File size: 77,742 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
"""
The :mod:`sklearn.model_selection._search` includes utilities to fine-tune the
parameters of an estimator.
"""

# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause

import numbers
import operator
import time
import warnings
from abc import ABCMeta, abstractmethod
from collections import defaultdict
from collections.abc import Iterable, Mapping, Sequence
from copy import deepcopy
from functools import partial, reduce
from itertools import product

import numpy as np
from numpy.ma import MaskedArray
from scipy.stats import rankdata

from ..base import BaseEstimator, MetaEstimatorMixin, _fit_context, clone, is_classifier
from ..exceptions import NotFittedError
from ..metrics import check_scoring
from ..metrics._scorer import (
    _check_multimetric_scoring,
    _MultimetricScorer,
    get_scorer_names,
)
from ..utils import Bunch, check_random_state
from ..utils._estimator_html_repr import _VisualBlock
from ..utils._param_validation import HasMethods, Interval, StrOptions
from ..utils._tags import get_tags
from ..utils.deprecation import _deprecate_Xt_in_inverse_transform
from ..utils.metadata_routing import (
    MetadataRouter,
    MethodMapping,
    _raise_for_params,
    _routing_enabled,
    process_routing,
)
from ..utils.metaestimators import available_if
from ..utils.parallel import Parallel, delayed
from ..utils.random import sample_without_replacement
from ..utils.validation import _check_method_params, check_is_fitted, indexable
from ._split import check_cv
from ._validation import (
    _aggregate_score_dicts,
    _fit_and_score,
    _insert_error_scores,
    _normalize_score_results,
    _warn_or_raise_about_fit_failures,
)

__all__ = ["GridSearchCV", "ParameterGrid", "ParameterSampler", "RandomizedSearchCV"]


class ParameterGrid:
    """Grid of parameters with a discrete number of values for each.

    Can be used to iterate over parameter value combinations with the
    Python built-in function iter.
    The order of the generated parameter combinations is deterministic.

    Read more in the :ref:`User Guide <grid_search>`.

    Parameters
    ----------
    param_grid : dict of str to sequence, or sequence of such
        The parameter grid to explore, as a dictionary mapping estimator
        parameters to sequences of allowed values.

        An empty dict signifies default parameters.

        A sequence of dicts signifies a sequence of grids to search, and is
        useful to avoid exploring parameter combinations that make no sense
        or have no effect. See the examples below.

    Examples
    --------
    >>> from sklearn.model_selection import ParameterGrid
    >>> param_grid = {'a': [1, 2], 'b': [True, False]}
    >>> list(ParameterGrid(param_grid)) == (
    ...    [{'a': 1, 'b': True}, {'a': 1, 'b': False},
    ...     {'a': 2, 'b': True}, {'a': 2, 'b': False}])
    True

    >>> grid = [{'kernel': ['linear']}, {'kernel': ['rbf'], 'gamma': [1, 10]}]
    >>> list(ParameterGrid(grid)) == [{'kernel': 'linear'},
    ...                               {'kernel': 'rbf', 'gamma': 1},
    ...                               {'kernel': 'rbf', 'gamma': 10}]
    True
    >>> ParameterGrid(grid)[1] == {'kernel': 'rbf', 'gamma': 1}
    True

    See Also
    --------
    GridSearchCV : Uses :class:`ParameterGrid` to perform a full parallelized
        parameter search.
    """

    def __init__(self, param_grid):
        if not isinstance(param_grid, (Mapping, Iterable)):
            raise TypeError(
                f"Parameter grid should be a dict or a list, got: {param_grid!r} of"
                f" type {type(param_grid).__name__}"
            )

        if isinstance(param_grid, Mapping):
            # wrap dictionary in a singleton list to support either dict
            # or list of dicts
            param_grid = [param_grid]

        # check if all entries are dictionaries of lists
        for grid in param_grid:
            if not isinstance(grid, dict):
                raise TypeError(f"Parameter grid is not a dict ({grid!r})")
            for key, value in grid.items():
                if isinstance(value, np.ndarray) and value.ndim > 1:
                    raise ValueError(
                        f"Parameter array for {key!r} should be one-dimensional, got:"
                        f" {value!r} with shape {value.shape}"
                    )
                if isinstance(value, str) or not isinstance(
                    value, (np.ndarray, Sequence)
                ):
                    raise TypeError(
                        f"Parameter grid for parameter {key!r} needs to be a list or a"
                        f" numpy array, but got {value!r} (of type "
                        f"{type(value).__name__}) instead. Single values "
                        "need to be wrapped in a list with one element."
                    )
                if len(value) == 0:
                    raise ValueError(
                        f"Parameter grid for parameter {key!r} need "
                        f"to be a non-empty sequence, got: {value!r}"
                    )

        self.param_grid = param_grid

    def __iter__(self):
        """Iterate over the points in the grid.

        Returns
        -------
        params : iterator over dict of str to any
            Yields dictionaries mapping each estimator parameter to one of its
            allowed values.
        """
        for p in self.param_grid:
            # Always sort the keys of a dictionary, for reproducibility
            items = sorted(p.items())
            if not items:
                yield {}
            else:
                keys, values = zip(*items)
                for v in product(*values):
                    params = dict(zip(keys, v))
                    yield params

    def __len__(self):
        """Number of points on the grid."""
        # Product function that can handle iterables (np.prod can't).
        product = partial(reduce, operator.mul)
        return sum(
            product(len(v) for v in p.values()) if p else 1 for p in self.param_grid
        )

    def __getitem__(self, ind):
        """Get the parameters that would be ``ind``th in iteration

        Parameters
        ----------
        ind : int
            The iteration index

        Returns
        -------
        params : dict of str to any
            Equal to list(self)[ind]
        """
        # This is used to make discrete sampling without replacement memory
        # efficient.
        for sub_grid in self.param_grid:
            # XXX: could memoize information used here
            if not sub_grid:
                if ind == 0:
                    return {}
                else:
                    ind -= 1
                    continue

            # Reverse so most frequent cycling parameter comes first
            keys, values_lists = zip(*sorted(sub_grid.items())[::-1])
            sizes = [len(v_list) for v_list in values_lists]
            total = np.prod(sizes)

            if ind >= total:
                # Try the next grid
                ind -= total
            else:
                out = {}
                for key, v_list, n in zip(keys, values_lists, sizes):
                    ind, offset = divmod(ind, n)
                    out[key] = v_list[offset]
                return out

        raise IndexError("ParameterGrid index out of range")


class ParameterSampler:
    """Generator on parameters sampled from given distributions.

    Non-deterministic iterable over random candidate combinations for hyper-
    parameter search. If all parameters are presented as a list,
    sampling without replacement is performed. If at least one parameter
    is given as a distribution, sampling with replacement is used.
    It is highly recommended to use continuous distributions for continuous
    parameters.

    Read more in the :ref:`User Guide <grid_search>`.

    Parameters
    ----------
    param_distributions : dict
        Dictionary with parameters names (`str`) as keys and distributions
        or lists of parameters to try. Distributions must provide a ``rvs``
        method for sampling (such as those from scipy.stats.distributions).
        If a list is given, it is sampled uniformly.
        If a list of dicts is given, first a dict is sampled uniformly, and
        then a parameter is sampled using that dict as above.

    n_iter : int
        Number of parameter settings that are produced.

    random_state : int, RandomState instance or None, default=None
        Pseudo random number generator state used for random uniform sampling
        from lists of possible values instead of scipy.stats distributions.
        Pass an int for reproducible output across multiple
        function calls.
        See :term:`Glossary <random_state>`.

    Returns
    -------
    params : dict of str to any
        **Yields** dictionaries mapping each estimator parameter to
        as sampled value.

    Examples
    --------
    >>> from sklearn.model_selection import ParameterSampler
    >>> from scipy.stats.distributions import expon
    >>> import numpy as np
    >>> rng = np.random.RandomState(0)
    >>> param_grid = {'a':[1, 2], 'b': expon()}
    >>> param_list = list(ParameterSampler(param_grid, n_iter=4,
    ...                                    random_state=rng))
    >>> rounded_list = [dict((k, round(v, 6)) for (k, v) in d.items())
    ...                 for d in param_list]
    >>> rounded_list == [{'b': 0.89856, 'a': 1},
    ...                  {'b': 0.923223, 'a': 1},
    ...                  {'b': 1.878964, 'a': 2},
    ...                  {'b': 1.038159, 'a': 2}]
    True
    """

    def __init__(self, param_distributions, n_iter, *, random_state=None):
        if not isinstance(param_distributions, (Mapping, Iterable)):
            raise TypeError(
                "Parameter distribution is not a dict or a list,"
                f" got: {param_distributions!r} of type "
                f"{type(param_distributions).__name__}"
            )

        if isinstance(param_distributions, Mapping):
            # wrap dictionary in a singleton list to support either dict
            # or list of dicts
            param_distributions = [param_distributions]

        for dist in param_distributions:
            if not isinstance(dist, dict):
                raise TypeError(
                    "Parameter distribution is not a dict ({!r})".format(dist)
                )
            for key in dist:
                if not isinstance(dist[key], Iterable) and not hasattr(
                    dist[key], "rvs"
                ):
                    raise TypeError(
                        f"Parameter grid for parameter {key!r} is not iterable "
                        f"or a distribution (value={dist[key]})"
                    )
        self.n_iter = n_iter
        self.random_state = random_state
        self.param_distributions = param_distributions

    def _is_all_lists(self):
        return all(
            all(not hasattr(v, "rvs") for v in dist.values())
            for dist in self.param_distributions
        )

    def __iter__(self):
        rng = check_random_state(self.random_state)

        # if all distributions are given as lists, we want to sample without
        # replacement
        if self._is_all_lists():
            # look up sampled parameter settings in parameter grid
            param_grid = ParameterGrid(self.param_distributions)
            grid_size = len(param_grid)
            n_iter = self.n_iter

            if grid_size < n_iter:
                warnings.warn(
                    "The total space of parameters %d is smaller "
                    "than n_iter=%d. Running %d iterations. For exhaustive "
                    "searches, use GridSearchCV." % (grid_size, self.n_iter, grid_size),
                    UserWarning,
                )
                n_iter = grid_size
            for i in sample_without_replacement(grid_size, n_iter, random_state=rng):
                yield param_grid[i]

        else:
            for _ in range(self.n_iter):
                dist = rng.choice(self.param_distributions)
                # Always sort the keys of a dictionary, for reproducibility
                items = sorted(dist.items())
                params = dict()
                for k, v in items:
                    if hasattr(v, "rvs"):
                        params[k] = v.rvs(random_state=rng)
                    else:
                        params[k] = v[rng.randint(len(v))]
                yield params

    def __len__(self):
        """Number of points that will be sampled."""
        if self._is_all_lists():
            grid_size = len(ParameterGrid(self.param_distributions))
            return min(self.n_iter, grid_size)
        else:
            return self.n_iter


def _check_refit(search_cv, attr):
    if not search_cv.refit:
        raise AttributeError(
            f"This {type(search_cv).__name__} instance was initialized with "
            f"`refit=False`. {attr} is available only after refitting on the best "
            "parameters. You can refit an estimator manually using the "
            "`best_params_` attribute"
        )


def _search_estimator_has(attr):
    """Check if we can delegate a method to the underlying estimator.

    Calling a prediction method will only be available if `refit=True`. In
    such case, we check first the fitted best estimator. If it is not
    fitted, we check the unfitted estimator.

    Checking the unfitted estimator allows to use `hasattr` on the `SearchCV`
    instance even before calling `fit`.
    """

    def check(self):
        _check_refit(self, attr)
        if hasattr(self, "best_estimator_"):
            # raise an AttributeError if `attr` does not exist
            getattr(self.best_estimator_, attr)
            return True
        # raise an AttributeError if `attr` does not exist
        getattr(self.estimator, attr)
        return True

    return check


def _yield_masked_array_for_each_param(candidate_params):
    """
    Yield a masked array for each candidate param.

    `candidate_params` is a sequence of params which were used in
    a `GridSearchCV`. We use masked arrays for the results, as not
    all params are necessarily present in each element of
    `candidate_params`. For example, if using `GridSearchCV` with
    a `SVC` model, then one might search over params like:

        - kernel=["rbf"], gamma=[0.1, 1]
        - kernel=["poly"], degree=[1, 2]

    and then param `'gamma'` would not be present in entries of
    `candidate_params` corresponding to `kernel='poly'`.
    """
    n_candidates = len(candidate_params)
    param_results = defaultdict(dict)

    for cand_idx, params in enumerate(candidate_params):
        for name, value in params.items():
            param_results["param_%s" % name][cand_idx] = value

    for key, param_result in param_results.items():
        param_list = list(param_result.values())
        try:
            arr = np.array(param_list)
        except ValueError:
            # This can happen when param_list contains lists of different
            # lengths, for example:
            # param_list=[[1], [2, 3]]
            arr_dtype = np.dtype(object)
        else:
            # There are two cases when we don't use the automatically inferred
            # dtype when creating the array and we use object instead:
            # - string dtype
            # - when array.ndim > 1, that means that param_list was something
            #   like a list of same-size sequences, which gets turned into a
            #   multi-dimensional array but we want a 1d array
            arr_dtype = arr.dtype if arr.dtype.kind != "U" and arr.ndim == 1 else object

        # Use one MaskedArray and mask all the places where the param is not
        # applicable for that candidate (which may not contain all the params).
        ma = MaskedArray(np.empty(n_candidates, dtype=arr_dtype), mask=True)
        for index, value in param_result.items():
            # Setting the value at an index unmasks that index
            ma[index] = value
        yield (key, ma)


class BaseSearchCV(MetaEstimatorMixin, BaseEstimator, metaclass=ABCMeta):
    """Abstract base class for hyper parameter search with cross-validation."""

    _parameter_constraints: dict = {
        "estimator": [HasMethods(["fit"])],
        "scoring": [
            StrOptions(set(get_scorer_names())),
            callable,
            list,
            tuple,
            dict,
            None,
        ],
        "n_jobs": [numbers.Integral, None],
        "refit": ["boolean", str, callable],
        "cv": ["cv_object"],
        "verbose": ["verbose"],
        "pre_dispatch": [numbers.Integral, str],
        "error_score": [StrOptions({"raise"}), numbers.Real],
        "return_train_score": ["boolean"],
    }

    @abstractmethod
    def __init__(
        self,
        estimator,
        *,
        scoring=None,
        n_jobs=None,
        refit=True,
        cv=None,
        verbose=0,
        pre_dispatch="2*n_jobs",
        error_score=np.nan,
        return_train_score=True,
    ):
        self.scoring = scoring
        self.estimator = estimator
        self.n_jobs = n_jobs
        self.refit = refit
        self.cv = cv
        self.verbose = verbose
        self.pre_dispatch = pre_dispatch
        self.error_score = error_score
        self.return_train_score = return_train_score

    @property
    # TODO(1.8) remove this property
    def _estimator_type(self):
        return self.estimator._estimator_type

    def __sklearn_tags__(self):
        tags = super().__sklearn_tags__()
        sub_estimator_tags = get_tags(self.estimator)
        tags.estimator_type = sub_estimator_tags.estimator_type
        tags.classifier_tags = deepcopy(sub_estimator_tags.classifier_tags)
        tags.regressor_tags = deepcopy(sub_estimator_tags.regressor_tags)
        # allows cross-validation to see 'precomputed' metrics
        tags.input_tags.pairwise = sub_estimator_tags.input_tags.pairwise
        tags.input_tags.sparse = sub_estimator_tags.input_tags.sparse
        tags.array_api_support = sub_estimator_tags.array_api_support
        return tags

    def score(self, X, y=None, **params):
        """Return the score on the given data, if the estimator has been refit.

        This uses the score defined by ``scoring`` where provided, and the
        ``best_estimator_.score`` method otherwise.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            Input data, where `n_samples` is the number of samples and
            `n_features` is the number of features.

        y : array-like of shape (n_samples, n_output) \
            or (n_samples,), default=None
            Target relative to X for classification or regression;
            None for unsupervised learning.

        **params : dict
            Parameters to be passed to the underlying scorer(s).

            .. versionadded:: 1.4
                Only available if `enable_metadata_routing=True`. See
                :ref:`Metadata Routing User Guide <metadata_routing>` for more
                details.

        Returns
        -------
        score : float
            The score defined by ``scoring`` if provided, and the
            ``best_estimator_.score`` method otherwise.
        """
        _check_refit(self, "score")
        check_is_fitted(self)

        _raise_for_params(params, self, "score")

        if _routing_enabled():
            score_params = process_routing(self, "score", **params).scorer["score"]
        else:
            score_params = dict()

        if self.scorer_ is None:
            raise ValueError(
                "No score function explicitly defined, "
                "and the estimator doesn't provide one %s" % self.best_estimator_
            )
        if isinstance(self.scorer_, dict):
            if self.multimetric_:
                scorer = self.scorer_[self.refit]
            else:
                scorer = self.scorer_
            return scorer(self.best_estimator_, X, y, **score_params)

        # callable
        score = self.scorer_(self.best_estimator_, X, y, **score_params)
        if self.multimetric_:
            score = score[self.refit]
        return score

    @available_if(_search_estimator_has("score_samples"))
    def score_samples(self, X):
        """Call score_samples on the estimator with the best found parameters.

        Only available if ``refit=True`` and the underlying estimator supports
        ``score_samples``.

        .. versionadded:: 0.24

        Parameters
        ----------
        X : iterable
            Data to predict on. Must fulfill input requirements
            of the underlying estimator.

        Returns
        -------
        y_score : ndarray of shape (n_samples,)
            The ``best_estimator_.score_samples`` method.
        """
        check_is_fitted(self)
        return self.best_estimator_.score_samples(X)

    @available_if(_search_estimator_has("predict"))
    def predict(self, X):
        """Call predict on the estimator with the best found parameters.

        Only available if ``refit=True`` and the underlying estimator supports
        ``predict``.

        Parameters
        ----------
        X : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

        Returns
        -------
        y_pred : ndarray of shape (n_samples,)
            The predicted labels or values for `X` based on the estimator with
            the best found parameters.
        """
        check_is_fitted(self)
        return self.best_estimator_.predict(X)

    @available_if(_search_estimator_has("predict_proba"))
    def predict_proba(self, X):
        """Call predict_proba on the estimator with the best found parameters.

        Only available if ``refit=True`` and the underlying estimator supports
        ``predict_proba``.

        Parameters
        ----------
        X : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

        Returns
        -------
        y_pred : ndarray of shape (n_samples,) or (n_samples, n_classes)
            Predicted class probabilities for `X` based on the estimator with
            the best found parameters. The order of the classes corresponds
            to that in the fitted attribute :term:`classes_`.
        """
        check_is_fitted(self)
        return self.best_estimator_.predict_proba(X)

    @available_if(_search_estimator_has("predict_log_proba"))
    def predict_log_proba(self, X):
        """Call predict_log_proba on the estimator with the best found parameters.

        Only available if ``refit=True`` and the underlying estimator supports
        ``predict_log_proba``.

        Parameters
        ----------
        X : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

        Returns
        -------
        y_pred : ndarray of shape (n_samples,) or (n_samples, n_classes)
            Predicted class log-probabilities for `X` based on the estimator
            with the best found parameters. The order of the classes
            corresponds to that in the fitted attribute :term:`classes_`.
        """
        check_is_fitted(self)
        return self.best_estimator_.predict_log_proba(X)

    @available_if(_search_estimator_has("decision_function"))
    def decision_function(self, X):
        """Call decision_function on the estimator with the best found parameters.

        Only available if ``refit=True`` and the underlying estimator supports
        ``decision_function``.

        Parameters
        ----------
        X : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

        Returns
        -------
        y_score : ndarray of shape (n_samples,) or (n_samples, n_classes) \
                or (n_samples, n_classes * (n_classes-1) / 2)
            Result of the decision function for `X` based on the estimator with
            the best found parameters.
        """
        check_is_fitted(self)
        return self.best_estimator_.decision_function(X)

    @available_if(_search_estimator_has("transform"))
    def transform(self, X):
        """Call transform on the estimator with the best found parameters.

        Only available if the underlying estimator supports ``transform`` and
        ``refit=True``.

        Parameters
        ----------
        X : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

        Returns
        -------
        Xt : {ndarray, sparse matrix} of shape (n_samples, n_features)
            `X` transformed in the new space based on the estimator with
            the best found parameters.
        """
        check_is_fitted(self)
        return self.best_estimator_.transform(X)

    @available_if(_search_estimator_has("inverse_transform"))
    def inverse_transform(self, X=None, Xt=None):
        """Call inverse_transform on the estimator with the best found params.

        Only available if the underlying estimator implements
        ``inverse_transform`` and ``refit=True``.

        Parameters
        ----------
        X : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

        Xt : indexable, length n_samples
            Must fulfill the input assumptions of the
            underlying estimator.

            .. deprecated:: 1.5
                `Xt` was deprecated in 1.5 and will be removed in 1.7. Use `X` instead.

        Returns
        -------
        X : {ndarray, sparse matrix} of shape (n_samples, n_features)
            Result of the `inverse_transform` function for `Xt` based on the
            estimator with the best found parameters.
        """
        X = _deprecate_Xt_in_inverse_transform(X, Xt)
        check_is_fitted(self)
        return self.best_estimator_.inverse_transform(X)

    @property
    def n_features_in_(self):
        """Number of features seen during :term:`fit`.

        Only available when `refit=True`.
        """
        # For consistency with other estimators we raise a AttributeError so
        # that hasattr() fails if the search estimator isn't fitted.
        try:
            check_is_fitted(self)
        except NotFittedError as nfe:
            raise AttributeError(
                "{} object has no n_features_in_ attribute.".format(
                    self.__class__.__name__
                )
            ) from nfe

        return self.best_estimator_.n_features_in_

    @property
    def classes_(self):
        """Class labels.

        Only available when `refit=True` and the estimator is a classifier.
        """
        _search_estimator_has("classes_")(self)
        return self.best_estimator_.classes_

    def _run_search(self, evaluate_candidates):
        """Repeatedly calls `evaluate_candidates` to conduct a search.

        This method, implemented in sub-classes, makes it possible to
        customize the scheduling of evaluations: GridSearchCV and
        RandomizedSearchCV schedule evaluations for their whole parameter
        search space at once but other more sequential approaches are also
        possible: for instance is possible to iteratively schedule evaluations
        for new regions of the parameter search space based on previously
        collected evaluation results. This makes it possible to implement
        Bayesian optimization or more generally sequential model-based
        optimization by deriving from the BaseSearchCV abstract base class.
        For example, Successive Halving is implemented by calling
        `evaluate_candidates` multiples times (once per iteration of the SH
        process), each time passing a different set of candidates with `X`
        and `y` of increasing sizes.

        Parameters
        ----------
        evaluate_candidates : callable
            This callback accepts:
                - a list of candidates, where each candidate is a dict of
                  parameter settings.
                - an optional `cv` parameter which can be used to e.g.
                  evaluate candidates on different dataset splits, or
                  evaluate candidates on subsampled data (as done in the
                  SucessiveHaling estimators). By default, the original `cv`
                  parameter is used, and it is available as a private
                  `_checked_cv_orig` attribute.
                - an optional `more_results` dict. Each key will be added to
                  the `cv_results_` attribute. Values should be lists of
                  length `n_candidates`

            It returns a dict of all results so far, formatted like
            ``cv_results_``.

            Important note (relevant whether the default cv is used or not):
            in randomized splitters, and unless the random_state parameter of
            cv was set to an int, calling cv.split() multiple times will
            yield different splits. Since cv.split() is called in
            evaluate_candidates, this means that candidates will be evaluated
            on different splits each time evaluate_candidates is called. This
            might be a methodological issue depending on the search strategy
            that you're implementing. To prevent randomized splitters from
            being used, you may use _split._yields_constant_splits()

        Examples
        --------

        ::

            def _run_search(self, evaluate_candidates):
                'Try C=0.1 only if C=1 is better than C=10'
                all_results = evaluate_candidates([{'C': 1}, {'C': 10}])
                score = all_results['mean_test_score']
                if score[0] < score[1]:
                    evaluate_candidates([{'C': 0.1}])
        """
        raise NotImplementedError("_run_search not implemented.")

    def _check_refit_for_multimetric(self, scores):
        """Check `refit` is compatible with `scores` is valid"""
        multimetric_refit_msg = (
            "For multi-metric scoring, the parameter refit must be set to a "
            "scorer key or a callable to refit an estimator with the best "
            "parameter setting on the whole data and make the best_* "
            "attributes available for that metric. If this is not needed, "
            f"refit should be set to False explicitly. {self.refit!r} was "
            "passed."
        )

        valid_refit_dict = isinstance(self.refit, str) and self.refit in scores

        if (
            self.refit is not False
            and not valid_refit_dict
            and not callable(self.refit)
        ):
            raise ValueError(multimetric_refit_msg)

    @staticmethod
    def _select_best_index(refit, refit_metric, results):
        """Select index of the best combination of hyperparemeters."""
        if callable(refit):
            # If callable, refit is expected to return the index of the best
            # parameter set.
            best_index = refit(results)
            if not isinstance(best_index, numbers.Integral):
                raise TypeError("best_index_ returned is not an integer")
            if best_index < 0 or best_index >= len(results["params"]):
                raise IndexError("best_index_ index out of range")
        else:
            best_index = results[f"rank_test_{refit_metric}"].argmin()
        return best_index

    def _get_scorers(self):
        """Get the scorer(s) to be used.

        This is used in ``fit`` and ``get_metadata_routing``.

        Returns
        -------
        scorers, refit_metric
        """
        refit_metric = "score"

        if callable(self.scoring):
            scorers = self.scoring
        elif self.scoring is None or isinstance(self.scoring, str):
            scorers = check_scoring(self.estimator, self.scoring)
        else:
            scorers = _check_multimetric_scoring(self.estimator, self.scoring)
            self._check_refit_for_multimetric(scorers)
            refit_metric = self.refit
            scorers = _MultimetricScorer(
                scorers=scorers, raise_exc=(self.error_score == "raise")
            )

        return scorers, refit_metric

    def _get_routed_params_for_fit(self, params):
        """Get the parameters to be used for routing.

        This is a method instead of a snippet in ``fit`` since it's used twice,
        here in ``fit``, and in ``HalvingRandomSearchCV.fit``.
        """
        if _routing_enabled():
            routed_params = process_routing(self, "fit", **params)
        else:
            params = params.copy()
            groups = params.pop("groups", None)
            routed_params = Bunch(
                estimator=Bunch(fit=params),
                splitter=Bunch(split={"groups": groups}),
                scorer=Bunch(score={}),
            )
        return routed_params

    @_fit_context(
        # *SearchCV.estimator is not validated yet
        prefer_skip_nested_validation=False
    )
    def fit(self, X, y=None, **params):
        """Run fit with all sets of parameters.

        Parameters
        ----------

        X : array-like of shape (n_samples, n_features) or (n_samples, n_samples)
            Training vectors, where `n_samples` is the number of samples and
            `n_features` is the number of features. For precomputed kernel or
            distance matrix, the expected shape of X is (n_samples, n_samples).

        y : array-like of shape (n_samples, n_output) \
            or (n_samples,), default=None
            Target relative to X for classification or regression;
            None for unsupervised learning.

        **params : dict of str -> object
            Parameters passed to the ``fit`` method of the estimator, the scorer,
            and the CV splitter.

            If a fit parameter is an array-like whose length is equal to
            `num_samples` then it will be split by cross-validation along with
            `X` and `y`. For example, the :term:`sample_weight` parameter is
            split because `len(sample_weights) = len(X)`. However, this behavior
            does not apply to `groups` which is passed to the splitter configured
            via the `cv` parameter of the constructor. Thus, `groups` is used
            *to perform the split* and determines which samples are
            assigned to the each side of the a split.

        Returns
        -------
        self : object
            Instance of fitted estimator.
        """
        estimator = self.estimator
        scorers, refit_metric = self._get_scorers()

        X, y = indexable(X, y)
        params = _check_method_params(X, params=params)

        routed_params = self._get_routed_params_for_fit(params)

        cv_orig = check_cv(self.cv, y, classifier=is_classifier(estimator))
        n_splits = cv_orig.get_n_splits(X, y, **routed_params.splitter.split)

        base_estimator = clone(self.estimator)

        parallel = Parallel(n_jobs=self.n_jobs, pre_dispatch=self.pre_dispatch)

        fit_and_score_kwargs = dict(
            scorer=scorers,
            fit_params=routed_params.estimator.fit,
            score_params=routed_params.scorer.score,
            return_train_score=self.return_train_score,
            return_n_test_samples=True,
            return_times=True,
            return_parameters=False,
            error_score=self.error_score,
            verbose=self.verbose,
        )
        results = {}
        with parallel:
            all_candidate_params = []
            all_out = []
            all_more_results = defaultdict(list)

            def evaluate_candidates(candidate_params, cv=None, more_results=None):
                cv = cv or cv_orig
                candidate_params = list(candidate_params)
                n_candidates = len(candidate_params)

                if self.verbose > 0:
                    print(
                        "Fitting {0} folds for each of {1} candidates,"
                        " totalling {2} fits".format(
                            n_splits, n_candidates, n_candidates * n_splits
                        )
                    )

                out = parallel(
                    delayed(_fit_and_score)(
                        clone(base_estimator),
                        X,
                        y,
                        train=train,
                        test=test,
                        parameters=parameters,
                        split_progress=(split_idx, n_splits),
                        candidate_progress=(cand_idx, n_candidates),
                        **fit_and_score_kwargs,
                    )
                    for (cand_idx, parameters), (split_idx, (train, test)) in product(
                        enumerate(candidate_params),
                        enumerate(cv.split(X, y, **routed_params.splitter.split)),
                    )
                )

                if len(out) < 1:
                    raise ValueError(
                        "No fits were performed. "
                        "Was the CV iterator empty? "
                        "Were there no candidates?"
                    )
                elif len(out) != n_candidates * n_splits:
                    raise ValueError(
                        "cv.split and cv.get_n_splits returned "
                        "inconsistent results. Expected {} "
                        "splits, got {}".format(n_splits, len(out) // n_candidates)
                    )

                _warn_or_raise_about_fit_failures(out, self.error_score)

                # For callable self.scoring, the return type is only know after
                # calling. If the return type is a dictionary, the error scores
                # can now be inserted with the correct key. The type checking
                # of out will be done in `_insert_error_scores`.
                if callable(self.scoring):
                    _insert_error_scores(out, self.error_score)

                all_candidate_params.extend(candidate_params)
                all_out.extend(out)

                if more_results is not None:
                    for key, value in more_results.items():
                        all_more_results[key].extend(value)

                nonlocal results
                results = self._format_results(
                    all_candidate_params, n_splits, all_out, all_more_results
                )

                return results

            self._run_search(evaluate_candidates)

            # multimetric is determined here because in the case of a callable
            # self.scoring the return type is only known after calling
            first_test_score = all_out[0]["test_scores"]
            self.multimetric_ = isinstance(first_test_score, dict)

            # check refit_metric now for a callable scorer that is multimetric
            if callable(self.scoring) and self.multimetric_:
                self._check_refit_for_multimetric(first_test_score)
                refit_metric = self.refit

        # For multi-metric evaluation, store the best_index_, best_params_ and
        # best_score_ iff refit is one of the scorer names
        # In single metric evaluation, refit_metric is "score"
        if self.refit or not self.multimetric_:
            self.best_index_ = self._select_best_index(
                self.refit, refit_metric, results
            )
            if not callable(self.refit):
                # With a non-custom callable, we can select the best score
                # based on the best index
                self.best_score_ = results[f"mean_test_{refit_metric}"][
                    self.best_index_
                ]
            self.best_params_ = results["params"][self.best_index_]

        if self.refit:
            # here we clone the estimator as well as the parameters, since
            # sometimes the parameters themselves might be estimators, e.g.
            # when we search over different estimators in a pipeline.
            # ref: https://github.com/scikit-learn/scikit-learn/pull/26786
            self.best_estimator_ = clone(base_estimator).set_params(
                **clone(self.best_params_, safe=False)
            )

            refit_start_time = time.time()
            if y is not None:
                self.best_estimator_.fit(X, y, **routed_params.estimator.fit)
            else:
                self.best_estimator_.fit(X, **routed_params.estimator.fit)
            refit_end_time = time.time()
            self.refit_time_ = refit_end_time - refit_start_time

            if hasattr(self.best_estimator_, "feature_names_in_"):
                self.feature_names_in_ = self.best_estimator_.feature_names_in_

        # Store the only scorer not as a dict for single metric evaluation
        if isinstance(scorers, _MultimetricScorer):
            self.scorer_ = scorers._scorers
        else:
            self.scorer_ = scorers

        self.cv_results_ = results
        self.n_splits_ = n_splits

        return self

    def _format_results(self, candidate_params, n_splits, out, more_results=None):
        n_candidates = len(candidate_params)
        out = _aggregate_score_dicts(out)

        results = dict(more_results or {})
        for key, val in results.items():
            # each value is a list (as per evaluate_candidate's convention)
            # we convert it to an array for consistency with the other keys
            results[key] = np.asarray(val)

        def _store(key_name, array, weights=None, splits=False, rank=False):
            """A small helper to store the scores/times to the cv_results_"""
            # When iterated first by splits, then by parameters
            # We want `array` to have `n_candidates` rows and `n_splits` cols.
            array = np.array(array, dtype=np.float64).reshape(n_candidates, n_splits)
            if splits:
                for split_idx in range(n_splits):
                    # Uses closure to alter the results
                    results["split%d_%s" % (split_idx, key_name)] = array[:, split_idx]

            array_means = np.average(array, axis=1, weights=weights)
            results["mean_%s" % key_name] = array_means

            if key_name.startswith(("train_", "test_")) and np.any(
                ~np.isfinite(array_means)
            ):
                warnings.warn(
                    (
                        f"One or more of the {key_name.split('_')[0]} scores "
                        f"are non-finite: {array_means}"
                    ),
                    category=UserWarning,
                )

            # Weighted std is not directly available in numpy
            array_stds = np.sqrt(
                np.average(
                    (array - array_means[:, np.newaxis]) ** 2, axis=1, weights=weights
                )
            )
            results["std_%s" % key_name] = array_stds

            if rank:
                # When the fit/scoring fails `array_means` contains NaNs, we
                # will exclude them from the ranking process and consider them
                # as tied with the worst performers.
                if np.isnan(array_means).all():
                    # All fit/scoring routines failed.
                    rank_result = np.ones_like(array_means, dtype=np.int32)
                else:
                    min_array_means = np.nanmin(array_means) - 1
                    array_means = np.nan_to_num(array_means, nan=min_array_means)
                    rank_result = rankdata(-array_means, method="min").astype(
                        np.int32, copy=False
                    )
                results["rank_%s" % key_name] = rank_result

        _store("fit_time", out["fit_time"])
        _store("score_time", out["score_time"])
        # Store a list of param dicts at the key 'params'
        for param, ma in _yield_masked_array_for_each_param(candidate_params):
            results[param] = ma
        results["params"] = candidate_params

        test_scores_dict = _normalize_score_results(out["test_scores"])
        if self.return_train_score:
            train_scores_dict = _normalize_score_results(out["train_scores"])

        for scorer_name in test_scores_dict:
            # Computed the (weighted) mean and std for test scores alone
            _store(
                "test_%s" % scorer_name,
                test_scores_dict[scorer_name],
                splits=True,
                rank=True,
                weights=None,
            )
            if self.return_train_score:
                _store(
                    "train_%s" % scorer_name,
                    train_scores_dict[scorer_name],
                    splits=True,
                )

        return results

    def get_metadata_routing(self):
        """Get metadata routing of this object.

        Please check :ref:`User Guide <metadata_routing>` on how the routing
        mechanism works.

        .. versionadded:: 1.4

        Returns
        -------
        routing : MetadataRouter
            A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
            routing information.
        """
        router = MetadataRouter(owner=self.__class__.__name__)
        router.add(
            estimator=self.estimator,
            method_mapping=MethodMapping().add(caller="fit", callee="fit"),
        )

        scorer, _ = self._get_scorers()
        router.add(
            scorer=scorer,
            method_mapping=MethodMapping()
            .add(caller="score", callee="score")
            .add(caller="fit", callee="score"),
        )
        router.add(
            splitter=self.cv,
            method_mapping=MethodMapping().add(caller="fit", callee="split"),
        )
        return router

    def _sk_visual_block_(self):
        if hasattr(self, "best_estimator_"):
            key, estimator = "best_estimator_", self.best_estimator_
        else:
            key, estimator = "estimator", self.estimator

        return _VisualBlock(
            "parallel",
            [estimator],
            names=[f"{key}: {estimator.__class__.__name__}"],
            name_details=[str(estimator)],
        )


class GridSearchCV(BaseSearchCV):
    """Exhaustive search over specified parameter values for an estimator.

    Important members are fit, predict.

    GridSearchCV implements a "fit" and a "score" method.
    It also implements "score_samples", "predict", "predict_proba",
    "decision_function", "transform" and "inverse_transform" if they are
    implemented in the estimator used.

    The parameters of the estimator used to apply these methods are optimized
    by cross-validated grid-search over a parameter grid.

    Read more in the :ref:`User Guide <grid_search>`.

    Parameters
    ----------
    estimator : estimator object
        This is assumed to implement the scikit-learn estimator interface.
        Either estimator needs to provide a ``score`` function,
        or ``scoring`` must be passed.

    param_grid : dict or list of dictionaries
        Dictionary with parameters names (`str`) as keys and lists of
        parameter settings to try as values, or a list of such
        dictionaries, in which case the grids spanned by each dictionary
        in the list are explored. This enables searching over any sequence
        of parameter settings.

    scoring : str, callable, list, tuple or dict, default=None
        Strategy to evaluate the performance of the cross-validated model on
        the test set.

        If `scoring` represents a single score, one can use:

        - a single string (see :ref:`scoring_parameter`);
        - a callable (see :ref:`scoring_callable`) that returns a single value.

        If `scoring` represents multiple scores, one can use:

        - a list or tuple of unique strings;
        - a callable returning a dictionary where the keys are the metric
          names and the values are the metric scores;
        - a dictionary with metric names as keys and callables as values.

        See :ref:`multimetric_grid_search` for an example.

    n_jobs : int, default=None
        Number of jobs to run in parallel.
        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
        for more details.

        .. versionchanged:: v0.20
           `n_jobs` default changed from 1 to None

    refit : bool, str, or callable, default=True
        Refit an estimator using the best found parameters on the whole
        dataset.

        For multiple metric evaluation, this needs to be a `str` denoting the
        scorer that would be used to find the best parameters for refitting
        the estimator at the end.

        Where there are considerations other than maximum score in
        choosing a best estimator, ``refit`` can be set to a function which
        returns the selected ``best_index_`` given ``cv_results_``. In that
        case, the ``best_estimator_`` and ``best_params_`` will be set
        according to the returned ``best_index_`` while the ``best_score_``
        attribute will not be available.

        The refitted estimator is made available at the ``best_estimator_``
        attribute and permits using ``predict`` directly on this
        ``GridSearchCV`` instance.

        Also for multiple metric evaluation, the attributes ``best_index_``,
        ``best_score_`` and ``best_params_`` will only be available if
        ``refit`` is set and all of them will be determined w.r.t this specific
        scorer.

        See ``scoring`` parameter to know more about multiple metric
        evaluation.

        See :ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_digits.py`
        to see how to design a custom selection strategy using a callable
        via `refit`.

        .. versionchanged:: 0.20
            Support for callable added.

    cv : int, cross-validation generator or an iterable, default=None
        Determines the cross-validation splitting strategy.
        Possible inputs for cv are:

        - None, to use the default 5-fold cross validation,
        - integer, to specify the number of folds in a `(Stratified)KFold`,
        - :term:`CV splitter`,
        - An iterable yielding (train, test) splits as arrays of indices.

        For integer/None inputs, if the estimator is a classifier and ``y`` is
        either binary or multiclass, :class:`StratifiedKFold` is used. In all
        other cases, :class:`KFold` is used. These splitters are instantiated
        with `shuffle=False` so the splits will be the same across calls.

        Refer :ref:`User Guide <cross_validation>` for the various
        cross-validation strategies that can be used here.

        .. versionchanged:: 0.22
            ``cv`` default value if None changed from 3-fold to 5-fold.

    verbose : int
        Controls the verbosity: the higher, the more messages.

        - >1 : the computation time for each fold and parameter candidate is
          displayed;
        - >2 : the score is also displayed;
        - >3 : the fold and candidate parameter indexes are also displayed
          together with the starting time of the computation.

    pre_dispatch : int, or str, default='2*n_jobs'
        Controls the number of jobs that get dispatched during parallel
        execution. Reducing this number can be useful to avoid an
        explosion of memory consumption when more jobs get dispatched
        than CPUs can process. This parameter can be:

        - None, in which case all the jobs are immediately created and spawned. Use
          this for lightweight and fast-running jobs, to avoid delays due to on-demand
          spawning of the jobs
        - An int, giving the exact number of total jobs that are spawned
        - A str, giving an expression as a function of n_jobs, as in '2*n_jobs'

    error_score : 'raise' or numeric, default=np.nan
        Value to assign to the score if an error occurs in estimator fitting.
        If set to 'raise', the error is raised. If a numeric value is given,
        FitFailedWarning is raised. This parameter does not affect the refit
        step, which will always raise the error.

    return_train_score : bool, default=False
        If ``False``, the ``cv_results_`` attribute will not include training
        scores.
        Computing training scores is used to get insights on how different
        parameter settings impact the overfitting/underfitting trade-off.
        However computing the scores on the training set can be computationally
        expensive and is not strictly required to select the parameters that
        yield the best generalization performance.

        .. versionadded:: 0.19

        .. versionchanged:: 0.21
            Default value was changed from ``True`` to ``False``

    Attributes
    ----------
    cv_results_ : dict of numpy (masked) ndarrays
        A dict with keys as column headers and values as columns, that can be
        imported into a pandas ``DataFrame``.

        For instance the below given table

        +------------+-----------+------------+-----------------+---+---------+
        |param_kernel|param_gamma|param_degree|split0_test_score|...|rank_t...|
        +============+===========+============+=================+===+=========+
        |  'poly'    |     --    |      2     |       0.80      |...|    2    |
        +------------+-----------+------------+-----------------+---+---------+
        |  'poly'    |     --    |      3     |       0.70      |...|    4    |
        +------------+-----------+------------+-----------------+---+---------+
        |  'rbf'     |     0.1   |     --     |       0.80      |...|    3    |
        +------------+-----------+------------+-----------------+---+---------+
        |  'rbf'     |     0.2   |     --     |       0.93      |...|    1    |
        +------------+-----------+------------+-----------------+---+---------+

        will be represented by a ``cv_results_`` dict of::

            {
            'param_kernel': masked_array(data = ['poly', 'poly', 'rbf', 'rbf'],
                                         mask = [False False False False]...)
            'param_gamma': masked_array(data = [-- -- 0.1 0.2],
                                        mask = [ True  True False False]...),
            'param_degree': masked_array(data = [2.0 3.0 -- --],
                                         mask = [False False  True  True]...),
            'split0_test_score'  : [0.80, 0.70, 0.80, 0.93],
            'split1_test_score'  : [0.82, 0.50, 0.70, 0.78],
            'mean_test_score'    : [0.81, 0.60, 0.75, 0.85],
            'std_test_score'     : [0.01, 0.10, 0.05, 0.08],
            'rank_test_score'    : [2, 4, 3, 1],
            'split0_train_score' : [0.80, 0.92, 0.70, 0.93],
            'split1_train_score' : [0.82, 0.55, 0.70, 0.87],
            'mean_train_score'   : [0.81, 0.74, 0.70, 0.90],
            'std_train_score'    : [0.01, 0.19, 0.00, 0.03],
            'mean_fit_time'      : [0.73, 0.63, 0.43, 0.49],
            'std_fit_time'       : [0.01, 0.02, 0.01, 0.01],
            'mean_score_time'    : [0.01, 0.06, 0.04, 0.04],
            'std_score_time'     : [0.00, 0.00, 0.00, 0.01],
            'params'             : [{'kernel': 'poly', 'degree': 2}, ...],
            }

        NOTE

        The key ``'params'`` is used to store a list of parameter
        settings dicts for all the parameter candidates.

        The ``mean_fit_time``, ``std_fit_time``, ``mean_score_time`` and
        ``std_score_time`` are all in seconds.

        For multi-metric evaluation, the scores for all the scorers are
        available in the ``cv_results_`` dict at the keys ending with that
        scorer's name (``'_<scorer_name>'``) instead of ``'_score'`` shown
        above. ('split0_test_precision', 'mean_train_precision' etc.)

    best_estimator_ : estimator
        Estimator that was chosen by the search, i.e. estimator
        which gave highest score (or smallest loss if specified)
        on the left out data. Not available if ``refit=False``.

        See ``refit`` parameter for more information on allowed values.

    best_score_ : float
        Mean cross-validated score of the best_estimator

        For multi-metric evaluation, this is present only if ``refit`` is
        specified.

        This attribute is not available if ``refit`` is a function.

    best_params_ : dict
        Parameter setting that gave the best results on the hold out data.

        For multi-metric evaluation, this is present only if ``refit`` is
        specified.

    best_index_ : int
        The index (of the ``cv_results_`` arrays) which corresponds to the best
        candidate parameter setting.

        The dict at ``search.cv_results_['params'][search.best_index_]`` gives
        the parameter setting for the best model, that gives the highest
        mean score (``search.best_score_``).

        For multi-metric evaluation, this is present only if ``refit`` is
        specified.

    scorer_ : function or a dict
        Scorer function used on the held out data to choose the best
        parameters for the model.

        For multi-metric evaluation, this attribute holds the validated
        ``scoring`` dict which maps the scorer key to the scorer callable.

    n_splits_ : int
        The number of cross-validation splits (folds/iterations).

    refit_time_ : float
        Seconds used for refitting the best model on the whole dataset.

        This is present only if ``refit`` is not False.

        .. versionadded:: 0.20

    multimetric_ : bool
        Whether or not the scorers compute several metrics.

    classes_ : ndarray of shape (n_classes,)
        The classes labels. This is present only if ``refit`` is specified and
        the underlying estimator is a classifier.

    n_features_in_ : int
        Number of features seen during :term:`fit`. Only defined if
        `best_estimator_` is defined (see the documentation for the `refit`
        parameter for more details) and that `best_estimator_` exposes
        `n_features_in_` when fit.

        .. versionadded:: 0.24

    feature_names_in_ : ndarray of shape (`n_features_in_`,)
        Names of features seen during :term:`fit`. Only defined if
        `best_estimator_` is defined (see the documentation for the `refit`
        parameter for more details) and that `best_estimator_` exposes
        `feature_names_in_` when fit.

        .. versionadded:: 1.0

    See Also
    --------
    ParameterGrid : Generates all the combinations of a hyperparameter grid.
    train_test_split : Utility function to split the data into a development
        set usable for fitting a GridSearchCV instance and an evaluation set
        for its final evaluation.
    sklearn.metrics.make_scorer : Make a scorer from a performance metric or
        loss function.

    Notes
    -----
    The parameters selected are those that maximize the score of the left out
    data, unless an explicit score is passed in which case it is used instead.

    If `n_jobs` was set to a value higher than one, the data is copied for each
    point in the grid (and not `n_jobs` times). This is done for efficiency
    reasons if individual jobs take very little time, but may raise errors if
    the dataset is large and not enough memory is available.  A workaround in
    this case is to set `pre_dispatch`. Then, the memory is copied only
    `pre_dispatch` many times. A reasonable value for `pre_dispatch` is `2 *
    n_jobs`.

    Examples
    --------
    >>> from sklearn import svm, datasets
    >>> from sklearn.model_selection import GridSearchCV
    >>> iris = datasets.load_iris()
    >>> parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}
    >>> svc = svm.SVC()
    >>> clf = GridSearchCV(svc, parameters)
    >>> clf.fit(iris.data, iris.target)
    GridSearchCV(estimator=SVC(),
                 param_grid={'C': [1, 10], 'kernel': ('linear', 'rbf')})
    >>> sorted(clf.cv_results_.keys())
    ['mean_fit_time', 'mean_score_time', 'mean_test_score',...
     'param_C', 'param_kernel', 'params',...
     'rank_test_score', 'split0_test_score',...
     'split2_test_score', ...
     'std_fit_time', 'std_score_time', 'std_test_score']
    """

    _parameter_constraints: dict = {
        **BaseSearchCV._parameter_constraints,
        "param_grid": [dict, list],
    }

    def __init__(
        self,
        estimator,
        param_grid,
        *,
        scoring=None,
        n_jobs=None,
        refit=True,
        cv=None,
        verbose=0,
        pre_dispatch="2*n_jobs",
        error_score=np.nan,
        return_train_score=False,
    ):
        super().__init__(
            estimator=estimator,
            scoring=scoring,
            n_jobs=n_jobs,
            refit=refit,
            cv=cv,
            verbose=verbose,
            pre_dispatch=pre_dispatch,
            error_score=error_score,
            return_train_score=return_train_score,
        )
        self.param_grid = param_grid

    def _run_search(self, evaluate_candidates):
        """Search all candidates in param_grid"""
        evaluate_candidates(ParameterGrid(self.param_grid))


class RandomizedSearchCV(BaseSearchCV):
    """Randomized search on hyper parameters.

    RandomizedSearchCV implements a "fit" and a "score" method.
    It also implements "score_samples", "predict", "predict_proba",
    "decision_function", "transform" and "inverse_transform" if they are
    implemented in the estimator used.

    The parameters of the estimator used to apply these methods are optimized
    by cross-validated search over parameter settings.

    In contrast to GridSearchCV, not all parameter values are tried out, but
    rather a fixed number of parameter settings is sampled from the specified
    distributions. The number of parameter settings that are tried is
    given by n_iter.

    If all parameters are presented as a list,
    sampling without replacement is performed. If at least one parameter
    is given as a distribution, sampling with replacement is used.
    It is highly recommended to use continuous distributions for continuous
    parameters.

    Read more in the :ref:`User Guide <randomized_parameter_search>`.

    .. versionadded:: 0.14

    Parameters
    ----------
    estimator : estimator object
        An object of that type is instantiated for each grid point.
        This is assumed to implement the scikit-learn estimator interface.
        Either estimator needs to provide a ``score`` function,
        or ``scoring`` must be passed.

    param_distributions : dict or list of dicts
        Dictionary with parameters names (`str`) as keys and distributions
        or lists of parameters to try. Distributions must provide a ``rvs``
        method for sampling (such as those from scipy.stats.distributions).
        If a list is given, it is sampled uniformly.
        If a list of dicts is given, first a dict is sampled uniformly, and
        then a parameter is sampled using that dict as above.

    n_iter : int, default=10
        Number of parameter settings that are sampled. n_iter trades
        off runtime vs quality of the solution.

    scoring : str, callable, list, tuple or dict, default=None
        Strategy to evaluate the performance of the cross-validated model on
        the test set.

        If `scoring` represents a single score, one can use:

        - a single string (see :ref:`scoring_parameter`);
        - a callable (see :ref:`scoring_callable`) that returns a single value.

        If `scoring` represents multiple scores, one can use:

        - a list or tuple of unique strings;
        - a callable returning a dictionary where the keys are the metric
          names and the values are the metric scores;
        - a dictionary with metric names as keys and callables as values.

        See :ref:`multimetric_grid_search` for an example.

        If None, the estimator's score method is used.

    n_jobs : int, default=None
        Number of jobs to run in parallel.
        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
        for more details.

        .. versionchanged:: v0.20
           `n_jobs` default changed from 1 to None

    refit : bool, str, or callable, default=True
        Refit an estimator using the best found parameters on the whole
        dataset.

        For multiple metric evaluation, this needs to be a `str` denoting the
        scorer that would be used to find the best parameters for refitting
        the estimator at the end.

        Where there are considerations other than maximum score in
        choosing a best estimator, ``refit`` can be set to a function which
        returns the selected ``best_index_`` given the ``cv_results_``. In that
        case, the ``best_estimator_`` and ``best_params_`` will be set
        according to the returned ``best_index_`` while the ``best_score_``
        attribute will not be available.

        The refitted estimator is made available at the ``best_estimator_``
        attribute and permits using ``predict`` directly on this
        ``RandomizedSearchCV`` instance.

        Also for multiple metric evaluation, the attributes ``best_index_``,
        ``best_score_`` and ``best_params_`` will only be available if
        ``refit`` is set and all of them will be determined w.r.t this specific
        scorer.

        See ``scoring`` parameter to know more about multiple metric
        evaluation.

        .. versionchanged:: 0.20
            Support for callable added.

    cv : int, cross-validation generator or an iterable, default=None
        Determines the cross-validation splitting strategy.
        Possible inputs for cv are:

        - None, to use the default 5-fold cross validation,
        - integer, to specify the number of folds in a `(Stratified)KFold`,
        - :term:`CV splitter`,
        - An iterable yielding (train, test) splits as arrays of indices.

        For integer/None inputs, if the estimator is a classifier and ``y`` is
        either binary or multiclass, :class:`StratifiedKFold` is used. In all
        other cases, :class:`KFold` is used. These splitters are instantiated
        with `shuffle=False` so the splits will be the same across calls.

        Refer :ref:`User Guide <cross_validation>` for the various
        cross-validation strategies that can be used here.

        .. versionchanged:: 0.22
            ``cv`` default value if None changed from 3-fold to 5-fold.

    verbose : int
        Controls the verbosity: the higher, the more messages.

        - >1 : the computation time for each fold and parameter candidate is
          displayed;
        - >2 : the score is also displayed;
        - >3 : the fold and candidate parameter indexes are also displayed
          together with the starting time of the computation.

    pre_dispatch : int, or str, default='2*n_jobs'
        Controls the number of jobs that get dispatched during parallel
        execution. Reducing this number can be useful to avoid an
        explosion of memory consumption when more jobs get dispatched
        than CPUs can process. This parameter can be:

        - None, in which case all the jobs are immediately created and spawned. Use
          this for lightweight and fast-running jobs, to avoid delays due to on-demand
          spawning of the jobs
        - An int, giving the exact number of total jobs that are spawned
        - A str, giving an expression as a function of n_jobs, as in '2*n_jobs'

    random_state : int, RandomState instance or None, default=None
        Pseudo random number generator state used for random uniform sampling
        from lists of possible values instead of scipy.stats distributions.
        Pass an int for reproducible output across multiple
        function calls.
        See :term:`Glossary <random_state>`.

    error_score : 'raise' or numeric, default=np.nan
        Value to assign to the score if an error occurs in estimator fitting.
        If set to 'raise', the error is raised. If a numeric value is given,
        FitFailedWarning is raised. This parameter does not affect the refit
        step, which will always raise the error.

    return_train_score : bool, default=False
        If ``False``, the ``cv_results_`` attribute will not include training
        scores.
        Computing training scores is used to get insights on how different
        parameter settings impact the overfitting/underfitting trade-off.
        However computing the scores on the training set can be computationally
        expensive and is not strictly required to select the parameters that
        yield the best generalization performance.

        .. versionadded:: 0.19

        .. versionchanged:: 0.21
            Default value was changed from ``True`` to ``False``

    Attributes
    ----------
    cv_results_ : dict of numpy (masked) ndarrays
        A dict with keys as column headers and values as columns, that can be
        imported into a pandas ``DataFrame``.

        For instance the below given table

        +--------------+-------------+-------------------+---+---------------+
        | param_kernel | param_gamma | split0_test_score |...|rank_test_score|
        +==============+=============+===================+===+===============+
        |    'rbf'     |     0.1     |       0.80        |...|       1       |
        +--------------+-------------+-------------------+---+---------------+
        |    'rbf'     |     0.2     |       0.84        |...|       3       |
        +--------------+-------------+-------------------+---+---------------+
        |    'rbf'     |     0.3     |       0.70        |...|       2       |
        +--------------+-------------+-------------------+---+---------------+

        will be represented by a ``cv_results_`` dict of::

            {
            'param_kernel' : masked_array(data = ['rbf', 'rbf', 'rbf'],
                                          mask = False),
            'param_gamma'  : masked_array(data = [0.1 0.2 0.3], mask = False),
            'split0_test_score'  : [0.80, 0.84, 0.70],
            'split1_test_score'  : [0.82, 0.50, 0.70],
            'mean_test_score'    : [0.81, 0.67, 0.70],
            'std_test_score'     : [0.01, 0.24, 0.00],
            'rank_test_score'    : [1, 3, 2],
            'split0_train_score' : [0.80, 0.92, 0.70],
            'split1_train_score' : [0.82, 0.55, 0.70],
            'mean_train_score'   : [0.81, 0.74, 0.70],
            'std_train_score'    : [0.01, 0.19, 0.00],
            'mean_fit_time'      : [0.73, 0.63, 0.43],
            'std_fit_time'       : [0.01, 0.02, 0.01],
            'mean_score_time'    : [0.01, 0.06, 0.04],
            'std_score_time'     : [0.00, 0.00, 0.00],
            'params'             : [{'kernel' : 'rbf', 'gamma' : 0.1}, ...],
            }

        NOTE

        The key ``'params'`` is used to store a list of parameter
        settings dicts for all the parameter candidates.

        The ``mean_fit_time``, ``std_fit_time``, ``mean_score_time`` and
        ``std_score_time`` are all in seconds.

        For multi-metric evaluation, the scores for all the scorers are
        available in the ``cv_results_`` dict at the keys ending with that
        scorer's name (``'_<scorer_name>'``) instead of ``'_score'`` shown
        above. ('split0_test_precision', 'mean_train_precision' etc.)

    best_estimator_ : estimator
        Estimator that was chosen by the search, i.e. estimator
        which gave highest score (or smallest loss if specified)
        on the left out data. Not available if ``refit=False``.

        For multi-metric evaluation, this attribute is present only if
        ``refit`` is specified.

        See ``refit`` parameter for more information on allowed values.

    best_score_ : float
        Mean cross-validated score of the best_estimator.

        For multi-metric evaluation, this is not available if ``refit`` is
        ``False``. See ``refit`` parameter for more information.

        This attribute is not available if ``refit`` is a function.

    best_params_ : dict
        Parameter setting that gave the best results on the hold out data.

        For multi-metric evaluation, this is not available if ``refit`` is
        ``False``. See ``refit`` parameter for more information.

    best_index_ : int
        The index (of the ``cv_results_`` arrays) which corresponds to the best
        candidate parameter setting.

        The dict at ``search.cv_results_['params'][search.best_index_]`` gives
        the parameter setting for the best model, that gives the highest
        mean score (``search.best_score_``).

        For multi-metric evaluation, this is not available if ``refit`` is
        ``False``. See ``refit`` parameter for more information.

    scorer_ : function or a dict
        Scorer function used on the held out data to choose the best
        parameters for the model.

        For multi-metric evaluation, this attribute holds the validated
        ``scoring`` dict which maps the scorer key to the scorer callable.

    n_splits_ : int
        The number of cross-validation splits (folds/iterations).

    refit_time_ : float
        Seconds used for refitting the best model on the whole dataset.

        This is present only if ``refit`` is not False.

        .. versionadded:: 0.20

    multimetric_ : bool
        Whether or not the scorers compute several metrics.

    classes_ : ndarray of shape (n_classes,)
        The classes labels. This is present only if ``refit`` is specified and
        the underlying estimator is a classifier.

    n_features_in_ : int
        Number of features seen during :term:`fit`. Only defined if
        `best_estimator_` is defined (see the documentation for the `refit`
        parameter for more details) and that `best_estimator_` exposes
        `n_features_in_` when fit.

        .. versionadded:: 0.24

    feature_names_in_ : ndarray of shape (`n_features_in_`,)
        Names of features seen during :term:`fit`. Only defined if
        `best_estimator_` is defined (see the documentation for the `refit`
        parameter for more details) and that `best_estimator_` exposes
        `feature_names_in_` when fit.

        .. versionadded:: 1.0

    See Also
    --------
    GridSearchCV : Does exhaustive search over a grid of parameters.
    ParameterSampler : A generator over parameter settings, constructed from
        param_distributions.

    Notes
    -----
    The parameters selected are those that maximize the score of the held-out
    data, according to the scoring parameter.

    If `n_jobs` was set to a value higher than one, the data is copied for each
    parameter setting(and not `n_jobs` times). This is done for efficiency
    reasons if individual jobs take very little time, but may raise errors if
    the dataset is large and not enough memory is available.  A workaround in
    this case is to set `pre_dispatch`. Then, the memory is copied only
    `pre_dispatch` many times. A reasonable value for `pre_dispatch` is `2 *
    n_jobs`.

    Examples
    --------
    >>> from sklearn.datasets import load_iris
    >>> from sklearn.linear_model import LogisticRegression
    >>> from sklearn.model_selection import RandomizedSearchCV
    >>> from scipy.stats import uniform
    >>> iris = load_iris()
    >>> logistic = LogisticRegression(solver='saga', tol=1e-2, max_iter=200,
    ...                               random_state=0)
    >>> distributions = dict(C=uniform(loc=0, scale=4),
    ...                      penalty=['l2', 'l1'])
    >>> clf = RandomizedSearchCV(logistic, distributions, random_state=0)
    >>> search = clf.fit(iris.data, iris.target)
    >>> search.best_params_
    {'C': np.float64(2...), 'penalty': 'l1'}
    """

    _parameter_constraints: dict = {
        **BaseSearchCV._parameter_constraints,
        "param_distributions": [dict, list],
        "n_iter": [Interval(numbers.Integral, 1, None, closed="left")],
        "random_state": ["random_state"],
    }

    def __init__(
        self,
        estimator,
        param_distributions,
        *,
        n_iter=10,
        scoring=None,
        n_jobs=None,
        refit=True,
        cv=None,
        verbose=0,
        pre_dispatch="2*n_jobs",
        random_state=None,
        error_score=np.nan,
        return_train_score=False,
    ):
        self.param_distributions = param_distributions
        self.n_iter = n_iter
        self.random_state = random_state
        super().__init__(
            estimator=estimator,
            scoring=scoring,
            n_jobs=n_jobs,
            refit=refit,
            cv=cv,
            verbose=verbose,
            pre_dispatch=pre_dispatch,
            error_score=error_score,
            return_train_score=return_train_score,
        )

    def _run_search(self, evaluate_candidates):
        """Search n_iter candidates from param_distributions"""
        evaluate_candidates(
            ParameterSampler(
                self.param_distributions, self.n_iter, random_state=self.random_state
            )
        )