File size: 81,581 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 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 |
"""K-means clustering."""
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import warnings
from abc import ABC, abstractmethod
from numbers import Integral, Real
import numpy as np
import scipy.sparse as sp
from ..base import (
BaseEstimator,
ClassNamePrefixFeaturesOutMixin,
ClusterMixin,
TransformerMixin,
_fit_context,
)
from ..exceptions import ConvergenceWarning
from ..metrics.pairwise import _euclidean_distances, euclidean_distances
from ..utils import check_array, check_random_state
from ..utils._openmp_helpers import _openmp_effective_n_threads
from ..utils._param_validation import Interval, StrOptions, validate_params
from ..utils.extmath import row_norms, stable_cumsum
from ..utils.parallel import (
_get_threadpool_controller,
_threadpool_controller_decorator,
)
from ..utils.sparsefuncs import mean_variance_axis
from ..utils.sparsefuncs_fast import assign_rows_csr
from ..utils.validation import (
_check_sample_weight,
_is_arraylike_not_scalar,
check_is_fitted,
validate_data,
)
from ._k_means_common import (
CHUNK_SIZE,
_inertia_dense,
_inertia_sparse,
_is_same_clustering,
)
from ._k_means_elkan import (
elkan_iter_chunked_dense,
elkan_iter_chunked_sparse,
init_bounds_dense,
init_bounds_sparse,
)
from ._k_means_lloyd import lloyd_iter_chunked_dense, lloyd_iter_chunked_sparse
from ._k_means_minibatch import _minibatch_update_dense, _minibatch_update_sparse
###############################################################################
# Initialization heuristic
@validate_params(
{
"X": ["array-like", "sparse matrix"],
"n_clusters": [Interval(Integral, 1, None, closed="left")],
"sample_weight": ["array-like", None],
"x_squared_norms": ["array-like", None],
"random_state": ["random_state"],
"n_local_trials": [Interval(Integral, 1, None, closed="left"), None],
},
prefer_skip_nested_validation=True,
)
def kmeans_plusplus(
X,
n_clusters,
*,
sample_weight=None,
x_squared_norms=None,
random_state=None,
n_local_trials=None,
):
"""Init n_clusters seeds according to k-means++.
.. versionadded:: 0.24
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The data to pick seeds from.
n_clusters : int
The number of centroids to initialize.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in `X`. If `None`, all observations
are assigned equal weight. `sample_weight` is ignored if `init`
is a callable or a user provided array.
.. versionadded:: 1.3
x_squared_norms : array-like of shape (n_samples,), default=None
Squared Euclidean norm of each data point.
random_state : int or RandomState instance, default=None
Determines random number generation for centroid initialization. Pass
an int for reproducible output across multiple function calls.
See :term:`Glossary <random_state>`.
n_local_trials : int, default=None
The number of seeding trials for each center (except the first),
of which the one reducing inertia the most is greedily chosen.
Set to None to make the number of trials depend logarithmically
on the number of seeds (2+log(k)) which is the recommended setting.
Setting to 1 disables the greedy cluster selection and recovers the
vanilla k-means++ algorithm which was empirically shown to work less
well than its greedy variant.
Returns
-------
centers : ndarray of shape (n_clusters, n_features)
The initial centers for k-means.
indices : ndarray of shape (n_clusters,)
The index location of the chosen centers in the data array X. For a
given index and center, X[index] = center.
Notes
-----
Selects initial cluster centers for k-mean clustering in a smart way
to speed up convergence. see: Arthur, D. and Vassilvitskii, S.
"k-means++: the advantages of careful seeding". ACM-SIAM symposium
on Discrete algorithms. 2007
Examples
--------
>>> from sklearn.cluster import kmeans_plusplus
>>> import numpy as np
>>> X = np.array([[1, 2], [1, 4], [1, 0],
... [10, 2], [10, 4], [10, 0]])
>>> centers, indices = kmeans_plusplus(X, n_clusters=2, random_state=0)
>>> centers
array([[10, 2],
[ 1, 0]])
>>> indices
array([3, 2])
"""
# Check data
check_array(X, accept_sparse="csr", dtype=[np.float64, np.float32])
sample_weight = _check_sample_weight(sample_weight, X, dtype=X.dtype)
if X.shape[0] < n_clusters:
raise ValueError(
f"n_samples={X.shape[0]} should be >= n_clusters={n_clusters}."
)
# Check parameters
if x_squared_norms is None:
x_squared_norms = row_norms(X, squared=True)
else:
x_squared_norms = check_array(x_squared_norms, dtype=X.dtype, ensure_2d=False)
if x_squared_norms.shape[0] != X.shape[0]:
raise ValueError(
f"The length of x_squared_norms {x_squared_norms.shape[0]} should "
f"be equal to the length of n_samples {X.shape[0]}."
)
random_state = check_random_state(random_state)
# Call private k-means++
centers, indices = _kmeans_plusplus(
X, n_clusters, x_squared_norms, sample_weight, random_state, n_local_trials
)
return centers, indices
def _kmeans_plusplus(
X, n_clusters, x_squared_norms, sample_weight, random_state, n_local_trials=None
):
"""Computational component for initialization of n_clusters by
k-means++. Prior validation of data is assumed.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The data to pick seeds for.
n_clusters : int
The number of seeds to choose.
sample_weight : ndarray of shape (n_samples,)
The weights for each observation in `X`.
x_squared_norms : ndarray of shape (n_samples,)
Squared Euclidean norm of each data point.
random_state : RandomState instance
The generator used to initialize the centers.
See :term:`Glossary <random_state>`.
n_local_trials : int, default=None
The number of seeding trials for each center (except the first),
of which the one reducing inertia the most is greedily chosen.
Set to None to make the number of trials depend logarithmically
on the number of seeds (2+log(k)); this is the default.
Returns
-------
centers : ndarray of shape (n_clusters, n_features)
The initial centers for k-means.
indices : ndarray of shape (n_clusters,)
The index location of the chosen centers in the data array X. For a
given index and center, X[index] = center.
"""
n_samples, n_features = X.shape
centers = np.empty((n_clusters, n_features), dtype=X.dtype)
# Set the number of local seeding trials if none is given
if n_local_trials is None:
# This is what Arthur/Vassilvitskii tried, but did not report
# specific results for other than mentioning in the conclusion
# that it helped.
n_local_trials = 2 + int(np.log(n_clusters))
# Pick first center randomly and track index of point
center_id = random_state.choice(n_samples, p=sample_weight / sample_weight.sum())
indices = np.full(n_clusters, -1, dtype=int)
if sp.issparse(X):
centers[0] = X[[center_id]].toarray()
else:
centers[0] = X[center_id]
indices[0] = center_id
# Initialize list of closest distances and calculate current potential
closest_dist_sq = _euclidean_distances(
centers[0, np.newaxis], X, Y_norm_squared=x_squared_norms, squared=True
)
current_pot = closest_dist_sq @ sample_weight
# Pick the remaining n_clusters-1 points
for c in range(1, n_clusters):
# Choose center candidates by sampling with probability proportional
# to the squared distance to the closest existing center
rand_vals = random_state.uniform(size=n_local_trials) * current_pot
candidate_ids = np.searchsorted(
stable_cumsum(sample_weight * closest_dist_sq), rand_vals
)
# XXX: numerical imprecision can result in a candidate_id out of range
np.clip(candidate_ids, None, closest_dist_sq.size - 1, out=candidate_ids)
# Compute distances to center candidates
distance_to_candidates = _euclidean_distances(
X[candidate_ids], X, Y_norm_squared=x_squared_norms, squared=True
)
# update closest distances squared and potential for each candidate
np.minimum(closest_dist_sq, distance_to_candidates, out=distance_to_candidates)
candidates_pot = distance_to_candidates @ sample_weight.reshape(-1, 1)
# Decide which candidate is the best
best_candidate = np.argmin(candidates_pot)
current_pot = candidates_pot[best_candidate]
closest_dist_sq = distance_to_candidates[best_candidate]
best_candidate = candidate_ids[best_candidate]
# Permanently add best center candidate found in local tries
if sp.issparse(X):
centers[c] = X[[best_candidate]].toarray()
else:
centers[c] = X[best_candidate]
indices[c] = best_candidate
return centers, indices
###############################################################################
# K-means batch estimation by EM (expectation maximization)
def _tolerance(X, tol):
"""Return a tolerance which is dependent on the dataset."""
if tol == 0:
return 0
if sp.issparse(X):
variances = mean_variance_axis(X, axis=0)[1]
else:
variances = np.var(X, axis=0)
return np.mean(variances) * tol
@validate_params(
{
"X": ["array-like", "sparse matrix"],
"sample_weight": ["array-like", None],
"return_n_iter": [bool],
},
prefer_skip_nested_validation=False,
)
def k_means(
X,
n_clusters,
*,
sample_weight=None,
init="k-means++",
n_init="auto",
max_iter=300,
verbose=False,
tol=1e-4,
random_state=None,
copy_x=True,
algorithm="lloyd",
return_n_iter=False,
):
"""Perform K-means clustering algorithm.
Read more in the :ref:`User Guide <k_means>`.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The observations to cluster. It must be noted that the data
will be converted to C ordering, which will cause a memory copy
if the given data is not C-contiguous.
n_clusters : int
The number of clusters to form as well as the number of
centroids to generate.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in `X`. If `None`, all observations
are assigned equal weight. `sample_weight` is not used during
initialization if `init` is a callable or a user provided array.
init : {'k-means++', 'random'}, callable or array-like of shape \
(n_clusters, n_features), default='k-means++'
Method for initialization:
- `'k-means++'` : selects initial cluster centers for k-mean
clustering in a smart way to speed up convergence. See section
Notes in k_init for more details.
- `'random'`: choose `n_clusters` observations (rows) at random from data
for the initial centroids.
- If an array is passed, it should be of shape `(n_clusters, n_features)`
and gives the initial centers.
- If a callable is passed, it should take arguments `X`, `n_clusters` and a
random state and return an initialization.
n_init : 'auto' or int, default="auto"
Number of time the k-means algorithm will be run with different
centroid seeds. The final results will be the best output of
n_init consecutive runs in terms of inertia.
When `n_init='auto'`, the number of runs depends on the value of init:
10 if using `init='random'` or `init` is a callable;
1 if using `init='k-means++'` or `init` is an array-like.
.. versionadded:: 1.2
Added 'auto' option for `n_init`.
.. versionchanged:: 1.4
Default value for `n_init` changed to `'auto'`.
max_iter : int, default=300
Maximum number of iterations of the k-means algorithm to run.
verbose : bool, default=False
Verbosity mode.
tol : float, default=1e-4
Relative tolerance with regards to Frobenius norm of the difference
in the cluster centers of two consecutive iterations to declare
convergence.
random_state : int, RandomState instance or None, default=None
Determines random number generation for centroid initialization. Use
an int to make the randomness deterministic.
See :term:`Glossary <random_state>`.
copy_x : bool, default=True
When pre-computing distances it is more numerically accurate to center
the data first. If `copy_x` is True (default), then the original data is
not modified. If False, the original data is modified, and put back
before the function returns, but small numerical differences may be
introduced by subtracting and then adding the data mean. Note that if
the original data is not C-contiguous, a copy will be made even if
`copy_x` is False. If the original data is sparse, but not in CSR format,
a copy will be made even if `copy_x` is False.
algorithm : {"lloyd", "elkan"}, default="lloyd"
K-means algorithm to use. The classical EM-style algorithm is `"lloyd"`.
The `"elkan"` variation can be more efficient on some datasets with
well-defined clusters, by using the triangle inequality. However it's
more memory intensive due to the allocation of an extra array of shape
`(n_samples, n_clusters)`.
.. versionchanged:: 0.18
Added Elkan algorithm
.. versionchanged:: 1.1
Renamed "full" to "lloyd", and deprecated "auto" and "full".
Changed "auto" to use "lloyd" instead of "elkan".
return_n_iter : bool, default=False
Whether or not to return the number of iterations.
Returns
-------
centroid : ndarray of shape (n_clusters, n_features)
Centroids found at the last iteration of k-means.
label : ndarray of shape (n_samples,)
The `label[i]` is the code or index of the centroid the
i'th observation is closest to.
inertia : float
The final value of the inertia criterion (sum of squared distances to
the closest centroid for all observations in the training set).
best_n_iter : int
Number of iterations corresponding to the best results.
Returned only if `return_n_iter` is set to True.
Examples
--------
>>> import numpy as np
>>> from sklearn.cluster import k_means
>>> X = np.array([[1, 2], [1, 4], [1, 0],
... [10, 2], [10, 4], [10, 0]])
>>> centroid, label, inertia = k_means(
... X, n_clusters=2, n_init="auto", random_state=0
... )
>>> centroid
array([[10., 2.],
[ 1., 2.]])
>>> label
array([1, 1, 1, 0, 0, 0], dtype=int32)
>>> inertia
16.0
"""
est = KMeans(
n_clusters=n_clusters,
init=init,
n_init=n_init,
max_iter=max_iter,
verbose=verbose,
tol=tol,
random_state=random_state,
copy_x=copy_x,
algorithm=algorithm,
).fit(X, sample_weight=sample_weight)
if return_n_iter:
return est.cluster_centers_, est.labels_, est.inertia_, est.n_iter_
else:
return est.cluster_centers_, est.labels_, est.inertia_
def _kmeans_single_elkan(
X,
sample_weight,
centers_init,
max_iter=300,
verbose=False,
tol=1e-4,
n_threads=1,
):
"""A single run of k-means elkan, assumes preparation completed prior.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The observations to cluster. If sparse matrix, must be in CSR format.
sample_weight : array-like of shape (n_samples,)
The weights for each observation in X.
centers_init : ndarray of shape (n_clusters, n_features)
The initial centers.
max_iter : int, default=300
Maximum number of iterations of the k-means algorithm to run.
verbose : bool, default=False
Verbosity mode.
tol : float, default=1e-4
Relative tolerance with regards to Frobenius norm of the difference
in the cluster centers of two consecutive iterations to declare
convergence.
It's not advised to set `tol=0` since convergence might never be
declared due to rounding errors. Use a very small number instead.
n_threads : int, default=1
The number of OpenMP threads to use for the computation. Parallelism is
sample-wise on the main cython loop which assigns each sample to its
closest center.
Returns
-------
centroid : ndarray of shape (n_clusters, n_features)
Centroids found at the last iteration of k-means.
label : ndarray of shape (n_samples,)
label[i] is the code or index of the centroid the
i'th observation is closest to.
inertia : float
The final value of the inertia criterion (sum of squared distances to
the closest centroid for all observations in the training set).
n_iter : int
Number of iterations run.
"""
n_samples = X.shape[0]
n_clusters = centers_init.shape[0]
# Buffers to avoid new allocations at each iteration.
centers = centers_init
centers_new = np.zeros_like(centers)
weight_in_clusters = np.zeros(n_clusters, dtype=X.dtype)
labels = np.full(n_samples, -1, dtype=np.int32)
labels_old = labels.copy()
center_half_distances = euclidean_distances(centers) / 2
distance_next_center = np.partition(
np.asarray(center_half_distances), kth=1, axis=0
)[1]
upper_bounds = np.zeros(n_samples, dtype=X.dtype)
lower_bounds = np.zeros((n_samples, n_clusters), dtype=X.dtype)
center_shift = np.zeros(n_clusters, dtype=X.dtype)
if sp.issparse(X):
init_bounds = init_bounds_sparse
elkan_iter = elkan_iter_chunked_sparse
_inertia = _inertia_sparse
else:
init_bounds = init_bounds_dense
elkan_iter = elkan_iter_chunked_dense
_inertia = _inertia_dense
init_bounds(
X,
centers,
center_half_distances,
labels,
upper_bounds,
lower_bounds,
n_threads=n_threads,
)
strict_convergence = False
for i in range(max_iter):
elkan_iter(
X,
sample_weight,
centers,
centers_new,
weight_in_clusters,
center_half_distances,
distance_next_center,
upper_bounds,
lower_bounds,
labels,
center_shift,
n_threads,
)
# compute new pairwise distances between centers and closest other
# center of each center for next iterations
center_half_distances = euclidean_distances(centers_new) / 2
distance_next_center = np.partition(
np.asarray(center_half_distances), kth=1, axis=0
)[1]
if verbose:
inertia = _inertia(X, sample_weight, centers, labels, n_threads)
print(f"Iteration {i}, inertia {inertia}")
centers, centers_new = centers_new, centers
if np.array_equal(labels, labels_old):
# First check the labels for strict convergence.
if verbose:
print(f"Converged at iteration {i}: strict convergence.")
strict_convergence = True
break
else:
# No strict convergence, check for tol based convergence.
center_shift_tot = (center_shift**2).sum()
if center_shift_tot <= tol:
if verbose:
print(
f"Converged at iteration {i}: center shift "
f"{center_shift_tot} within tolerance {tol}."
)
break
labels_old[:] = labels
if not strict_convergence:
# rerun E-step so that predicted labels match cluster centers
elkan_iter(
X,
sample_weight,
centers,
centers,
weight_in_clusters,
center_half_distances,
distance_next_center,
upper_bounds,
lower_bounds,
labels,
center_shift,
n_threads,
update_centers=False,
)
inertia = _inertia(X, sample_weight, centers, labels, n_threads)
return labels, inertia, centers, i + 1
# Threadpoolctl context to limit the number of threads in second level of
# nested parallelism (i.e. BLAS) to avoid oversubscription.
@_threadpool_controller_decorator(limits=1, user_api="blas")
def _kmeans_single_lloyd(
X,
sample_weight,
centers_init,
max_iter=300,
verbose=False,
tol=1e-4,
n_threads=1,
):
"""A single run of k-means lloyd, assumes preparation completed prior.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The observations to cluster. If sparse matrix, must be in CSR format.
sample_weight : ndarray of shape (n_samples,)
The weights for each observation in X.
centers_init : ndarray of shape (n_clusters, n_features)
The initial centers.
max_iter : int, default=300
Maximum number of iterations of the k-means algorithm to run.
verbose : bool, default=False
Verbosity mode
tol : float, default=1e-4
Relative tolerance with regards to Frobenius norm of the difference
in the cluster centers of two consecutive iterations to declare
convergence.
It's not advised to set `tol=0` since convergence might never be
declared due to rounding errors. Use a very small number instead.
n_threads : int, default=1
The number of OpenMP threads to use for the computation. Parallelism is
sample-wise on the main cython loop which assigns each sample to its
closest center.
Returns
-------
centroid : ndarray of shape (n_clusters, n_features)
Centroids found at the last iteration of k-means.
label : ndarray of shape (n_samples,)
label[i] is the code or index of the centroid the
i'th observation is closest to.
inertia : float
The final value of the inertia criterion (sum of squared distances to
the closest centroid for all observations in the training set).
n_iter : int
Number of iterations run.
"""
n_clusters = centers_init.shape[0]
# Buffers to avoid new allocations at each iteration.
centers = centers_init
centers_new = np.zeros_like(centers)
labels = np.full(X.shape[0], -1, dtype=np.int32)
labels_old = labels.copy()
weight_in_clusters = np.zeros(n_clusters, dtype=X.dtype)
center_shift = np.zeros(n_clusters, dtype=X.dtype)
if sp.issparse(X):
lloyd_iter = lloyd_iter_chunked_sparse
_inertia = _inertia_sparse
else:
lloyd_iter = lloyd_iter_chunked_dense
_inertia = _inertia_dense
strict_convergence = False
for i in range(max_iter):
lloyd_iter(
X,
sample_weight,
centers,
centers_new,
weight_in_clusters,
labels,
center_shift,
n_threads,
)
if verbose:
inertia = _inertia(X, sample_weight, centers, labels, n_threads)
print(f"Iteration {i}, inertia {inertia}.")
centers, centers_new = centers_new, centers
if np.array_equal(labels, labels_old):
# First check the labels for strict convergence.
if verbose:
print(f"Converged at iteration {i}: strict convergence.")
strict_convergence = True
break
else:
# No strict convergence, check for tol based convergence.
center_shift_tot = (center_shift**2).sum()
if center_shift_tot <= tol:
if verbose:
print(
f"Converged at iteration {i}: center shift "
f"{center_shift_tot} within tolerance {tol}."
)
break
labels_old[:] = labels
if not strict_convergence:
# rerun E-step so that predicted labels match cluster centers
lloyd_iter(
X,
sample_weight,
centers,
centers,
weight_in_clusters,
labels,
center_shift,
n_threads,
update_centers=False,
)
inertia = _inertia(X, sample_weight, centers, labels, n_threads)
return labels, inertia, centers, i + 1
def _labels_inertia(X, sample_weight, centers, n_threads=1, return_inertia=True):
"""E step of the K-means EM algorithm.
Compute the labels and the inertia of the given samples and centers.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The input samples to assign to the labels. If sparse matrix, must
be in CSR format.
sample_weight : ndarray of shape (n_samples,)
The weights for each observation in X.
x_squared_norms : ndarray of shape (n_samples,)
Precomputed squared euclidean norm of each data point, to speed up
computations.
centers : ndarray of shape (n_clusters, n_features)
The cluster centers.
n_threads : int, default=1
The number of OpenMP threads to use for the computation. Parallelism is
sample-wise on the main cython loop which assigns each sample to its
closest center.
return_inertia : bool, default=True
Whether to compute and return the inertia.
Returns
-------
labels : ndarray of shape (n_samples,)
The resulting assignment.
inertia : float
Sum of squared distances of samples to their closest cluster center.
Inertia is only returned if return_inertia is True.
"""
n_samples = X.shape[0]
n_clusters = centers.shape[0]
labels = np.full(n_samples, -1, dtype=np.int32)
center_shift = np.zeros(n_clusters, dtype=centers.dtype)
if sp.issparse(X):
_labels = lloyd_iter_chunked_sparse
_inertia = _inertia_sparse
else:
_labels = lloyd_iter_chunked_dense
_inertia = _inertia_dense
_labels(
X,
sample_weight,
centers,
centers_new=None,
weight_in_clusters=None,
labels=labels,
center_shift=center_shift,
n_threads=n_threads,
update_centers=False,
)
if return_inertia:
inertia = _inertia(X, sample_weight, centers, labels, n_threads)
return labels, inertia
return labels
# Same as _labels_inertia but in a threadpool_limits context.
_labels_inertia_threadpool_limit = _threadpool_controller_decorator(
limits=1, user_api="blas"
)(_labels_inertia)
class _BaseKMeans(
ClassNamePrefixFeaturesOutMixin, TransformerMixin, ClusterMixin, BaseEstimator, ABC
):
"""Base class for KMeans and MiniBatchKMeans"""
_parameter_constraints: dict = {
"n_clusters": [Interval(Integral, 1, None, closed="left")],
"init": [StrOptions({"k-means++", "random"}), callable, "array-like"],
"n_init": [
StrOptions({"auto"}),
Interval(Integral, 1, None, closed="left"),
],
"max_iter": [Interval(Integral, 1, None, closed="left")],
"tol": [Interval(Real, 0, None, closed="left")],
"verbose": ["verbose"],
"random_state": ["random_state"],
}
def __init__(
self,
n_clusters,
*,
init,
n_init,
max_iter,
tol,
verbose,
random_state,
):
self.n_clusters = n_clusters
self.init = init
self.max_iter = max_iter
self.tol = tol
self.n_init = n_init
self.verbose = verbose
self.random_state = random_state
def _check_params_vs_input(self, X, default_n_init=None):
# n_clusters
if X.shape[0] < self.n_clusters:
raise ValueError(
f"n_samples={X.shape[0]} should be >= n_clusters={self.n_clusters}."
)
# tol
self._tol = _tolerance(X, self.tol)
# n-init
if self.n_init == "auto":
if isinstance(self.init, str) and self.init == "k-means++":
self._n_init = 1
elif isinstance(self.init, str) and self.init == "random":
self._n_init = default_n_init
elif callable(self.init):
self._n_init = default_n_init
else: # array-like
self._n_init = 1
else:
self._n_init = self.n_init
if _is_arraylike_not_scalar(self.init) and self._n_init != 1:
warnings.warn(
(
"Explicit initial center position passed: performing only"
f" one init in {self.__class__.__name__} instead of "
f"n_init={self._n_init}."
),
RuntimeWarning,
stacklevel=2,
)
self._n_init = 1
@abstractmethod
def _warn_mkl_vcomp(self, n_active_threads):
"""Issue an estimator specific warning when vcomp and mkl are both present
This method is called by `_check_mkl_vcomp`.
"""
def _check_mkl_vcomp(self, X, n_samples):
"""Check when vcomp and mkl are both present"""
# The BLAS call inside a prange in lloyd_iter_chunked_dense is known to
# cause a small memory leak when there are less chunks than the number
# of available threads. It only happens when the OpenMP library is
# vcomp (microsoft OpenMP) and the BLAS library is MKL. see #18653
if sp.issparse(X):
return
n_active_threads = int(np.ceil(n_samples / CHUNK_SIZE))
if n_active_threads < self._n_threads:
modules = _get_threadpool_controller().info()
has_vcomp = "vcomp" in [module["prefix"] for module in modules]
has_mkl = ("mkl", "intel") in [
(module["internal_api"], module.get("threading_layer", None))
for module in modules
]
if has_vcomp and has_mkl:
self._warn_mkl_vcomp(n_active_threads)
def _validate_center_shape(self, X, centers):
"""Check if centers is compatible with X and n_clusters."""
if centers.shape[0] != self.n_clusters:
raise ValueError(
f"The shape of the initial centers {centers.shape} does not "
f"match the number of clusters {self.n_clusters}."
)
if centers.shape[1] != X.shape[1]:
raise ValueError(
f"The shape of the initial centers {centers.shape} does not "
f"match the number of features of the data {X.shape[1]}."
)
def _check_test_data(self, X):
X = validate_data(
self,
X,
accept_sparse="csr",
reset=False,
dtype=[np.float64, np.float32],
order="C",
accept_large_sparse=False,
)
return X
def _init_centroids(
self,
X,
x_squared_norms,
init,
random_state,
sample_weight,
init_size=None,
n_centroids=None,
):
"""Compute the initial centroids.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The input samples.
x_squared_norms : ndarray of shape (n_samples,)
Squared euclidean norm of each data point. Pass it if you have it
at hands already to avoid it being recomputed here.
init : {'k-means++', 'random'}, callable or ndarray of shape \
(n_clusters, n_features)
Method for initialization.
random_state : RandomState instance
Determines random number generation for centroid initialization.
See :term:`Glossary <random_state>`.
sample_weight : ndarray of shape (n_samples,)
The weights for each observation in X. `sample_weight` is not used
during initialization if `init` is a callable or a user provided
array.
init_size : int, default=None
Number of samples to randomly sample for speeding up the
initialization (sometimes at the expense of accuracy).
n_centroids : int, default=None
Number of centroids to initialize.
If left to 'None' the number of centroids will be equal to
number of clusters to form (self.n_clusters).
Returns
-------
centers : ndarray of shape (n_clusters, n_features)
Initial centroids of clusters.
"""
n_samples = X.shape[0]
n_clusters = self.n_clusters if n_centroids is None else n_centroids
if init_size is not None and init_size < n_samples:
init_indices = random_state.randint(0, n_samples, init_size)
X = X[init_indices]
x_squared_norms = x_squared_norms[init_indices]
n_samples = X.shape[0]
sample_weight = sample_weight[init_indices]
if isinstance(init, str) and init == "k-means++":
centers, _ = _kmeans_plusplus(
X,
n_clusters,
random_state=random_state,
x_squared_norms=x_squared_norms,
sample_weight=sample_weight,
)
elif isinstance(init, str) and init == "random":
seeds = random_state.choice(
n_samples,
size=n_clusters,
replace=False,
p=sample_weight / sample_weight.sum(),
)
centers = X[seeds]
elif _is_arraylike_not_scalar(self.init):
centers = init
elif callable(init):
centers = init(X, n_clusters, random_state=random_state)
centers = check_array(centers, dtype=X.dtype, copy=False, order="C")
self._validate_center_shape(X, centers)
if sp.issparse(centers):
centers = centers.toarray()
return centers
def fit_predict(self, X, y=None, sample_weight=None):
"""Compute cluster centers and predict cluster index for each sample.
Convenience method; equivalent to calling fit(X) followed by
predict(X).
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
New data to transform.
y : Ignored
Not used, present here for API consistency by convention.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in X. If None, all observations
are assigned equal weight.
Returns
-------
labels : ndarray of shape (n_samples,)
Index of the cluster each sample belongs to.
"""
return self.fit(X, sample_weight=sample_weight).labels_
def predict(self, X):
"""Predict the closest cluster each sample in X belongs to.
In the vector quantization literature, `cluster_centers_` is called
the code book and each value returned by `predict` is the index of
the closest code in the code book.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
New data to predict.
Returns
-------
labels : ndarray of shape (n_samples,)
Index of the cluster each sample belongs to.
"""
check_is_fitted(self)
X = self._check_test_data(X)
# sample weights are not used by predict but cython helpers expect an array
sample_weight = np.ones(X.shape[0], dtype=X.dtype)
labels = _labels_inertia_threadpool_limit(
X,
sample_weight,
self.cluster_centers_,
n_threads=self._n_threads,
return_inertia=False,
)
return labels
def fit_transform(self, X, y=None, sample_weight=None):
"""Compute clustering and transform X to cluster-distance space.
Equivalent to fit(X).transform(X), but more efficiently implemented.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
New data to transform.
y : Ignored
Not used, present here for API consistency by convention.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in X. If None, all observations
are assigned equal weight.
Returns
-------
X_new : ndarray of shape (n_samples, n_clusters)
X transformed in the new space.
"""
return self.fit(X, sample_weight=sample_weight)._transform(X)
def transform(self, X):
"""Transform X to a cluster-distance space.
In the new space, each dimension is the distance to the cluster
centers. Note that even if X is sparse, the array returned by
`transform` will typically be dense.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
New data to transform.
Returns
-------
X_new : ndarray of shape (n_samples, n_clusters)
X transformed in the new space.
"""
check_is_fitted(self)
X = self._check_test_data(X)
return self._transform(X)
def _transform(self, X):
"""Guts of transform method; no input validation."""
return euclidean_distances(X, self.cluster_centers_)
def score(self, X, y=None, sample_weight=None):
"""Opposite of the value of X on the K-means objective.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
New data.
y : Ignored
Not used, present here for API consistency by convention.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in X. If None, all observations
are assigned equal weight.
Returns
-------
score : float
Opposite of the value of X on the K-means objective.
"""
check_is_fitted(self)
X = self._check_test_data(X)
sample_weight = _check_sample_weight(sample_weight, X, dtype=X.dtype)
_, scores = _labels_inertia_threadpool_limit(
X, sample_weight, self.cluster_centers_, self._n_threads
)
return -scores
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
tags.input_tags.sparse = True
return tags
class KMeans(_BaseKMeans):
"""K-Means clustering.
Read more in the :ref:`User Guide <k_means>`.
Parameters
----------
n_clusters : int, default=8
The number of clusters to form as well as the number of
centroids to generate.
For an example of how to choose an optimal value for `n_clusters` refer to
:ref:`sphx_glr_auto_examples_cluster_plot_kmeans_silhouette_analysis.py`.
init : {'k-means++', 'random'}, callable or array-like of shape \
(n_clusters, n_features), default='k-means++'
Method for initialization:
* 'k-means++' : selects initial cluster centroids using sampling \
based on an empirical probability distribution of the points' \
contribution to the overall inertia. This technique speeds up \
convergence. The algorithm implemented is "greedy k-means++". It \
differs from the vanilla k-means++ by making several trials at \
each sampling step and choosing the best centroid among them.
* 'random': choose `n_clusters` observations (rows) at random from \
data for the initial centroids.
* If an array is passed, it should be of shape (n_clusters, n_features)\
and gives the initial centers.
* If a callable is passed, it should take arguments X, n_clusters and a\
random state and return an initialization.
For an example of how to use the different `init` strategies, see
:ref:`sphx_glr_auto_examples_cluster_plot_kmeans_digits.py`.
For an evaluation of the impact of initialization, see the example
:ref:`sphx_glr_auto_examples_cluster_plot_kmeans_stability_low_dim_dense.py`.
n_init : 'auto' or int, default='auto'
Number of times the k-means algorithm is run with different centroid
seeds. The final results is the best output of `n_init` consecutive runs
in terms of inertia. Several runs are recommended for sparse
high-dimensional problems (see :ref:`kmeans_sparse_high_dim`).
When `n_init='auto'`, the number of runs depends on the value of init:
10 if using `init='random'` or `init` is a callable;
1 if using `init='k-means++'` or `init` is an array-like.
.. versionadded:: 1.2
Added 'auto' option for `n_init`.
.. versionchanged:: 1.4
Default value for `n_init` changed to `'auto'`.
max_iter : int, default=300
Maximum number of iterations of the k-means algorithm for a
single run.
tol : float, default=1e-4
Relative tolerance with regards to Frobenius norm of the difference
in the cluster centers of two consecutive iterations to declare
convergence.
verbose : int, default=0
Verbosity mode.
random_state : int, RandomState instance or None, default=None
Determines random number generation for centroid initialization. Use
an int to make the randomness deterministic.
See :term:`Glossary <random_state>`.
copy_x : bool, default=True
When pre-computing distances it is more numerically accurate to center
the data first. If copy_x is True (default), then the original data is
not modified. If False, the original data is modified, and put back
before the function returns, but small numerical differences may be
introduced by subtracting and then adding the data mean. Note that if
the original data is not C-contiguous, a copy will be made even if
copy_x is False. If the original data is sparse, but not in CSR format,
a copy will be made even if copy_x is False.
algorithm : {"lloyd", "elkan"}, default="lloyd"
K-means algorithm to use. The classical EM-style algorithm is `"lloyd"`.
The `"elkan"` variation can be more efficient on some datasets with
well-defined clusters, by using the triangle inequality. However it's
more memory intensive due to the allocation of an extra array of shape
`(n_samples, n_clusters)`.
.. versionchanged:: 0.18
Added Elkan algorithm
.. versionchanged:: 1.1
Renamed "full" to "lloyd", and deprecated "auto" and "full".
Changed "auto" to use "lloyd" instead of "elkan".
Attributes
----------
cluster_centers_ : ndarray of shape (n_clusters, n_features)
Coordinates of cluster centers. If the algorithm stops before fully
converging (see ``tol`` and ``max_iter``), these will not be
consistent with ``labels_``.
labels_ : ndarray of shape (n_samples,)
Labels of each point
inertia_ : float
Sum of squared distances of samples to their closest cluster center,
weighted by the sample weights if provided.
n_iter_ : int
Number of iterations run.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
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
--------
MiniBatchKMeans : Alternative online implementation that does incremental
updates of the centers positions using mini-batches.
For large scale learning (say n_samples > 10k) MiniBatchKMeans is
probably much faster than the default batch implementation.
Notes
-----
The k-means problem is solved using either Lloyd's or Elkan's algorithm.
The average complexity is given by O(k n T), where n is the number of
samples and T is the number of iteration.
The worst case complexity is given by O(n^(k+2/p)) with
n = n_samples, p = n_features.
Refer to :doi:`"How slow is the k-means method?" D. Arthur and S. Vassilvitskii -
SoCG2006.<10.1145/1137856.1137880>` for more details.
In practice, the k-means algorithm is very fast (one of the fastest
clustering algorithms available), but it falls in local minima. That's why
it can be useful to restart it several times.
If the algorithm stops before fully converging (because of ``tol`` or
``max_iter``), ``labels_`` and ``cluster_centers_`` will not be consistent,
i.e. the ``cluster_centers_`` will not be the means of the points in each
cluster. Also, the estimator will reassign ``labels_`` after the last
iteration to make ``labels_`` consistent with ``predict`` on the training
set.
Examples
--------
>>> from sklearn.cluster import KMeans
>>> import numpy as np
>>> X = np.array([[1, 2], [1, 4], [1, 0],
... [10, 2], [10, 4], [10, 0]])
>>> kmeans = KMeans(n_clusters=2, random_state=0, n_init="auto").fit(X)
>>> kmeans.labels_
array([1, 1, 1, 0, 0, 0], dtype=int32)
>>> kmeans.predict([[0, 0], [12, 3]])
array([1, 0], dtype=int32)
>>> kmeans.cluster_centers_
array([[10., 2.],
[ 1., 2.]])
For examples of common problems with K-Means and how to address them see
:ref:`sphx_glr_auto_examples_cluster_plot_kmeans_assumptions.py`.
For a demonstration of how K-Means can be used to cluster text documents see
:ref:`sphx_glr_auto_examples_text_plot_document_clustering.py`.
For a comparison between K-Means and MiniBatchKMeans refer to example
:ref:`sphx_glr_auto_examples_cluster_plot_mini_batch_kmeans.py`.
For a comparison between K-Means and BisectingKMeans refer to example
:ref:`sphx_glr_auto_examples_cluster_plot_bisect_kmeans.py`.
"""
_parameter_constraints: dict = {
**_BaseKMeans._parameter_constraints,
"copy_x": ["boolean"],
"algorithm": [StrOptions({"lloyd", "elkan"})],
}
def __init__(
self,
n_clusters=8,
*,
init="k-means++",
n_init="auto",
max_iter=300,
tol=1e-4,
verbose=0,
random_state=None,
copy_x=True,
algorithm="lloyd",
):
super().__init__(
n_clusters=n_clusters,
init=init,
n_init=n_init,
max_iter=max_iter,
tol=tol,
verbose=verbose,
random_state=random_state,
)
self.copy_x = copy_x
self.algorithm = algorithm
def _check_params_vs_input(self, X):
super()._check_params_vs_input(X, default_n_init=10)
self._algorithm = self.algorithm
if self._algorithm == "elkan" and self.n_clusters == 1:
warnings.warn(
(
"algorithm='elkan' doesn't make sense for a single "
"cluster. Using 'lloyd' instead."
),
RuntimeWarning,
)
self._algorithm = "lloyd"
def _warn_mkl_vcomp(self, n_active_threads):
"""Warn when vcomp and mkl are both present"""
warnings.warn(
"KMeans is known to have a memory leak on Windows "
"with MKL, when there are less chunks than available "
"threads. You can avoid it by setting the environment"
f" variable OMP_NUM_THREADS={n_active_threads}."
)
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y=None, sample_weight=None):
"""Compute k-means clustering.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Training instances to cluster. It must be noted that the data
will be converted to C ordering, which will cause a memory
copy if the given data is not C-contiguous.
If a sparse matrix is passed, a copy will be made if it's not in
CSR format.
y : Ignored
Not used, present here for API consistency by convention.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in X. If None, all observations
are assigned equal weight. `sample_weight` is not used during
initialization if `init` is a callable or a user provided array.
.. versionadded:: 0.20
Returns
-------
self : object
Fitted estimator.
"""
X = validate_data(
self,
X,
accept_sparse="csr",
dtype=[np.float64, np.float32],
order="C",
copy=self.copy_x,
accept_large_sparse=False,
)
self._check_params_vs_input(X)
random_state = check_random_state(self.random_state)
sample_weight = _check_sample_weight(sample_weight, X, dtype=X.dtype)
self._n_threads = _openmp_effective_n_threads()
# Validate init array
init = self.init
init_is_array_like = _is_arraylike_not_scalar(init)
if init_is_array_like:
init = check_array(init, dtype=X.dtype, copy=True, order="C")
self._validate_center_shape(X, init)
# subtract of mean of x for more accurate distance computations
if not sp.issparse(X):
X_mean = X.mean(axis=0)
# The copy was already done above
X -= X_mean
if init_is_array_like:
init -= X_mean
# precompute squared norms of data points
x_squared_norms = row_norms(X, squared=True)
if self._algorithm == "elkan":
kmeans_single = _kmeans_single_elkan
else:
kmeans_single = _kmeans_single_lloyd
self._check_mkl_vcomp(X, X.shape[0])
best_inertia, best_labels = None, None
for i in range(self._n_init):
# Initialize centers
centers_init = self._init_centroids(
X,
x_squared_norms=x_squared_norms,
init=init,
random_state=random_state,
sample_weight=sample_weight,
)
if self.verbose:
print("Initialization complete")
# run a k-means once
labels, inertia, centers, n_iter_ = kmeans_single(
X,
sample_weight,
centers_init,
max_iter=self.max_iter,
verbose=self.verbose,
tol=self._tol,
n_threads=self._n_threads,
)
# determine if these results are the best so far
# we chose a new run if it has a better inertia and the clustering is
# different from the best so far (it's possible that the inertia is
# slightly better even if the clustering is the same with potentially
# permuted labels, due to rounding errors)
if best_inertia is None or (
inertia < best_inertia
and not _is_same_clustering(labels, best_labels, self.n_clusters)
):
best_labels = labels
best_centers = centers
best_inertia = inertia
best_n_iter = n_iter_
if not sp.issparse(X):
if not self.copy_x:
X += X_mean
best_centers += X_mean
distinct_clusters = len(set(best_labels))
if distinct_clusters < self.n_clusters:
warnings.warn(
"Number of distinct clusters ({}) found smaller than "
"n_clusters ({}). Possibly due to duplicate points "
"in X.".format(distinct_clusters, self.n_clusters),
ConvergenceWarning,
stacklevel=2,
)
self.cluster_centers_ = best_centers
self._n_features_out = self.cluster_centers_.shape[0]
self.labels_ = best_labels
self.inertia_ = best_inertia
self.n_iter_ = best_n_iter
return self
def _mini_batch_step(
X,
sample_weight,
centers,
centers_new,
weight_sums,
random_state,
random_reassign=False,
reassignment_ratio=0.01,
verbose=False,
n_threads=1,
):
"""Incremental update of the centers for the Minibatch K-Means algorithm.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The original data array. If sparse, must be in CSR format.
x_squared_norms : ndarray of shape (n_samples,)
Squared euclidean norm of each data point.
sample_weight : ndarray of shape (n_samples,)
The weights for each observation in `X`.
centers : ndarray of shape (n_clusters, n_features)
The cluster centers before the current iteration
centers_new : ndarray of shape (n_clusters, n_features)
The cluster centers after the current iteration. Modified in-place.
weight_sums : ndarray of shape (n_clusters,)
The vector in which we keep track of the numbers of points in a
cluster. This array is modified in place.
random_state : RandomState instance
Determines random number generation for low count centers reassignment.
See :term:`Glossary <random_state>`.
random_reassign : boolean, default=False
If True, centers with very low counts are randomly reassigned
to observations.
reassignment_ratio : float, default=0.01
Control the fraction of the maximum number of counts for a
center to be reassigned. A higher value means that low count
centers are more likely to be reassigned, which means that the
model will take longer to converge, but should converge in a
better clustering.
verbose : bool, default=False
Controls the verbosity.
n_threads : int, default=1
The number of OpenMP threads to use for the computation.
Returns
-------
inertia : float
Sum of squared distances of samples to their closest cluster center.
The inertia is computed after finding the labels and before updating
the centers.
"""
# Perform label assignment to nearest centers
# For better efficiency, it's better to run _mini_batch_step in a
# threadpool_limit context than using _labels_inertia_threadpool_limit here
labels, inertia = _labels_inertia(X, sample_weight, centers, n_threads=n_threads)
# Update centers according to the labels
if sp.issparse(X):
_minibatch_update_sparse(
X, sample_weight, centers, centers_new, weight_sums, labels, n_threads
)
else:
_minibatch_update_dense(
X,
sample_weight,
centers,
centers_new,
weight_sums,
labels,
n_threads,
)
# Reassign clusters that have very low weight
if random_reassign and reassignment_ratio > 0:
to_reassign = weight_sums < reassignment_ratio * weight_sums.max()
# pick at most .5 * batch_size samples as new centers
if to_reassign.sum() > 0.5 * X.shape[0]:
indices_dont_reassign = np.argsort(weight_sums)[int(0.5 * X.shape[0]) :]
to_reassign[indices_dont_reassign] = False
n_reassigns = to_reassign.sum()
if n_reassigns:
# Pick new clusters amongst observations with uniform probability
new_centers = random_state.choice(
X.shape[0], replace=False, size=n_reassigns
)
if verbose:
print(f"[MiniBatchKMeans] Reassigning {n_reassigns} cluster centers.")
if sp.issparse(X):
assign_rows_csr(
X,
new_centers.astype(np.intp, copy=False),
np.where(to_reassign)[0].astype(np.intp, copy=False),
centers_new,
)
else:
centers_new[to_reassign] = X[new_centers]
# reset counts of reassigned centers, but don't reset them too small
# to avoid instant reassignment. This is a pretty dirty hack as it
# also modifies the learning rates.
weight_sums[to_reassign] = np.min(weight_sums[~to_reassign])
return inertia
class MiniBatchKMeans(_BaseKMeans):
"""
Mini-Batch K-Means clustering.
Read more in the :ref:`User Guide <mini_batch_kmeans>`.
Parameters
----------
n_clusters : int, default=8
The number of clusters to form as well as the number of
centroids to generate.
init : {'k-means++', 'random'}, callable or array-like of shape \
(n_clusters, n_features), default='k-means++'
Method for initialization:
'k-means++' : selects initial cluster centroids using sampling based on
an empirical probability distribution of the points' contribution to the
overall inertia. This technique speeds up convergence. The algorithm
implemented is "greedy k-means++". It differs from the vanilla k-means++
by making several trials at each sampling step and choosing the best centroid
among them.
'random': choose `n_clusters` observations (rows) at random from data
for the initial centroids.
If an array is passed, it should be of shape (n_clusters, n_features)
and gives the initial centers.
If a callable is passed, it should take arguments X, n_clusters and a
random state and return an initialization.
For an evaluation of the impact of initialization, see the example
:ref:`sphx_glr_auto_examples_cluster_plot_kmeans_stability_low_dim_dense.py`.
max_iter : int, default=100
Maximum number of iterations over the complete dataset before
stopping independently of any early stopping criterion heuristics.
batch_size : int, default=1024
Size of the mini batches.
For faster computations, you can set the ``batch_size`` greater than
256 * number of cores to enable parallelism on all cores.
.. versionchanged:: 1.0
`batch_size` default changed from 100 to 1024.
verbose : int, default=0
Verbosity mode.
compute_labels : bool, default=True
Compute label assignment and inertia for the complete dataset
once the minibatch optimization has converged in fit.
random_state : int, RandomState instance or None, default=None
Determines random number generation for centroid initialization and
random reassignment. Use an int to make the randomness deterministic.
See :term:`Glossary <random_state>`.
tol : float, default=0.0
Control early stopping based on the relative center changes as
measured by a smoothed, variance-normalized of the mean center
squared position changes. This early stopping heuristics is
closer to the one used for the batch variant of the algorithms
but induces a slight computational and memory overhead over the
inertia heuristic.
To disable convergence detection based on normalized center
change, set tol to 0.0 (default).
max_no_improvement : int, default=10
Control early stopping based on the consecutive number of mini
batches that does not yield an improvement on the smoothed inertia.
To disable convergence detection based on inertia, set
max_no_improvement to None.
init_size : int, default=None
Number of samples to randomly sample for speeding up the
initialization (sometimes at the expense of accuracy): the
only algorithm is initialized by running a batch KMeans on a
random subset of the data. This needs to be larger than n_clusters.
If `None`, the heuristic is `init_size = 3 * batch_size` if
`3 * batch_size < n_clusters`, else `init_size = 3 * n_clusters`.
n_init : 'auto' or int, default="auto"
Number of random initializations that are tried.
In contrast to KMeans, the algorithm is only run once, using the best of
the `n_init` initializations as measured by inertia. Several runs are
recommended for sparse high-dimensional problems (see
:ref:`kmeans_sparse_high_dim`).
When `n_init='auto'`, the number of runs depends on the value of init:
3 if using `init='random'` or `init` is a callable;
1 if using `init='k-means++'` or `init` is an array-like.
.. versionadded:: 1.2
Added 'auto' option for `n_init`.
.. versionchanged:: 1.4
Default value for `n_init` changed to `'auto'` in version.
reassignment_ratio : float, default=0.01
Control the fraction of the maximum number of counts for a center to
be reassigned. A higher value means that low count centers are more
easily reassigned, which means that the model will take longer to
converge, but should converge in a better clustering. However, too high
a value may cause convergence issues, especially with a small batch
size.
Attributes
----------
cluster_centers_ : ndarray of shape (n_clusters, n_features)
Coordinates of cluster centers.
labels_ : ndarray of shape (n_samples,)
Labels of each point (if compute_labels is set to True).
inertia_ : float
The value of the inertia criterion associated with the chosen
partition if compute_labels is set to True. If compute_labels is set to
False, it's an approximation of the inertia based on an exponentially
weighted average of the batch inertiae.
The inertia is defined as the sum of square distances of samples to
their cluster center, weighted by the sample weights if provided.
n_iter_ : int
Number of iterations over the full dataset.
n_steps_ : int
Number of minibatches processed.
.. versionadded:: 1.0
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
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
--------
KMeans : The classic implementation of the clustering method based on the
Lloyd's algorithm. It consumes the whole set of input data at each
iteration.
Notes
-----
See https://www.eecs.tufts.edu/~dsculley/papers/fastkmeans.pdf
When there are too few points in the dataset, some centers may be
duplicated, which means that a proper clustering in terms of the number
of requesting clusters and the number of returned clusters will not
always match. One solution is to set `reassignment_ratio=0`, which
prevents reassignments of clusters that are too small.
See :ref:`sphx_glr_auto_examples_cluster_plot_birch_vs_minibatchkmeans.py` for a
comparison with :class:`~sklearn.cluster.BIRCH`.
Examples
--------
>>> from sklearn.cluster import MiniBatchKMeans
>>> import numpy as np
>>> X = np.array([[1, 2], [1, 4], [1, 0],
... [4, 2], [4, 0], [4, 4],
... [4, 5], [0, 1], [2, 2],
... [3, 2], [5, 5], [1, -1]])
>>> # manually fit on batches
>>> kmeans = MiniBatchKMeans(n_clusters=2,
... random_state=0,
... batch_size=6,
... n_init="auto")
>>> kmeans = kmeans.partial_fit(X[0:6,:])
>>> kmeans = kmeans.partial_fit(X[6:12,:])
>>> kmeans.cluster_centers_
array([[3.375, 3. ],
[0.75 , 0.5 ]])
>>> kmeans.predict([[0, 0], [4, 4]])
array([1, 0], dtype=int32)
>>> # fit on the whole data
>>> kmeans = MiniBatchKMeans(n_clusters=2,
... random_state=0,
... batch_size=6,
... max_iter=10,
... n_init="auto").fit(X)
>>> kmeans.cluster_centers_
array([[3.55102041, 2.48979592],
[1.06896552, 1. ]])
>>> kmeans.predict([[0, 0], [4, 4]])
array([1, 0], dtype=int32)
"""
_parameter_constraints: dict = {
**_BaseKMeans._parameter_constraints,
"batch_size": [Interval(Integral, 1, None, closed="left")],
"compute_labels": ["boolean"],
"max_no_improvement": [Interval(Integral, 0, None, closed="left"), None],
"init_size": [Interval(Integral, 1, None, closed="left"), None],
"reassignment_ratio": [Interval(Real, 0, None, closed="left")],
}
def __init__(
self,
n_clusters=8,
*,
init="k-means++",
max_iter=100,
batch_size=1024,
verbose=0,
compute_labels=True,
random_state=None,
tol=0.0,
max_no_improvement=10,
init_size=None,
n_init="auto",
reassignment_ratio=0.01,
):
super().__init__(
n_clusters=n_clusters,
init=init,
max_iter=max_iter,
verbose=verbose,
random_state=random_state,
tol=tol,
n_init=n_init,
)
self.max_no_improvement = max_no_improvement
self.batch_size = batch_size
self.compute_labels = compute_labels
self.init_size = init_size
self.reassignment_ratio = reassignment_ratio
def _check_params_vs_input(self, X):
super()._check_params_vs_input(X, default_n_init=3)
self._batch_size = min(self.batch_size, X.shape[0])
# init_size
self._init_size = self.init_size
if self._init_size is None:
self._init_size = 3 * self._batch_size
if self._init_size < self.n_clusters:
self._init_size = 3 * self.n_clusters
elif self._init_size < self.n_clusters:
warnings.warn(
(
f"init_size={self._init_size} should be larger than "
f"n_clusters={self.n_clusters}. Setting it to "
"min(3*n_clusters, n_samples)"
),
RuntimeWarning,
stacklevel=2,
)
self._init_size = 3 * self.n_clusters
self._init_size = min(self._init_size, X.shape[0])
# reassignment_ratio
if self.reassignment_ratio < 0:
raise ValueError(
"reassignment_ratio should be >= 0, got "
f"{self.reassignment_ratio} instead."
)
def _warn_mkl_vcomp(self, n_active_threads):
"""Warn when vcomp and mkl are both present"""
warnings.warn(
"MiniBatchKMeans is known to have a memory leak on "
"Windows with MKL, when there are less chunks than "
"available threads. You can prevent it by setting "
f"batch_size >= {self._n_threads * CHUNK_SIZE} or by "
"setting the environment variable "
f"OMP_NUM_THREADS={n_active_threads}"
)
def _mini_batch_convergence(
self, step, n_steps, n_samples, centers_squared_diff, batch_inertia
):
"""Helper function to encapsulate the early stopping logic"""
# Normalize inertia to be able to compare values when
# batch_size changes
batch_inertia /= self._batch_size
# count steps starting from 1 for user friendly verbose mode.
step = step + 1
# Ignore first iteration because it's inertia from initialization.
if step == 1:
if self.verbose:
print(
f"Minibatch step {step}/{n_steps}: mean batch "
f"inertia: {batch_inertia}"
)
return False
# Compute an Exponentially Weighted Average of the inertia to
# monitor the convergence while discarding minibatch-local stochastic
# variability: https://en.wikipedia.org/wiki/Moving_average
if self._ewa_inertia is None:
self._ewa_inertia = batch_inertia
else:
alpha = self._batch_size * 2.0 / (n_samples + 1)
alpha = min(alpha, 1)
self._ewa_inertia = self._ewa_inertia * (1 - alpha) + batch_inertia * alpha
# Log progress to be able to monitor convergence
if self.verbose:
print(
f"Minibatch step {step}/{n_steps}: mean batch inertia: "
f"{batch_inertia}, ewa inertia: {self._ewa_inertia}"
)
# Early stopping based on absolute tolerance on squared change of
# centers position
if self._tol > 0.0 and centers_squared_diff <= self._tol:
if self.verbose:
print(f"Converged (small centers change) at step {step}/{n_steps}")
return True
# Early stopping heuristic due to lack of improvement on smoothed
# inertia
if self._ewa_inertia_min is None or self._ewa_inertia < self._ewa_inertia_min:
self._no_improvement = 0
self._ewa_inertia_min = self._ewa_inertia
else:
self._no_improvement += 1
if (
self.max_no_improvement is not None
and self._no_improvement >= self.max_no_improvement
):
if self.verbose:
print(
"Converged (lack of improvement in inertia) at step "
f"{step}/{n_steps}"
)
return True
return False
def _random_reassign(self):
"""Check if a random reassignment needs to be done.
Do random reassignments each time 10 * n_clusters samples have been
processed.
If there are empty clusters we always want to reassign.
"""
self._n_since_last_reassign += self._batch_size
if (self._counts == 0).any() or self._n_since_last_reassign >= (
10 * self.n_clusters
):
self._n_since_last_reassign = 0
return True
return False
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y=None, sample_weight=None):
"""Compute the centroids on X by chunking it into mini-batches.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Training instances to cluster. It must be noted that the data
will be converted to C ordering, which will cause a memory copy
if the given data is not C-contiguous.
If a sparse matrix is passed, a copy will be made if it's not in
CSR format.
y : Ignored
Not used, present here for API consistency by convention.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in X. If None, all observations
are assigned equal weight. `sample_weight` is not used during
initialization if `init` is a callable or a user provided array.
.. versionadded:: 0.20
Returns
-------
self : object
Fitted estimator.
"""
X = validate_data(
self,
X,
accept_sparse="csr",
dtype=[np.float64, np.float32],
order="C",
accept_large_sparse=False,
)
self._check_params_vs_input(X)
random_state = check_random_state(self.random_state)
sample_weight = _check_sample_weight(sample_weight, X, dtype=X.dtype)
self._n_threads = _openmp_effective_n_threads()
n_samples, n_features = X.shape
# Validate init array
init = self.init
if _is_arraylike_not_scalar(init):
init = check_array(init, dtype=X.dtype, copy=True, order="C")
self._validate_center_shape(X, init)
self._check_mkl_vcomp(X, self._batch_size)
# precompute squared norms of data points
x_squared_norms = row_norms(X, squared=True)
# Validation set for the init
validation_indices = random_state.randint(0, n_samples, self._init_size)
X_valid = X[validation_indices]
sample_weight_valid = sample_weight[validation_indices]
# perform several inits with random subsets
best_inertia = None
for init_idx in range(self._n_init):
if self.verbose:
print(f"Init {init_idx + 1}/{self._n_init} with method {init}")
# Initialize the centers using only a fraction of the data as we
# expect n_samples to be very large when using MiniBatchKMeans.
cluster_centers = self._init_centroids(
X,
x_squared_norms=x_squared_norms,
init=init,
random_state=random_state,
init_size=self._init_size,
sample_weight=sample_weight,
)
# Compute inertia on a validation set.
_, inertia = _labels_inertia_threadpool_limit(
X_valid,
sample_weight_valid,
cluster_centers,
n_threads=self._n_threads,
)
if self.verbose:
print(f"Inertia for init {init_idx + 1}/{self._n_init}: {inertia}")
if best_inertia is None or inertia < best_inertia:
init_centers = cluster_centers
best_inertia = inertia
centers = init_centers
centers_new = np.empty_like(centers)
# Initialize counts
self._counts = np.zeros(self.n_clusters, dtype=X.dtype)
# Attributes to monitor the convergence
self._ewa_inertia = None
self._ewa_inertia_min = None
self._no_improvement = 0
# Initialize number of samples seen since last reassignment
self._n_since_last_reassign = 0
n_steps = (self.max_iter * n_samples) // self._batch_size
with _get_threadpool_controller().limit(limits=1, user_api="blas"):
# Perform the iterative optimization until convergence
for i in range(n_steps):
# Sample a minibatch from the full dataset
minibatch_indices = random_state.randint(0, n_samples, self._batch_size)
# Perform the actual update step on the minibatch data
batch_inertia = _mini_batch_step(
X=X[minibatch_indices],
sample_weight=sample_weight[minibatch_indices],
centers=centers,
centers_new=centers_new,
weight_sums=self._counts,
random_state=random_state,
random_reassign=self._random_reassign(),
reassignment_ratio=self.reassignment_ratio,
verbose=self.verbose,
n_threads=self._n_threads,
)
if self._tol > 0.0:
centers_squared_diff = np.sum((centers_new - centers) ** 2)
else:
centers_squared_diff = 0
centers, centers_new = centers_new, centers
# Monitor convergence and do early stopping if necessary
if self._mini_batch_convergence(
i, n_steps, n_samples, centers_squared_diff, batch_inertia
):
break
self.cluster_centers_ = centers
self._n_features_out = self.cluster_centers_.shape[0]
self.n_steps_ = i + 1
self.n_iter_ = int(np.ceil(((i + 1) * self._batch_size) / n_samples))
if self.compute_labels:
self.labels_, self.inertia_ = _labels_inertia_threadpool_limit(
X,
sample_weight,
self.cluster_centers_,
n_threads=self._n_threads,
)
else:
self.inertia_ = self._ewa_inertia * n_samples
return self
@_fit_context(prefer_skip_nested_validation=True)
def partial_fit(self, X, y=None, sample_weight=None):
"""Update k means estimate on a single mini-batch X.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Training instances to cluster. It must be noted that the data
will be converted to C ordering, which will cause a memory copy
if the given data is not C-contiguous.
If a sparse matrix is passed, a copy will be made if it's not in
CSR format.
y : Ignored
Not used, present here for API consistency by convention.
sample_weight : array-like of shape (n_samples,), default=None
The weights for each observation in X. If None, all observations
are assigned equal weight. `sample_weight` is not used during
initialization if `init` is a callable or a user provided array.
Returns
-------
self : object
Return updated estimator.
"""
has_centers = hasattr(self, "cluster_centers_")
X = validate_data(
self,
X,
accept_sparse="csr",
dtype=[np.float64, np.float32],
order="C",
accept_large_sparse=False,
reset=not has_centers,
)
self._random_state = getattr(
self, "_random_state", check_random_state(self.random_state)
)
sample_weight = _check_sample_weight(sample_weight, X, dtype=X.dtype)
self.n_steps_ = getattr(self, "n_steps_", 0)
# precompute squared norms of data points
x_squared_norms = row_norms(X, squared=True)
if not has_centers:
# this instance has not been fitted yet (fit or partial_fit)
self._check_params_vs_input(X)
self._n_threads = _openmp_effective_n_threads()
# Validate init array
init = self.init
if _is_arraylike_not_scalar(init):
init = check_array(init, dtype=X.dtype, copy=True, order="C")
self._validate_center_shape(X, init)
self._check_mkl_vcomp(X, X.shape[0])
# initialize the cluster centers
self.cluster_centers_ = self._init_centroids(
X,
x_squared_norms=x_squared_norms,
init=init,
random_state=self._random_state,
init_size=self._init_size,
sample_weight=sample_weight,
)
# Initialize counts
self._counts = np.zeros(self.n_clusters, dtype=X.dtype)
# Initialize number of samples seen since last reassignment
self._n_since_last_reassign = 0
with _get_threadpool_controller().limit(limits=1, user_api="blas"):
_mini_batch_step(
X,
sample_weight=sample_weight,
centers=self.cluster_centers_,
centers_new=self.cluster_centers_,
weight_sums=self._counts,
random_state=self._random_state,
random_reassign=self._random_reassign(),
reassignment_ratio=self.reassignment_ratio,
verbose=self.verbose,
n_threads=self._n_threads,
)
if self.compute_labels:
self.labels_, self.inertia_ = _labels_inertia_threadpool_limit(
X,
sample_weight,
self.cluster_centers_,
n_threads=self._n_threads,
)
self.n_steps_ += 1
self._n_features_out = self.cluster_centers_.shape[0]
return self
|