁严肃，但也不会不好看啊，除非本来就不喜欢漫威电影。场面更加宏大...     1   \n",
       "4   看毕，我激动地对友人说，等等奥创要来毁灭台北怎么办厚，她拍了拍我肩膀，没事，反正你买了两份...     1   \n",
       "5                                  绝逼不质疑尾灯的导演和编剧水平       1   \n",
       "6                     avengers1睡着1次 avengers2睡着两次。。。     0   \n",
       "7                           谁再喊我看这种电影我和谁急！实在是接受无能。。。     0   \n",
       "8   超愉悦以及超满足。在历经了第一阶段比漫画更普世的设定融合之后，发展到#AoU#居然出现了不...     1   \n",
       "9   观影过程中，耳边一直有一种突突突突突的声音，我还感慨电影为了让奥创给观众带来紧张感，声音上...     1   \n",
       "\n",
       "                                       comment_clean  \\\n",
       "0                                       连奥创都知道整容要去韩国   \n",
       "1  一个没有黑暗面的人不值得信任   第二部剥去冗长的铺垫 开场即高潮 一直到结束 会有人觉得只...   \n",
       "2                                       奥创弱爆了弱爆了弱爆了啊   \n",
       "3  与第一集不同 承上启下 阴郁严肃 但也不会不好看啊 除非本来就不喜欢漫威电影 场面更加宏大 ...   \n",
       "4  看毕 我激动地对友人说 等等奥创要来毁灭台北怎么办厚 她拍了拍我肩膀 没事 反正你买了两份旅...   \n",
       "5                                    绝逼不质疑尾灯的导演和编剧水平   \n",
       "6                                          睡着 次 睡着两次   \n",
       "7                              谁再喊我看这种电影我和谁急 实在是接受无能   \n",
       "8  超愉悦以及超满足 在历经了第一阶段比漫画更普世的设定融合之后 发展到   居然出现了不少传统...   \n",
       "9  观影过程中 耳边一直有一种突突突突突的声音 我还感慨电影为了让奥创给观众带来紧张感 声音上真...   \n",
       "\n",
       "                                   comment_processed  \\\n",
       "0                                   [奥创, 知道, 整容, 韩国]   \n",
       "1  [一个, 没有, 黑暗面, 值得, 信任, 第二部, 冗长, 铺垫, 开场, 高潮, 一直,...   \n",
       "2                             [奥创, 弱, 爆, 弱, 爆, 弱, 爆]   \n",
       "3  [第一集, 不同, 承上启下, 阴郁, 严肃, 不会, 好看, 本来, 喜欢, 漫威, 电影...   \n",
       "4  [激动, 友人, 说, 奥创, 毁灭, 台北, 厚, 肩膀, 没事, 反正, 买, 两份, ...   \n",
       "5                           [绝逼, 质疑, 尾灯, 导演, 编剧, 水平]   \n",
       "6                                    [睡着, 次, 睡着, 两次]   \n",
       "7                         [喊, 这种, 电影, 急, 实在, 接受, 无能]   \n",
       "8  [超, 愉悦, 超, 满足, 历经, 漫画, 设定, 融合, 之后, 发展, 居然, 出现,...   \n",
       "9  [观影, 过程, 中, 耳边, 一直, 一种, 突突突, 声音, 感慨, 电影, 奥创, 观...   \n",
       "\n",
       "                               comment_processed_str  \n",
       "0                                        奥创 知道 整容 韩国  \n",
       "1  一个 没有 黑暗面 值得 信任 第二部 冗长 铺垫 开场 高潮 一直 结束 会 有人 觉得 ...  \n",
       "2                                     奥创 弱 爆 弱 爆 弱 爆  \n",
       "3  第一集 不同 承上启下 阴郁 严肃 不会 好看 本来 喜欢 漫威 电影 场面 更加 宏大 团...  \n",
       "4              激动 友人 说 奥创 毁灭 台北 厚 肩膀 没事 反正 买 两份 旅行 惹  \n",
       "5                                  绝逼 质疑 尾灯 导演 编剧 水平  \n",
       "6                                         睡着 次 睡着 两次  \n",
       "7                                 喊 这种 电影 急 实在 接受 无能  \n",
       "8  超 愉悦 超 满足 历经 漫画 设定 融合 之后 发展 居然 出现 不少 传统 科幻 尾灯 ...  \n",
       "9  观影 过程 中 耳边 一直 一种 突突突 声音 感慨 电影 奥创 观众 带来 紧张感 声音 ...  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# TODO4: 去除低频词, 去掉词频小于10的单词，并把结果存放在data['comment_processed']里\n",
    "word_counter = Counter([w for s in data['comment_processed'].values for w in s])\n",
    "\n",
    "\n",
    "def rm_low_frequency_words(word_list):\n",
    "    return [w for w in word_list if word_counter[w] >= 10]\n",
    "\n",
    "data['comment_processed'] = data['comment_processed'].progress_apply(rm_low_frequency_words)\n",
    "data['comment_processed_str'] = data['comment_processed'].apply(lambda x: ' '.join(x))\n",
    "data.head(10)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. 把文本分为训练集和测试集\n",
    "选择语料库中的20%作为测试数据，剩下的作为训练数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# TODO5: 把数据分为训练集和测试集. comments_train（list)保存用于训练的文本，comments_test(list)保存用于测试的文本。 y_train, y_test是对应的标签（0、1）\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "test_ratio = 0.2\n",
    "\n",
    "# https://machinelearningmastery.com/train-test-split-for-evaluating-machine-learning-algorithms/\n",
    "src_training, src_testing = train_test_split(data, test_size=test_ratio, stratify=data['Star'])\n",
    "\n",
    "comments_train, comments_test = src_training['comment_processed_str'].values, src_testing['comment_processed_str'].values\n",
    "y_train, y_test = src_training['Star'].values, src_testing['Star'].values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. 把文本转换成向量的形式\n",
    "\n",
    "在这个部分我们会采用三种不同的方式:\n",
    "- 使用tf-idf向量\n",
    "- 使用word2vec\n",
    "- 使用bert向量\n",
    "\n",
    "转换成向量之后，我们接着做模型的训练"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务6：把文本转换成tf-idf向量"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(170004, 15762) (42502, 15762)\n"
     ]
    }
   ],
   "source": [
    "# TODO6: 把训练文本和测试文本转换成tf-idf向量。使用sklearn的feature_extraction.text.TfidfTransformer模块\n",
    "#    请留意fit_transform和transform之间的区别。 常见的错误是在训练集和测试集上都使用 fit_transform，需要避免！ \n",
    "#    另外，可以留意一下结果是否为稀疏矩阵\n",
    "\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.feature_extraction.text import TfidfTransformer\n",
    "\n",
    "count_vectorizer = CountVectorizer(token_pattern=r\"(?u)\\b\\w+\\b\")\n",
    "tfidf_transformer = TfidfTransformer()\n",
    "\n",
    "word_count_train = count_vectorizer.fit_transform(comments_train)\n",
    "tfidf_train = tfidf_transformer.fit_transform(word_count_train)\n",
    "\n",
    "word_count_test = count_vectorizer.transform(comments_test)\n",
    "tfidf_test = tfidf_transformer.transform(word_count_test)\n",
    "\n",
    "print(tfidf_train.shape, tfidf_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务7：把文本转换成word2vec向量"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 由于训练出一个高效的word2vec词向量往往需要非常大的语料库与计算资源，所以我们通常不自己训练Wordvec词向量，而直接使用网上开源的已训练好的词向量。\n",
    "# data/sgns.zhihu.word是从https://github.com/Embedding/Chinese-Word-Vectors下载到的预训练好的中文词向量文件\n",
    "# 使用KeyedVectors.load_word2vec_format()函数加载预训练好的词向量文件\n",
    "model = KeyedVectors.load_word2vec_format('data/sgns.zhihu.word')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-0.200708,  0.188213, -0.20941 ,  0.048857,  0.116663,  0.547244,\n",
       "       -0.449441, -0.177554,  0.123547,  0.161301, -0.20861 ,  0.429821,\n",
       "       -0.429595, -0.45094 ,  0.190053,  0.175438,  0.066855, -0.157346,\n",
       "        0.134905, -0.128076,  0.111503, -0.03149 , -0.347445, -0.231517,\n",
       "        0.212383,  0.29857 ,  0.167368, -0.064022, -0.048241,  0.109434,\n",
       "       -0.156835, -0.558394, -0.005307,  0.127788, -0.053521, -0.154787,\n",
       "       -0.048875,  0.109031,  0.160019,  0.273365, -0.023131, -0.257962,\n",
       "       -0.051904,  0.103058,  0.019103,  0.210418, -0.12053 ,  0.084021,\n",
       "        0.085243, -0.406479, -0.285062, -0.229883, -0.125173, -0.141597,\n",
       "       -0.018101, -0.215311, -0.091788,  0.315358,  0.242912,  0.013785,\n",
       "       -0.078914,  0.158206,  0.180421, -0.050306, -0.008539, -0.201157,\n",
       "        0.047753,  0.293518,  0.340344,  0.098132,  0.356952,  0.189959,\n",
       "       -0.107122, -0.176698,  0.011044,  0.131703,  0.134601, -0.078891,\n",
       "        0.217989,  0.05074 ,  0.063365,  0.30178 ,  0.161369,  0.157998,\n",
       "       -0.128195, -0.060345,  0.047446, -0.146161,  0.005427, -0.06684 ,\n",
       "        0.056229, -0.04922 , -0.122368,  0.181634,  0.180599,  0.026725,\n",
       "       -0.383503, -0.10855 ,  0.06524 , -0.095767,  0.08362 ,  0.287755,\n",
       "       -0.325982, -0.026982,  0.147817,  0.041374,  0.342181, -0.010403,\n",
       "       -0.082642,  0.124128, -0.104747,  0.002654, -0.086981, -0.044065,\n",
       "       -0.085694, -0.020068, -0.125195, -0.154542, -0.030115,  0.100488,\n",
       "        0.081022,  0.06612 ,  0.088058, -0.102289, -0.061927, -0.054882,\n",
       "        0.510755, -0.154545,  0.029478, -0.191885, -0.048633, -0.218267,\n",
       "       -0.14659 , -0.028195,  0.223698,  0.101008,  0.100562, -0.237451,\n",
       "        0.492519, -0.163208, -0.466598,  0.041121,  0.153394,  0.066931,\n",
       "        0.428429,  0.238117,  0.188347,  0.290581,  0.147405, -0.222624,\n",
       "        0.336171, -0.128802,  0.032038,  0.036617,  0.042459,  0.031089,\n",
       "        0.092689,  0.092509, -0.206014, -0.093757, -0.079919,  0.052213,\n",
       "        0.176261,  0.030587, -0.222407, -0.293368, -0.210982,  0.086169,\n",
       "       -0.41054 ,  0.168664, -0.110555,  0.104398,  0.131111,  0.034967,\n",
       "       -0.240558,  0.050963,  0.002297, -0.231932,  0.138751, -0.162152,\n",
       "        0.128286,  0.11232 ,  0.085235,  0.16869 ,  0.072754,  0.004705,\n",
       "       -0.175828, -0.082598, -0.245999,  0.103419,  0.357173, -0.05588 ,\n",
       "        0.030934, -0.13984 ,  0.011164, -0.277783, -0.168691, -0.223155,\n",
       "       -0.203391, -0.015567,  0.161146, -0.110572, -0.06779 , -0.006586,\n",
       "       -0.039414,  0.245169, -0.182014,  0.38548 ,  0.039947,  0.36978 ,\n",
       "        0.167039, -0.055724,  0.051462,  0.044205, -0.255853, -0.194969,\n",
       "       -0.215543,  0.367193, -0.268322,  0.048425,  0.181398,  0.203609,\n",
       "        0.04321 , -0.280908,  0.215055, -0.410717,  0.209178,  0.365696,\n",
       "       -0.26421 ,  0.008008, -0.167048,  0.07082 ,  0.148507, -0.121757,\n",
       "       -0.227046, -0.161108, -0.084349,  0.173502,  0.07519 , -0.203567,\n",
       "        0.151776, -0.21104 , -0.334659,  0.090743,  0.049097,  0.080783,\n",
       "       -0.062416, -0.089825,  0.230757, -0.065472,  0.313976,  0.096314,\n",
       "       -0.145926,  0.146772, -0.007169, -0.041627, -0.050497, -0.34267 ,\n",
       "       -0.144144, -0.140267,  0.000677, -0.114036, -0.017044, -0.030107,\n",
       "       -0.098467, -0.233114,  0.103173,  0.093112, -0.11863 ,  0.086859,\n",
       "        0.300346,  0.146062, -0.173922,  0.162061,  0.143895, -0.158726,\n",
       "       -0.123311,  0.166061, -0.196121,  0.207249,  0.053585,  0.025314,\n",
       "       -0.24309 , -0.074694, -0.238774, -0.056441, -0.099747, -0.271508,\n",
       "        0.212461,  0.189918,  0.162701, -0.154819,  0.235821, -0.131372,\n",
       "       -0.052284,  0.101817,  0.088172,  0.107883,  0.020072,  0.188443],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#预训练词向量使用举例\n",
    "model['我们']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(170004, 300) (42502, 300)\n"
     ]
    }
   ],
   "source": [
    "vocabulary = model.vocab\n",
    "\n",
    "def word_vec_averaging(words, dim=300):\n",
    "    \"\"\"\n",
    "    Average all words vectors in one sentence.\n",
    "    :param words: input sentence\n",
    "    :param dim: 'size' of model\n",
    "    :return: the averaged word vectors as the vector for the sentence\n",
    "    \"\"\"\n",
    "    vec_mean = np.zeros((dim,), dtype=np.float32)\n",
    "    word_num = 0\n",
    "    first_dim_sum = 0\n",
    "    for word in words:\n",
    "        if word in vocabulary:\n",
    "            word_num += 1\n",
    "            vec_mean = np.add(vec_mean, model[word])\n",
    "            first_dim_sum += model[word][0]\n",
    "    if word_num > 0:\n",
    "        vec_mean = np.divide(vec_mean, word_num)\n",
    "    return vec_mean\n",
    "\n",
    "word2vec_train = np.array([word_vec_averaging(s.split()) for s in comments_train])\n",
    "word2vec_test = np.array([word_vec_averaging(s.split()) for s in comments_test])\n",
    "print(word2vec_train.shape, word2vec_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务8：把文本转换成bert向量"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at ./data/chinese_wwm_pytorch were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.decoder.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight']\n",
      "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
     ]
    }
   ],
   "source": [
    "from transformers import BertTokenizer, BertModel\n",
    "\n",
    "\n",
    "tokenizer = BertTokenizer.from_pretrained(\"./data/chinese_wwm_pytorch\")\n",
    "model = BertModel.from_pretrained(\"./data/chinese_wwm_pytorch\")\n",
    "\n",
    "inputs = tokenizer(\"北京欢迎你\", return_tensors=\"pt\")\n",
    "outputs = model(**inputs)\n",
    "\n",
    "last_hidden_states = outputs.last_hidden_state"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([1, 7, 768])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "last_hidden_states.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "\n",
    "gpu_device_name = tf.test.gpu_device_name()\n",
    "print(gpu_device_name)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tf.test.is_gpu_available()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.python.client import device_lib\n",
    "\n",
    "# 列出所有的本地机器设备\n",
    "local_device_protos = device_lib.list_local_devices()\n",
    "# 打印\n",
    "print(local_device_protos)\n",
    "\n",
    "# 只打印GPU设备\n",
    "[print(x) for x in local_device_protos if x.device_type == 'GPU']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tf.test.is_gpu_available(\n",
    "    cuda_only=False,\n",
    "    min_cuda_compute_capability=None\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 导入gpu版本的bert embedding预训练的模型。\n",
    "# 若没有gpu，则ctx可使用其默认值cpu(0)。但使用cpu会使程序运行的时间变得非常慢\n",
    "# 若之前没有下载过bert embedding预训练的模型，执行此句时会花费一些时间来下载预训练的模型\n",
    "ctx = mxnet.cpu()\n",
    "embedding = BertEmbedding(ctx=ctx)\n",
    "\n",
    "# TODO8: 跟word2vec一样，计算出训练文本和测试文本的向量，仍然采用单词向量的平均。\n",
    "def bert_embedding_averaging(sentence):\n",
    "    \"\"\"返回sentence bert 句向量\"\"\"\n",
    "    tokens, token_embeddings = embedding([sentence])[0]\n",
    "    return np.mean(np.array(token_embeddings), axis=0).astype(np.float32)\n",
    "bert_train = np.array([bert_embedding_averaging(s) for s in comments_train])\n",
    "bert_test = np.array([bert_embedding_averaging(s) for s in comments_test])\n",
    "print (bert_train.shape, bert_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print (tfidf_train.shape, tfidf_test.shape)\n",
    "print (word2vec_train.shape, word2vec_test.shape)\n",
    "print (bert_train.shape, bert_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4. 训练模型以及评估\n",
    "对如上三种不同的向量表示法，分别训练逻辑回归模型，需要做：\n",
    "- 搭建模型\n",
    "- 训练模型（并做交叉验证）\n",
    "- 输出最好的结果"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 导入逻辑回归的包\n",
    "from sklearn.linear_model import LogisticRegression"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务9：使用tf-idf，并结合逻辑回归训练模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# TODO9: 使用tf-idf + 逻辑回归训练模型，需要用gridsearchCV做交叉验证，并选择最好的超参数\n",
    "clf = LogisticRegression()\n",
    "\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "search_grid = {\n",
    "    'C': [0.01, 1, 10, 100],\n",
    "    'class_weight': [None, 'balanced']\n",
    "}\n",
    "\n",
    "grid_search = GridSearchCV(estimator = clf, \n",
    "                           param_grid = search_grid, \n",
    "                           cv = 55, \n",
    "                           n_jobs=-1, \n",
    "                           scoring='accuracy')\n",
    "\n",
    "grid_result = grid_search.fit(tfidf_train, y_train)\n",
    "print(f'Best parameters: {grid_result.best_params_}')\n",
    "\n",
    "\n",
    "lr = LogisticRegression(C=1, class_weight=None)\n",
    "lr.fit(tfidf_train, y_train)\n",
    "tf_idf_y_pred = lr.predict(tfidf_test)\n",
    "print('TF-IDF LR test accuracy %s' % metrics.accuracy_score(y_test, tf_idf_y_pred))\n",
    "#逻辑回归模型在测试集上的F1_Score\n",
    "print('TF-IDF LR test F1_score %s' % metrics.f1_score(y_test, tf_idf_y_pred,average=\"macro\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务10：使用word2vec，并结合逻辑回归训练模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# TODO10: 使用word2vec + 逻辑回归训练模型，需要用gridsearchCV做交叉验证，并选择最好的超参数\n",
    "clf = LogisticRegression()\n",
    "\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "search_grid = {\n",
    "    'C': [0.01, 1, 10, 100],\n",
    "    'class_weight': [None, 'balanced']\n",
    "}\n",
    "\n",
    "grid_search = GridSearchCV(estimator = clf, \n",
    "                           param_grid = search_grid, \n",
    "                           cv = 5, \n",
    "                           n_jobs=-1, \n",
    "                           scoring='accuracy')\n",
    "\n",
    "grid_result = grid_search.fit(word2vec_train, y_train)\n",
    "print(f'Best parameters: {grid_result.best_params_}')\n",
    "\n",
    "lr = LogisticRegression(C=0.01, class_weight=None)\n",
    "lr.fit(word2vec_train, y_train)\n",
    "word2vec_y_pred = lr.predict(word2vec_test)\n",
    "print('Word2vec LR test accuracy %s' % metrics.accuracy_score(y_test, word2vec_y_pred))\n",
    "#逻辑回归模型在测试集上的F1_Score\n",
    "print('Word2vec LR test F1_score %s' % metrics.f1_score(y_test, word2vec_y_pred,average=\"macro\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务11：使用bert，并结合逻辑回归训练模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# TODO11: 使用bert + 逻辑回归训练模型，需要用gridsearchCV做交叉验证，并选择最好的超参数\n",
    "\n",
    "lr = LogisticRegression()\n",
    "lr.fit(bert_train, y_train)\n",
    "bert_y_pred = lr.predict(bert_test)\n",
    "\n",
    "print('Bert LR test accuracy %s' % metrics.accuracy_score(y_test, bert_y_pred))\n",
    "#逻辑回归模型在测试集上的F1_Score\n",
    "print('Bert LR test F1_score %s' % metrics.f1_score(y_test, bert_y_pred,average=\"macro\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 任务12：对于以上结果请做一下简单的总结，按照1，2，3，4提取几个关键点，包括：\n",
    "- 结果说明什么问题？\n",
    "- 接下来如何提高？"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.\n",
    "2.\n",
    "3.\n",
    "4.\n",
    "5.\n",
    "6."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}