下面，我有以下数据集（以制表符分隔为可重现的示例）。我正在使用dplyr函数集将四个列添加到我的数据框中。如果组1）{ID，2）gene和3）gene + {{ 1}}。我或多或少都得到了最后两个，但是由于某种原因我无法得到第一个，如果观察到的是其exon组中的最后一个，则将其标记。
我的代码为2）ID和3）gene + gene中的最后观察生成标志：
exon对于1）df2 <- df %>%
dplyr::group_by(gene) %>%
dplyr::mutate(lastObsFlagG = ifelse(is.na(replace(gene, n(), 1)),1,0)) %>%
ungroup %>%
dplyr::group_by(gene,exon) %>%
dplyr::mutate(lastObsFlagGE = ifelse(is.na(replace(gene, n(), 1)),1,0)) %>%
data.frame()
，我已经尝试
ID，但这在最后一次观察中没有给出值1。
数据集
dplyr::group_by(ID) %>%
dplyr::mutate(lastObsFlagID = ifelse(row_number()==1, "1", "0"))
更新
列"ID" "gene" "exon" "mutation"
"TCGA-AN-A046" "OR4F5" "E1" 69767
"TCGA-A2-A0CP" "SAMD11" "E2" 925952
"TCGA-A8-A08H" "NOC2L" "E5" 956126
"TCGA-GM-A2DM" "NOC2L" "E4" 956911
"TCGA-GM-A2DM" "NOC2L" "E4" 956912
"TCGA-D8-A1XM" "KLHL17" "E3" 961658
"TCGA-BH-A18G" "KLHL17" "E5" 962441
"TCGA-3C-AALI" "KLHL17" "E8" 963353
"TCGA-AC-A62Y" "KLHL17" "E9" 964004
"TCGA-AR-A2LE" "PLEKHN1" "E1" 966556
"TCGA-E2-A14N" "PLEKHN1" "E5" 970728
"TCGA-AO-A0J4" "PLEKHN1" "E12" 973506
"TCGA-D8-A1J9" "HES4" "E3" 999551
"TCGA-EW-A1PH" "ISG15" "E2" 1014276
"TCGA-A2-A0T0" "AGRN" "E2" 1022338
"TCGA-GM-A2DD" "AGRN" "E3" 1035303
"TCGA-5L-AAT1" "AGRN" "E4" 1040690
"TCGA-OL-A5RW" "AGRN" "E8" 1043314
"TCGA-D8-A27M" "AGRN" "E25" 1049355
"TCGA-AR-A1AI" "AGRN" "E29" 1050430
"TCGA-5L-AAT0" "AGRN" "E36" 1055374
"TCGA-5L-AAT0" "AGRN" "E36" 1055376
"TCGA-C8-A8HP" "AGRN" "E36" 1055442
"TCGA-A7-A4SD" "TTLL10" "E13" 1184971
"TCGA-BH-A1F0" "SDF4" "E4" 1223283
"TCGA-AO-A128" "SDF4" "E4" 1223330
"TCGA-E9-A1R0" "SDF4" "E2" 1228592
"TCGA-A2-A04P" "UBE2J2" "E7" 1255246
"TCGA-C8-A274" "UBE2J2" "E7" 1255342
"TCGA-5L-AAT1" "SCNN1D" "E1" 1281422
"TCGA-AO-A128" "SCNN1D" "E6" 1287116
"TCGA-E2-A15R" "SCNN1D" "E7" 1287596
"TCGA-AC-A62V" "SCNN1D" "E11" 1290543
"TCGA-BH-A18V" "ACAP3" "E22" 1294187
"TCGA-A7-A6VX" "ACAP3" "E6" 1300640
"TCGA-GM-A2DB" "ACAP3" "E3" 1303170
"TCGA-EW-A1IY" "ACAP3" "E3" 1303176
"TCGA-D8-A1XQ" "CPSF3L" "E9" 1313879
"TCGA-5L-AAT1" "CPSF3L" "E9" 1313888
"TCGA-C8-A26Y" "CPSF3L" "E7" 1314919
"TCGA-D8-A1XK" "CPSF3L" "E2" 1321057
"TCGA-AO-A128" "TAS1R3" "E2" 1331863
"TCGA-A8-A07P" "TAS1R3" "E6" 1334323
"TCGA-A7-A0DA" "DVL1" "E14" 1338066
"TCGA-C8-A8HQ" "DVL1" "E10" 1339589
"TCGA-BH-A18T" "DVL1" "E8" 1340130
"TCGA-C8-A12V" "MXRA8" "E6" 1354445
"TCGA-C8-A3M8" "AURKAIP1" "E2" 1374747
"TCGA-BH-A0B6" "CCNL2" "E11" 1387308
"TCGA-A8-A09Z" "CCNL2" "E4" 1395413
"TCGA-AC-A23H" "MRPL20" "E4" 1402084
"TCGA-BH-A1FU" "MRPL20" "E4" 1402116
"TCGA-BH-A0W4" "MRPL20" "E4" 1402194
"TCGA-AR-A1AH" "MRPL20" "E4" 1402205
"TCGA-A8-A06Q" "ANKRD65" "E1" 1420868
"TCGA-AC-A8OQ" "ATAD3C" "E1" 1450566
"TCGA-A2-A25A" "ATAD3C" "E11" 1462661
"TCGA-AR-A5QQ" "ATAD3B" "E7" 1482563
"TCGA-AO-A1KS" "ATAD3B" "E12" 1487900
"TCGA-AO-A124" "ATAD3B" "E15" 1490662
"TCGA-A7-A56D" "ATAD3B" "E16" 1495857
"TCGA-D8-A27N" "ATAD3B" "E16" 1495961
"TCGA-AR-A2LH" "ATAD3A" "E5" 1518929
"TCGA-EW-A1OY" "ATAD3A" "E12" 1525277
"TCGA-AO-A128" "ATAD3A" "E16" 1533987
"TCGA-BH-A1FM" "SSU72" "E3" 1544993
"TCGA-C8-A12Y" "MIB2" "E4" 1623874
"TCGA-AC-A23H" "MIB2" "E7" 1625321
"TCGA-B6-A0RV" "MIB2" "E10" 1626960
"TCGA-E2-A1LG" "MIB2" "E19" 1629667
"TCGA-C8-A1HI" "SLC35E2B" "E8" 1668398
"TCGA-A2-A0CR" "SLC35E2B" "E8" 1668406
"TCGA-PL-A8LZ" "SLC35E2B" "E7" 1669727
"TCGA-C8-A3M7" "CDK11A" "E17" 1703847
"TCGA-D8-A1JP" "CDK11A" "E17" 1703884
"TCGA-C8-A1HK" "CDK11A" "E17" 1703915
"TCGA-D8-A27G" "CDK11A" "E15" 1704265
"TCGA-5L-AAT1" "CDK11A" "E13" 1705003
"TCGA-D8-A1JE" "CDK11A" "E11" 1707419
"TCGA-BH-A18P" "CDK11A" "E5" 1716352
"TCGA-D8-A27G" "CDK11A" "E5" 1716387
"TCGA-EW-A6SD" "CDK11A" "E5" 1716477
"TCGA-BH-A0W4" "CDK11A" "E3" 1721601
"TCGA-AN-A049" "CDK11A" "E3" 1721603
"TCGA-D8-A1XK" "SLC35E2" "E3" 1739030
"TCGA-LL-A5YM" "SLC35E2" "E1" 1745772
"TCGA-A7-A26H" "NADK" "E5" 1756596
"TCGA-AO-A128" "GNB1" "E5" 1815804
"TCGA-A2-A3Y0" "CALML6" "E4" 1916819
"TCGA-AR-A0U3" "CALML6" "E4" 1916828
"TCGA-AR-A5QQ" "GABRD" "E3" 2025399
"TCGA-A2-A0CP" "PRKCZ" "E8" 2148880
"TCGA-A2-A3Y0" "PRKCZ" "E13" 2172304
"TCGA-E2-A15E" "PRKCZ" "E13" 2172364
"TCGA-BH-A18N" "C1orf86" "E2" 2194056
"TCGA-OL-A5D6" "SKI" "E1" 2229410
"TCGA-BH-A2L8" "SKI" "E3" 2303317
"TCGA-D8-A4Z1" "SKI" "E5" 2304504
"TCGA-BH-A0B6" "SKI" "E5" 2304579
"TCGA-GM-A2D9" "MORN1" "E14" 2321445
"TCGA-AR-A0TR" "MORN1" "E12" 2336532
"TCGA-BH-A18G" "MORN1" "E8" 2372498
"TCGA-AN-A0FV" "MORN1" "E8" 2372505
"TCGA-AN-A0FV" "MORN1" "E8" 2372506
"TCGA-BH-A0HF" "MORN1" "E8" 2372521
"TCGA-E2-A1IG" "MORN1" "E8" 2372562
"TCGA-AQ-A04J" "MORN1" "E7" 2374471
"TCGA-BH-A1F5" "MORN1" "E4" 2387496
"TCGA-A8-A09Z" "MORN1" "E3" 2388258
"TCGA-BH-A0HA" "MORN1" "E3" 2388291
"TCGA-B6-A0IA" "RER1" "E2" 2397118
"TCGA-E2-A10C" "PEX10" "E3" 2408786
"TCGA-AC-A3HN" "PLCH2" "E1" 2476493
"TCGA-AC-A8OP" "PLCH2" "E3" 2479760
"TCGA-A2-A0YK" "PLCH2" "E5" 2484610
"TCGA-B6-A0IK" "PLCH2" "E11" 2491251
"TCGA-C8-A135" "PLCH2" "E18" 2498827
"TCGA-E2-A15E" "PLCH2" "E19" 2499127
"TCGA-PE-A5DE" "PLCH2" "E22" 2504427
"TCGA-LD-A74U" "PANK4" "E16" 2510680
"TCGA-S3-AA10" "PANK4" "E15" 2511386
"TCGA-C8-A1HM" "PANK4" "E10" 2515609
"TCGA-AC-A23H" "PANK4" "E7" 2519284
"TCGA-BH-A18N" "PANK4" "E4" 2520820
"TCGA-BH-A0HF" "PANK4" "E4" 2520821
"TCGA-BH-A0HF" "PANK4" "E3" 2521173
"TCGA-5L-AAT1" "PANK4" "E3" 2521297
"TCGA-B6-A0RN" "PANK4" "E2" 2521747
"TCGA-5L-AAT1" "PANK4" "E1" 2526579
"TCGA-C8-A12V" "TNFRSF14" "E3" 2558349
"TCGA-OL-A66P" "TNFRSF14" "E6" 2561704
"TCGA-A2-A25F" "TNFRSF14" "E6" 2561714
"TCGA-AC-A23H" "TNFRSF14" "E8" 2563296
"TCGA-A7-A6VV" "MMEL1" "E20" 2592868
"TCGA-D8-A1J8" "MMEL1" "E20" 2592908
"TCGA-A2-A0EU" "MMEL1" "E15" 2596056
"TCGA-AR-A1AJ" "MMEL1" "E11" 2603941
"TCGA-E2-A572" "MMEL1" "E10" 2604271
"TCGA-EW-A1J5" "MMEL1" "E10" 2604275
"TCGA-E2-A574" "MMEL1" "E9" 2605620
"TCGA-AC-A23H" "MMEL1" "E5" 2609733
"TCGA-B6-A0IA" "MMEL1" "E5" 2609757
"TCGA-AN-A0XS" "ACTRT2" "E1" 3021531
"TCGA-E9-A1RC" "ACTRT2" "E1" 3022445
"TCGA-AC-A6IW" "ACTRT2" "E1" 3022597
"TCGA-A2-A4S3" "ACTRT2" "E1" 3022696
"TCGA-A2-A0EX" "PRDM16" "E4" 3385231
"TCGA-B6-A0WZ" "PRDM16" "E5" 3396498
"TCGA-E9-A22E" "PRDM16" "E6" 3402898
"TCGA-BH-A8FZ" "PRDM16" "E9" 3411750
"TCGA-BH-A0HF" "PRDM16" "E9" 3412534
"TCGA-A8-A09V" "PRDM16" "E15" 3431074
"TCGA-5L-AAT1" "ARHGEF16" "E2" 3463558
"TCGA-AR-A1AI" "ARHGEF16" "E4" 3467276
"TCGA-E9-A1R4" "ARHGEF16" "E13" 3479535
"TCGA-AC-A5XS" "MEGF6" "E37" 3490581
"TCGA-AC-A23H" "MEGF6" "E7" 3514608
"TCGA-A2-A0SY" "MEGF6" "E2" 3602584
"TCGA-AC-A23H" "TPRG1L" "E2" 3625459
"TCGA-AR-A1AS" "WRAP73" "E1" 3649987
"TCGA-BH-A0DX" "TP73" "E2" 3682353
"TCGA-A1-A0SF" "TP73" "E3" 3683095
"TCGA-5L-AAT1" "TP73" "E3" 3683125
"TCGA-A8-A095" "TP73" "E4" 3707673
"TCGA-BH-A0HA" "TP73" "E8" 3727733
"TCGA-E9-A1R5" "CCDC27" "E1" 3752488
"TCGA-BH-A0C0" "CCDC27" "E3" 3755474
"TCGA-GM-A5PV" "CCDC27" "E6" 3762664
"TCGA-A2-A3Y0" "CCDC27" "E9" 3766586
"TCGA-BH-A1F6" "LRRC47" "E7" 3781140
"TCGA-B6-A0WZ" "LRRC47" "E7" 3781267
"TCGA-BH-A0B6" "LRRC47" "E2" 3787022
"TCGA-AR-A2LE" "CEP104" "E19" 3823467
"TCGA-A2-A0EN" "CEP104" "E12" 3833888
"TCGA-A8-A09Z" "CEP104" "E11" 3835070
"TCGA-AC-A4ZE" "DFFB" "E7" 3883608
"TCGA-AR-A1AH" "C1orf174" "E4" 3890056
"TCGA-BH-A18G" "AJAP1" "E2" 4711920
"TCGA-BH-A1F2" "AJAP1" "E3" 4769894
"TCGA-AC-A23H" "AJAP1" "E4" 4772372
"TCGA-C8-A12L" "AJAP1" "E4" 4772486
"TCGA-AC-A23H" "NPHP4" "E28" 5864419
"TCGA-BH-A1FD" "NPHP4" "E28" 5864478
"TCGA-EW-A1IZ" "NPHP4" "E27" 5865131
"TCGA-EW-A1J5" "NPHP4" "E27" 5865172
"TCGA-A2-A04P" "NPHP4" "E26" 5866378
"TCGA-D8-A1XZ" "NPHP4" "E24" 5867849
"TCGA-4H-AAAK" "NPHP4" "E20" 5877217
"TCGA-D8-A1JD" "NPHP4" "E19" 5880178
"TCGA-GM-A2D9" "NPHP4" "E17" 5890905
"TCGA-E2-A1LA" "NPHP4" "E17" 5890987
"TCGA-D8-A1J8" "NPHP4" "E17" 5891009
"TCGA-E2-A1B4" "NPHP4" "E16" 5904787
"TCGA-EW-A1P3" "NPHP4" "E13" 5907125
"TCGA-BH-A0EE" "NPHP4" "E12" 5909177
"TCGA-A2-A0ER" "NPHP4" "E11" 5927714
"TCGA-BH-A0HF" "NPHP4" "E11" 5927761
"TCGA-AO-A128" "NPHP4" "E9" 5947174
"TCGA-AC-A23H" "NPHP4" "E4" 5969131
"TCGA-AC-A23H" "NPHP4" "E2" 5986185
和lastObsFlagG看起来像这样。同样，lastObsFlagGE（未显示）应主要为1，但如果观察值不在该唯一ID的最后一行（例如，第4行应具有lastObsFlagID = 0，但第5行应具有lastObsFlagID = 1），则应具有0。
lastObsFlagID答案 0 :(得分：1)
我们可以使用相同的逻辑为不同的组生成标志1/0。在这里，我们检查当前组中的row_number()是否是最后一个（n()），该值返回TRUE/FALSE值，然后使用as.integer将其转换为1/0。
library(dplyr)
library(data.table)
df %>%
group_by(gene) %>%
mutate(lastObsFlagG = as.integer(row_number() == n())) %>%
group_by(gene,exon) %>%
mutate(lastObsFlagGE = as.integer(row_number() == n())) %>%
ungroup() %>%
group_by(group = rleid(ID)) %>%
mutate(lastObsFlagID = as.integer(row_number() == n())) %>%
ungroup() %>%
select(-group)
# ID gene exon mutation lastObsFlagG lastObsFlagGE lastObsFlagID
# <fct> <fct> <fct> <int> <int> <int> <int>
# 1 TCGA-AN-A046 OR4F5 E1 69767 1 1 1
# 2 TCGA-A2-A0CP SAMD11 E2 925952 1 1 1
# 3 TCGA-A8-A08H NOC2L E5 956126 0 1 1
# 4 TCGA-GM-A2DM NOC2L E4 956911 0 0 0
# 5 TCGA-GM-A2DM NOC2L E4 956912 1 1 1
# 6 TCGA-D8-A1XM KLHL17 E3 961658 0 1 1
# 7 TCGA-BH-A18G KLHL17 E5 962441 0 1 1
# 8 TCGA-3C-AALI KLHL17 E8 963353 0 1 1
# 9 TCGA-AC-A62Y KLHL17 E9 964004 1 1 1
#10 TCGA-AR-A2LE PLEKHN1 E1 966556 0 1 1
# … with 190 more rows