File size: 77,377 Bytes
7885a28 |
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 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 |
"""Utilities to build feature vectors from text documents."""
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import array
import re
import unicodedata
import warnings
from collections import defaultdict
from collections.abc import Mapping
from functools import partial
from numbers import Integral
from operator import itemgetter
import numpy as np
import scipy.sparse as sp
from sklearn.utils import metadata_routing
from ..base import BaseEstimator, OneToOneFeatureMixin, TransformerMixin, _fit_context
from ..exceptions import NotFittedError
from ..preprocessing import normalize
from ..utils._param_validation import HasMethods, Interval, RealNotInt, StrOptions
from ..utils.fixes import _IS_32BIT
from ..utils.validation import FLOAT_DTYPES, check_array, check_is_fitted, validate_data
from ._hash import FeatureHasher
from ._stop_words import ENGLISH_STOP_WORDS
__all__ = [
"HashingVectorizer",
"CountVectorizer",
"ENGLISH_STOP_WORDS",
"TfidfTransformer",
"TfidfVectorizer",
"strip_accents_ascii",
"strip_accents_unicode",
"strip_tags",
]
def _preprocess(doc, accent_function=None, lower=False):
"""Chain together an optional series of text preprocessing steps to
apply to a document.
Parameters
----------
doc: str
The string to preprocess
accent_function: callable, default=None
Function for handling accented characters. Common strategies include
normalizing and removing.
lower: bool, default=False
Whether to use str.lower to lowercase all of the text
Returns
-------
doc: str
preprocessed string
"""
if lower:
doc = doc.lower()
if accent_function is not None:
doc = accent_function(doc)
return doc
def _analyze(
doc,
analyzer=None,
tokenizer=None,
ngrams=None,
preprocessor=None,
decoder=None,
stop_words=None,
):
"""Chain together an optional series of text processing steps to go from
a single document to ngrams, with or without tokenizing or preprocessing.
If analyzer is used, only the decoder argument is used, as the analyzer is
intended to replace the preprocessor, tokenizer, and ngrams steps.
Parameters
----------
analyzer: callable, default=None
tokenizer: callable, default=None
ngrams: callable, default=None
preprocessor: callable, default=None
decoder: callable, default=None
stop_words: list, default=None
Returns
-------
ngrams: list
A sequence of tokens, possibly with pairs, triples, etc.
"""
if decoder is not None:
doc = decoder(doc)
if analyzer is not None:
doc = analyzer(doc)
else:
if preprocessor is not None:
doc = preprocessor(doc)
if tokenizer is not None:
doc = tokenizer(doc)
if ngrams is not None:
if stop_words is not None:
doc = ngrams(doc, stop_words)
else:
doc = ngrams(doc)
return doc
def strip_accents_unicode(s):
"""Transform accentuated unicode symbols into their simple counterpart.
Warning: the python-level loop and join operations make this
implementation 20 times slower than the strip_accents_ascii basic
normalization.
Parameters
----------
s : str
The string to strip.
Returns
-------
s : str
The stripped string.
See Also
--------
strip_accents_ascii : Remove accentuated char for any unicode symbol that
has a direct ASCII equivalent.
"""
try:
# If `s` is ASCII-compatible, then it does not contain any accented
# characters and we can avoid an expensive list comprehension
s.encode("ASCII", errors="strict")
return s
except UnicodeEncodeError:
normalized = unicodedata.normalize("NFKD", s)
return "".join([c for c in normalized if not unicodedata.combining(c)])
def strip_accents_ascii(s):
"""Transform accentuated unicode symbols into ascii or nothing.
Warning: this solution is only suited for languages that have a direct
transliteration to ASCII symbols.
Parameters
----------
s : str
The string to strip.
Returns
-------
s : str
The stripped string.
See Also
--------
strip_accents_unicode : Remove accentuated char for any unicode symbol.
"""
nkfd_form = unicodedata.normalize("NFKD", s)
return nkfd_form.encode("ASCII", "ignore").decode("ASCII")
def strip_tags(s):
"""Basic regexp based HTML / XML tag stripper function.
For serious HTML/XML preprocessing you should rather use an external
library such as lxml or BeautifulSoup.
Parameters
----------
s : str
The string to strip.
Returns
-------
s : str
The stripped string.
"""
return re.compile(r"<([^>]+)>", flags=re.UNICODE).sub(" ", s)
def _check_stop_list(stop):
if stop == "english":
return ENGLISH_STOP_WORDS
elif isinstance(stop, str):
raise ValueError("not a built-in stop list: %s" % stop)
elif stop is None:
return None
else: # assume it's a collection
return frozenset(stop)
class _VectorizerMixin:
"""Provides common code for text vectorizers (tokenization logic)."""
_white_spaces = re.compile(r"\s\s+")
def decode(self, doc):
"""Decode the input into a string of unicode symbols.
The decoding strategy depends on the vectorizer parameters.
Parameters
----------
doc : bytes or str
The string to decode.
Returns
-------
doc: str
A string of unicode symbols.
"""
if self.input == "filename":
with open(doc, "rb") as fh:
doc = fh.read()
elif self.input == "file":
doc = doc.read()
if isinstance(doc, bytes):
doc = doc.decode(self.encoding, self.decode_error)
if doc is np.nan:
raise ValueError(
"np.nan is an invalid document, expected byte or unicode string."
)
return doc
def _word_ngrams(self, tokens, stop_words=None):
"""Turn tokens into a sequence of n-grams after stop words filtering"""
# handle stop words
if stop_words is not None:
tokens = [w for w in tokens if w not in stop_words]
# handle token n-grams
min_n, max_n = self.ngram_range
if max_n != 1:
original_tokens = tokens
if min_n == 1:
# no need to do any slicing for unigrams
# just iterate through the original tokens
tokens = list(original_tokens)
min_n += 1
else:
tokens = []
n_original_tokens = len(original_tokens)
# bind method outside of loop to reduce overhead
tokens_append = tokens.append
space_join = " ".join
for n in range(min_n, min(max_n + 1, n_original_tokens + 1)):
for i in range(n_original_tokens - n + 1):
tokens_append(space_join(original_tokens[i : i + n]))
return tokens
def _char_ngrams(self, text_document):
"""Tokenize text_document into a sequence of character n-grams"""
# normalize white spaces
text_document = self._white_spaces.sub(" ", text_document)
text_len = len(text_document)
min_n, max_n = self.ngram_range
if min_n == 1:
# no need to do any slicing for unigrams
# iterate through the string
ngrams = list(text_document)
min_n += 1
else:
ngrams = []
# bind method outside of loop to reduce overhead
ngrams_append = ngrams.append
for n in range(min_n, min(max_n + 1, text_len + 1)):
for i in range(text_len - n + 1):
ngrams_append(text_document[i : i + n])
return ngrams
def _char_wb_ngrams(self, text_document):
"""Whitespace sensitive char-n-gram tokenization.
Tokenize text_document into a sequence of character n-grams
operating only inside word boundaries. n-grams at the edges
of words are padded with space."""
# normalize white spaces
text_document = self._white_spaces.sub(" ", text_document)
min_n, max_n = self.ngram_range
ngrams = []
# bind method outside of loop to reduce overhead
ngrams_append = ngrams.append
for w in text_document.split():
w = " " + w + " "
w_len = len(w)
for n in range(min_n, max_n + 1):
offset = 0
ngrams_append(w[offset : offset + n])
while offset + n < w_len:
offset += 1
ngrams_append(w[offset : offset + n])
if offset == 0: # count a short word (w_len < n) only once
break
return ngrams
def build_preprocessor(self):
"""Return a function to preprocess the text before tokenization.
Returns
-------
preprocessor: callable
A function to preprocess the text before tokenization.
"""
if self.preprocessor is not None:
return self.preprocessor
# accent stripping
if not self.strip_accents:
strip_accents = None
elif callable(self.strip_accents):
strip_accents = self.strip_accents
elif self.strip_accents == "ascii":
strip_accents = strip_accents_ascii
elif self.strip_accents == "unicode":
strip_accents = strip_accents_unicode
else:
raise ValueError(
'Invalid value for "strip_accents": %s' % self.strip_accents
)
return partial(_preprocess, accent_function=strip_accents, lower=self.lowercase)
def build_tokenizer(self):
"""Return a function that splits a string into a sequence of tokens.
Returns
-------
tokenizer: callable
A function to split a string into a sequence of tokens.
"""
if self.tokenizer is not None:
return self.tokenizer
token_pattern = re.compile(self.token_pattern)
if token_pattern.groups > 1:
raise ValueError(
"More than 1 capturing group in token pattern. Only a single "
"group should be captured."
)
return token_pattern.findall
def get_stop_words(self):
"""Build or fetch the effective stop words list.
Returns
-------
stop_words: list or None
A list of stop words.
"""
return _check_stop_list(self.stop_words)
def _check_stop_words_consistency(self, stop_words, preprocess, tokenize):
"""Check if stop words are consistent
Returns
-------
is_consistent : True if stop words are consistent with the preprocessor
and tokenizer, False if they are not, None if the check
was previously performed, "error" if it could not be
performed (e.g. because of the use of a custom
preprocessor / tokenizer)
"""
if id(self.stop_words) == getattr(self, "_stop_words_id", None):
# Stop words are were previously validated
return None
# NB: stop_words is validated, unlike self.stop_words
try:
inconsistent = set()
for w in stop_words or ():
tokens = list(tokenize(preprocess(w)))
for token in tokens:
if token not in stop_words:
inconsistent.add(token)
self._stop_words_id = id(self.stop_words)
if inconsistent:
warnings.warn(
"Your stop_words may be inconsistent with "
"your preprocessing. Tokenizing the stop "
"words generated tokens %r not in "
"stop_words." % sorted(inconsistent)
)
return not inconsistent
except Exception:
# Failed to check stop words consistency (e.g. because a custom
# preprocessor or tokenizer was used)
self._stop_words_id = id(self.stop_words)
return "error"
def build_analyzer(self):
"""Return a callable to process input data.
The callable handles preprocessing, tokenization, and n-grams generation.
Returns
-------
analyzer: callable
A function to handle preprocessing, tokenization
and n-grams generation.
"""
if callable(self.analyzer):
return partial(_analyze, analyzer=self.analyzer, decoder=self.decode)
preprocess = self.build_preprocessor()
if self.analyzer == "char":
return partial(
_analyze,
ngrams=self._char_ngrams,
preprocessor=preprocess,
decoder=self.decode,
)
elif self.analyzer == "char_wb":
return partial(
_analyze,
ngrams=self._char_wb_ngrams,
preprocessor=preprocess,
decoder=self.decode,
)
elif self.analyzer == "word":
stop_words = self.get_stop_words()
tokenize = self.build_tokenizer()
self._check_stop_words_consistency(stop_words, preprocess, tokenize)
return partial(
_analyze,
ngrams=self._word_ngrams,
tokenizer=tokenize,
preprocessor=preprocess,
decoder=self.decode,
stop_words=stop_words,
)
else:
raise ValueError(
"%s is not a valid tokenization scheme/analyzer" % self.analyzer
)
def _validate_vocabulary(self):
vocabulary = self.vocabulary
if vocabulary is not None:
if isinstance(vocabulary, set):
vocabulary = sorted(vocabulary)
if not isinstance(vocabulary, Mapping):
vocab = {}
for i, t in enumerate(vocabulary):
if vocab.setdefault(t, i) != i:
msg = "Duplicate term in vocabulary: %r" % t
raise ValueError(msg)
vocabulary = vocab
else:
indices = set(vocabulary.values())
if len(indices) != len(vocabulary):
raise ValueError("Vocabulary contains repeated indices.")
for i in range(len(vocabulary)):
if i not in indices:
msg = "Vocabulary of size %d doesn't contain index %d." % (
len(vocabulary),
i,
)
raise ValueError(msg)
if not vocabulary:
raise ValueError("empty vocabulary passed to fit")
self.fixed_vocabulary_ = True
self.vocabulary_ = dict(vocabulary)
else:
self.fixed_vocabulary_ = False
def _check_vocabulary(self):
"""Check if vocabulary is empty or missing (not fitted)"""
if not hasattr(self, "vocabulary_"):
self._validate_vocabulary()
if not self.fixed_vocabulary_:
raise NotFittedError("Vocabulary not fitted or provided")
if len(self.vocabulary_) == 0:
raise ValueError("Vocabulary is empty")
def _validate_ngram_range(self):
"""Check validity of ngram_range parameter"""
min_n, max_m = self.ngram_range
if min_n > max_m:
raise ValueError(
"Invalid value for ngram_range=%s "
"lower boundary larger than the upper boundary." % str(self.ngram_range)
)
def _warn_for_unused_params(self):
if self.tokenizer is not None and self.token_pattern is not None:
warnings.warn(
"The parameter 'token_pattern' will not be used"
" since 'tokenizer' is not None'"
)
if self.preprocessor is not None and callable(self.analyzer):
warnings.warn(
"The parameter 'preprocessor' will not be used"
" since 'analyzer' is callable'"
)
if (
self.ngram_range != (1, 1)
and self.ngram_range is not None
and callable(self.analyzer)
):
warnings.warn(
"The parameter 'ngram_range' will not be used"
" since 'analyzer' is callable'"
)
if self.analyzer != "word" or callable(self.analyzer):
if self.stop_words is not None:
warnings.warn(
"The parameter 'stop_words' will not be used"
" since 'analyzer' != 'word'"
)
if (
self.token_pattern is not None
and self.token_pattern != r"(?u)\b\w\w+\b"
):
warnings.warn(
"The parameter 'token_pattern' will not be used"
" since 'analyzer' != 'word'"
)
if self.tokenizer is not None:
warnings.warn(
"The parameter 'tokenizer' will not be used"
" since 'analyzer' != 'word'"
)
class HashingVectorizer(
TransformerMixin, _VectorizerMixin, BaseEstimator, auto_wrap_output_keys=None
):
r"""Convert a collection of text documents to a matrix of token occurrences.
It turns a collection of text documents into a scipy.sparse matrix holding
token occurrence counts (or binary occurrence information), possibly
normalized as token frequencies if norm='l1' or projected on the euclidean
unit sphere if norm='l2'.
This text vectorizer implementation uses the hashing trick to find the
token string name to feature integer index mapping.
This strategy has several advantages:
- it is very low memory scalable to large datasets as there is no need to
store a vocabulary dictionary in memory.
- it is fast to pickle and un-pickle as it holds no state besides the
constructor parameters.
- it can be used in a streaming (partial fit) or parallel pipeline as there
is no state computed during fit.
There are also a couple of cons (vs using a CountVectorizer with an
in-memory vocabulary):
- there is no way to compute the inverse transform (from feature indices to
string feature names) which can be a problem when trying to introspect
which features are most important to a model.
- there can be collisions: distinct tokens can be mapped to the same
feature index. However in practice this is rarely an issue if n_features
is large enough (e.g. 2 ** 18 for text classification problems).
- no IDF weighting as this would render the transformer stateful.
The hash function employed is the signed 32-bit version of Murmurhash3.
For an efficiency comparison of the different feature extractors, see
:ref:`sphx_glr_auto_examples_text_plot_hashing_vs_dict_vectorizer.py`.
For an example of document clustering and comparison with
:class:`~sklearn.feature_extraction.text.TfidfVectorizer`, see
:ref:`sphx_glr_auto_examples_text_plot_document_clustering.py`.
Read more in the :ref:`User Guide <text_feature_extraction>`.
Parameters
----------
input : {'filename', 'file', 'content'}, default='content'
- If `'filename'`, the sequence passed as an argument to fit is
expected to be a list of filenames that need reading to fetch
the raw content to analyze.
- If `'file'`, the sequence items must have a 'read' method (file-like
object) that is called to fetch the bytes in memory.
- If `'content'`, the input is expected to be a sequence of items that
can be of type string or byte.
encoding : str, default='utf-8'
If bytes or files are given to analyze, this encoding is used to
decode.
decode_error : {'strict', 'ignore', 'replace'}, default='strict'
Instruction on what to do if a byte sequence is given to analyze that
contains characters not of the given `encoding`. By default, it is
'strict', meaning that a UnicodeDecodeError will be raised. Other
values are 'ignore' and 'replace'.
strip_accents : {'ascii', 'unicode'} or callable, default=None
Remove accents and perform other character normalization
during the preprocessing step.
'ascii' is a fast method that only works on characters that have
a direct ASCII mapping.
'unicode' is a slightly slower method that works on any character.
None (default) means no character normalization is performed.
Both 'ascii' and 'unicode' use NFKD normalization from
:func:`unicodedata.normalize`.
lowercase : bool, default=True
Convert all characters to lowercase before tokenizing.
preprocessor : callable, default=None
Override the preprocessing (string transformation) stage while
preserving the tokenizing and n-grams generation steps.
Only applies if ``analyzer`` is not callable.
tokenizer : callable, default=None
Override the string tokenization step while preserving the
preprocessing and n-grams generation steps.
Only applies if ``analyzer == 'word'``.
stop_words : {'english'}, list, default=None
If 'english', a built-in stop word list for English is used.
There are several known issues with 'english' and you should
consider an alternative (see :ref:`stop_words`).
If a list, that list is assumed to contain stop words, all of which
will be removed from the resulting tokens.
Only applies if ``analyzer == 'word'``.
token_pattern : str or None, default=r"(?u)\\b\\w\\w+\\b"
Regular expression denoting what constitutes a "token", only used
if ``analyzer == 'word'``. The default regexp selects tokens of 2
or more alphanumeric characters (punctuation is completely ignored
and always treated as a token separator).
If there is a capturing group in token_pattern then the
captured group content, not the entire match, becomes the token.
At most one capturing group is permitted.
ngram_range : tuple (min_n, max_n), default=(1, 1)
The lower and upper boundary of the range of n-values for different
n-grams to be extracted. All values of n such that min_n <= n <= max_n
will be used. For example an ``ngram_range`` of ``(1, 1)`` means only
unigrams, ``(1, 2)`` means unigrams and bigrams, and ``(2, 2)`` means
only bigrams.
Only applies if ``analyzer`` is not callable.
analyzer : {'word', 'char', 'char_wb'} or callable, default='word'
Whether the feature should be made of word or character n-grams.
Option 'char_wb' creates character n-grams only from text inside
word boundaries; n-grams at the edges of words are padded with space.
If a callable is passed it is used to extract the sequence of features
out of the raw, unprocessed input.
.. versionchanged:: 0.21
Since v0.21, if ``input`` is ``'filename'`` or ``'file'``, the data
is first read from the file and then passed to the given callable
analyzer.
n_features : int, default=(2 ** 20)
The number of features (columns) in the output matrices. Small numbers
of features are likely to cause hash collisions, but large numbers
will cause larger coefficient dimensions in linear learners.
binary : bool, default=False
If True, all non zero counts are set to 1. This is useful for discrete
probabilistic models that model binary events rather than integer
counts.
norm : {'l1', 'l2'}, default='l2'
Norm used to normalize term vectors. None for no normalization.
alternate_sign : bool, default=True
When True, an alternating sign is added to the features as to
approximately conserve the inner product in the hashed space even for
small n_features. This approach is similar to sparse random projection.
.. versionadded:: 0.19
dtype : type, default=np.float64
Type of the matrix returned by fit_transform() or transform().
See Also
--------
CountVectorizer : Convert a collection of text documents to a matrix of
token counts.
TfidfVectorizer : Convert a collection of raw documents to a matrix of
TF-IDF features.
Notes
-----
This estimator is :term:`stateless` and does not need to be fitted.
However, we recommend to call :meth:`fit_transform` instead of
:meth:`transform`, as parameter validation is only performed in
:meth:`fit`.
Examples
--------
>>> from sklearn.feature_extraction.text import HashingVectorizer
>>> corpus = [
... 'This is the first document.',
... 'This document is the second document.',
... 'And this is the third one.',
... 'Is this the first document?',
... ]
>>> vectorizer = HashingVectorizer(n_features=2**4)
>>> X = vectorizer.fit_transform(corpus)
>>> print(X.shape)
(4, 16)
"""
_parameter_constraints: dict = {
"input": [StrOptions({"filename", "file", "content"})],
"encoding": [str],
"decode_error": [StrOptions({"strict", "ignore", "replace"})],
"strip_accents": [StrOptions({"ascii", "unicode"}), None, callable],
"lowercase": ["boolean"],
"preprocessor": [callable, None],
"tokenizer": [callable, None],
"stop_words": [StrOptions({"english"}), list, None],
"token_pattern": [str, None],
"ngram_range": [tuple],
"analyzer": [StrOptions({"word", "char", "char_wb"}), callable],
"n_features": [Interval(Integral, 1, np.iinfo(np.int32).max, closed="left")],
"binary": ["boolean"],
"norm": [StrOptions({"l1", "l2"}), None],
"alternate_sign": ["boolean"],
"dtype": "no_validation", # delegate to numpy
}
def __init__(
self,
*,
input="content",
encoding="utf-8",
decode_error="strict",
strip_accents=None,
lowercase=True,
preprocessor=None,
tokenizer=None,
stop_words=None,
token_pattern=r"(?u)\b\w\w+\b",
ngram_range=(1, 1),
analyzer="word",
n_features=(2**20),
binary=False,
norm="l2",
alternate_sign=True,
dtype=np.float64,
):
self.input = input
self.encoding = encoding
self.decode_error = decode_error
self.strip_accents = strip_accents
self.preprocessor = preprocessor
self.tokenizer = tokenizer
self.analyzer = analyzer
self.lowercase = lowercase
self.token_pattern = token_pattern
self.stop_words = stop_words
self.n_features = n_features
self.ngram_range = ngram_range
self.binary = binary
self.norm = norm
self.alternate_sign = alternate_sign
self.dtype = dtype
@_fit_context(prefer_skip_nested_validation=True)
def partial_fit(self, X, y=None):
"""Only validates estimator's parameters.
This method allows to: (i) validate the estimator's parameters and
(ii) be consistent with the scikit-learn transformer API.
Parameters
----------
X : ndarray of shape [n_samples, n_features]
Training data.
y : Ignored
Not used, present for API consistency by convention.
Returns
-------
self : object
HashingVectorizer instance.
"""
return self
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y=None):
"""Only validates estimator's parameters.
This method allows to: (i) validate the estimator's parameters and
(ii) be consistent with the scikit-learn transformer API.
Parameters
----------
X : ndarray of shape [n_samples, n_features]
Training data.
y : Ignored
Not used, present for API consistency by convention.
Returns
-------
self : object
HashingVectorizer instance.
"""
# triggers a parameter validation
if isinstance(X, str):
raise ValueError(
"Iterable over raw text documents expected, string object received."
)
self._warn_for_unused_params()
self._validate_ngram_range()
self._get_hasher().fit(X, y=y)
return self
def transform(self, X):
"""Transform a sequence of documents to a document-term matrix.
Parameters
----------
X : iterable over raw text documents, length = n_samples
Samples. Each sample must be a text document (either bytes or
unicode strings, file name or file object depending on the
constructor argument) which will be tokenized and hashed.
Returns
-------
X : sparse matrix of shape (n_samples, n_features)
Document-term matrix.
"""
if isinstance(X, str):
raise ValueError(
"Iterable over raw text documents expected, string object received."
)
self._validate_ngram_range()
analyzer = self.build_analyzer()
X = self._get_hasher().transform(analyzer(doc) for doc in X)
if self.binary:
X.data.fill(1)
if self.norm is not None:
X = normalize(X, norm=self.norm, copy=False)
return X
def fit_transform(self, X, y=None):
"""Transform a sequence of documents to a document-term matrix.
Parameters
----------
X : iterable over raw text documents, length = n_samples
Samples. Each sample must be a text document (either bytes or
unicode strings, file name or file object depending on the
constructor argument) which will be tokenized and hashed.
y : any
Ignored. This parameter exists only for compatibility with
sklearn.pipeline.Pipeline.
Returns
-------
X : sparse matrix of shape (n_samples, n_features)
Document-term matrix.
"""
return self.fit(X, y).transform(X)
def _get_hasher(self):
return FeatureHasher(
n_features=self.n_features,
input_type="string",
dtype=self.dtype,
alternate_sign=self.alternate_sign,
)
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
tags.input_tags.string = True
tags.input_tags.two_d_array = False
return tags
def _document_frequency(X):
"""Count the number of non-zero values for each feature in sparse X."""
if sp.issparse(X) and X.format == "csr":
return np.bincount(X.indices, minlength=X.shape[1])
else:
return np.diff(X.indptr)
class CountVectorizer(_VectorizerMixin, BaseEstimator):
r"""Convert a collection of text documents to a matrix of token counts.
This implementation produces a sparse representation of the counts using
scipy.sparse.csr_matrix.
If you do not provide an a-priori dictionary and you do not use an analyzer
that does some kind of feature selection then the number of features will
be equal to the vocabulary size found by analyzing the data.
For an efficiency comparison of the different feature extractors, see
:ref:`sphx_glr_auto_examples_text_plot_hashing_vs_dict_vectorizer.py`.
Read more in the :ref:`User Guide <text_feature_extraction>`.
Parameters
----------
input : {'filename', 'file', 'content'}, default='content'
- If `'filename'`, the sequence passed as an argument to fit is
expected to be a list of filenames that need reading to fetch
the raw content to analyze.
- If `'file'`, the sequence items must have a 'read' method (file-like
object) that is called to fetch the bytes in memory.
- If `'content'`, the input is expected to be a sequence of items that
can be of type string or byte.
encoding : str, default='utf-8'
If bytes or files are given to analyze, this encoding is used to
decode.
decode_error : {'strict', 'ignore', 'replace'}, default='strict'
Instruction on what to do if a byte sequence is given to analyze that
contains characters not of the given `encoding`. By default, it is
'strict', meaning that a UnicodeDecodeError will be raised. Other
values are 'ignore' and 'replace'.
strip_accents : {'ascii', 'unicode'} or callable, default=None
Remove accents and perform other character normalization
during the preprocessing step.
'ascii' is a fast method that only works on characters that have
a direct ASCII mapping.
'unicode' is a slightly slower method that works on any characters.
None (default) means no character normalization is performed.
Both 'ascii' and 'unicode' use NFKD normalization from
:func:`unicodedata.normalize`.
lowercase : bool, default=True
Convert all characters to lowercase before tokenizing.
preprocessor : callable, default=None
Override the preprocessing (strip_accents and lowercase) stage while
preserving the tokenizing and n-grams generation steps.
Only applies if ``analyzer`` is not callable.
tokenizer : callable, default=None
Override the string tokenization step while preserving the
preprocessing and n-grams generation steps.
Only applies if ``analyzer == 'word'``.
stop_words : {'english'}, list, default=None
If 'english', a built-in stop word list for English is used.
There are several known issues with 'english' and you should
consider an alternative (see :ref:`stop_words`).
If a list, that list is assumed to contain stop words, all of which
will be removed from the resulting tokens.
Only applies if ``analyzer == 'word'``.
If None, no stop words will be used. In this case, setting `max_df`
to a higher value, such as in the range (0.7, 1.0), can automatically detect
and filter stop words based on intra corpus document frequency of terms.
token_pattern : str or None, default=r"(?u)\\b\\w\\w+\\b"
Regular expression denoting what constitutes a "token", only used
if ``analyzer == 'word'``. The default regexp select tokens of 2
or more alphanumeric characters (punctuation is completely ignored
and always treated as a token separator).
If there is a capturing group in token_pattern then the
captured group content, not the entire match, becomes the token.
At most one capturing group is permitted.
ngram_range : tuple (min_n, max_n), default=(1, 1)
The lower and upper boundary of the range of n-values for different
word n-grams or char n-grams to be extracted. All values of n such
such that min_n <= n <= max_n will be used. For example an
``ngram_range`` of ``(1, 1)`` means only unigrams, ``(1, 2)`` means
unigrams and bigrams, and ``(2, 2)`` means only bigrams.
Only applies if ``analyzer`` is not callable.
analyzer : {'word', 'char', 'char_wb'} or callable, default='word'
Whether the feature should be made of word n-gram or character
n-grams.
Option 'char_wb' creates character n-grams only from text inside
word boundaries; n-grams at the edges of words are padded with space.
If a callable is passed it is used to extract the sequence of features
out of the raw, unprocessed input.
.. versionchanged:: 0.21
Since v0.21, if ``input`` is ``filename`` or ``file``, the data is
first read from the file and then passed to the given callable
analyzer.
max_df : float in range [0.0, 1.0] or int, default=1.0
When building the vocabulary ignore terms that have a document
frequency strictly higher than the given threshold (corpus-specific
stop words).
If float, the parameter represents a proportion of documents, integer
absolute counts.
This parameter is ignored if vocabulary is not None.
min_df : float in range [0.0, 1.0] or int, default=1
When building the vocabulary ignore terms that have a document
frequency strictly lower than the given threshold. This value is also
called cut-off in the literature.
If float, the parameter represents a proportion of documents, integer
absolute counts.
This parameter is ignored if vocabulary is not None.
max_features : int, default=None
If not None, build a vocabulary that only consider the top
`max_features` ordered by term frequency across the corpus.
Otherwise, all features are used.
This parameter is ignored if vocabulary is not None.
vocabulary : Mapping or iterable, default=None
Either a Mapping (e.g., a dict) where keys are terms and values are
indices in the feature matrix, or an iterable over terms. If not
given, a vocabulary is determined from the input documents. Indices
in the mapping should not be repeated and should not have any gap
between 0 and the largest index.
binary : bool, default=False
If True, all non zero counts are set to 1. This is useful for discrete
probabilistic models that model binary events rather than integer
counts.
dtype : dtype, default=np.int64
Type of the matrix returned by fit_transform() or transform().
Attributes
----------
vocabulary_ : dict
A mapping of terms to feature indices.
fixed_vocabulary_ : bool
True if a fixed vocabulary of term to indices mapping
is provided by the user.
See Also
--------
HashingVectorizer : Convert a collection of text documents to a
matrix of token counts.
TfidfVectorizer : Convert a collection of raw documents to a matrix
of TF-IDF features.
Examples
--------
>>> from sklearn.feature_extraction.text import CountVectorizer
>>> corpus = [
... 'This is the first document.',
... 'This document is the second document.',
... 'And this is the third one.',
... 'Is this the first document?',
... ]
>>> vectorizer = CountVectorizer()
>>> X = vectorizer.fit_transform(corpus)
>>> vectorizer.get_feature_names_out()
array(['and', 'document', 'first', 'is', 'one', 'second', 'the', 'third',
'this'], ...)
>>> print(X.toarray())
[[0 1 1 1 0 0 1 0 1]
[0 2 0 1 0 1 1 0 1]
[1 0 0 1 1 0 1 1 1]
[0 1 1 1 0 0 1 0 1]]
>>> vectorizer2 = CountVectorizer(analyzer='word', ngram_range=(2, 2))
>>> X2 = vectorizer2.fit_transform(corpus)
>>> vectorizer2.get_feature_names_out()
array(['and this', 'document is', 'first document', 'is the', 'is this',
'second document', 'the first', 'the second', 'the third', 'third one',
'this document', 'this is', 'this the'], ...)
>>> print(X2.toarray())
[[0 0 1 1 0 0 1 0 0 0 0 1 0]
[0 1 0 1 0 1 0 1 0 0 1 0 0]
[1 0 0 1 0 0 0 0 1 1 0 1 0]
[0 0 1 0 1 0 1 0 0 0 0 0 1]]
"""
# raw_documents should not be in the routing mechanism. It should have been
# called X in the first place.
__metadata_request__fit = {"raw_documents": metadata_routing.UNUSED}
__metadata_request__transform = {"raw_documents": metadata_routing.UNUSED}
_parameter_constraints: dict = {
"input": [StrOptions({"filename", "file", "content"})],
"encoding": [str],
"decode_error": [StrOptions({"strict", "ignore", "replace"})],
"strip_accents": [StrOptions({"ascii", "unicode"}), None, callable],
"lowercase": ["boolean"],
"preprocessor": [callable, None],
"tokenizer": [callable, None],
"stop_words": [StrOptions({"english"}), list, None],
"token_pattern": [str, None],
"ngram_range": [tuple],
"analyzer": [StrOptions({"word", "char", "char_wb"}), callable],
"max_df": [
Interval(RealNotInt, 0, 1, closed="both"),
Interval(Integral, 1, None, closed="left"),
],
"min_df": [
Interval(RealNotInt, 0, 1, closed="both"),
Interval(Integral, 1, None, closed="left"),
],
"max_features": [Interval(Integral, 1, None, closed="left"), None],
"vocabulary": [Mapping, HasMethods("__iter__"), None],
"binary": ["boolean"],
"dtype": "no_validation", # delegate to numpy
}
def __init__(
self,
*,
input="content",
encoding="utf-8",
decode_error="strict",
strip_accents=None,
lowercase=True,
preprocessor=None,
tokenizer=None,
stop_words=None,
token_pattern=r"(?u)\b\w\w+\b",
ngram_range=(1, 1),
analyzer="word",
max_df=1.0,
min_df=1,
max_features=None,
vocabulary=None,
binary=False,
dtype=np.int64,
):
self.input = input
self.encoding = encoding
self.decode_error = decode_error
self.strip_accents = strip_accents
self.preprocessor = preprocessor
self.tokenizer = tokenizer
self.analyzer = analyzer
self.lowercase = lowercase
self.token_pattern = token_pattern
self.stop_words = stop_words
self.max_df = max_df
self.min_df = min_df
self.max_features = max_features
self.ngram_range = ngram_range
self.vocabulary = vocabulary
self.binary = binary
self.dtype = dtype
def _sort_features(self, X, vocabulary):
"""Sort features by name
Returns a reordered matrix and modifies the vocabulary in place
"""
sorted_features = sorted(vocabulary.items())
map_index = np.empty(len(sorted_features), dtype=X.indices.dtype)
for new_val, (term, old_val) in enumerate(sorted_features):
vocabulary[term] = new_val
map_index[old_val] = new_val
X.indices = map_index.take(X.indices, mode="clip")
return X
def _limit_features(self, X, vocabulary, high=None, low=None, limit=None):
"""Remove too rare or too common features.
Prune features that are non zero in more samples than high or less
documents than low, modifying the vocabulary, and restricting it to
at most the limit most frequent.
This does not prune samples with zero features.
"""
if high is None and low is None and limit is None:
return X, set()
# Calculate a mask based on document frequencies
dfs = _document_frequency(X)
mask = np.ones(len(dfs), dtype=bool)
if high is not None:
mask &= dfs <= high
if low is not None:
mask &= dfs >= low
if limit is not None and mask.sum() > limit:
tfs = np.asarray(X.sum(axis=0)).ravel()
mask_inds = (-tfs[mask]).argsort()[:limit]
new_mask = np.zeros(len(dfs), dtype=bool)
new_mask[np.where(mask)[0][mask_inds]] = True
mask = new_mask
new_indices = np.cumsum(mask) - 1 # maps old indices to new
for term, old_index in list(vocabulary.items()):
if mask[old_index]:
vocabulary[term] = new_indices[old_index]
else:
del vocabulary[term]
kept_indices = np.where(mask)[0]
if len(kept_indices) == 0:
raise ValueError(
"After pruning, no terms remain. Try a lower min_df or a higher max_df."
)
return X[:, kept_indices]
def _count_vocab(self, raw_documents, fixed_vocab):
"""Create sparse feature matrix, and vocabulary where fixed_vocab=False"""
if fixed_vocab:
vocabulary = self.vocabulary_
else:
# Add a new value when a new vocabulary item is seen
vocabulary = defaultdict()
vocabulary.default_factory = vocabulary.__len__
analyze = self.build_analyzer()
j_indices = []
indptr = []
values = _make_int_array()
indptr.append(0)
for doc in raw_documents:
feature_counter = {}
for feature in analyze(doc):
try:
feature_idx = vocabulary[feature]
if feature_idx not in feature_counter:
feature_counter[feature_idx] = 1
else:
feature_counter[feature_idx] += 1
except KeyError:
# Ignore out-of-vocabulary items for fixed_vocab=True
continue
j_indices.extend(feature_counter.keys())
values.extend(feature_counter.values())
indptr.append(len(j_indices))
if not fixed_vocab:
# disable defaultdict behaviour
vocabulary = dict(vocabulary)
if not vocabulary:
raise ValueError(
"empty vocabulary; perhaps the documents only contain stop words"
)
if indptr[-1] > np.iinfo(np.int32).max: # = 2**31 - 1
if _IS_32BIT:
raise ValueError(
(
"sparse CSR array has {} non-zero "
"elements and requires 64 bit indexing, "
"which is unsupported with 32 bit Python."
).format(indptr[-1])
)
indices_dtype = np.int64
else:
indices_dtype = np.int32
j_indices = np.asarray(j_indices, dtype=indices_dtype)
indptr = np.asarray(indptr, dtype=indices_dtype)
values = np.frombuffer(values, dtype=np.intc)
X = sp.csr_matrix(
(values, j_indices, indptr),
shape=(len(indptr) - 1, len(vocabulary)),
dtype=self.dtype,
)
X.sort_indices()
return vocabulary, X
def fit(self, raw_documents, y=None):
"""Learn a vocabulary dictionary of all tokens in the raw documents.
Parameters
----------
raw_documents : iterable
An iterable which generates either str, unicode or file objects.
y : None
This parameter is ignored.
Returns
-------
self : object
Fitted vectorizer.
"""
self.fit_transform(raw_documents)
return self
@_fit_context(prefer_skip_nested_validation=True)
def fit_transform(self, raw_documents, y=None):
"""Learn the vocabulary dictionary and return document-term matrix.
This is equivalent to fit followed by transform, but more efficiently
implemented.
Parameters
----------
raw_documents : iterable
An iterable which generates either str, unicode or file objects.
y : None
This parameter is ignored.
Returns
-------
X : array of shape (n_samples, n_features)
Document-term matrix.
"""
# We intentionally don't call the transform method to make
# fit_transform overridable without unwanted side effects in
# TfidfVectorizer.
if isinstance(raw_documents, str):
raise ValueError(
"Iterable over raw text documents expected, string object received."
)
self._validate_ngram_range()
self._warn_for_unused_params()
self._validate_vocabulary()
max_df = self.max_df
min_df = self.min_df
max_features = self.max_features
if self.fixed_vocabulary_ and self.lowercase:
for term in self.vocabulary:
if any(map(str.isupper, term)):
warnings.warn(
"Upper case characters found in"
" vocabulary while 'lowercase'"
" is True. These entries will not"
" be matched with any documents"
)
break
vocabulary, X = self._count_vocab(raw_documents, self.fixed_vocabulary_)
if self.binary:
X.data.fill(1)
if not self.fixed_vocabulary_:
n_doc = X.shape[0]
max_doc_count = max_df if isinstance(max_df, Integral) else max_df * n_doc
min_doc_count = min_df if isinstance(min_df, Integral) else min_df * n_doc
if max_doc_count < min_doc_count:
raise ValueError("max_df corresponds to < documents than min_df")
if max_features is not None:
X = self._sort_features(X, vocabulary)
X = self._limit_features(
X, vocabulary, max_doc_count, min_doc_count, max_features
)
if max_features is None:
X = self._sort_features(X, vocabulary)
self.vocabulary_ = vocabulary
return X
def transform(self, raw_documents):
"""Transform documents to document-term matrix.
Extract token counts out of raw text documents using the vocabulary
fitted with fit or the one provided to the constructor.
Parameters
----------
raw_documents : iterable
An iterable which generates either str, unicode or file objects.
Returns
-------
X : sparse matrix of shape (n_samples, n_features)
Document-term matrix.
"""
if isinstance(raw_documents, str):
raise ValueError(
"Iterable over raw text documents expected, string object received."
)
self._check_vocabulary()
# use the same matrix-building strategy as fit_transform
_, X = self._count_vocab(raw_documents, fixed_vocab=True)
if self.binary:
X.data.fill(1)
return X
def inverse_transform(self, X):
"""Return terms per document with nonzero entries in X.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Document-term matrix.
Returns
-------
X_inv : list of arrays of shape (n_samples,)
List of arrays of terms.
"""
self._check_vocabulary()
# We need CSR format for fast row manipulations.
X = check_array(X, accept_sparse="csr")
n_samples = X.shape[0]
terms = np.array(list(self.vocabulary_.keys()))
indices = np.array(list(self.vocabulary_.values()))
inverse_vocabulary = terms[np.argsort(indices)]
if sp.issparse(X):
return [
inverse_vocabulary[X[i, :].nonzero()[1]].ravel()
for i in range(n_samples)
]
else:
return [
inverse_vocabulary[np.flatnonzero(X[i, :])].ravel()
for i in range(n_samples)
]
def get_feature_names_out(self, input_features=None):
"""Get output feature names for transformation.
Parameters
----------
input_features : array-like of str or None, default=None
Not used, present here for API consistency by convention.
Returns
-------
feature_names_out : ndarray of str objects
Transformed feature names.
"""
self._check_vocabulary()
return np.asarray(
[t for t, i in sorted(self.vocabulary_.items(), key=itemgetter(1))],
dtype=object,
)
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
tags.input_tags.string = True
tags.input_tags.two_d_array = False
return tags
def _make_int_array():
"""Construct an array.array of a type suitable for scipy.sparse indices."""
return array.array(str("i"))
class TfidfTransformer(
OneToOneFeatureMixin, TransformerMixin, BaseEstimator, auto_wrap_output_keys=None
):
"""Transform a count matrix to a normalized tf or tf-idf representation.
Tf means term-frequency while tf-idf means term-frequency times inverse
document-frequency. This is a common term weighting scheme in information
retrieval, that has also found good use in document classification.
The goal of using tf-idf instead of the raw frequencies of occurrence of a
token in a given document is to scale down the impact of tokens that occur
very frequently in a given corpus and that are hence empirically less
informative than features that occur in a small fraction of the training
corpus.
The formula that is used to compute the tf-idf for a term t of a document d
in a document set is tf-idf(t, d) = tf(t, d) * idf(t), and the idf is
computed as idf(t) = log [ n / df(t) ] + 1 (if ``smooth_idf=False``), where
n is the total number of documents in the document set and df(t) is the
document frequency of t; the document frequency is the number of documents
in the document set that contain the term t. The effect of adding "1" to
the idf in the equation above is that terms with zero idf, i.e., terms
that occur in all documents in a training set, will not be entirely
ignored.
(Note that the idf formula above differs from the standard textbook
notation that defines the idf as
idf(t) = log [ n / (df(t) + 1) ]).
If ``smooth_idf=True`` (the default), the constant "1" is added to the
numerator and denominator of the idf as if an extra document was seen
containing every term in the collection exactly once, which prevents
zero divisions: idf(t) = log [ (1 + n) / (1 + df(t)) ] + 1.
Furthermore, the formulas used to compute tf and idf depend
on parameter settings that correspond to the SMART notation used in IR
as follows:
Tf is "n" (natural) by default, "l" (logarithmic) when
``sublinear_tf=True``.
Idf is "t" when use_idf is given, "n" (none) otherwise.
Normalization is "c" (cosine) when ``norm='l2'``, "n" (none)
when ``norm=None``.
Read more in the :ref:`User Guide <text_feature_extraction>`.
Parameters
----------
norm : {'l1', 'l2'} or None, default='l2'
Each output row will have unit norm, either:
- 'l2': Sum of squares of vector elements is 1. The cosine
similarity between two vectors is their dot product when l2 norm has
been applied.
- 'l1': Sum of absolute values of vector elements is 1.
See :func:`~sklearn.preprocessing.normalize`.
- None: No normalization.
use_idf : bool, default=True
Enable inverse-document-frequency reweighting. If False, idf(t) = 1.
smooth_idf : bool, default=True
Smooth idf weights by adding one to document frequencies, as if an
extra document was seen containing every term in the collection
exactly once. Prevents zero divisions.
sublinear_tf : bool, default=False
Apply sublinear tf scaling, i.e. replace tf with 1 + log(tf).
Attributes
----------
idf_ : array of shape (n_features)
The inverse document frequency (IDF) vector; only defined
if ``use_idf`` is True.
.. versionadded:: 0.20
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 1.0
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
See Also
--------
CountVectorizer : Transforms text into a sparse matrix of n-gram counts.
TfidfVectorizer : Convert a collection of raw documents to a matrix of
TF-IDF features.
HashingVectorizer : Convert a collection of text documents to a matrix
of token occurrences.
References
----------
.. [Yates2011] R. Baeza-Yates and B. Ribeiro-Neto (2011). Modern
Information Retrieval. Addison Wesley, pp. 68-74.
.. [MRS2008] C.D. Manning, P. Raghavan and H. Schütze (2008).
Introduction to Information Retrieval. Cambridge University
Press, pp. 118-120.
Examples
--------
>>> from sklearn.feature_extraction.text import TfidfTransformer
>>> from sklearn.feature_extraction.text import CountVectorizer
>>> from sklearn.pipeline import Pipeline
>>> corpus = ['this is the first document',
... 'this document is the second document',
... 'and this is the third one',
... 'is this the first document']
>>> vocabulary = ['this', 'document', 'first', 'is', 'second', 'the',
... 'and', 'one']
>>> pipe = Pipeline([('count', CountVectorizer(vocabulary=vocabulary)),
... ('tfid', TfidfTransformer())]).fit(corpus)
>>> pipe['count'].transform(corpus).toarray()
array([[1, 1, 1, 1, 0, 1, 0, 0],
[1, 2, 0, 1, 1, 1, 0, 0],
[1, 0, 0, 1, 0, 1, 1, 1],
[1, 1, 1, 1, 0, 1, 0, 0]])
>>> pipe['tfid'].idf_
array([1. , 1.22314355, 1.51082562, 1. , 1.91629073,
1. , 1.91629073, 1.91629073])
>>> pipe.transform(corpus).shape
(4, 8)
"""
_parameter_constraints: dict = {
"norm": [StrOptions({"l1", "l2"}), None],
"use_idf": ["boolean"],
"smooth_idf": ["boolean"],
"sublinear_tf": ["boolean"],
}
def __init__(self, *, norm="l2", use_idf=True, smooth_idf=True, sublinear_tf=False):
self.norm = norm
self.use_idf = use_idf
self.smooth_idf = smooth_idf
self.sublinear_tf = sublinear_tf
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y=None):
"""Learn the idf vector (global term weights).
Parameters
----------
X : sparse matrix of shape (n_samples, n_features)
A matrix of term/token counts.
y : None
This parameter is not needed to compute tf-idf.
Returns
-------
self : object
Fitted transformer.
"""
# large sparse data is not supported for 32bit platforms because
# _document_frequency uses np.bincount which works on arrays of
# dtype NPY_INTP which is int32 for 32bit platforms. See #20923
X = validate_data(
self, X, accept_sparse=("csr", "csc"), accept_large_sparse=not _IS_32BIT
)
if not sp.issparse(X):
X = sp.csr_matrix(X)
dtype = X.dtype if X.dtype in (np.float64, np.float32) else np.float64
if self.use_idf:
n_samples, _ = X.shape
df = _document_frequency(X)
df = df.astype(dtype, copy=False)
# perform idf smoothing if required
df += float(self.smooth_idf)
n_samples += int(self.smooth_idf)
# log+1 instead of log makes sure terms with zero idf don't get
# suppressed entirely.
# Force the dtype of `idf_` to be the same as `df`. In NumPy < 2, the dtype
# was depending on the value of `n_samples`.
self.idf_ = np.full_like(df, fill_value=n_samples, dtype=dtype)
self.idf_ /= df
# `np.log` preserves the dtype of `df` and thus `dtype`.
np.log(self.idf_, out=self.idf_)
self.idf_ += 1.0
return self
def transform(self, X, copy=True):
"""Transform a count matrix to a tf or tf-idf representation.
Parameters
----------
X : sparse matrix of (n_samples, n_features)
A matrix of term/token counts.
copy : bool, default=True
Whether to copy X and operate on the copy or perform in-place
operations. `copy=False` will only be effective with CSR sparse matrix.
Returns
-------
vectors : sparse matrix of shape (n_samples, n_features)
Tf-idf-weighted document-term matrix.
"""
check_is_fitted(self)
X = validate_data(
self,
X,
accept_sparse="csr",
dtype=[np.float64, np.float32],
copy=copy,
reset=False,
)
if not sp.issparse(X):
X = sp.csr_matrix(X, dtype=X.dtype)
if self.sublinear_tf:
np.log(X.data, X.data)
X.data += 1.0
if hasattr(self, "idf_"):
# the columns of X (CSR matrix) can be accessed with `X.indices `and
# multiplied with the corresponding `idf` value
X.data *= self.idf_[X.indices]
if self.norm is not None:
X = normalize(X, norm=self.norm, copy=False)
return X
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
tags.input_tags.sparse = True
# FIXME: np.float16 could be preserved if _inplace_csr_row_normalize_l2
# accepted it.
tags.transformer_tags.preserves_dtype = ["float64", "float32"]
return tags
class TfidfVectorizer(CountVectorizer):
r"""Convert a collection of raw documents to a matrix of TF-IDF features.
Equivalent to :class:`CountVectorizer` followed by
:class:`TfidfTransformer`.
For an example of usage, see
:ref:`sphx_glr_auto_examples_text_plot_document_classification_20newsgroups.py`.
For an efficiency comparison of the different feature extractors, see
:ref:`sphx_glr_auto_examples_text_plot_hashing_vs_dict_vectorizer.py`.
For an example of document clustering and comparison with
:class:`~sklearn.feature_extraction.text.HashingVectorizer`, see
:ref:`sphx_glr_auto_examples_text_plot_document_clustering.py`.
Read more in the :ref:`User Guide <text_feature_extraction>`.
Parameters
----------
input : {'filename', 'file', 'content'}, default='content'
- If `'filename'`, the sequence passed as an argument to fit is
expected to be a list of filenames that need reading to fetch
the raw content to analyze.
- If `'file'`, the sequence items must have a 'read' method (file-like
object) that is called to fetch the bytes in memory.
- If `'content'`, the input is expected to be a sequence of items that
can be of type string or byte.
encoding : str, default='utf-8'
If bytes or files are given to analyze, this encoding is used to
decode.
decode_error : {'strict', 'ignore', 'replace'}, default='strict'
Instruction on what to do if a byte sequence is given to analyze that
contains characters not of the given `encoding`. By default, it is
'strict', meaning that a UnicodeDecodeError will be raised. Other
values are 'ignore' and 'replace'.
strip_accents : {'ascii', 'unicode'} or callable, default=None
Remove accents and perform other character normalization
during the preprocessing step.
'ascii' is a fast method that only works on characters that have
a direct ASCII mapping.
'unicode' is a slightly slower method that works on any characters.
None (default) means no character normalization is performed.
Both 'ascii' and 'unicode' use NFKD normalization from
:func:`unicodedata.normalize`.
lowercase : bool, default=True
Convert all characters to lowercase before tokenizing.
preprocessor : callable, default=None
Override the preprocessing (string transformation) stage while
preserving the tokenizing and n-grams generation steps.
Only applies if ``analyzer`` is not callable.
tokenizer : callable, default=None
Override the string tokenization step while preserving the
preprocessing and n-grams generation steps.
Only applies if ``analyzer == 'word'``.
analyzer : {'word', 'char', 'char_wb'} or callable, default='word'
Whether the feature should be made of word or character n-grams.
Option 'char_wb' creates character n-grams only from text inside
word boundaries; n-grams at the edges of words are padded with space.
If a callable is passed it is used to extract the sequence of features
out of the raw, unprocessed input.
.. versionchanged:: 0.21
Since v0.21, if ``input`` is ``'filename'`` or ``'file'``, the data
is first read from the file and then passed to the given callable
analyzer.
stop_words : {'english'}, list, default=None
If a string, it is passed to _check_stop_list and the appropriate stop
list is returned. 'english' is currently the only supported string
value.
There are several known issues with 'english' and you should
consider an alternative (see :ref:`stop_words`).
If a list, that list is assumed to contain stop words, all of which
will be removed from the resulting tokens.
Only applies if ``analyzer == 'word'``.
If None, no stop words will be used. In this case, setting `max_df`
to a higher value, such as in the range (0.7, 1.0), can automatically detect
and filter stop words based on intra corpus document frequency of terms.
token_pattern : str, default=r"(?u)\\b\\w\\w+\\b"
Regular expression denoting what constitutes a "token", only used
if ``analyzer == 'word'``. The default regexp selects tokens of 2
or more alphanumeric characters (punctuation is completely ignored
and always treated as a token separator).
If there is a capturing group in token_pattern then the
captured group content, not the entire match, becomes the token.
At most one capturing group is permitted.
ngram_range : tuple (min_n, max_n), default=(1, 1)
The lower and upper boundary of the range of n-values for different
n-grams to be extracted. All values of n such that min_n <= n <= max_n
will be used. For example an ``ngram_range`` of ``(1, 1)`` means only
unigrams, ``(1, 2)`` means unigrams and bigrams, and ``(2, 2)`` means
only bigrams.
Only applies if ``analyzer`` is not callable.
max_df : float or int, default=1.0
When building the vocabulary ignore terms that have a document
frequency strictly higher than the given threshold (corpus-specific
stop words).
If float in range [0.0, 1.0], the parameter represents a proportion of
documents, integer absolute counts.
This parameter is ignored if vocabulary is not None.
min_df : float or int, default=1
When building the vocabulary ignore terms that have a document
frequency strictly lower than the given threshold. This value is also
called cut-off in the literature.
If float in range of [0.0, 1.0], the parameter represents a proportion
of documents, integer absolute counts.
This parameter is ignored if vocabulary is not None.
max_features : int, default=None
If not None, build a vocabulary that only consider the top
`max_features` ordered by term frequency across the corpus.
Otherwise, all features are used.
This parameter is ignored if vocabulary is not None.
vocabulary : Mapping or iterable, default=None
Either a Mapping (e.g., a dict) where keys are terms and values are
indices in the feature matrix, or an iterable over terms. If not
given, a vocabulary is determined from the input documents.
binary : bool, default=False
If True, all non-zero term counts are set to 1. This does not mean
outputs will have only 0/1 values, only that the tf term in tf-idf
is binary. (Set `binary` to True, `use_idf` to False and
`norm` to None to get 0/1 outputs).
dtype : dtype, default=float64
Type of the matrix returned by fit_transform() or transform().
norm : {'l1', 'l2'} or None, default='l2'
Each output row will have unit norm, either:
- 'l2': Sum of squares of vector elements is 1. The cosine
similarity between two vectors is their dot product when l2 norm has
been applied.
- 'l1': Sum of absolute values of vector elements is 1.
See :func:`~sklearn.preprocessing.normalize`.
- None: No normalization.
use_idf : bool, default=True
Enable inverse-document-frequency reweighting. If False, idf(t) = 1.
smooth_idf : bool, default=True
Smooth idf weights by adding one to document frequencies, as if an
extra document was seen containing every term in the collection
exactly once. Prevents zero divisions.
sublinear_tf : bool, default=False
Apply sublinear tf scaling, i.e. replace tf with 1 + log(tf).
Attributes
----------
vocabulary_ : dict
A mapping of terms to feature indices.
fixed_vocabulary_ : bool
True if a fixed vocabulary of term to indices mapping
is provided by the user.
idf_ : array of shape (n_features,)
The inverse document frequency (IDF) vector; only defined
if ``use_idf`` is True.
See Also
--------
CountVectorizer : Transforms text into a sparse matrix of n-gram counts.
TfidfTransformer : Performs the TF-IDF transformation from a provided
matrix of counts.
Examples
--------
>>> from sklearn.feature_extraction.text import TfidfVectorizer
>>> corpus = [
... 'This is the first document.',
... 'This document is the second document.',
... 'And this is the third one.',
... 'Is this the first document?',
... ]
>>> vectorizer = TfidfVectorizer()
>>> X = vectorizer.fit_transform(corpus)
>>> vectorizer.get_feature_names_out()
array(['and', 'document', 'first', 'is', 'one', 'second', 'the', 'third',
'this'], ...)
>>> print(X.shape)
(4, 9)
"""
_parameter_constraints: dict = {**CountVectorizer._parameter_constraints}
_parameter_constraints.update(
{
"norm": [StrOptions({"l1", "l2"}), None],
"use_idf": ["boolean"],
"smooth_idf": ["boolean"],
"sublinear_tf": ["boolean"],
}
)
def __init__(
self,
*,
input="content",
encoding="utf-8",
decode_error="strict",
strip_accents=None,
lowercase=True,
preprocessor=None,
tokenizer=None,
analyzer="word",
stop_words=None,
token_pattern=r"(?u)\b\w\w+\b",
ngram_range=(1, 1),
max_df=1.0,
min_df=1,
max_features=None,
vocabulary=None,
binary=False,
dtype=np.float64,
norm="l2",
use_idf=True,
smooth_idf=True,
sublinear_tf=False,
):
super().__init__(
input=input,
encoding=encoding,
decode_error=decode_error,
strip_accents=strip_accents,
lowercase=lowercase,
preprocessor=preprocessor,
tokenizer=tokenizer,
analyzer=analyzer,
stop_words=stop_words,
token_pattern=token_pattern,
ngram_range=ngram_range,
max_df=max_df,
min_df=min_df,
max_features=max_features,
vocabulary=vocabulary,
binary=binary,
dtype=dtype,
)
self.norm = norm
self.use_idf = use_idf
self.smooth_idf = smooth_idf
self.sublinear_tf = sublinear_tf
# Broadcast the TF-IDF parameters to the underlying transformer instance
# for easy grid search and repr
@property
def idf_(self):
"""Inverse document frequency vector, only defined if `use_idf=True`.
Returns
-------
ndarray of shape (n_features,)
"""
if not hasattr(self, "_tfidf"):
raise NotFittedError(
f"{self.__class__.__name__} is not fitted yet. Call 'fit' with "
"appropriate arguments before using this attribute."
)
return self._tfidf.idf_
@idf_.setter
def idf_(self, value):
if not self.use_idf:
raise ValueError("`idf_` cannot be set when `user_idf=False`.")
if not hasattr(self, "_tfidf"):
# We should support transferring `idf_` from another `TfidfTransformer`
# and therefore, we need to create the transformer instance it does not
# exist yet.
self._tfidf = TfidfTransformer(
norm=self.norm,
use_idf=self.use_idf,
smooth_idf=self.smooth_idf,
sublinear_tf=self.sublinear_tf,
)
self._validate_vocabulary()
if hasattr(self, "vocabulary_"):
if len(self.vocabulary_) != len(value):
raise ValueError(
"idf length = %d must be equal to vocabulary size = %d"
% (len(value), len(self.vocabulary))
)
self._tfidf.idf_ = value
def _check_params(self):
if self.dtype not in FLOAT_DTYPES:
warnings.warn(
"Only {} 'dtype' should be used. {} 'dtype' will "
"be converted to np.float64.".format(FLOAT_DTYPES, self.dtype),
UserWarning,
)
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, raw_documents, y=None):
"""Learn vocabulary and idf from training set.
Parameters
----------
raw_documents : iterable
An iterable which generates either str, unicode or file objects.
y : None
This parameter is not needed to compute tfidf.
Returns
-------
self : object
Fitted vectorizer.
"""
self._check_params()
self._warn_for_unused_params()
self._tfidf = TfidfTransformer(
norm=self.norm,
use_idf=self.use_idf,
smooth_idf=self.smooth_idf,
sublinear_tf=self.sublinear_tf,
)
X = super().fit_transform(raw_documents)
self._tfidf.fit(X)
return self
def fit_transform(self, raw_documents, y=None):
"""Learn vocabulary and idf, return document-term matrix.
This is equivalent to fit followed by transform, but more efficiently
implemented.
Parameters
----------
raw_documents : iterable
An iterable which generates either str, unicode or file objects.
y : None
This parameter is ignored.
Returns
-------
X : sparse matrix of (n_samples, n_features)
Tf-idf-weighted document-term matrix.
"""
self._check_params()
self._tfidf = TfidfTransformer(
norm=self.norm,
use_idf=self.use_idf,
smooth_idf=self.smooth_idf,
sublinear_tf=self.sublinear_tf,
)
X = super().fit_transform(raw_documents)
self._tfidf.fit(X)
# X is already a transformed view of raw_documents so
# we set copy to False
return self._tfidf.transform(X, copy=False)
def transform(self, raw_documents):
"""Transform documents to document-term matrix.
Uses the vocabulary and document frequencies (df) learned by fit (or
fit_transform).
Parameters
----------
raw_documents : iterable
An iterable which generates either str, unicode or file objects.
Returns
-------
X : sparse matrix of (n_samples, n_features)
Tf-idf-weighted document-term matrix.
"""
check_is_fitted(self, msg="The TF-IDF vectorizer is not fitted")
X = super().transform(raw_documents)
return self._tfidf.transform(X, copy=False)
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
tags.input_tags.string = True
tags.input_tags.two_d_array = False
tags._skip_test = True
return tags
|